Front. Med.Frontiers in MedicineFront. Med.2296-858XFrontiers Media S.A.10.3389/fmed.2024.1477898MedicineMini ReviewLarge language models in patient education: a scoping review of applications in medicineAydinSerhat1KarabacakMert2VlachosVictoria3MargetisKonstantinos2*1School of Medicine, Koç University, Istanbul, Türkiye2Department of Neurosurgery, Mount Sinai Health System, New York, NY, United States3College of Human Ecology, Cornell University, Ithaca, NY, United States
Edited by: Rafat Damseh, United Arab Emirates University, United Arab Emirates
Reviewed by: Johanna Mora, Bristol Myers Squibb, United States
Beenish Chaudhry, University of Louisiana at Lafayette, United States
This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
Introduction
Large Language Models (LLMs) are sophisticated algorithms that analyze and generate vast amounts of textual data, mimicking human communication. Notable LLMs include GPT-4o by Open AI, Claude 3.5 Sonnet by Anthropic, and Gemini by Google. This scoping review aims to synthesize the current applications and potential uses of LLMs in patient education and engagement.
Materials and methods
Following the PRISMA-ScR checklist and methodologies by Arksey, O’Malley, and Levac, we conducted a scoping review. We searched PubMed in June 2024, using keywords and MeSH terms related to LLMs and patient education. Two authors conducted the initial screening, and discrepancies were resolved by consensus. We employed thematic analysis to address our primary research question.
Results
The review identified 201 studies, predominantly from the United States (58.2%). Six themes emerged: generating patient education materials, interpreting medical information, providing lifestyle recommendations, supporting customized medication use, offering perioperative care instructions, and optimizing doctor-patient interaction. LLMs were found to provide accurate responses to patient queries, enhance existing educational materials, and translate medical information into patient-friendly language. However, challenges such as readability, accuracy, and potential biases were noted.
Discussion
LLMs demonstrate significant potential in patient education and engagement by creating accessible educational materials, interpreting complex medical information, and enhancing communication between patients and healthcare providers. Nonetheless, issues related to the accuracy and readability of LLM-generated content, as well as ethical concerns, require further research and development. Future studies should focus on improving LLMs and ensuring content reliability while addressing ethical considerations.
large language modelsChatGPTpatient educationartificial intelligencemachine learningdeep learningsection-at-acceptanceRegulatory ScienceIntroduction
Large Language Models (LLMs) are sophisticated algorithms that analyze and generate extensive textual data (1). These models leverage vast corpora of unlabeled text and incorporate reinforcement learning from human feedback to discern syntactical patterns and contextual nuances within languages. Consequently, LLMs can produce responses that closely mimic human communication when presented with diverse, open-ended queries (2–4). Several notable LLMs have emerged recently, including GPT-4o by Open AI (5), Claude 3.5 Sonnet by Anthropic (6), and Gemini by Google (7).
LLMs have demonstrated significant potential in medicine, with transformative applications across various domains, including clinical settings. These AI-powered systems can streamline clinical workflows, help with clinical decision-making, and ultimately improve patient outcomes. Recent studies highlight the utility of LLMs in clinical decision support, providing valuable insights that enable healthcare teams to make more informed treatment decisions (8–10). LLMs also show promise as educational tools by enhancing the quality and accessibility of materials. However, from a patient’s perspective, they present both opportunities and risks. The varying levels of medical knowledge among patients may impede their ability to critically assess the information provided by LLMs, unlike clinicians who are trained to do so.
As of July 2024, there was limited synthesis of knowledge regarding the evidence base, applications, and evaluation methods of LLMs in patient education and engagement. This scoping review aims to address this gap by mapping the available literature on potential applications of LLMs in patient education and identifying future research directions. Our primary research question is: “What are the current and potential uses of LLMs in patient education and engagement as described in the literature?” This review seeks to enhance future discussions on using LLMs for patient care, including education, engagement, workload reduction, patient-centered health customization, and communication.
Materials and methods
This study employed a scoping review methodology, adhering to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews (PRISMA-ScR) checklist (11). The review process was based on the methodological framework developed by Arksey and O’Malley (12), with further refinements as proposed by Levac et al. (13).
Literature search
A literature search was conducted in June 2024 using the PubMed database. The search strategy, detailed in Supplementary Methods S1, combined relevant keywords and Medical Subject Headings (MeSH) terms related to LLMs and patient education.
Study selection
Citation management was facilitated by Covidence software (Veritas Health Innovation). The inclusion criteria encompassed studies addressing the use, accuracy, relevance, or effectiveness of LLMs in patient education, patient engagement, answering patient-specific questions, or generating patient education materials. Studies were excluded if they did not primarily focus on LLMs for patient education, engagement, or answering patient questions; did not assess LLMs in healthcare settings or had only indirect relations to patients; or focused solely on technical aspects or architecture of LLMs without considering their application in patient education or engagement. A detailed description of the inclusion and exclusion criteria is provided in Supplementary Methods S2.
The selection process involved two stages. In the initial screening, two authors (SA and VV) independently reviewed the titles and abstracts of retrieved articles. Studies passing the initial screening were then read in full by both authors. Studies deemed eligible by both reviewers were included in the analysis. In cases of disagreement, a third author (MK) was consulted to resolve discrepancies.
Thematic analysis
We employed thematic analysis, following the methodology proposed by Braun and Clarke (14), to address our primary research question. The process began with an author (SA) reading and coding 25 randomly selected articles, focusing on content related to the potential uses of LLMs in patient education and engagement. Subsequently, two authors (SA and MK) examined the remaining manuscripts, seeking additional themes or data that could either reinforce or challenge the established themes. This iterative process facilitated further refinement of the themes through group discussions centered on patient education and engagement.
ResultsLiterature search
The initial search strategy yielded 661 papers. After removing one duplicate, 660 papers remained for screening. Based on title and abstract screening, 365 papers (55.3%) were excluded. Full-text review was conducted for 295 papers (44.7% of the initial pool), resulting in 201 papers (30% of the initial pool) meeting the study inclusion criteria (Supplementary Figure S1). Supplementary Data S1 presents all of the included papers.
Descriptive analysis
The geographical distribution of the studies revealed a predominance from the United States, accounting for 58.2% (117/201) of the articles. Turkey and China followed, each contributing 6.4% (13/201) of the articles (Figure 1A). The studies spanned 35 medical specialties, with general medicine representing the largest proportion at 12.9% (26/201), closely followed by orthopedic surgery at 12.4% (25/201), and otolaryngology at 9.4% (19/201) (Figure 1B).
(A) Geographical distribution of studies on large language models (LLMs) in patient education. (B) Specialty distribution of studies on large language models (LLMs) in patient education.
Thematic analysis
Our analysis identified six main themes with associated subthemes regarding the use of LLMs in patient education and engagement:
Generating Patient Education Materials
Answering Patient Questions
Enhancing Existing Patient Education Materials
Translation of Patient Education Materials
Interpreting Medical Information from a Patient Perspective
Providing Lifestyle Recommendations and Improving Health Literacy
Customized Medication Use and Self-Decision
Providing Pre-, Peri-, and Post-Operative Care Instructions
Optimizing Doctor-Patient Interaction
Facilitating Understanding of Consent Forms
Enhancing Communication Establishment
Table 1 presents these six themes as represented across the analyzed articles, along with illustrative quotes. Supplementary Data S2 indicates the theme to which each paper belongs.
Representative quotes illustrating key themes identified in studies on the use of large language models (LLMs) in patient education.
Theme
Representative quotes
Generating Patient Education Materials
Answering Patient Questions
Enhancing Existing Patient Education Materials
Translation of Patient Education Materials
New Frontiers in Health Literacy: Using ChatGPT to Simplify Health Information for People in the Community [Ayre et al. (159)]Ayre et al. evaluated ChatGPT-3.5’s ability to simplify health information for individuals with low literacy. The study found that ChatGPT effectively reduced text complexity by lowering the reading level, using simpler language, and decreasing passive voice usage. It retained about 80% of key messages, with more complex texts seeing greater improvements. However, most simplified texts still did not meet recommended health literacy targets. The researchers concluded that ChatGPT could provide a useful “first draft” of plain language health information, which could then be refined through human review.Enhancing Readability of Online Patient-Facing Content: The Role of AI Chatbots in Improving Cancer Information Accessibility [Abreu et al. (158)]Abreu et al. assessed ChatGPT-4’s effectiveness in improving the readability of cancer-related content from NCCN Member Institutions. The AI-generated outputs significantly reduced the reading level from university freshman to high school freshman level. This improvement in accessibility did not compromise content accuracy or quality. The simplified text featured shorter sentences and simpler words, earning a “good” quality rating on the DISCERN instrument. This study demonstrates AI’s potential to make complex medical information more accessible to patients.Leveraging large language models for generating responses to patient messages – a subjective analysis [Liu et al. (94)]Liu et al. compared fine-tuned LLaMA-based models (CLAIR-Short and CLAIR-Long) with ChatGPT in generating responses to patient messages. CLAIR-Long, fine-tuned with a mix of local patient messages and open-source data, performed comparably to ChatGPT-4 in empathy, responsiveness, and accuracy. CLAIR-Short, fine-tuned only with local data, produced concise responses similar to healthcare providers but less detailed. While ChatGPT-4 generally ranked highest, the study showed that fine-tuned models, especially CLAIR-Long, could be effective for patient education and empathetic communication.Assessing the Accuracy and Reliability of AI-Generated Responses to Patient Questions Regarding Spine Surgery [Kasthuri et al. (76)]Kasthuri et al. evaluated the GPT-4-enhanced Bing search engine’s responses to common spine surgery questions. Spine surgeons found the responses generally accurate and complete, with re-querying improving initially inaccurate answers. The study highlighted GPT-4-based models’ ability to provide useful summaries from web sources, but noted concerns about response quality variability. Most information came from commercial websites, with no significant correlation between response accuracy and source type. This research underscores the need for ongoing evaluation and refinement of LLMs for clinical use.Easing the Burden on Caregivers-Applications of Artificial Intelligence for Physicians and Caregivers of Children with Cleft Lip and Palate [Chaker et al. (199)]Chaker et al. tested ChatGPT-3.5’s ability to assist caregivers of children with cleft lip and palate. The AI achieved a 69% accuracy rate compared to senior pediatric plastic surgeons when answering common postoperative questions. While information-related errors were the AI’s main weakness, the study emphasized AI’s potential to ease caregiver burden by generating educational materials and offering perioperative support. This research highlights both the promise and current limitations of AI in specialized medical fields.The utility of ChatGPT as a generative medical translator [Grimm et al. (175)]Grimm et al. explored GPT-4’s utility in translating otolaryngology-related medical content into English, Spanish, and Mandarin. Using the Patient Education Materials Assessment Tool (PEMAT), they found that GPT-4 produced translations with comparable accuracy, understandability, and actionability across all three languages. This study suggests that LLMs like GPT-4 could play a valuable role in bridging language barriers in healthcare, potentially improving access to medical information for diverse patient populations.
