The Use of Deep Learning and Machine Learning on LongitudinalElectronic Health Records for the Early Detection and Preventionof Diseases:Scoping Review

Background: Electronic health records (EHRs) contain patients'health information over time, including possible early indicatorsof disease. However, the increasing amount of data hinders clinicians from using them. There is accumulating evidence suggestingthat machine learning (ML) and deep learning (DL) can assist clinicians in analyzing these large-scale EHRs, as algorithms thriveon high volumes of data. Although ML has become well developed, studies mainly focus on engineering but lack medicaloutcomes.Objective: This study aims for a scoping review of the evidence on how the use of ML on longitudinal EHRs can support theearly detection and prevention of disease. The medical insights and clinical benefits that have been generated were investigatedby reviewing applications in a variety of diseases.Methods: This study was conducted according to the PRISMA (Preferred Reporting Items for Systematic Reviews andMeta-Analyses) guidelines. A literature search was performed in 2022 in collaboration with a medical information specialist inthe following databases: PubMed, Embase, Web of Science Core Collection (Clarivate Analytics), and IEEE Xplore DigitalLibrary and computer science bibliography. Studies were eligible when longitudinal EHRs were used that aimed for the earlydetection of disease via ML in a prevention context. Studies with a technical focus or using imaging or hospital admission datawere beyond the scope of this review. Study screening and selection and data extraction were performed independently by 2researchers.Results: In total, 20 studies were included, mainly published between 2018 and 2022. They showed that a variety of diseasescould be detected or predicted, particularly diabetes; kidney diseases; diseases of the circulatory system; and mental, behavioral,and neurodevelopmental disorders. Demographics, symptoms, procedures, laboratory test results, diagnoses, medications, andBMI were frequently used EHR data in basic recurrent neural network or long short-term memory techniques. By developingand comparing ML and DL models, medical insights such as a high diagnostic performance, an earlier detection, the most importantpredictors, and additional health indicators were obtained. A clinical benefit that has been evaluated positively was preliminaryscreening. If these models are applied in practice, patients might also benefit from personalized health care and prevention, withpractical benefits such as workload reduction and policy insights.Conclusions: Longitudinal EHRs proved to be helpful for support in health care. Current ML models on EHRs can support thedetection of diseases in terms of accuracy and offer preliminary screening benefits. Regarding the prevention of diseases, MLand specifically DL models can accurately predict or detect diseases earlier than current clinical diagnoses. Adding personallyresponsible factors allows targeted prevention interventions. While ML models based on textual EHRs are still in the developmentalstage, they have high potential to support clinicians and the health care system and improve patient outcomes