Maintenance Notice

Due to necessary scheduled maintenance, the JMIR Publications website will be unavailable from Wednesday, July 01, 2020 at 8:00 PM to 10:00 PM EST. We apologize in advance for any inconvenience this may cause you.

Who will be affected?

Accepted for/Published in: Interactive Journal of Medical Research

Date Submitted: Apr 20, 2026
Date Accepted: Sep 14, 2026

The final, peer-reviewed published version of this preprint can be found here:

Application of Machine Learning Algorithms to Health Systems Planning and Public Policy Using Real-World Data: Scoping Review

Rocha DMA, Barbosa GV, Bermejo PHdS

Application of Machine Learning Algorithms to Health Systems Planning and Public Policy Using Real-World Data: Scoping Review

Interact J Med Res 2026;15:e96779

DOI: 10.2196/96779

Application of Machine Learning Algorithms in Health Systems Planning and Public Policy Using Real-World Data: A Scoping Review

  • Deusa Maria Arruda Rocha; 
  • Gentil Veloso Barbosa; 
  • Paulo Henrique de Souza Bermejo

ABSTRACT

Background:

The rapid advancement of Information Technology and Machine Learning (ML) has garnered significant interest from healthcare managers and policymakers. However, incorporating reliable and transparent predictions into health systems remains challenging, necessitating an investigation into digital health intervention gaps within real-world settings characterized by resource constraints and reliability issues.

Objective:

To map and synthesize evidence on ML algorithm applications in the health domain, identifying their clinical implications for health planning and public policy formulation.

Methods:

A scoping review was conducted following the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) guidelines. Comprehensive searches were performed across MEDLINE (via PubMed), EMBASE, Scopus, and LILACS databases. The search strategy included quantitative studies utilizing real-world data and elective surgical workflows published between 2016 and 2025. Methodological quality was independently assessed using the Quality Assessment Tool for Quantitative Studies from the Effective Public Health Practice Project (EPHPP).

Results:

Results:

Six studies met the eligibility criteria. Interventions were synthesized by objective, design, algorithms, primary outcomes, and statistical significance. The predictive models demonstrated high discriminatory capacity, with Area Under the Receiver Operating Characteristic (AUROC) curve values ranging from 0.76 to 0.99. Key applications included orthopedic outcomes, patient blood management, and urgency classification, suggesting positive impacts on patient safety and service delivery efficiency.

Conclusions:

ML applications are promising for clinical decision support and health planning, although low methodological standardization and algorithmic opacity remain significant challenges. Future research should prioritize real-world evidence for flow management and waiting-list reduction, integrating emerging technologies such as Natural Language Processing (NLP) to enhance outcome monitoring and policy transparency. Clinical Trial: Not applicable (Scoping Review). The complete electronic search strategies were documented and registered with persistent identifiers (DOI) via the searchRxiv repository to ensure transparency and reproducibility.


 Citation

Please cite as:

Rocha DMA, Barbosa GV, Bermejo PHdS

Application of Machine Learning Algorithms to Health Systems Planning and Public Policy Using Real-World Data: Scoping Review

Interact J Med Res 2026;15:e96779

DOI: 10.2196/96779

Download PDF


Request queued. Please wait while the file is being generated. It may take some time.

© 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.