Interpreting Medical Information from a Patient Perspective
Quality of Answers of Generative Large Language Models Versus Peer Users for Interpreting Laboratory Test Results for Lay Patients: Evaluation Study [He et al. (176)]He et al. conducted a comprehensive evaluation of several LLMs in interpreting laboratory test results for lay patients. The study compared GPT-4, GPT-3.5, LLaMA 2, MedAlpaca, and ORCA_mini across multiple metrics including accuracy, relevance, helpfulness, and safety. GPT-4 emerged as the top performer in all categories, followed closely by GPT-3.5. LLaMA 2, while providing detailed explanations, ranked third. MedAlpaca and ORCA_mini were less effective, with MedAlpaca showing the poorest performance. This study highlights the current superiority of GPT-4 and GPT-3.5 in translating complex medical information for patient understanding, suggesting their potential utility in healthcare communication.Translating musculoskeletal radiology reports into patient-friendly summaries using ChatGPT-4 [Kuckelman et al. (82)]Kuckelman et al. explored GPT-4’s capability in simplifying musculoskeletal radiology reports for patients. The AI successfully generated summaries that were both readable and concise, with independent readers generally rating them as accurate and complete. GPT-4 demonstrated proficiency in simplifying medical jargon, making reports more accessible to patients. While there was some variation in accuracy and completeness ratings among readers, indicating a degree of subjectivity, the overall results were positive. The study suggests that GPT-4 could be a valuable tool in enhancing patient comprehension of radiology results, potentially reducing the immediate need for physician explanation.Generative Artificial Intelligence to Transform Inpatient Discharge Summaries to Patient-Friendly Language and Format [Zaretsky et al. (183)]Zaretsky et al. investigated GPT-4’s ability to transform complex inpatient discharge summaries into more patient-friendly formats. The AI-transformed summaries showed marked improvements in readability, with the Flesch–Kincaid Grade Level decreasing from 11.0 to 6.2. Understandability scores, measured by PEMAT, increased significantly from 13 to 81%. However, the study revealed mixed results in terms of accuracy and completeness. While 54% of reviews gave the highest accuracy rating, 18% identified safety concerns due to omissions or incorrect information (hallucinations). These findings indicate that while GPT-4 can greatly enhance the accessibility of discharge information, further refinement is necessary to ensure consistent accuracy and safety for practical use in healthcare settings.
Providing Lifestyle Recommendations and Improving Health Literacy
Examining the role of ChatGPT in promoting health behaviors and lifestyle changes among cancer patients [Alanezi et al. (184)]Alanezi et al. explored ChatGPT-3.5’s potential in promoting health behavior changes among cancer patients. The study found that the AI significantly improved health literacy, enhanced self-management practices, and provided valuable emotional and motivational support. Patients appreciated the AI’s ability to address their concerns, offer personalized suggestions, and connect them with relevant resources. However, the research also identified challenges, including privacy concerns, limitations in deep personalization, and occasional reliability issues. Despite these drawbacks, ChatGPT-3.5 proved effective in facilitating positive health behaviors and lifestyle changes, particularly in helping patients better understand and manage their conditions.Assessing the Accuracy of Generative Conversational Artificial Intelligence in Debunking Sleep Health Myths: Mixed Methods Comparative Study With Expert Analysis [Bragazzi et al. (185)]Bragazzi et al. assessed GPT-4’s accuracy in debunking common sleep-related myths. The AI correctly identified 85% of the presented myths as either “false” or “generally false,” demonstrating a sensitivity of 85% and a positive predictive value of 100%. GPT-4’s performance in identifying false statements was comparable to that of sleep experts, with high interrater agreement (ICC = 0.83). However, the AI sometimes struggled with nuanced scenarios, particularly myths containing partial truths or complex scientific concepts. The study concluded that while GPT-4 is a reliable tool for addressing sleep-related misinformation, it should not replace expert opinion in more nuanced areas.Is ChatGPT an Effective Tool for Providing Dietary Advice? [Ponzo et al. (190)]Ponzo et al. evaluated ChatGPT-3.5’s ability to provide accurate and appropriate dietary advice for various non-communicable diseases (NCDs). The AI’s advice was generally appropriate, with correctness rates ranging from 55.5% for sarcopenia to 73.3% for non-alcoholic fatty liver disease (NAFLD). However, the study revealed limitations in complex scenarios involving multiple overlapping conditions, where ChatGPT-3.5 sometimes provided contradictory or inappropriate recommendations. The researchers concluded that while ChatGPT-3.5 shows promise as a supplementary tool for dietary advice, it cannot yet replace personalized guidance from healthcare professionals, especially in managing complex cases.
Customized Medication Use and Self-Decision
Snakebite Advice and Counseling From Artificial Intelligence: An Acute Venomous Snakebite Consultation With ChatGPT [Altamimi et al. (192)]Altamimi et al. evaluated ChatGPT-3.5’s performance in providing information for managing venomous snakebites. The AI offered clear, evidence-based advice on initial first aid, the importance of seeking urgent medical attention, potential symptoms, and the role of antivenom. However, the study identified several limitations in the AI’s capabilities. These included a lack of personalization, outdated information, and an inability to account for regional variations in snake species and venom characteristics. While ChatGPT-3.5 proved effective in delivering general advice and preliminary guidance, the researchers emphasized that it should not replace professional medical consultations, especially in critical situations like snakebites. The study concluded by recommending future developments focus on addressing these limitations to enhance the AI’s utility in such scenarios.Automating untruths: ChatGPT, self-managed medication abortion, and the threat of misinformation in a post-Roe world [McMahon et al. (193)]McMahon et al. investigated the accuracy of ChatGPT-3.5’s responses regarding self-managed medication abortion (SMMA). The study revealed a concerning discrepancy in the AI’s information provision. While ChatGPT-3.5 correctly described clinician-managed medication abortion as safe and effective, it inaccurately portrayed SMMA as significantly more dangerous, exaggerating the risks of complications. This misrepresentation contradicts substantial evidence supporting SMMA’s safety and effectiveness. The researchers highlighted the potential dangers of such misinformation, noting it could increase stigma and deter individuals from seeking safe abortion methods, thereby posing a threat to public health. These findings emphasize the critical need for improving AI models to ensure they provide accurate and reliable health information, particularly on sensitive topics with significant public health implications.
Providing Pre-, Peri-, and Post-Operative Care Instructions
Enhancing Postoperative Cochlear Implant Care With ChatGPT-4: A Study on Artificial Intelligence (AI)-Assisted Patient Education and Support [Aliyeva et al. (194)]Aliyeva et al. evaluated ChatGPT-4’s effectiveness in providing postoperative care information for cochlear implant patients. The AI demonstrated high accuracy, clarity, and relevance in answering common postoperative questions. Its responses aligned well with current medical guidelines, ensuring patients received accurate and comprehensible information. The study found ChatGPT-4 to be a valuable supplementary resource, especially when access to healthcare professionals is limited. While emphasizing that ChatGPT-4 cannot replace professional medical advice, the researchers noted its potential to support patient education and reduce anxiety by providing timely information in resource-constrained settings.Evaluation of large language model responses to Mohs surgery preoperative questions [Breneman et al. (206)]Breneman et al. compared the performance of three large language models (ChatGPT-3.5, Google Bard, and Microsoft CoPilot) in answering preoperative questions about Mohs surgery. ChatGPT-3.5 outperformed the other models in accuracy (80%) and completeness (100%) of responses. However, its higher reading level (12.7) potentially made the information less accessible to some patients. Google Bard and Microsoft CoPilot, while less accurate and complete, provided more readable responses. The study highlighted the potential of LLMs like ChatGPT-3.5 in offering valuable preoperative information but cautioned about possible inaccuracies or irrelevant details, emphasizing the need for careful implementation in patient education.Feasibility of GPT-3 and GPT-4 for in-Depth Patient Education Prior to Interventional Radiological Procedures: A Comparative Analysis [Scheschenja et al. (195)]Scheschenja et al. conducted a comparative analysis of GPT-3 and GPT-4 in providing patient education for interventional radiology procedures. GPT-4 showed superior performance, with 35.3% of its responses rated as “completely correct” compared to GPT-3’s 30.8%. GPT-4 also had fewer “mostly incorrect” responses (2.3% vs. GPT-3’s 5.3%). Despite these differences, both models were considered safe and effective for patient education, with GPT-4 having a slight edge. The researchers concluded that while these AI tools can enhance patient understanding of complex procedures, they should be used cautiously due to the potential for inaccuracies or incomplete information.
Optimizing Doctor-Patient Interaction
Facilitating Understanding of Consent Forms
Enhancing Communication Establishment
Bridging the literacy gap for surgical consents: an AI-human expert collaborative approach [Ali et al. (208)]Ali et al. investigated the use of GPT-4 to simplify surgical consent forms, aiming to make them more accessible to patients with varying health literacy levels. The study found that GPT-4 significantly improved the readability of consent forms from 15 academic medical centers, reducing the average reading level from college freshman to 8th-grade level. Moreover, GPT-4 generated procedure-specific consent forms that maintained medical and legal sufficiency, scoring perfectly on a validated rubric and passing expert review without changes. This research demonstrates the potential of AI-human collaboration in enhancing the clarity and comprehensibility of consent forms, ensuring patients receive clear, detailed information about their surgical procedures.Generating Informed Consent Documents Related to Blepharoplasty Using ChatGPT [Shiraishi et al. (209)]Shiraishi et al. evaluated ChatGPT’s performance in generating informed consent (IC) documents for blepharoplasty. While the study showed promise for LLMs in enhancing patient communication, it also highlighted areas needing improvement. Board-certified plastic surgeons rated AI-generated documents lower than original IC documents in accuracy, informativeness, and accessibility. Even after revisions, the AI-generated documents still scored lower in accuracy and accessibility. Interestingly, nonmedical staff found no significant difference between AI-generated and original documents. The study concluded that while ChatGPT has potential, it currently cannot replace human-generated IC documents due to issues with professional terminology and content accuracy, emphasizing the need for further refinement.Putting ChatGPT’s Medical Advice to the (Turing) Test: Survey Study [Nov et al. (110)]Nov et al. assessed laypeople’s ability to distinguish between medical advice from ChatGPT-3.5 and human healthcare providers. Participants could only weakly differentiate between the sources, correctly identifying them about 65% of the time. Trust in ChatGPT-3.5’s responses decreased with increasing medical complexity of the questions, with higher trust in logistical responses and lower trust in diagnostic and treatment-related responses. The study concluded that while ChatGPT-3.5 can provide credible advice for low-risk queries, it may not be reliable for more complex health issues, suggesting the need for further research to optimize its use in patient-provider communications.Can Large Language Models Generate Outpatient Clinic Letters at First Consultation That Incorporate Complication Profiles From UK and USA Aesthetic Plastic Surgery Associations? [Roberts et al. (211)]Roberts et al. compared ChatGPT-4, ChatGPT-3.5, and Google Bard in generating outpatient clinic letters incorporating complication profiles from aesthetic plastic surgery associations. ChatGPT-4 showed the highest overall compliance, scoring 0.92 for BAAPS and 0.99 for ASPS compliance. However, its performance dropped to 0.52 for ASPS gold-standard profiles, indicating challenges with paywalled content. ChatGPT-3.5 and Google Bard demonstrated lower compliance overall. This study highlights the potential of advanced LLMs in generating compliant medical documentation, while also revealing limitations in accessing and integrating specialized, restricted information.
The theme “Generating Patient Education Materials” was predominant, encompassing 80.5% (162/201) of the articles across its three subthemes. Within this theme, “Answering Patient Questions” was the most prevalent subtheme, representing 71.6% (144/201) of all articles. The remaining themes were distributed as follows: “Interpreting Medical Information from a Patient Perspective” and “Providing Lifestyle Recommendations and Improving Health Literacy” each accounted for 4.5% (9/201) of the articles. “Providing Pre-, Peri-, and Post-Operative Care Instructions” was represented in 6.9% (14/201) of the articles, while “Optimizing Doctor-Patient Interaction” appeared in 2.5% (5/201) of the articles. The least represented theme was “Customized Medication Use and Self-Decision,” accounting for 1% (2/201) of the articles.
