Artificial Intelligence is a field in which a machine exhibits intelligence by learning about itself. Artificial Intelligence may employ various approaches and algorithms to comprehend human intellect, but it is not limited. Machine Learning is a branch of AI that deals with techniques that can learn from experience on their own (1). In automated decision-making and predictive analytics, AI plays a crucial role (2). Methods based on various kinds of AI are already being used in a variety of climate change and environmental monitoring research sectors (3). Machine Learning and Deep Learning are used in education, finance, healthcare, agriculture, and many more. The application of Machine Learning in healthcare demonstrated encouraging results, instilling trust in the sector (4). There are varied reasons for using artificial intelligence in healthcare. Primarily, it helps to manage the clinical records of patients and aids in providing personalized treatment and medicines, early identification of disease, providing predictive analytics, which could help health officials take preventive measures in advance before the outbreak of any disease (5). Artificial Intelligence goes back to the too early 1990s and today has evolved into a burgeoning field with a significant contribution in healthcare (6) through various modes like drug and discovery, personalized treatment and medicine, preventive measures, a health assistant chatbot, clinical trial and researches, diagnosing and pathology, analytics, image processing and prediction of an outbreak. Artificial Intelligence is a boon, and Figure 1 demonstrates the evolution of AI in healthcare throughout 1950–2020. Climate change is long-term changes in temperature and weather patterns.These variations might be attributed to natural causes such as solar cycle oscillations. Due to the use of fossil fuels such as coal, oil, and gas, human activities have been the leading cause of climate change since the 1800s (7). Greenhouse gas emissions from fossil fuel combustion act as a blanket, trapping the sun's heat and boosting global temperatures. The amount of greenhouse gases in the atmosphere is at its highest level in 2 million years. Artificial Intelligence is a field in which a machine exhibits intelligence by learning about itself. Artificial Intelligence may employ various approaches and algorithms to comprehend human intellect, but it is not limited. Machine Learning is a branch of AI that deals with techniques that can learn from experience on their own. In automated decision-making and predictive analytics, AI plays a crucial role. Methods based on various kinds of AI are already being used in a variety of climate change and environmental monitoring research sectors. Machine Learning and Deep Learning are used in education, finance, healthcare, agriculture, and many more. The application of Machine Learning in healthcare demonstrated encouraging results, instilling trust in the sector (8). There are varied reasons for using artificial intelligence in healthcare. Primarily, it helps to manage the clinical records of patients and aids in providing personalized treatment and medicines, early identification of disease, providing predictive analytics, which could help health officials take preventive measures in advance before the outbreak of any disease. Artificial Intelligence goes back to the too early 1990s and today has evolved into a burgeoning field with a significant contribution in healthcare through various modes like drug and discovery, personalized treatment and medicine, preventive measures, a health assistant chatbot, clinical trial and researches, diagnosing and pathology, analytics, image processing and prediction of an outbreak. Artificial Intelligence is a boon, and Figure 1 demonstrates the evolution of AI in healthcare throughout 1950–2020. Climate change is long-term changes in temperature and weather patterns.These variations might be attributed to natural causes such as solar cycle oscillations. Due to the use of fossil fuels such as coal, oil, and gas, human activities have been the leading cause of climate change since the 1800s. Greenhouse gas emissions from fossil fuel combustion act as a blanket, trapping the sun's heat and boosting global temperatures. The amount of greenhouse gases in the atmosphere is at its highest level in 2 million years. Emissions are steadily increasing. Since the late 1800s, the Earth has warmed by around 1.1°C. The previous 10 years (2011–2020) have been the hottest on record. Figure 2 explains the causes of climate change and the effects due to those variations. Vector-borne illness is a severe public health threat in underdeveloped nations that is only becoming worse. Temperatures in the air and water, precipitation patterns, severe rainfall events, and seasonal changes are all known to impact disease transmission (9). At the moment, dengue (10) is spreading widely after COVID-19; dengue is a vector-borne disease that spreads through an infected female mosquito of species Aedes aegypti (11) and is one of the most common diseases in more than 100 countries (12). Aedes aegypti can be found in urban and suburban settings with high human population density and housing density. This species is endophilic, which means it seeks shelter inside structures. As a result, the intradomicile is more typically seen than the peridomicile. Tires, cans, bottles, pots, vats, brass, swimming pools, and abandoned aquariums are frequent breeding habitats filled with rainwater or household water.

