Predict Predict uses integrated data from across Abu Dhabi’s health ecosystem to generate system-wide foresight. It consolidates clinical, financial, genomic, behavioural and environmental information into continuous analytics that identify risk, anticipate demand and guide early decision-making. Curation and integration transform this information into a reliable, interoperable resource, where data is standardized, cleaned and validated through automated and human quality-assurance processes. Consistent formatting, redundancy removal and continuous completeness checks ensure that datasets from different domains can be linked without loss of accuracy. Machine learning (ML) and statistical models scan these linked datasets for anomalies and trends. They detect, for example, spikes in respiratory illness, shifts in prescribing behaviour or facilities nearing capacity. Abu Dhabi’s data sources and contributors BOX 2 More than 100,000 integrated data streams feed Abu Dhabi’s system, including: –Medical records – Malaffi14 – Health Information Exchange: 3.5 billion unique clinical records, more than 3,000 connected facilities –Claims – Shafafiya15 – Health Financial Exchange: 2 billion activities, over 10 million unique individuals –Genomics – Emirati Genome Programme16 – 850,000 samples sequenced, more than 110 petabytes of data, 1.2 million-plus biobank samples –Lifestyle and wellness – data from Sahatna17 – wearables and preventive initiatives –Environmental signals – air quality, heat, pollutants, Rasid Laboratory wastewater surveillance18 Prevent Once predictive models identify emerging risks, the signals are distributed to providers, payers and planners. Each uses defined response protocols to adjust care delivery, resource allocation or oversight measures before service impact occurs. The “Prevent” strand applies predictive signals across the ecosystem, and even across government entities, to reduce avoidable risk before it becomes visible in clinical or operational outcomes: –Individuals receive personalized recommendations and screening prompts through Sahatna, guiding lifestyle choices and adherence to treatment plans. –Providers act on early warnings generated by predictive models – adjusting staffing, scheduling and infection-control measures in response to projected demand. –Payers and regulators use usage forecasts and anomaly detection to refine authorization criteria and monitor high-risk patterns before costs escalate. –System planners apply predictive maintenance schedules and procurement triggers that secure stock levels and keep essential infrastructure running. –Other government entities, including education, environment and social policy departments, draw on shared intelligence to design preventive actions beyond the health sector, from school-based well-being initiatives to environmental risk mitigation and urban planning decisions. These actions occur upstream of pressure points, allowing the health system to prevent disease progression, maintain service quality and sustain fiscal and operational resilience. A New Era for Digital Health: Abu Dhabi’s Leap to Health Intelligence 15

A New Era for Digital Health 2026