Theme 1: generating patient education materials
The generation of patient education materials emerged as a prominent theme, with three key subthemes: answering patient questions, enhancing existing materials, and translating medical content. Answering patient questions was the most significant subtheme, representing 71.6% of the articles (8, 15–157). In these studies, LLMs created educational content by responding to common questions, direct patient inquiries, and expert-formulated queries, demonstrating their potential to address diverse patient information needs.
Most studies found LLMs provided accurate responses to patient queries. Almagazzachi et al. reported 92.5% accuracy for ChatGPT’s answers to hypertension questions (18). However, accuracy varied by specialty. In a study on pediatric in-toeing, Amaral et al. found 46% of responses were excellent, and 44% were satisfactory with minimal clarification needed (19). These findings suggest LLMs’ potential in patient education, while highlighting performance differences across medical fields.
The readability of LLM-generated content varied considerably across studies. ChatGPT’s responses often required a higher reading level, potentially limiting accessibility for some patients. Campbell et al. demonstrated that ChatGPT’s unprompted answers on obstructive sleep apnea had a mean Flesch–Kincaid grade level of 14.15, which decreased to 12.45 when prompted (32). This indicates that even with specific instructions, the content remained at a college reading level. In contrast, other LLMs showed better readability in some cases. Chervonski et al. reported that Google BARD produced more accessible content, with responses on vascular surgery diseases achieving a mean Flesch Reading Ease score of 58.9, indicating improved readability (40). When compared to traditional search engines, LLMs revealed a trade-off between comprehensiveness and readability. Cohen et al. found that while ChatGPT provided more detailed and higher-quality responses to cataract surgery FAQs compared to Google, these responses were at a higher reading level (42). These findings suggest that while LLMs may offer more comprehensive information, they do not always improve accessibility for the average patient.
LLMs show promise in transforming existing materials into more readable, patient-centered formats (158–174). Numerous studies demonstrate their ability to enhance readability across various medical education materials (158–161, 163–165, 168, 170–172, 174). Fanning et al. found comparable performance between ChatGPT-3.5 and ChatGPT-4 in improving plastic surgery material readability (166). Moons et al. reported Google BARD surpassed GPT in readability improvement but tended to omit information (169). Some studies, however, found no improvement or decreased readability (162, 167), indicating variability in LLM effectiveness. Interestingly, Sudharshan et al. noted LLMs were more accurate in creating readable Spanish materials (173), suggesting potential for addressing language-specific challenges.
Research on LLMs for translating patient education materials remains limited. However, a significant study by Grimm et al. showed ChatGPT-4’s ability to produce accurate, understandable, and actionable translations of otorhinolaryngology content in English, Spanish, and Mandarin (175). This finding suggests LLMs’ potential in overcoming language barriers in patient education.
Theme 2: interpreting medical information from a patient perspective
Nine studies investigated LLMs’ capacity to interpret complex medical information, evaluating their feasibility, accuracy, readability, and effectiveness in translating medical jargon. He et al. found ChatGPT-4 outperformed other LLMs and human responses from Q&A websites in accuracy, helpfulness, relevance, and safety when answering laboratory test result questions (176). However, Meyer et al. reported that ChatGPT, Gemini, and Le Chat were less accurate and more generalized than certified physicians in interpreting laboratory results (177), highlighting the variability in LLM performance across different contexts.
LLMs demonstrate potential in improving radiological information interpretation and communication. Kuckelman et al. found ChatGPT-4 produced generally accurate summaries of musculoskeletal radiology reports, noting some variability in human interpretation (82). Lyu et al. showed ChatGPT-4 enhanced translated radiology report quality and accessibility, despite occasional oversimplifications (178). Sarangi et al. reported ChatGPT-3.5 effectively simplified radiological reports while maintaining essential diagnostic information, though performance varied across conditions and imaging modalities (179). Several other studies support these findings, suggesting LLMs’ promising role in radiology communication (180–182).
Zaretsky et al. evaluated ChatGPT-4’s ability to convert discharge summaries into patient-friendly formats. The transformed summaries showed significant improvements in readability and understandability. However, the study raised concerns about accuracy and completeness, noting instances of omissions and hallucinations (183).
Theme 3: providing lifestyle recommendations and improving health literacy
Nine studies explored LLMs’ potential in offering lifestyle recommendations and enhancing health literacy. Alanezi et al. found ChatGPT effective in promoting health behavior changes among cancer patients, boosting health literacy and self-management (184). Bragazzi et al. showed ChatGPT’s capability to debunk sleep-related myths and provide accessible advice (185). In a follow-up study, they found Google BARD slightly outperformed ChatGPT-4 in identifying false statements and offering practical sleep-related advice (186). These findings suggest LLMs’ promising role in health education and lifestyle guidance.
Gray et al. demonstrated ChatGPT’s ability to generate realistic prenatal counseling dialogues (187). Minutolo et al. proposed a conversational agent to enhance health literacy by making Patient Information Leaflets queryable (188). Mondal et al. found ChatGPT provided reasonably accurate responses to lifestyle-related disease queries (189). Ponzo et al. reported ChatGPT offered general dietary guidance for NCDs but struggled with complex, multi-condition cases (190). Willms et al. explored ChatGPT’s potential in creating physical activity app content, emphasizing the need for expert review (1). Zaleski et al. found AI-generated exercise recommendations generally accurate but lacking comprehensiveness and at a college reading level (191). These studies highlight LLMs’ diverse applications in health education while noting their limitations.
Theme 4: customized medication use and self-decision
Two studies explored LLMs’ potential in medication guidance and self-decision support. Altamimi et al. found ChatGPT provided accurate advice on acute venomous snakebite management, while emphasizing the importance of professional care (192). In contrast, McMahon et al. observed ChatGPT accurately described clinician-managed abortion as safe but incorrectly portrayed self-managed abortion as dangerous, highlighting potential misinformation risks (193). These findings underscore both the promise and pitfalls of using LLMs for sensitive medical information.
Theme 5: providing pre-/peri-/post-operative care instructions
Studies investigated LLMs’ use in surgical patient education. Aliyeva et al. found ChatGPT-4 excelled in providing postoperative care instructions for cochlear implant patients, especially in remote settings (194). LLMs showed proficiency in offering postoperative guidance across various surgical specialties (180, 195–202). Dhar et al. noted ChatGPT’s accuracy in answering tonsillectomy questions, with some pain management inaccuracies (203). Patil et al. reported ChatGPT provided quality preoperative information for ophthalmic surgeries, though occasionally overlooking adverse events (204). Meyer et al. found ChatGPT reliable for postoperative gynecological surgery instructions (205). Breneman et al. and Kienzle et al. evaluated ChatGPT for preoperative counseling in Mohs surgery and knee arthroplasty, finding it potentially useful but cautioning about non-existing references (206, 207).
Theme 6: optimizing doctor-patient interaction
This theme explores LLMs’ potential to enhance doctor-patient communication, particularly in simplifying consent forms and improving general medical communication. Ali et al. found ChatGPT-4 successfully simplified surgical consent forms to an 8th-grade reading level while maintaining accuracy (208). Shiraishi et al. reported that revised ChatGPT-prepared informed consent documents for blepharoplasty were more desirable than originals (209).
LLMs also showed promise in broader doctor-patient communication. An et al. introduced an LLM-based education model that improved patients’ understanding of their conditions and treatments (210). Roberts et al. demonstrated LLMs could generate comprehensible outpatient clinic letters for cosmetic surgery, potentially saving clinicians’ time (211). Xue et al. found ChatGPT performed well in logical reasoning and medical knowledge education during remote orthopedic consultations (212). These studies highlight LLMs’ potential to enhance various aspects of medical communication.
Discussion
This scoping review synthesizes current applications and potential uses of LLMs in patient education and engagement, offering insights into their transformative potential and integration challenges in healthcare settings. LLMs demonstrate significant promise in creating patient education materials, with studies reporting that health-related questions were accurately answered over 90% of the time by systems like ChatGPT, covering a broad range of topics from hypertension to pediatric conditions (18, 31). The depth of these responses potentially offers substantial value to patients seeking detailed understanding of their ailments. However, readability remains a notable concern, potentially limiting accessibility for some patient populations.
LLMs have demonstrated competence in interpreting complex medical information from laboratory reports, radiology results, and discharge summaries. ChatGPT-4, for instance, generated informative summaries of radiology reports, making them more accessible to non-medical professionals (82, 178). However, concerns about the quality and comprehensiveness of LLM-generated information persist. Issues such as hallucinations, omissions, or plausible but incorrect information have been noted. Zaretsky et al. observed that while ChatGPT-4 could transform discharge summaries into more patient-friendly formats, occasional inaccuracies, and omissions could potentially mislead patients (183). These findings underscore the necessity for professional oversight in deploying LLMs in healthcare settings to ensure the reliability and accuracy of AI-generated content.
LLMs show promise as lifestyle recommendations and health literacy tools, effectively encouraging healthy behaviors and dispelling health myths. Alanezi et al. found that ChatGPT provided significant support in developing health literacy among cancer patients, motivating self-management through emotional, informational, and motivational assistance (184). Bragazzi and Garbarino demonstrated ChatGPT’s effectiveness in debunking sleep-related misconceptions, accurately distinguishing between false and genuine health information (185). However, personalization and accuracy remain challenging. While AI can offer useful preliminary advice, it requires further development to provide relevant, situation-specific suggestions tailored to individual patients. This customization is crucial for ensuring that patients can trust and adhere to the recommendations provided.
LLMs play a significant role in providing information on self-medication and personalized drug utilization, offering detailed insights on drug interactions, correct usage, and potential side effects. Altamimi et al. found ChatGPT’s information helpful and accurate in guiding acute venomous snakebite management, though it appropriately emphasized the need for professional medical care (192). LLMs also show potential in patient triage, quickly analyzing symptoms and medical history to prioritize cases based on severity (10). However, the quality of LLM-provided information varies considerably. McMahon et al. reported that ChatGPT gave inaccurate and misleading information about self-managed medication abortion, incorrectly portraying it as dangerous despite evidence of its safety and efficacy (193). This inconsistency highlights the risks of relying on AI without professional oversight and underscores the need for LLMs to provide accurate, up-to-date, and context-sensitive information to support safe self-medication practices.
Implications and future research
The integration of LLMs into patient education and engagement shows significant potential for improving health literacy and healthcare delivery efficiency. However, this review highlights the need for continued improvement in the accuracy and personalization of AI-generated content. Future research should focus on developing more accurate LLM algorithms to enhance reliability as medical information sources, exploring multimodal LLMs, and establishing robust validation frameworks for their ethical use. Ensuring AI-based information aligns with the latest medical guidelines and is tailored for diverse patient populations is crucial. Conducting longitudinal studies to assess the long-term effects of LLMs on patient outcomes and satisfaction will provide valuable insights. Additionally, addressing ethical concerns, including data privacy and potential biases in LLM-generated content, is essential. These research directions are crucial for the responsible and effective integration of LLMs in healthcare settings. Finally, LLMs may carry biases from their training data, potentially propagating misinformation or reinforcing healthcare disparities. Future research should address these limitations by ensuring LLM tools are accurate, reliable, and equitable across diverse patient populations, while also exploring their long-term effects and ethical implications.
Limitations
This scoping review has several limitations. The quality of included studies varied, with some using small sample sizes or subjective assessments, potentially limiting result generalizability. Most studies were conducted in high-income countries, raising questions about their relevance to low-and middle-income settings with different healthcare needs and infrastructure. The evaluation of various LLMs and versions complicates drawing overarching conclusions. Inconsistent evaluation metrics across studies hindered result comparison and synthesis.