These mosquitos carry the Chikungunya, yellow fever, and Zika viruses. Dengue fever is widespread in the tropics, with different risk levels based on rainfall, temperature, relative humidity, and unplanned fast urbanization. Dengue fever may be fatal if it is not treated appropriately. It was first discovered during dengue epidemics in the Philippines and Thailand in the 1950s. Most Asian and Latin American nations now have severe dengue fever, a leading cause of hospitalization and mortality among children and adults. A Flaviviridae virus causes dengue with four unique but closely related serotypes (DENV-1, DENV-2, DENV-3, DENV-4), and the fifth serotype of dengue has been detected in the Malaysian state of Sarawak (13). Dengue fever is caused by DENV infection in our bodies. Figure 3 depicts the common symptoms of dengue. Dengue fever causes severe joint and muscle pain, enlarged lymph nodes, headaches, fever, exhaustion, and a rash. Dengue fever is characterized by non-specific flu-like symptoms such as chills, appetite loss, lethargy, and low backache. According to a recent WHO research, dengue fever grew in several countries in 2020, including Bangladesh, Brazil, the Cook Islands, Ecuador, India, Indonesia, the Maldives, Mauritania, Mayotte, Nepal, Singapore, Sri Lanka, Sudan, Thailand, Timor-Leste, and Yemen. In 2019, dengue fever cases reached an all-time high in the world. Dengue fever is slowly gaining ground in 2021, with instances documented in several nations. Around 40 per cent of the world's population lives in areas with a high risk of dengue fever, such as tropical and subtropical climates. Dengue fever has become much more common in recent decades worldwide. According to one estimate, 390 million dengue virus infections occur each year (12). Emissions are steadily increasing. Since the late 1800s, the Earth has warmed by around 1.1°C. The previous 10 years (2011–2020) have been the hottest on record (9). Figure 2 explains the causes of climate change and the effects due to those variations. Vector-borne illness is a severe public health threat in underdeveloped nations that is only becoming worse. Temperatures in the air and water, precipitation patterns, severe rainfall events, and seasonal changes are all known to impact disease transmission (10). At the moment, dengue (11) is spreading widely after COVID-19; dengue is a vector-borne disease that spreads through an infected female mosquito of species Aedes aegypti (12) and is one of the most common diseases in more than 100 countries (14). Aedes aegypti can be found in urban and suburban settings with high human population density and housing density. This species is endophilic, which means it seeks shelter inside structures. As a result, the intradomicile is more typically seen than the peridomicile. Tires, cans, bottles, pots, vats, brass, swimming pools, and abandoned aquariums are frequent breeding habitats filled with rainwater or household water (13). These mosquitos carry the Chikungunya, yellow fever, and Zika viruses. Dengue fever is widespread in the tropics, with different risk levels based on rainfall, temperature, relative humidity, and unplanned fast urbanization. Dengue fever may be fatal if it is not treated appropriately. It was first discovered during dengue epidemics in the Philippines and Thailand in the 1950s. Most Asian and Latin American nations now have severe dengue fever, a leading cause of hospitalization and mortality among children and adults. A Flaviviridae virus causes dengue with four unique but closely related serotypes (DENV-1, DENV-2, DENV-3, DENV-4), and the fifth serotype of dengue has been detected in the Malaysian state of Sarawak (15). Dengue fever is caused by DENV infection in our bodies. Dengue fever causes severe joint and muscle pain, enlarged lymph nodes, headaches, fever, exhaustion, and a rash. Dengue fever is characterized by non-specific flu-like symptoms such as chills, appetite