A Meta-Analysis of Machine Learning Techniques for Predicting Disease Progression in Electronic Health Records

Predicting disease progression is crucial for personalized medicine, enabling tai-lored treatment strategies. Electronic Health Records (EHRs) provide a valu-able data source for predictive modeling, and integrating machine learning (ML) en-hances accuracy and clinical utility. This meta-analysis examines ML tech-niques applied to disease progression prediction using EHR data, synthesizing findings from eight studies published in the last five years. Results reveal diverse ML ap-plications, from traditional regression to deep learning, with performance varying by disease type, data quality, and model complexity. While certain tech-niques show superior predictive accuracy in specific conditions, challenges such as data heterogeneity and model interpretability remain. The findings empha-size the need for disease-specific model selection and improved data integration to enhance clinical applicability. This study provides a roadmap for advancing ML-driven predictive models in personalized healthcare.