Conclusion
LLMs demonstrate transformative potential in patient education and engagement across various levels of medical care. Their ability to provide accurate, detailed, and timely information can significantly enhance patients’ understanding of their healthcare and promote active involvement. However, current limitations in accuracy and readability highlight the need for further refinement to ensure reliable integration with healthcare systems. Extensive research and development of AI tools are necessary to fully harness their potential for improving patient outcomes and healthcare efficiency. A critical priority for medical applications is to ensure the ethical and responsible use of these tools, necessitating robust supervision and validation processes.
The author(s) declare that no financial support was received for the research, authorship, and/or publication of this article.
Conflict of interest
The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.
Publisher’s note
All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article, or claim that may be made by its manufacturer, is not guaranteed or endorsed by the publisher.
Supplementary material
The Supplementary material for this article can be found online at: https://www.frontiersin.org/articles/10.3389/fmed.2024.1477898/full#supplementary-material
ReferencesWillmsALiuS. Exploring the feasibility of using Chatgpt to create just-in-time adaptive physical activity mHealth intervention content: case study. JMIR Med Educ. (2024) 10:e51426. doi: 10.2196/51426ParkYJPillaiADengJGuoEGuptaMPagetM. Assessing the research landscape and clinical utility of large language models: a scoping review. BMC Med Inform Decis Mak. (2024) 24:72. doi: 10.1186/s12911-024-02459-6, PMID: 38475802MengXYanXZhangKLiuDCuiXYangY. The application of large language models in medicine: a scoping review. iScience. (2024) 27:109713. doi: 10.1016/j.isci.2024.109713, PMID: 38746668MinssenTVayenaECohenIG. The challenges for regulating medical use of Chatgpt and other large language models. JAMA. (2023) 330:315–6. doi: 10.1001/jama.2023.9651, PMID: 37410482Open AI. (2024). Available at:https://openai.com/index/hello-gpt-4o (accessed 2024).Anthropic. (2024). Available at:https://www.anthropic.com/news/claude-3-5-sonnet (accessed 2024).Google. (2023). Available at:https://gemini.google.com/ (accessed 2024).PengWFengYYaoCZhangSZhuoHQiuT. Evaluating Ai in medicine: a comparative analysis of expert and Chatgpt responses to colorectal Cancer questions. Sci Rep. (2024) 14:2840. doi: 10.1038/s41598-024-52853-3, PMID: 38310152SallamM. Healthcare Chatgpt utility in healthcare education, research, and practice: systematic review on the promising perspectives and valid concerns. Healthcare (Basel). (2023) 11:887. doi: 10.3390/healthcare11060887, PMID: 36981544PreiksaitisCAshenburgNBunneyGChuAKabeerRRileyF. The Role of large language models in transforming emergency medicine: scoping review. JMIR Med Inform. (2024) 12:e53787:e53787. doi: 10.2196/53787, PMID: 38728687TriccoACLillieEZarinWO'BrienKKColquhounHLevacD. Prisma extension for scoping reviews (Prisma-Scr): checklist and explanation. Ann Intern Med. (2018) 169:467–73. doi: 10.7326/M18-0850, PMID: 30178033ArkseyHO'MalleyL. Scoping studies: towards a methodological framework. Int J Soc Res Methodol. (2005) 8:19–32. doi: 10.1080/1364557032000119616LevacDColquhounHO'BrienKK. Scoping studies: advancing the methodology. Implement Sci. (2010) 5:1–9. doi: 10.1186/1748-5908-5-69/TABLES/3BraunVClarkeV. Using thematic analysis in psychology. Qual Res Psychol. (2006) 3:77–101. doi: 10.1191/1478088706qp063oaAl-SharifEMPenteadoRCDib El JalboutNTopilowNJShojiMKKikkawaDO. Evaluating the accuracy of Chatgpt and Google Bard in fielding oculoplastic patient queries: a comparative study on artificial versus human intelligence. Ophthalmic. Plast Reconstr Surg. (2024) 40:303–11. doi: 10.1097/IOP.0000000000002567, PMID: 38215452AlapatiRCampbellDMolinNCreightonEWeiZBoonM. Evaluating insomnia queries from an artificial intelligence Chatbot for patient education. J Clin Sleep Med. (2024) 20:583–94. doi: 10.5664/jcsm.10948, PMID: 38217478Alessandri-BonettiMLiuHYPalmesanoMNguyenVTEgroFM. Online patient education in body contouring: a comparison between Google and Chatgpt. J Plast Reconstr Aesthet Surg. (2023) 87:390–402. doi: 10.1016/j.bjps.2023.10.091, PMID: 37939643AlmagazzachiAMustafaAEighaei SedehAVazquez GonzalezAEPolianovskaiaAAboodM. Generative artificial intelligence in patient education: Chatgpt takes on hypertension questions. Cureus. (2024) 16:e53441. doi: 10.7759/cureus.53441, PMID: 38435177AmaralJZSchultzRJMartinBMTaylorTToubanBMcGraw-HeinrichJ. Evaluating chat generative pre-trained transformer responses to common pediatric in-toeing questions. J Pediatr Orthop. (2024) 44:e592–7. doi: 10.1097/BPO.0000000000002695AminKSMayesLCKhoslaPDoshiRH. Assessing the efficacy of large language models in health literacy: a comprehensive cross-sectional study. Yale J Biol Med. (2024) 97:17–27. doi: 10.59249/ZTOZ1966, PMID: 38559461AnastasioATFBTMKaravanMPJrAdamsSBJr. Evaluating the quality and usability of artificial intelligence-generated responses to common patient questions in foot and ankle surgery. Foot Ankle Orthop. (2023) 8:24730114231209919. doi: 10.1177/24730114231209919, PMID: 38027458AtarereJNaqviHHaasCAdewunmiCBandaruSAllamneniR. Applicability of online chat-based artificial intelligence models to colorectal Cancer screening. Dig Dis Sci. (2024) 69:791–7. doi: 10.1007/s10620-024-08274-3, PMID: 38267726AthavaleABaierJRossEFukayaE. The potential of Chatbots in chronic venous disease patient management. JVS Vasc Insights. (2023) 1:1. doi: 10.1016/j.jvsvi.2023.100019, PMID: 37701430AyersJWPoliakADredzeMLeasECZhuZKelleyJB. Comparing physician and artificial intelligence Chatbot responses to patient questions posted to a public social media forum. JAMA Intern Med. (2023) 183:589–96. doi: 10.1001/jamainternmed.2023.1838, PMID: 37115527AyoubNFLeeYJGrimmDBalakrishnanK. Comparison between Chatgpt and Google search as sources of postoperative patient instructions. JAMA Otolaryngol Head Neck Surg. (2023) 149:556–8. doi: 10.1001/jamaoto.2023.0704, PMID: 37103921AyoubNFLeeYJGrimmDDiviV. Head-to-head comparison of Chatgpt versus Google search for medical knowledge acquisition. Otolaryngol Head Neck Surg. (2024) 170:1484–91. doi: 10.1002/ohn.465, PMID: 37529853BalelY. Can Chatgpt be used in Oral and maxillofacial surgery?J Stomatol Oral Maxillofac Surg. (2023) 124:101471. doi: 10.1016/j.jormas.2023.101471BellingerJRDe La ChapaJSKwakMWRamosGAMorrisonDKesserBW. Bppv information on Google versus ai (Chatgpt). Otolaryngol Head Neck Surg. (2024) 170:1504–11. doi: 10.1002/ohn.506, PMID: 37622581BernsteinIAZhangYVGovilDMajidIChangRTSunY. Comparison of ophthalmologist and large language model Chatbot responses to online patient eye care questions. JAMA Netw Open. (2023) 6:e2330320. doi: 10.1001/jamanetworkopen.2023.30320, PMID: 37606922BrozovićJMikulićBTomasMJuzbašićMBlaškovićM. Assessing the performance of Bing chat artificial intelligence: dental exams, clinical guidelines, and Patients' frequent questions. J Dent. (2024) 144:104927. doi: 10.1016/j.jdent.2024.104927, PMID: 38458379CaglarUYildizOMericAAyranciAGelmisMSarilarO. Evaluating the performance of Chatgpt in answering questions related to pediatric urology. J Pediatr Urol. (2024) 20:26.e1–5. doi: 10.1016/j.jpurol.2023.08.003, PMID: 37596194CampbellDJEstephanLEMastrolonardoEVAminDRHuntleyCTBoonMS. Evaluating Chatgpt responses on obstructive sleep apnea for patient education. J Clin Sleep Med. (2023) 19:1989–95. doi: 10.5664/jcsm.10728, PMID: 37485676CampbellDJEstephanLESinaEMMastrolonardoEVAlapatiRAminDR. Evaluating Chatgpt responses on thyroid nodules for patient education. Thyroid. (2024) 34:371–7. doi: 10.1089/thy.2023.0491, PMID: 38010917CappellaniFCardKRShieldsCLPulidoJSHallerJA. Reliability and accuracy of artificial intelligence Chatgpt in providing information on ophthalmic diseases and management to patients. Eye (Lond). (2024) 38:1368–73. doi: 10.1038/s41433-023-02906-0, PMID: 38245622CarninoJMPellegriniWRWillisMCohenMBPaz-LansbergMDavisEM. Assessing Chatgpt's responses to otolaryngology patient questions. Ann Otol Rhinol Laryngol. (2024) 133:658–64. doi: 10.1177/00034894241249621, PMID: 38676440ChenDParsaRHopeAHannonBMakEEngL. Physician and artificial intelligence Chatbot responses to Cancer questions from social media. JAMA Oncol. (2024) 10:956–60. doi: 10.1001/jamaoncol.2024.0836ChenXZhangWZhaoZXuPZhengYShiD. Icga-Gpt: report generation and question answering for Indocyanine green angiography images. Br J Ophthalmol. (2024) 108:1450–6. doi: 10.1136/bjo-2023-324446, PMID: 38508675CheongKXZhangCTanTEFennerBJWongWMTeoKY. Comparing generative and retrieval-based Chatbots in answering patient questions regarding age-related macular degeneration and diabetic retinopathy. Br J Ophthalmol. (2024) 108:1443–9. doi: 10.1136/bjo-2023-324533, PMID: 38749531CheongRCTUnadkatSMcNeillisVWilliamsonAJosephJRandhawaP. Artificial intelligence Chatbots as sources of patient education material for obstructive sleep Apnoea: Chatgpt versus Google Bard. Eur Arch Otorrinolaringol. (2024) 281:985–93. doi: 10.1007/s00405-023-08319-9, PMID: 37917165ChervonskiEHarishKBRockmanCBSadekMTeterKAJacobowitzGR. Generative artificial intelligence Chatbots may provide appropriate informational responses to common vascular surgery questions by patients. Vascular. (2024):17085381241240550. doi: 10.1177/17085381241240550, PMID: 38500300ChristyMMorrisMTGoldfarbCADyCJ. Appropriateness and reliability of an online artificial intelligence Platform's responses to common questions regarding distal radius fractures. J Hand Surg Am. (2024) 49:91–8. doi: 10.1016/j.jhsa.2023.10.019, PMID: 38069953CohenSABrantAFisherACPershingSDoDPanC. Dr. Google vs. Dr. Chatgpt: exploring the use of artificial intelligence in ophthalmology by comparing the accuracy, safety, and readability of responses to frequently asked patient questions regarding