loss, lethargy, and low backache. According to a recent WHO research, dengue fever grew in several countries in 2020, including Bangladesh, Brazil (16), the Cook Islands, Ecuador, India (17), Indonesia (18), the Maldives, Mauritania, Mayotte, Nepal, Singapore (19), Sri Lanka, Sudan, Thailand (20), Timor-Leste, and Yemen. In 2019, dengue fever cases reached an all-time high in the world. Dengue fever is slowly gaining ground in 2021, with instances documented in several nations (14). Around 40 per cent of the world's population lives in areas with a high risk of dengue fever, such as tropical and sub-tropical climates. Dengue fever has become much more common in recent decades worldwide. According to one estimate, 390 million dengue virus infections occur each year (14). Dengue fever will affect 60 per cent of the world's population by 2080, according to researchers who blame climate change for the disease's spread. Climate change is widely cited as a contributing factor in the rapid spread of pandemic disease (21). Climate change is frequently identified by WHO, national, and international health authorities as one of the primary causes of the global spread of dengue fever and other Aedes-transmitted viral infections. According to the World Health Organization, dengue fever has become increasingly widespread internationally in recent decades (WHO). According to the World Health Organization, dengue fever affects 50–100 million people globally each year. As a result, it is vital to anticipate dengue epidemics. The accuracy of dengue epidemic prediction is currently a problem that must be addressed. The role of climate variables in predicting dengue outbreaks has been studied in a small number of studies. Tropical countries are the hardest hit because of their environmental, climatic, and socioeconomic characteristics (22). The weather has an impact on the vector-borne illness dengue's temporal and geographical spread. As a result, rainfall and ambient temperature are referred to as macro factors that influence dengue since they directly impact Aedes aegypti population density, which varies seasonally based on these important variables. Its population density tends to decline drastically during less precipitation and lower average temperatures in regions with a tropical or subtropical climate. Still, it grows consistently in locations with a tropical or subtropical environment (23). As the vector-weather association is as significant as the vector-human interaction, studies of climatic variables can have a better understanding of epidemic seasonality and the ability to anticipate it (24). In recent years, epidemiological research has focused on developing mathematical and statistical models based on weather parameters to explain the dynamics of dengue fever incidence. Its main goal was to find models with promising future predicting the potential of dengue incidence to help public health officials. Several researchers investigate the link between climate variables and dengue fever, frequently employing time-series analyses to characterize temporal trends, uncover patterns, and even make forecasts. Bhatt et al. (21) Many parameters, such as entomological, epidemiological, and geographic characteristics, can help predict the dengue outbreak effectively. Artificial intelligence has been employed in healthcare for a long time. This review study discusses the studies undertaken until now. Figure 4 represents road-map of the present study. It investigates several other vulnerable groups that will be useful in predicting positive dengue cases and eventually help prevent the outbreak and take preventive measures at an early stage. The present study is structured as follows: Section 2 describes the methodology and objectives of the survey carried out; Section 3 provides a detailed analytical review of the papers; Section 4 discusses the challenges and future work, and Section 5 concludes the present study.

