Author:
Yang Siyue,Varghese Paul,Stephenson Ellen,Tu Karen,Gronsbell Jessica
Abstract
ABSTRACTObjectiveAccurate and rapid phenotyping is a prerequisite to leveraging electronic health records (EHRs) 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 (i) the data sources used, (ii) the phenotypes considered, (iii) the methods applied, and (iv) the reporting and evaluation methods used.Materials and MethodsWe searched PubMed and Web of Science for articles published between 2018 and 2022. After screening 850 articles, we recorded 37 variables on 100 studies.ResultsMost studies utilized data from a single institution and included information in clinical notes. Although chronic conditions were most commonly considered, ML also enabled 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 marginal improvement over traditional ML for many conditions.DiscussionDespite 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.ConclusionContinued 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.
Publisher
Cold Spring Harbor Laboratory
Cited by
9 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献