cataracts and cataract surgery. Semin Ophthalmol. (2024) 39:472–9. doi: 10.1080/08820538.2024.2326058ConnorsCGuptaKKhusidJAKhargiRYaghoubianAJLevyM. Evaluation of the current status of artificial intelligence for Endourology patient education: a blind comparison of Chatgpt and Google Bard against traditional information resources. J Endourol. (2024) 38:843–51. doi: 10.1089/end.2023.0696, PMID: 38441078CornelisonBRErstadBLEdwardsC. Accuracy of a Chatbot in answering questions that patients should ask before taking a new medication. J Am Pharm Assoc. (2003) 64:102110. doi: 10.1016/j.japh.2024.102110, PMID: 38670493CroenBJAbdullahMSBernsERapaportSHahnAKBarrettCC. Evaluation of patient education materials from large-language artificial intelligence models on carpal tunnel release. Hand. (2024) N Y:15589447241247332. doi: 10.1177/15589447241247332, PMID: 38660977CrookBSParkCNHurleyETRichardMJPidgeonTS. Evaluation of online artificial intelligence-generated information on common hand procedures. J Hand Surg Am. (2023) 48:1122–7. doi: 10.1016/j.jhsa.2023.08.003, PMID: 37690015CungMSosaBYangHSMcDonaldMMMatthewsBGVlugAG. The performance of artificial intelligence Chatbot large language models to address skeletal biology and bone health queries. J Bone Miner Res. (2024) 39:106–15. doi: 10.1093/jbmr/zjad007, PMID: 38477743DavisREpplerMAyo-AjibolaOLoh-DoyleJCNabhaniJSamplaskiM. Evaluating the effectiveness of artificial intelligence-powered large language models application in disseminating appropriate and readable health information in urology. J Urol. (2023) 210:688–94. doi: 10.1097/JU.0000000000003615, PMID: 37428117DimitriadisFAlkagietSTsigkrikiLKleitsiotiPSidiropoulosGEfstratiouD. Chatgpt and patients with heart failure. Angiology. (2024):33197241238403. doi: 10.1177/00033197241238403, PMID: 38451243DoğanLÖzçakmakcıGBYılmazĬE. The performance of Chatbots and the Aapos website as a tool for amblyopia education. J Pediatr Ophthalmol Strabismus. (2024) 61:325–31. doi: 10.3928/01913913-20240409-01, PMID: 38661309DubinJABainsSSDeRogatisMJMooreMCHameedDMontMA. Appropriateness of frequently asked patient questions following Total hip arthroplasty from Chatgpt compared to arthroplasty-trained nurses. J Arthroplast. (2024) 39:S306–11. doi: 10.1016/j.arth.2024.04.020, PMID: 38626863DurairajKKBakerOBertossiDDayanSKarimiKKimR. Artificial intelligence versus expert plastic surgeon: comparative study shows Chatgpt "wins" Rhinoplasty consultations: should we be worried?Facial Plast Surg Aesthet Med. (2023) 26:270–5. doi: 10.1089/fpsam.2023.0224, PMID: 37982677FahySNiemannMBöhmPWinklerTOehmeS. Assessment of the quality and readability of information provided by Chatgpt in relation to the use of platelet-rich plasma therapy for osteoarthritis. J Pers Med. (2024) 14:495. doi: 10.3390/jpm14050495FahySOehmeSMilinkovicDJungTBartekB. Assessment of quality and readability of information provided by Chatgpt in relation to anterior cruciate ligament injury. J Pers Med. (2024) 14:104. doi: 10.3390/jpm14010104, PMID: 38248805GabrielJShafikLAlanbukiALarnerT. The utility of the Chatgpt artificial intelligence tool for patient education and enquiry in robotic radical prostatectomy. Int Urol Nephrol. (2023) 55:2717–32. doi: 10.1007/s11255-023-03729-4, PMID: 37528247GajjarAAKumarRPPaliwodaEDKuoCCAdidaSLegarretaAD. Usefulness and accuracy of artificial intelligence Chatbot responses to patient questions for neurosurgical procedures. Neurosurgery. (2024) 95:171–178. doi: 10.1227/neu.0000000000002856, PMID: 38353558Garcia ValenciaOAThongprayoonCMiaoJSuppadungsukSKrisanapanPCraiciIM. Empowering inclusivity: improving readability of living kidney donation information with Chatgpt. Front Digit Health. (2024) 6:1366967. doi: 10.3389/fdgth.2024.1366967, PMID: 38659656GhanemDShuHBergsteinVMarracheMLoveAHughesA. Educating patients on osteoporosis and bone health: can "Chatgpt" provide high-quality content?Eur J Orthop Surg Traumatol. (2024) 34:2757–65. doi: 10.1007/s00590-024-03990-y, PMID: 38769125GhanemYKRouhiADAl-HoussanASalehZMocciaMCJoshiH. Dr. Google to Dr. Chatgpt: assessing the content and quality of artificial intelligence-generated medical information on appendicitis. Surg Endosc. (2024) 38:2887–93. doi: 10.1007/s00464-024-10739-5GordonEBTowbinAJWingrovePShafiqueUHaasBKittsAB. Enhancing patient communication with chat-Gpt in radiology: evaluating the efficacy and readability of answers to common imaging-related questions. J Am Coll Radiol. (2024) 21:353–9. doi: 10.1016/j.jacr.2023.09.011, PMID: 37863153GülŞErdemirİHanciVAydoğmuşEErkoçYS. How artificial intelligence can provide information about subdural hematoma: assessment of readability, reliability, and quality of Chatgpt, Bard, and perplexity responses. Medicine (Baltimore). (2024) 103:e38009. doi: 10.1097/MD.0000000000038009, PMID: 38701313GünaySYiğitYHalhalliHCTulgarSAlkahloutBHAzadAM. Ai in patient education: assessing the impact of Chatgpt-4 on conveying comprehensive information about chest pain. Am J Emerg Med. (2024) 77:220–1. doi: 10.1016/j.ajem.2023.12.047, PMID: 38242775HaidarOJaquesAMcCaughranPWMetcalfeMJ. Ai-generated information for vascular patients: assessing the standard of procedure-specific information provided by the Chatgpt Ai-language model. Cureus. (2023) 15:e49764. doi: 10.7759/cureus.49764, PMID: 38046759HalawaniAMitchellASaffarzadehMWongVChewBHForbesCM. Accuracy and readability of kidney stone patient information materials generated by a large language model compared to official urologic organizations. Urology. (2024) 186:107–13. doi: 10.1016/j.urology.2023.11.042, PMID: 38395071HernandezCAVazquez GonzalezAEPolianovskaiaAAmoro SanchezRMuyolema ArceVMustafaA. The future of patient education: Ai-driven guide for type 2 diabetes. Cureus. (2023) 15:e48919. doi: 10.7759/cureus.48919, PMID: 38024047HershenhouseJSMokhtarDEpplerMBRodlerSStorino RamacciottiLGanjaviC. Accuracy, readability, and understandability of large language models for prostate Cancer information to the public. Prostate Cancer Prostatic Dis. (2024). doi: 10.1038/s41391-024-00826-y, PMID: 38744934HillmannHAKAngeliniEKarfoulNFeickertSMueller-LeisseJDunckerD. Accuracy and comprehensibility of chat-based artificial intelligence for patient information on atrial fibrillation and cardiac implantable electronic devices. Europace. (2023) 26:euad369. doi: 10.1093/europace/euad369, PMID: 38127304HirparaMMAminLAloyanTShillehNLewisP. Does the internet provide quality information on metoidioplasty? Using the modified ensuring quality information for patients tool to evaluate artificial intelligence-generated and online information on metoidioplasty. Ann Plast Surg. (2024) 92:S361–5. doi: 10.1097/SAP.0000000000003797, PMID: 38689420HøjSThomsenSFMeteranHSigsgaardT. Artificial intelligence and allergic rhinitis: does Chatgpt increase or impair the knowledge?J Public Health (Oxf). (2024) 46:123–6. doi: 10.1093/pubmed/fdad219HristidisVRuggianoNBrownELGantaSRRStewartS. Chatgpt vs Google for queries related to dementia and other cognitive decline: comparison of results. J Med Internet Res. (2023) 25:e48966. doi: 10.2196/48966, PMID: 37490317IbrahimMTKhaskheliSAShahzadHNoordinS. Language-adaptive artificial intelligence: assessing Chatgpt's answer to frequently asked questions on Total hip arthroplasty questions. J Pak Med Assoc. (2024) 74:S161–4. doi: 10.47391/JPMA.AKU-9S-25, PMID: 38712426JaziAHDMahjoubiMShahabiSAlqahtaniARHaddadAPazoukiA. Bariatric evaluation through Ai: a survey of expert opinions versus Chatgpt-4 (Beta-Seov). Obes Surg. (2023) 33:3971–80. doi: 10.1007/s11695-023-06903-w, PMID: 37889368JohnsWLKellishAFarronatoDCiccottiMGHammoudS. Chatgpt can offer satisfactory responses to common patient questions regarding elbow ulnar collateral ligament reconstruction. Arthrosc Sports Med Rehabil. (2024) 6:100893. doi: 10.1016/j.asmr.2024.100893, PMID: 38375341JohnsonCMBradleyCSKenneKARabiceSTakacsEVollstedtA. Evaluation of Chatgpt for pelvic floor surgery counseling. Urogynecology (Phila). (2024) 30:245–50. doi: 10.1097/SPV.0000000000001459, PMID: 38484238JuhiAPipilNSantraSMondalSBeheraJKMondalH. The capability of Chatgpt in predicting and explaining common drug-drug interactions. Cureus. (2023) 15:e36272. doi: 10.7759/cureus.36272, PMID: 37073184KasthuriVSGlueckJPhamHDaherMBalmaceno-CrissMMcDonaldCL. Assessing the accuracy and reliability of Ai-generated responses to patient questions regarding spine surgery. J Bone Joint Surg Am. (2024) 106:1136–42. doi: 10.2106/JBJS.23.00914KimMJAdmaneSChangYKShihKKReddyATangM. Chatbot performance in defining and differentiating palliative care, supportive care, hospice care. J Pain Symptom Manage. (2024) 67:e381–91. doi: 10.1016/j.jpainsymman.2024.01.008, PMID: 38219964KingRCSamaanJSYeoYHModyBLombardoDMGhashghaeiR. Appropriateness of Chatgpt in answering heart failure related questions. Heart Lung Circ. (2024) 33:1314–8. doi: 10.1016/j.hlc.2024.03.005, PMID: 38821760KingRCSamaanJSYeoYHPengYKunkelDCHabibAA. A multidisciplinary assessment of Chatgpt's knowledge of amyloidosis: observational study. JMIR Cardio. (2024) 8:e53421. doi: 10.2196/53421, PMID: 38640472KöroğluEYFakıSBeştepeNTamAAÇuhacı SeyrekNTopalogluO. A novel approach: evaluating Chatgpt's utility for the management of thyroid nodules. Cureus. (2023) 15:e47576. doi: 10.7759/cureus.47576, PMID: 38021609KozailyEGeageaMAkdoganERAtkinsJElshazlyMBGuglinM. Accuracy and consistency of online large language model-based artificial intelligence chat platforms in answering Patients' questions about heart failure. Int J Cardiol. (2024) 408:132115. doi: 10.1016/j.ijcard.2024.132115KuckelmanIJWetleyKYiPHRossAB. Translating musculoskeletal radiology reports into patient-friendly summaries using Chatgpt-4. Skeletal Radiol. (2024) 53:1621–4. doi: 10.1007/s00256-024-04599-2KuckelmanIJYiPHBuiMOnuhIAndersonJARossAB. Assessing Ai-powered patient education: a case study in radiology. Acad Radiol. (2024) 31:338–42. doi: 10.1016/j.acra.2023.08.020, PMID: 37709612KuşcuOPamukAESütay SüslüNHosalS. Is Chatgpt accurate