A systematic review of clinical health conditions predicted by machine learning diagnostic and prognostic models trained or validated using real-world primary health care data

Abstract

Aim: With the rapid advances in technology and data science, machine learning (ML) is being adopted by the health care sector; but there is a lack of literature addressing the health conditions targeted by the ML prediction models within primary health care (PHC). To fill this gap in knowledge, we conducted a systematic review following the PRISMA guidelines to identify the health conditions targeted by ML in PHC. Methods: We searched the Cochrane Library, Web of Science, PubMed, Elsevier, BioRxiv, Association of Computing Machinery (ACM), and IEEE Xplore databases for studies published from January 1990 to January 2022. We included any primary study addressing ML diagnostic or prognostic predictive models that were supplied completely or partially by real-world PHC data. We performed literature screening, data extraction, and risk of bias assessment. Health conditions were categorized according to international classification of diseases. Extracted date were analyzed quantitatively and qualitatively. Results: We identified 109 studies investigating 42 health conditions. These studies included 273 ML prediction models supplied by the PHC data of 24.2 million participants from 19 countries. We found that 82% of the studies were retrospective. 76.6% of the studies reported diagnostic predictive ML models. 77% of all reported models aimed for models’ development without external validation. Risk of bias assessment revealed that 90.8% of the studies were of high or unclear risk of bias. The most frequently reported health conditions were Alzheimer’s disease and diabetes mellitus. Conclusions: To the best of our knowledge, this is the first review to investigate the extent of the health conditions targeted by the ML prediction models within PHC settings. Our study provides an important summary on the presently available ML models in PHC, which can be used in further research and implementation efforts.

Can adverse childhood experiences predict chronic health conditions? Development of trauma-informed, explainable machine learning models

“…Our primary focus on ACEs and relevant socioeconomic and behavioral factors can distinguish the current study from others. While previous studies have documented excellent performance of classical ML models (e.g., RF, gradient boost, SVM, LR, KNN, decision trees, and NB) to predict chronic health conditions, they commonly focused on biomedical predictors such as clinical, biomarker, and genetics data ( 58 , 60 , 63 , 64 ).…”

“…Existing classical ML models in the literature have predicted health outcomes based on SDoH with accuracies between 61 and 74% ( 65 ). It is common to combine different types and sources of data for these analyses, such as electronic medical records linked to omics data ( 63 ); clinical information linked to sociodemographic, behavioral, or anthropometric factors ( 58 ); and primary care data linked to insurance claims, cancer registries, or administrative sources ( 64 ). In terms of predictors, sociodemographic (e.g., age, sex, gender) and lifestyle factors (e.g., physical activity, lack of sleep, and use of alcohol, tobacco, and other drugs) are predominantly used for modeling chronic health conditions ( 58 ).…”