To carry out the systematic literature review of dengue prediction models, process was followed which included i) establishing research questions, ii) developing a search strategy to narrow down the results, iii) selecting papers using eligibility criteria and iv) analyzing to extract strengths, weaknesses, and difficulties to overcome from articles. The main objectives of this systematic literature review are i) To gather and describe dengue machine learning models for dengue surveillance systems and ii) To illustrate the obstacles that future dengue modeling studies will face.

Forty articles of period 2019–2021 were reviewed and analyzed to understand the dengue prediction models and how different factors like meteorological conditions, laboratory tests, symptoms, demographic features were dependent variables for the rise of dengue cases.

According to the number of people infected, dengue fever is the most common arboviral disease in the world. Understanding the precise relationship between meteorology and dengue transmission is not a simple process because dengue transmission involves dengue viruses, vectors, and susceptible people. Furthermore, forecasting the future of dengue under various climate change scenarios involves a complete understanding of the association between climate and dengue and future climate and other variables. Despite this, a lot of progress has been achieved in this area. Despite the advances achieved in forecasting dengue's future, numerous uncertainties remain (59). To begin with, socio-demographic factors play a significant influence in dengue transmission, and including socio-demographic components into future dengue, projections remains a challenge. Second, in previous studies estimating the future of dengue, the increasing temperature has been commonly employed as a climate change indicator, with rainfall and humidity being under-researched. According to Hales et al., the climate indicator that most correctly predicts the occurrence of dengue fever is vapor pressure, which is a temperature and humidity measurements. However, the relationships between numerous environmental conditions and dengue transmission are complex and sometimes non-linear. Dengue modeling is an essential technique for early detection of dengue outbreaks, assessing risk factors for Severe Dengue, and possibly controlling the disease's vectors. Although much research has been done on these topics, it is critical to understand what areas of dengue modeling still have to be explored to build future research that will significantly reduce disease morbidity rates. The primary goal of this study was to provide an overview of dengue modeling and identify critical issues for future research. This section focuses on the limitations of the studies that have been reviewed. Some research problems or opportunities are described based on those restrictions.

A systematic literature review was conducted on predicting dengue based on climatic change using machine learning techniques. The main objective was to understand the research and studies that have been carried in building a dengue outbreak prediction model. Forty articles were chosen and analyzed to determine the state-of-the-art from many scientific libraries. The results of the review represent that dengue modeling is continuously growing. Logistic Regression, LASSO Regression, and Support Vector Machine approaches were the most commonly used diagnostic models. Because of their ease of implementation and interpretation, they are the most widely used modeling techniques. Although alternative strategies, such as decision trees, are simple to understand, they have a large number of nodes and take a significant amount of mental work to comprehend a specific forecast. These models, on the other hand, are just a set of coefficients, which makes it appealing to learn about the impact of attributes on the predictor variable. Furthermore, continuous independent variables do not have a normal distribution, and continuous and discrete predictors can be used in the regression. In terms of feature types, climate data was the most commonly used in these models. Dengue incidence data of patients is not readily available through APIs, which has been a restriction in many studies and should be considered for future work by forecasting dengue incidence for sensitive groups such as the age and gender of patients. The examined articles had several flaws, including the lack of documentation of the pre-processing procedures employed, the unavailability of patient data, and incomplete data. Following the review of the papers' strengths and shortcomings, future research projects were identified: i) using microclimatic parameters such as wind speed, air pressure, or vegetation index, ii) using demographic and socioeconomic aspects, iii) exploring climatic conditions in different places, iv) using vector density data, and v) taking vaccination drives into account when building a prediction model. Forecasting the future of dengue fever in the context of climate change can assist governments and public health professionals in implementing timely and preventative steps to protect people from dengue in the future. To sum up, climate change is creating an alarming situation affecting many sectors. Dengue has been a reason of concern for a long time. Hence, monitoring the fluctuations of weather patterns can aid in creating a dengue surveillance system that would be of great help to the health sector in taking preventive measures well in advance.

The original contributions presented in the study are included in the article/supplementary material, further inquiries can be directed to the corresponding author.

SPat, SPan, and DB: conceptualization. SB, QI, and SI: funding acquisition. DB and SPat: investigation and methodology, writing of the original draft, and data curation. SB: project administration and visualization. QI and SI: resources and supervision. SPan and SB: writing of the review and editing. SPan: validation. All authors contributed to the article and approved the submitted version.

This work was supported by the Deanship of Scientific Research, Vice Presidency for Graduate Studies and Scientific Research, King Faisal University, Saudi Arabia (Project no. GRANT 268).

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.

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.