and reliable in answering questions regarding head and neck Cancer?Front Oncol. (2023) 13:1256459. doi: 10.3389/fonc.2023.1256459, PMID: 38107064LambertRChooZYGradwohlKSchroedlLRuiz De LuzuriagaA. Assessing the application of large language models in generating dermatologic patient education materials according to Reading level: qualitative study. JMIR Dermatol. (2024) 7:e55898. doi: 10.2196/55898, PMID: 38754096LangSVitaleJFeketeTFHaschtmannDReitmeirRRopelatoM. Are large language models valid tools for patient information on lumbar disc herniation? The spine surgeons' perspective. Brain Spine. (2024) 4:102804. doi: 10.1016/j.bas.2024.102804, PMID: 38706800LechienJRCarrollTLHustonMNNaunheimMR. Chatgpt-4 accuracy for patient education in laryngopharyngeal reflux. Eur Arch Otorrinolaringol. (2024) 281:2547–52. doi: 10.1007/s00405-024-08560-w, PMID: 38492008LeeTJCampbellDJPatelSHossainARadfarNSiddiquiE. Unlocking health literacy: the ultimate guide to hypertension education from Chatgpt versus Google Gemini. Cureus. (2024) 16:e59898. doi: 10.7759/cureus.59898, PMID: 38721479LeeTJRaoAKCampbellDJRadfarNDayalMKhraisA. Evaluating Chatgpt-3.5 and Chatgpt-4.0 responses on hyperlipidemia for patient education. Cureus. (2024) 16:e61067. doi: 10.7759/cureus.61067, PMID: 38803402LiLLiPWangKZhangLZhaoHJiH. Benchmarking state-of-the-art large language models for migraine patient education: a comparison of performances on the responses to common queries. J Med Internet Res. (2024) 26:e55927. doi: 10.2196/55927, PMID: 38828692LiWChenJChenFLiangJYuH. Exploring the potential of Chatgpt-4 in responding to common questions about Abdominoplasty: An Ai-based case study of a plastic surgery consultation. Aesth Plast Surg. (2024) 48:1571–83. doi: 10.1007/s00266-023-03660-0, PMID: 37770637LimBSethIKahSSofiadellisFRossRJRozenWM. Using generative artificial intelligence tools in cosmetic surgery: a study on Rhinoplasty, facelifts, and blepharoplasty procedures. J Clin Med. (2023) 12:6524. doi: 10.3390/jcm12206524, PMID: 37892665LiuHYAlessandri BonettiMDe LorenziFGimbelMLNguyenVTEgroFM. Consulting the digital doctor: Google versus Chatgpt as sources of information on breast implant-associated anaplastic large cell lymphoma and breast implant illness. Aesth Plast Surg. (2024) 48:590–607. doi: 10.1007/s00266-023-03713-4, PMID: 37903939LiuSMcCoyABWrightAPCarewBGenkinsJZHuangSS. Leveraging large language models for generating responses to patient messages-a subjective analysis. J Am Med Inform Assoc. (2024) 31:1367–79. doi: 10.1093/jamia/ocae052, PMID: 38497958LvXZhangXLiYDingXLaiHShiJ. Leveraging large language models for improved patient access and self-management: Assessor-blinded comparison between expert-and Ai-generated content. J Med Internet Res. (2024) 26:e55847. doi: 10.2196/55847, PMID: 38663010MashatianSArmstrongDGRitterARobbinsJAzizSAlenabiI. Building trustworthy generative artificial intelligence for diabetes care and limb preservation: a medical knowledge extraction case. J Diabetes Sci Technol. (2024):19322968241253568. doi: 10.1177/19322968241253568, PMID: 38767382MastrokostasPGMastrokostasLEEmaraAKWellingtonIJGinalisEHoutenJK. Gpt-4 as a source of patient information for anterior cervical discectomy and fusion: a comparative analysis against Google web search. Global. Spine J. (2024):21925682241241241. doi: 10.1177/21925682241241241, PMID: 38513636McCarthyCJBerkowitzSRamalingamVAhmedM. Evaluation of an artificial intelligence Chatbot for delivery of Ir patient education material: a comparison with societal website content. J Vasc Interv Radiol. (2023) 34:1760–8.e32. doi: 10.1016/j.jvir.2023.05.037, PMID: 37330210MikaAPMartinJREngstromSMPolkowskiGGWilsonJM. Assessing Chatgpt responses to common patient questions regarding Total hip arthroplasty. J Bone Joint Surg Am. (2023) 105:1519–26. doi: 10.2106/JBJS.23.00209, PMID: 37459402MikaAPMulveyHEEngstromSMPolkowskiGGMartinJRWilsonJM. Can Chatgpt answer patient questions regarding Total knee arthroplasty?J Knee Surg. (2024) 37:664–73. doi: 10.1055/s-0044-1782233, PMID: 38442904MishraVSarrajuAKalwaniNMDexterJP. Evaluation of prompts to simplify cardiovascular disease information generated using a large language model: cross-sectional study. J Med Internet Res. (2024) 26:e55388. doi: 10.2196/55388, PMID: 38648104MoazzamZLimaHAEndoYNoriaSNeedlemanBPawlikTM. A paradigm shift: online artificial intelligence platforms as an informational resource in bariatric surgery. Obes Surg. (2023) 33:2611–4. doi: 10.1007/s11695-023-06675-3MoiseACentomo-BozzoAOrishchakOAlnouryMKDanielSJ. Can Chatgpt guide parents on Tympanostomy tube insertion?Children (Basel). (2023) 10:1634. doi: 10.3390/children10101634MondalHMondalSPodderI. Using Chatgpt for writing articles for Patients' education for dermatological diseases: a pilot study. Indian Dermatol Online J. (2023) 14:482–6. doi: 10.4103/idoj.idoj_72_23, PMID: 37521213MondalHPanigrahiMMishraBBeheraJKMondalS. A pilot study on the capability of artificial intelligence in preparation of Patients' educational materials for Indian public health issues. J Family Med Prim Care. (2023) 12:1659–62. doi: 10.4103/jfmpc.jfmpc_262_23, PMID: 37767452MonroeCLAbdelhafezYGAtsinaKAmanENardoLMadaniMH. Evaluation of responses to cardiac imaging questions by the artificial intelligence large language model Chatgpt. Clin Imaging. (2024) 112:110193. doi: 10.1016/j.clinimag.2024.110193, PMID: 38820977MootzAACarvalhoBSultanPNguyenTPRealeSC. The accuracy of Chatgpt-generated responses in answering commonly asked patient questions about labor epidurals: a survey-based study. Anesth Analg. (2024) 138:1142–4. doi: 10.1213/ANE.0000000000006801, PMID: 38180897MunirMMEndoYEjazADillhoffMCloydJMPawlikTM. Online artificial intelligence platforms and their applicability to gastrointestinal surgical operations. J Gastrointest Surg. (2024) 28:64–9. doi: 10.1016/j.gassur.2023.11.019, PMID: 38353076MusheyevDPanALoebSKabarritiAE. How well Do artificial intelligence Chatbots respond to the top search queries about urological malignancies?Eur Urol. (2024) 85:13–6. doi: 10.1016/j.eururo.2023.07.004, PMID: 37567827NovOSinghNMannD. Putting Chatgpt's medical advice to the (Turing) test: survey study. JMIR Med Educ. (2023) 9:e46939. doi: 10.2196/46939, PMID: 37428540O'HaganRKimRHAbittanBJCaldasSUngarJUngarB. Trends in accuracy and appropriateness of alopecia Areata information obtained from a popular online large language model, Chatgpt. Dermatology. (2023) 239:952–7. doi: 10.1159/000534005, PMID: 37722370PanAMusheyevDBockelmanDLoebSKabarritiAE. Assessment of artificial intelligence Chatbot responses to top searched queries about Cancer. JAMA Oncol. (2023) 9:1437–40. doi: 10.1001/jamaoncol.2023.2947, PMID: 37615960ParekhASMcCahonJASNgheAPedowitzDIDanielJNParekhSG. Foot and ankle patient education materials and artificial intelligence Chatbots: a comparative analysis. Foot Ankle Spec. (2024):19386400241235834. doi: 10.1177/19386400241235834, PMID: 38504411PohlNBDerectorERivlinMBachouraATostiRKachooeiAR. A quality and readability comparison of artificial intelligence and popular health website education materials for common hand surgery procedures. Hand Surg Rehabil. (2024) 43:101723. doi: 10.1016/j.hansur.2024.101723, PMID: 38782361PotapenkoIMalmqvistLSubhiYHamannS. Artificial intelligence-based Chatgpt responses for patient questions on optic disc Drusen. Ophthalmol Ther. (2023) 12:3109–19. doi: 10.1007/s40123-023-00800-2, PMID: 37698823PradhanFFiedlerASamsonKOlivera-MartinezMManatsathitWPeeraphatditT. Artificial intelligence compared with human-derived patient educational materials on cirrhosis. Hepatol Commun. (2024) 8:e0367. doi: 10.1097/HC9.0000000000000367, PMID: 38358382Rahimli OcakogluSCoskunB. The emerging role of Ai in patient education: a comparative analysis of Llm accuracy for pelvic organ prolapse. Med Princ Pract. (2024) 33:330–7. doi: 10.1159/000538538RazdanSSiegalARBrewerYSljivichMValenzuelaRJ. Assessing Chatgpt's ability to answer questions pertaining to erectile dysfunction: can our patients trust it?Int J Impot Res. (2023). doi: 10.1038/s41443-023-00797-z, PMID: 37985815ReichenpfaderDRösslhuemerPDeneckeK. Large language model-based evaluation of medical question answering systems: algorithm development and case study. Stud Health Technol Inform. (2024) 313:22–7. doi: 10.3233/SHTI240006, PMID: 38682499RosterKKannRBFarabiBGronbeckCBrownstoneNLipnerSR. Readability and health literacy scores for Chatgpt-generated dermatology public education materials: cross-sectional analysis of sunscreen and melanoma questions. JMIR Dermatol. (2024) 7:e50163. doi: 10.2196/50163, PMID: 38446502SamaanJSYeoYHRajeevNHawleyLAbelSNgWH. Assessing the accuracy of responses by the language model Chatgpt to questions regarding bariatric surgery. Obes Surg. (2023) 33:1790–6. doi: 10.1007/s11695-023-06603-5, PMID: 37106269ŞanHBayrakçiÖÇağdaşBSerdengeçtiMAlagözE. Reliability and readability analysis of Gpt-4 and Google Bard as a patient information source for the Most commonly applied radionuclide treatments in Cancer patients. Rev Esp Med Nucl Imagen Mol (Engl Ed). (2024):500021. doi: 10.1016/j.remnie.2024.500021SciberrasMFarrugiaYGordonHFurfaroFAlloccaMTorresJ. Accuracy of information given by Chatgpt for patients with inflammatory bowel disease in relation to Ecco guidelines. J Crohns Colitis. (2024) 18:1215–21. doi: 10.1093/ecco-jcc/jjae040ŞenoymakMCErbaturNHŞenoymakİFıratSN. The role of artificial intelligence in endocrine management: assessing Chatgpt's responses to Prolactinoma queries. J Pers Med. (2024) 14:330. doi: 10.3390/jpm14040330, PMID: 38672957SethICoxAXieYBullochGHunter-SmithDJRozenWM. Evaluating Chatbot efficacy for answering frequently asked questions in plastic surgery: a Chatgpt case study focused on breast augmentation. Aesthet Surg J. (2023) 43:1126–35. doi: 10.1093/asj/sjad140, PMID: 37158147ShahYBGhoshAHochbergARRapoportELallasCDShahMS. Comparison of Chatgpt and traditional patient education materials for Men's health. Urol Pract. (2024) 11:87–94. doi: 