Machine Learning in Health Economic Evaluations: Protocol for a Scoping Review

Area of Science:

• Health Economics
• Artificial Intelligence
• Health Services Research

Background:

• Machine learning (ML) applications are rapidly advancing, showing significant potential to transform healthcare.
• However, the integration of ML into health economic evaluations remains underexplored and presents unique challenges.

Purpose of the Study:

• To conduct a scoping review on the applications of ML in health economic evaluations.
• To identify potential challenges and barriers associated with using ML in health economic evaluations.

Main Methods:

• Utilizing PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) methodology.
• Conducting a comprehensive search across MEDLINE (Ovid), Embase (Ovid), IEEE Xplore, and Cochrane Library databases.
• Applying the study types, data sources, methods, and outcomes (SDMO) framework for eligibility criteria.

Main Results:

• Initial search yielded 4141 records, with 3718 records screened for titles and abstracts.
• 30 reports have been retrieved for detailed eligibility assessment.
• Data extraction and charting are ongoing, with results anticipated for publication by the end of 2025.

Conclusions:

• This review will contribute to a better understanding of ML integration within health economic evaluations.
• It aims to elucidate the barriers and challenges hindering the adoption of ML in this domain.
• Findings will inform future research and practical implementation strategies for ML in health economics.