Machine learning approaches for electronic health records phenotyping: a methodical review

Abstract

Objective Accurate and rapid phenotyping is a prerequisite to leveraging electronic health records for biomedical research. While early phenotyping relied on rule-based algorithms curated by experts, machine learning (ML) approaches have emerged as an alternative to improve scalability across phenotypes and healthcare settings. This study evaluates ML-based phenotyping with respect to (1) the data sources used, (2) the phenotypes considered, (3) the methods applied, and (4) the reporting and evaluation methods used. Materials and methods We searched PubMed and Web of Science for articles published between 2018 and 2022. After screening 850 articles, we recorded 37 variables on 100 studies. Results Most studies utilized data from a single institution and included information in clinical notes. Although chronic conditions were most commonly considered, ML also enabled the characterization of nuanced phenotypes such as social determinants of health. Supervised deep learning was the most popular ML paradigm, while semi-supervised and weakly supervised learning were applied to expedite algorithm development and unsupervised learning to facilitate phenotype discovery. ML approaches did not uniformly outperform rule-based algorithms, but deep learning offered a marginal improvement over traditional ML for many conditions. Discussion Despite the progress in ML-based phenotyping, most articles focused on binary phenotypes and few articles evaluated external validity or used multi-institution data. Study settings were infrequently reported and analytic code was rarely released. Conclusion Continued research in ML-based phenotyping is warranted, with emphasis on characterizing nuanced phenotypes, establishing reporting and evaluation standards, and developing methods to accommodate misclassified phenotypes due to algorithm errors in downstream applications.

Calcium pyrophosphate deposition disease: historical overview and potential gaps

“…2021. Development of Machine Learning approaches and Electronic Health Record Data algorithms for the identification of CPPD ( 51 ).…”

Inductive reasoning with large language models: a simulated randomized controlled trial for epilepsy

“…It is very challenging to extract knowledge from the electronic medical system 1 . Various approaches, including the use of structured data 2 , natural language processing toolboxes 3–5 , and others have been shown to hold some promise.…”

Knowledge-Driven Online Multimodal Automated Phenotyping System

“…Recent efforts have been directed towards enhancing the accuracy of assigning disease phenotypes while maintaining scalability of EHR driven studies. This has led to the development of label-efficient, high-throughput, semi-supervised or weakly supervised machine learning algorithms that can precisely identify disease phenotypes (4; 9). Since relevant information pertaining to a phenotype is often dispersed across different fields in the EHR, including unstructured clinical notes, weakly supervised techniques that utilize multiple features have proven to be effective across diverse healthcare systems and disease phenotypes.…”