10.1097/UPJ.0000000000000490, PMID: 37914380ShenSAPerez-HeydrichCAXieDXNellisJC. Chatgpt vs. web search for patient questions: what does Chatgpt Do better?Eur Arch Otorrinolaringol. (2024) 281:3219–25. doi: 10.1007/s00405-024-08524-0, PMID: 38416195ShiraishiMLeeHKanayamaKMoriwakiYOkazakiM. Appropriateness of artificial intelligence Chatbots in diabetic foot ulcer management. Int J Low Extrem Wounds. (2024):15347346241236811. doi: 10.1177/15347346241236811, PMID: 38419470SongHXiaYLuoZLiuHSongYZengX. Evaluating the performance of different large language models on health consultation and patient education in Urolithiasis. J Med Syst. (2023) 47:125. doi: 10.1007/s10916-023-02021-3, PMID: 37999899SpallekSBirrellLKershawSDevineEKThorntonL. Can we use Chatgpt for mental health and substance use education? Examining its quality and potential harms. JMIR Med Educ. (2023) 9:e51243. doi: 10.2196/51243, PMID: 38032714SrinivasanNSamaanJSRajeevNDKanuMUYeoYHSamakarK. Large language models and bariatric surgery patient education: a comparative readability analysis of Gpt-3.5, Gpt-4, Bard, and online institutional resources. Surg Endosc. (2024) 38:2522–32. doi: 10.1007/s00464-024-10720-2, PMID: 38472531SubramanianTAraghiKAmenTBKaidiASosaBShahiP. Chat generative Pretraining transformer answers patient-focused questions in cervical spine surgery. Clin Spine Surg. (2024) 37:E278–81. doi: 10.1097/BSD.0000000000001600, PMID: 38531823TailorPDDalvinLAChenJJIezziROlsenTWScruggsBA. A comparative study of responses to retina questions from either experts, expert-edited large language models, or expert-edited large language models alone. Ophthalmol Sci. (2024) 4:100485. doi: 10.1016/j.xops.2024.100485, PMID: 38660460TailorPDXuTTFortesBHIezziROlsenTWStarrMR. Appropriateness of ophthalmology recommendations from an online chat-based artificial intelligence model. Mayo Clin Proc Digit Health. (2024) 2:119–28. doi: 10.1016/j.mcpdig.2024.01.003, PMID: 38577703TaoBKHandzicAHuaNJVosoughiARMargolinEAMicieliJA. Utility of Chatgpt for automated creation of patient education handouts: An application in neuro-ophthalmology. J Neuroophthalmol. (2024) 44:119–24. doi: 10.1097/WNO.0000000000002074, PMID: 38175720WLTTChengRWeinblattAIBergsteinVLongWJ. An artificial intelligence Chatbot is an accurate and useful online patient resource prior to Total knee arthroplasty. J Arthroplast. (2024) 39:S358–62. doi: 10.1016/j.arth.2024.02.005, PMID: 38350517TepeMEmekliE. Assessing the responses of large language models (Chatgpt-4, Gemini, and Microsoft Copilot) to frequently asked questions in breast imaging: a study on readability and accuracy. Cureus. (2024) 16:e59960. doi: 10.7759/cureus.59960, PMID: 38726360TharakanSKleinBBartlettLAtlasAParadaSACohnRM. Do Chatgpt and Google differ in answers to commonly asked patient questions regarding Total shoulder and Total elbow arthroplasty?J Shoulder Elb Surg. (2024) 33:e429–37. doi: 10.1016/j.jse.2023.11.014, PMID: 38182023ThiaISalujaM. Chatgpt: is this patient education tool for urological malignancies readable for the general population?Res Rep Urol. (2024) 16:31–7. doi: 10.2147/RRU.S440633, PMID: 38259300Van BulckLMoonsP. What if your patient switches from Dr. Google to Dr. Chatgpt? A vignette-based survey of the trustworthiness, value, and danger of Chatgpt-generated responses to health questions. Eur J Cardiovasc Nurs. (2024) 23:95–8. doi: 10.1093/eurjcn/zvad038, PMID: 37094282WashingtonCJAbouyaredMKaranthSBraithwaiteDBirkelandASilvermanDA. The use of Chatbots in head and neck mucosal malignancy treatment recommendations. Otolaryngol Head Neck Surg. (2024) 171:1062–8. doi: 10.1002/ohn.818, PMID: 38769872WeiKFritzCRajasekaranK. Answering head and neck Cancer questions: An assessment of Chatgpt responses. Am J Otolaryngol. (2024) 45:104085. doi: 10.1016/j.amjoto.2023.104085, PMID: 37844413WrennSPMikaAPPonceRBMitchellPM. Evaluating Chatgpt's ability to answer common patient questions regarding hip fracture. J Am Acad Orthop Surg. (2024) 32:656–9. doi: 10.5435/JAAOS-D-23-00877, PMID: 38743959WrightBMBodnarMSMooreADMasedaMCKucharikMPDiazCC. Is Chatgpt a trusted source of information for Total hip and knee arthroplasty patients?Bone Jt Open. (2024) 5:139–46. doi: 10.1302/2633-1462.52.BJO-2023-0113.R1, PMID: 38354748WuGZhaoWWongALeeDA. Patients with floaters: answers from virtual assistants and large language models. Digit Health. (2024) 10:20552076241229933. doi: 10.1177/20552076241229933, PMID: 38362238WuYZhangZDongXHongSHuYLiangP. Evaluating the performance of the language model Chatgpt in responding to common questions of people with epilepsy. Epilepsy Behav. (2024) 151:109645. doi: 10.1016/j.yebeh.2024.109645, PMID: 38244419YallaGRHymanNHockLEZhangQShuklaAGKolomeyerNN. Performance of artificial intelligence Chatbots on Glaucoma questions adapted from patient brochures. Cureus. (2024) 16:e56766. doi: 10.7759/cureus.56766, PMID: 38650824YanSDuDLiuXDaiYKimMKZhouX. Assessment of the reliability and clinical applicability of Chatgpt's responses to Patients' common queries about Rosacea. Patient Prefer Adherence. (2024) 18:249–53. doi: 10.2147/PPA.S444928, PMID: 38313827YanSYLiuYFMaLXiaoLLHuXGuoR. Walking forward or on hold: could the Chatgpt be applied for seeking health information in neurosurgical settings?Ibrain. (2024) 10:111–5. doi: 10.1002/ibra.12149, PMID: 38682012YeCZweckEMaZSmithJKatzS. Doctor versus artificial intelligence: patient and physician evaluation of large language model responses to rheumatology patient questions in a cross-sectional study. Arthritis Rheumatol. (2024) 76:479–84. doi: 10.1002/art.42737, PMID: 37902018YeoYHSamaanJSNgWHTingPSTrivediHVipaniA. Assessing the performance of Chatgpt in answering questions regarding cirrhosis and hepatocellular carcinoma. Clin Mol Hepatol. (2023) 29:721–32. doi: 10.3350/cmh.2023.0089, PMID: 36946005YılmazIBEDoğanL. Talking technology: exploring Chatbots as a tool for cataract patient education. Clin Exp Optom. (2024):1–9. doi: 10.1080/08164622.2023.2298812YüceAErkurtNYerliMMisirA. The potential of Chatgpt for high-quality information in patient education for sports surgery. Cureus. (2024) 16:e58874. doi: 10.7759/cureus.58874, PMID: 38800159YunJYKimDJLeeNKimEK. A comprehensive evaluation of Chatgpt consultation quality for augmentation mammoplasty: a comparative analysis between plastic surgeons and laypersons. Int J Med Inform. (2023) 179:105219. doi: 10.1016/j.ijmedinf.2023.105219, PMID: 37776670ZalzalHGAbrahamAChengJShahRK. Can ChatGPT help patients answer their otolaryngology questions?Laryngoscope Investig Otolaryngol. (2024) 9:e1193. doi: 10.1002/lio2.1193, PMID: 38362184ZhangSLiauZQGTanKLMChuaWL. Evaluating the accuracy and relevance of Chatgpt responses to frequently asked questions regarding total knee replacement. Knee Surg Relat Res. (2024) 36:15. doi: 10.1186/s43019-024-00218-5, PMID: 38566254ZhangYDongYMeiZHouYWeiMYeungYH. Performance of large language models on benign prostatic hyperplasia frequently asked questions. Prostate. (2024) 84:807–13. doi: 10.1002/pros.24699, PMID: 38558009AbreuAAMurimwaGZFarahEStewartJWZhangLRodriguezJ. Enhancing readability of online patient-facing content: the role of Ai Chatbots in improving Cancer information accessibility. J Natl Compr Cancer Netw. (2024) 22:e237334. doi: 10.6004/jnccn.2023.7334AyreJMacOMcCafferyKMcKayBRLiuMShiY. New Frontiers in health literacy: using Chatgpt to simplify health information for people in the community. J Gen Intern Med. (2024) 39:573–7. doi: 10.1007/s11606-023-08469-w, PMID: 37940756BaldwinAJ. An artificial intelligence language model improves readability of burns first aid information. Burns. (2024) 50:1122–7. doi: 10.1016/j.burns.2024.03.005, PMID: 38492982BrowneRGullKHurleyCMSugrueRMO'SullivanJB. Chatgpt-4 can help hand surgeons communicate better with patients. J Hand Surg Glob Online. (2024) 6:436–8. doi: 10.1016/j.jhsg.2024.03.008, PMID: 38817773CovingtonEWWatts AlexanderCSSewellJHutchisonAMKayJToccoL. Unlocking the future of patient education: Chatgpt vs. Lexicomp® as sources of patient education materials. J Am Pharm Assoc (2003). (2024):102119. doi: 10.1016/j.japh.2024.102119DihanQChauhanMZEleiwaTKHassanAKSallamABKhouriAS. Using large language models to generate educational materials on childhood Glaucoma. Am J Ophthalmol. (2024) 265:28–38. doi: 10.1016/j.ajo.2024.04.004, PMID: 38614196EidKEidAWangDRaikerRSChenSNguyenJ. Optimizing ophthalmology patient education via Chatbot-generated materials: readability analysis of Ai-generated patient education materials and the American Society of Ophthalmic Plastic and Reconstructive Surgery Patient Brochures. Ophthalmic Plast Reconstr Surg. (2024) 40:212–6. doi: 10.1097/IOP.0000000000002549, PMID: 37972974EpplerMBGanjaviCKnudsenJEDavisRJAyo-AjibolaODesaiA. Bridging the gap between urological research and patient understanding: the role of large language models in automated generation of Layperson's summaries. Urol Pract. (2023) 10:436–43. doi: 10.1097/UPJ.0000000000000428, PMID: 37410015FanningJEEscobar-DomingoMJFoppianiJLeeDMillerASJanisJE. Improving readability and automating content analysis of plastic surgery webpages with Chatgpt. J Surg Res. (2024) 299:103–11. doi: 10.1016/j.jss.2024.04.006, PMID: 38749313HungYCChakerSCSigelMSaadMSlaterED. Comparison of patient education materials generated by chat generative pre-trained transformer versus experts: An innovative way to increase readability of patient education materials. Ann Plast Surg. (2023) 91:409–12. doi: 10.1097/SAP.0000000000003634, PMID: 37713147KirchnerGJKimRYWeddleJBBibleJE. Can artificial intelligence improve the readability of patient education materials?Clin Orthop Relat Res. (2023) 481:2260–7. doi: 10.1097/CORR.0000000000002668, PMID: 37116006MoonsPVan BulckL. Using Chatgpt and Google Bard to improve the readability of written patient information: a proof of concept. Eur J Cardiovasc Nurs. (2024) 23:122–6. doi: 10.1093/eurjcn/zvad087, PMID: 37603843PatelEAFleischerLFilipPEggerstedtMHutzMMichaelidesE. The use of artificial intelligence