Through surveillance and reporting, Saudi Arabia’s PHO is currently responsible for tracking key public health indicators such as the prevalence of comorbidities and mortality rates, risk factors, and healthcare service utilisation rates (22, 23). This information is extracted and synthesised from multiple resources, such as electronic health records (EHRs), administrative databases, and national surveys (24). This standard was adapted from an international standard set by the WHO and the CDC (25, 26). As an example of such information compiled by the PHO, an executive summary of stroke patients in the Kingdom is shown in Figure 1. It indicates the number of cases and their location, sex, and age at diagnosis. This information is valuable for data-driven, precise decision-making, providing prompt intervention and early prevention where they are most required. This, in turn, helps ensure that the provided services are sustainable and of high quality in order to achieve better health outcomes.

To provide targeted interventions in high-risk or underserved communities, the PHO assesses disease distribution across regions by conducting a geospatial analysis (27, 28). This sheds light on regional health cluster performance and helps reduce regional health inequities (29).

PHOs are also intended to be the main authoritative source of accurate and validated population-level health data. In the case of Saudi Arabia’s PHO, one of its main functions is to aid in the update of policies for national programmes, such as those against obesity and smoking and for promoting maternal health, as well as to evaluate their performance based on actual individual-level records rather than estimates (30–32). It also plays a critical role in integrating data across the MoH using demographic registries and Sehaty to support longitudinal analytics (29, 33, 34). Through this work, the PHO can help decision-makers by providing data-driven and evidence-based recommendations.

The sectors involved in health and healthcare-related legislative and/or medical activities in Saudi Arabia include the government, public, and private sectors. The role of the MoH is to oversee all healthcare providers, providing legislation and governance (35), while ensuring alignment across different sectors and engaging research centres, academic institutions, and regional public health departments (36). This collaboration also extends to international organisations, including the WHO, the Global Health Data Exchange (GHDx), and the World Bank, enhancing methodological transparency and benchmarking (18, 26, 28).

The PHO of Saudi Arabia’s MoH is also involved in stratifying health risks and priorities and introducing population health management (PHM) (2). This encompasses broader population-level strategies and prioritises individualised personalised care and stakeholder engagement to address changing demographics and disease patterns, health promotion, and policy development (37, 38). Integrated data analytics are crucial to enhance care delivery and understand the needs of the population in question, particularly when healthcare payment models change (39). Looking forward, the PHO is intended to expand into a national observatory of PPH, including data streams, to develop actionable insights from environmental, socio-economic, behavioural, and genetic perspectives (40–42). Collaboration with regional health clusters and universities will strengthen data governance capabilities and improve customised prediction models that are tailored specifically to Saudi Arabia’s epidemiological and demographic landscape (43, 44). Functioning within the PHO, the PHM should align with existing public health entities, such as the MoH regional health clusters, and the Public Health Authority requires clarification of analytical roles, data governance, and strategic responsibilities (29, 42). This aligns with Vision 2030 and should increase the average life expectancy and enable PPH (2, 45).

The Saudi PHO currently utilises machine learning (ML) and AI for various healthcare-related purposes, which presents significant opportunities in epidemic modelling, hospital demand forecasting, and chronic disease risk prediction and stratification (46–48). Such models offer a substantial opportunity for analytics to support descriptive and stratified population health reporting through predictive dashboards and health behaviour trend models, rule-based risk stratification, data linkage across multiple sources, and automated generation of indicators to notify policy dashboards (49, 50). Furthermore, to improve public health responses, pattern recognition, such as natural language processing, could be used to enable disease spread forecasting and enhance epidemic preparedness (49, 50).

Current AI models primarily focus on enhancing analytic efficiency for decision-making support rather than on fully autonomous predictive modelling; however, they provide a foundation for the development of advanced AI applications. Benefits for primary healthcare and hospital demand forecasting can accrue from the PHO if it employs ML algorithms to analyse EHRs for predicting patient inflow and optimising hospital operations and resource allocation (51, 52). Predictive models can also improve triage and treatment planning by reducing costs and ensuring patient safety through predictive models (52). AI tools can also be used to stratify patients based on their likelihood of developing non-communicable diseases by identifying risk factors that can prevent their development or progression through targeted interventions (51, 53). These technologies can provide early warning alerts through predictive dashboards as well as health behaviour trend models, which could revolutionise proactive public health planning (49, 50). With scalability framed as future directions by a plan for phased developments, by integrating ML techniques for early warning systems, introducing population risk stratification with governance safeguards and validation processes. This aligns with evidence from around the world, emphasising that successful AI adoption in healthcare systems necessitates a development-staged approach relying on data transparency, maturity, human oversight, and robust data infrastructure (46–48).

The PHO has the potential to grow into a national public health intelligence with links to academia, enabling innovation and independent evaluation (74). However, this requires a legal framework to ensure that data sharing occurs appropriately and safely (75).

It is necessary to develop collaborative programmes between national and international public health agencies and universities to create a skilled workforce capable of analysing and interpreting different sets of data (34, 76).

Knowledge translation is an essential role of the PHO, which should involve the regular issuance of publications such as risk reports and health bulletins, along with dashboards to provide real-time visual updates, not only for policymakers but also for the public through the Digital Twin (DT), healthcare professionals, and the media. This can also provide data-driven evidence translation, which is key to maximising data utility (18, 75, 77).

The PHO provides real-time updates on the disease burden and SDoH on a national scale, focusing on those with disabilities and other vulnerable populations, including migrants, by monitoring, updating, and creating solutions for new and impactful national policies (78, 79). For future PHO development, the integration of indicators reflecting commercial and digital determinants, including environmental exposure, consumption of unhealthy products, and utilisation patterns, should also be considered while strengthening digital transformation efforts and monitoring health equities with a focus on reducing disparities (80, 81).

Rather than focusing solely on individuals, genetic data can be monitored across populations to prevent diseases and promote health (82). Screening programmes can also be monitored and updated, accelerating the identification of rare diseases and providing early interventions, thus facilitating personalised medical plans that can improve public health outcomes (83). The PHO can also monitor current programmes for screening newborns and couples prior to attempts to conceive, including efforts to prevent rare diseases (84–87). It can also provide a database that accelerates the identification of genetic variations arising from the founder effect, which is associated with the Saudi population, and recalibrates variants of unknown significance (88, 89). Models for predicting diseases with complex inheritance can also be employed to identify the possibility of psychological, behavioural, and other complex phenotypes based on genetic/genomic sequences (77, 90). Beyond genomics, the integration of multi-omics technologies (i.e., metabolomics, proteomics, transcriptomics and epigenetics) will provide a more holistic view of health, incorporating the accurate prediction of biological functional modules and enabling comprehensive health assessments that correlate with health conditions (91, 92). This will activate the DT with a precision model, such as the BFM-ash model, which provides an assessment of health status based on biological functional modules (92). This PPH approach within the PHO is reflected in (i) the development of standardised indicators, (ii) datasets integrating data from multiple sectors, (iii) interactive dashboards to aid decision-making, and (iv) reporting stratified by individual or region, and alternatively nationwide, to support prioritisation and targeted interventions.

Despite the substantial efforts made by the MoH to implement the Saudi PHO, which oversees the country’s healthcare system and its activities, clear legal autonomy aligned with the national health strategy is required. There is also a need to introduce a performance index to provide accurate assessments for decision-makers.