Currently submitted to: Online Journal of Public Health Informatics
Date Submitted: Jul 15, 2026
Open Peer Review Period: Jul 27, 2026 - Sep 21, 2026
(currently open for review)
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Assessing the Capacity of U.S. Health Data Systems to Support AI-Driven Population Health Surveillance and Risk Prediction
ABSTRACT
Background:
Background:
With rapid development of artificial intelligence in health care, the ability of health systems to support artificial intelligence (AI)-enabled population health surveillance and risk prediction is unknown. Fragmented data infrastructure, structural disparities, and variation in system performance limit the scalability and equity of AI.
Objective:
Objective:
The aim of this study was to assess the capacity of U.S. health data systems to support AI-driven population health surveillance and risk prediction by evaluating patient experience, clinical outcomes, and data infrastructure using publicly available national health data reports.
Methods:
Methods:
We conducted a cross-sectional observational study using publicly available datasets from the Centers for Medicare & Medicaid Services (HCAHPS), the Agency for Healthcare Research and Quality (HCUP), and the Office of the National Coordinator/American Hospital Association. The studied variables were patient experience stability, clinical outcome variation/disparity, and data infrastructure capacity. We calculated comparative measures across the nation using the Kruskal–Wallis test and developed an AI Readiness Index using normalized (0–1 scale) and equally weighted aggregated indicators.
Results:
Results:
The overall readiness was moderate (AI Readiness Index = 0.64). The patient experience and clinical outcome showed high stability with no statistical significant difference across regions, suggesting structural consistency among health systems. Meanwhile, significant disparities were observed across age, income, payer, and geographic groups (P < .05), which may pose potential biases in AI prediction across systems. The data infrastructure exhibited strong availability (83%) but low interoperability (60%) and standardization (46) percentages, which hinder further implementation
Conclusions:
Conclusions:
The US health data system exhibits moderate capacity to support AI-enabled population health surveillance and risk prediction. System stability to support scalability is present, while structural disparities and data infrastructure limitations exist. Addressing these barriers through improved interoperability, data quality, and equity-focused governance frameworks are necessary to enable reliable and scalable equitable AI health monitoring.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.