to improve readability of otolaryngology patient education materials. Otolaryngol Head Neck Surg. (2024) 171:603–8. doi: 10.1002/ohn.816, PMID: 38751109RouhiADGhanemYKYolchievaLSalehZJoshiHMocciaMC. Can artificial intelligence improve the readability of patient education materials on aortic stenosis? A pilot study. Cardiol Ther. (2024) 13:137–47. doi: 10.1007/s40119-023-00347-0, PMID: 38194058SridharanKSivaramakrishnanG. Enhancing readability of Usfda patient communications through large language models: a proof-of-concept study. Expert Rev Clin Pharmacol. (2024) 17:731–41. doi: 10.1080/17512433.2024.2363840, PMID: 38823007SudharshanRShenAGuptaSZhang-NunesS. Assessing the utility of Chatgpt in simplifying text complexity of patient educational materials. Cureus. (2024) 16:e55304. doi: 10.7759/cureus.55304, PMID: 38559518VallurupalliMShahNDVyasRM. Validation of Chatgpt 3.5 as a tool to optimize readability of patient-facing craniofacial education materials. Plast Reconstr Surg Glob Open. (2024) 12:e5575. doi: 10.1097/GOX.0000000000005575, PMID: 38313589GrimmDRLeeYJHuKLiuLGarciaOBalakrishnanK. The utility of Chatgpt as a generative medical translator. Eur Arch Otorrinolaringol. (2024). doi: 10.1007/s00405-024-08708-8, PMID: 38705894HeZBhasuranBJinQTianSHannaKShavorC. Quality of answers of generative large language models versus peer users for interpreting laboratory test results for lay patients: evaluation study. J Med Internet Res. (2024) 26:e56655. doi: 10.2196/56655, PMID: 38630520MeyerASolemanARieseJStreichertT. Comparison of Chatgpt, Gemini, and Le chat with physician interpretations of medical laboratory questions from an online health forum. Clin Chem Lab Med. (2024) 62:2425–34. doi: 10.1515/cclm-2024-0246, PMID: 38804035LyuQTanJZapadkaMEPonnatapuraJNiuCMyersKJ. Translating radiology reports into plain language using Chatgpt and Gpt-4 with prompt learning: results, limitations, and potential. Vis Comput Ind Biomed Art. (2023) 6:9. doi: 10.1186/s42492-023-00136-5SarangiPKLumbaniASwarupMSPandaSSahooSSHuiP. Assessing Chatgpt's proficiency in simplifying radiological reports for healthcare professionals and patients. Cureus. (2023) 15:e50881. doi: 10.7759/cureus.50881, PMID: 38249202RogaschJMMMetzgerGPreislerMGallerMThieleFBrennerW. Chatgpt: can You prepare my patients for [(18) F] Fdg pet/Ct and explain my reports?J Nucl Med. (2023) 64:1876–9. doi: 10.2967/jnumed.123.266114, PMID: 37709536TepeMEmekliE. Decoding medical jargon: the use of Ai language models (Chatgpt-4, Bard, Microsoft Copilot) in radiology reports. Patient Educ Couns. (2024) 126:108307. doi: 10.1016/j.pec.2024.108307, PMID: 38743965WooKCSimonGWAkindutireOAphinyanaphongsYAustrianJSKimJG. Evaluation of Gpt-4 ability to identify and generate patient instructions for actionable incidental radiology findings. J Am Med Inform Assoc. (2024) 31:1983–93. doi: 10.1093/jamia/ocae117, PMID: 38778578ZaretskyJKimJMBaskharounSZhaoYAustrianJAphinyanaphongsY. Generative artificial intelligence to transform inpatient discharge summaries to patient-friendly language and format. JAMA Netw Open. (2024) 7:e240357. doi: 10.1001/jamanetworkopen.2024.0357, PMID: 38466307AlaneziF. Examining the role of Chatgpt in promoting health behaviors and lifestyle changes among Cancer patients. Nutr Health. (2024):2601060241244563. doi: 10.1177/02601060241244563, PMID: 38567408BragazziNLGarbarinoS. Assessing the accuracy of generative conversational artificial intelligence in debunking sleep health myths: mixed methods comparative study with expert analysis. JMIR Form Res. (2024) 8:e55762. doi: 10.2196/55762, PMID: 38501898GarbarinoSBragazziNL. Evaluating the effectiveness of artificial intelligence-based tools in detecting and understanding sleep health misinformation: comparative analysis using Google Bard and Openai Chatgpt-4. J Sleep Res. (2024):e14210. doi: 10.1111/jsr.14210, PMID: 38577714GrayMBairdASawyerTJamesJDeBrouxTBartlettM. Increasing realism and variety of virtual patient dialogues for prenatal counseling education through a novel application of Chatgpt: exploratory observational study. JMIR Med Educ. (2024) 10:e50705. doi: 10.2196/50705, PMID: 38300696MinutoloADamianoEDe PietroGFujitaHEspositoM. A conversational agent for querying Italian patient information leaflets and improving health literacy. Comput Biol Med. (2022) 141:105004. doi: 10.1016/j.compbiomed.2021.105004, PMID: 34774337MondalHDashIMondalSBeheraJK. Chatgpt in answering queries related to lifestyle-related diseases and disorders. Cureus. (2023) 15:e48296. doi: 10.7759/cureus.48296, PMID: 38058315PonzoVGoitreIFavaroEMerloFDMancinoMVRisoS. Is Chatgpt an effective tool for providing dietary advice?Nutrients. (2024) 16:469. doi: 10.3390/nu16040469, PMID: 38398794ZaleskiALBerkowskyRCraigKJTPescatelloLS. Comprehensiveness, accuracy, and readability of exercise recommendations provided by an Ai-based Chatbot: mixed methods study. JMIR Med Educ. (2024) 10:e51308. doi: 10.2196/51308, PMID: 38206661AltamimiIAltamimiAAlhumimidiASTemsahMH. Snakebite advice and counseling from artificial intelligence: An acute venomous snakebite consultation with Chatgpt. Cureus. (2023) 15:e40351. doi: 10.7759/cureus.40351, PMID: 37456381McMahonHVMcMahonBD. Automating untruths: Chatgpt, self-managed medication abortion, and the threat of misinformation in a post-roe world. Front Digit Health. (2024) 6:1287186. doi: 10.3389/fdgth.2024.1287186, PMID: 38419805AliyevaASariEAlaskarovENasirovR. Enhancing postoperative Cochlear implant care with Chatgpt-4: a study on artificial intelligence (Ai)-assisted patient education and support. Cureus. (2024) 16:e53897. doi: 10.7759/cureus.53897ScheschenjaMViniolSBastianMBWessendorfJKönigAMMahnkenAH. Feasibility of Gpt-3 and Gpt-4 for in-depth patient education prior to interventional radiological procedures: a comparative analysis. Cardiovasc Intervent Radiol. (2024) 47:245–50. doi: 10.1007/s00270-023-03563-2, PMID: 37872295BainsSSDubinJAHameedDSaxOCDouglasSMontMA. Use and application of large language models for patient questions following Total knee arthroplasty. J Arthroplast. (2024) 39:2289–94. doi: 10.1016/j.arth.2024.03.017, PMID: 38490569BornaSGomez-CabelloCAPressmanSMHaiderSASehgalALeibovichBC. Comparative analysis of artificial intelligence virtual assistant and large language models in post-operative care. Eur J Investig Health Psychol Educ. (2024) 14:1413–24. doi: 10.3390/ejihpe14050093, PMID: 38785591CapellerasMSoto-GalindoGACruellasMApaydinF. Chatgpt and Rhinoplasty recovery: An exploration of Ai's role in postoperative guidance. Facial Plast Surg. (2024) 40:628–31. doi: 10.1055/a-2219-4901, PMID: 38029791ChakerSCHungYCSaadMGolinkoMSGaldynIA. Easing the burden on caregivers-applications of artificial intelligence for physicians and caregivers of children with cleft lip and palate. Cleft Palate Craniofac J. (2024):10556656231223596. doi: 10.1177/10556656231223596ShaoCYLiHLiuXLLiCYangLQZhangYJ. Appropriateness and comprehensiveness of using Chatgpt for perioperative patient education in thoracic surgery in different language contexts: survey study. Interact J Med Res. (2023) 12:e46900. doi: 10.2196/46900, PMID: 37578819LeeJCHamillCSShnayderYBuczekEKakaralaKBurAM. Exploring the role of artificial intelligence Chatbots in preoperative counseling for head and neck Cancer surgery. Laryngoscope. (2024) 134:2757–61. doi: 10.1002/lary.31243, PMID: 38126511NanjiKYuCWWongTYSivaprasadSSteelDHWykoffCC. Evaluation of postoperative ophthalmology patient instructions from Chatgpt and Google search. Can J Ophthalmol. (2024) 59:e69–71. doi: 10.1016/j.jcjo.2023.10.001DharSKothariDVasquezMClarkeTMarodaAMcClainWG. The utility and accuracy of Chatgpt in providing post-operative instructions following tonsillectomy: a pilot study. Int J Pediatr Otorhinolaryngol. (2024) 179:111901. doi: 10.1016/j.ijporl.2024.111901, PMID: 38447265PatilNSHuangRMihalacheAKisilevskyEKwokJPopovicMM. The ability of artificial intelligence Chatbots Chatgpt and Google Bard to accurately convey preoperative information for patients undergoing ophthalmic surgeries. Retina. (2024) 44:950–3. doi: 10.1097/IAE.0000000000004044, PMID: 38215455MeyerRHamiltonKMTruongMDWrightKNSiedhoffMTBrezinovY. Chatgpt compared with Google search and healthcare institution as sources of postoperative patient instructions after gynecological surgery. BJOG. (2024) 131:1154–6. doi: 10.1111/1471-0528.17746, PMID: 38177090BrenemanAGordonERTragerMHEnsslinCJFisherJHumphreysTR. Evaluation of large language model responses to Mohs surgery preoperative questions. Arch Dermatol Res. (2024) 316:227. doi: 10.1007/s00403-024-02956-8, PMID: 38787433KienzleANiemannMMellerSGwinnerC. Chatgpt may offer an adequate substitute for informed consent to patients prior to Total knee arthroplasty-yet caution is needed. J Pers Med. (2024) 14:69. doi: 10.3390/jpm14010069, PMID: 38248771AliRConnollyIDTangOYMirzaFNJohnstonBAbdulrazeqHF. Bridging the literacy gap for surgical consents: An Ai-human expert collaborative approach. NPJ Digit Med. (2024) 7:63. doi: 10.1038/s41746-024-01039-2, PMID: 38459205ShiraishiMTomiokaYMiyakuniAMoriwakiYYangRObaJ. Generating informed consent documents related to blepharoplasty using Chatgpt. Ophthalmic Plast Reconstr Surg. (2024) 40:316–20. doi: 10.1097/IOP.0000000000002574, PMID: 38133626AnYFangQWangL. Enhancing patient education in Cancer care: intelligent Cancer patient education model for effective communication. Comput Biol Med. (2024) 169:107874. doi: 10.1016/j.compbiomed.2023.107874, PMID: 38157775RobertsRHRAliSRDobbsTDWhitakerIS. Can large language models generate outpatient clinic letters at first consultation that incorporate complication profiles from Uk and USA aesthetic plastic surgery associations?Aesthet Surg J Open Forum. (2024) 6:ojad 109. doi: 10.1093/asjof/ojad109, PMID: 38192329XueZZhangYGanWWangHSheGZhengX. Quality and dependability of Chatgpt and Dingxiangyuan forums for remote orthopedic consultations: comparative analysis. J Med Internet Res. (2024) 26:e50882. doi: 10.2196/50882, PMID: 38483451