Journal article 407 views 47 downloads
Mining Primary Care Electronic Health Records for Automatic Disease Phenotyping: A Transparent Machine Learning Framework
Diagnostics, Volume: 11, Issue: 10, Start page: 1908
PDF | Version of Record
Copyright: © 2021 by the authors. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) licenseDownload (1.72MB)
(1) Background: We aimed to develop a transparent machine-learning (ML) framework to automatically identify patients with a condition from electronic health records (EHRs) via a parsimonious set of features. (2) Methods: We linked multiple sources of EHRs, including 917,496,869 primary care records...
Check full text
No Tags, Be the first to tag this record!
(1) Background: We aimed to develop a transparent machine-learning (ML) framework to automatically identify patients with a condition from electronic health records (EHRs) via a parsimonious set of features. (2) Methods: We linked multiple sources of EHRs, including 917,496,869 primary care records and 40,656,805 secondary care records and 694,954 records from specialist surgeries between 2002 and 2012, to generate a unique dataset. Then, we treated patient identification as a problem of text classification and proposed a transparent disease-phenotyping framework. This framework comprises a generation of patient representation, feature selection, and optimal phenotyping algorithm development to tackle the imbalanced nature of the data. This framework was extensively evaluated by identifying rheumatoid arthritis (RA) and ankylosing spondylitis (AS). (3) Results: Being applied to the linked dataset of 9657 patients with 1484 cases of rheumatoid arthritis (RA) and 204 cases of ankylosing spondylitis (AS), this framework achieved accuracy and positive predictive values of 86.19% and 88.46%, respectively, for RA and 99.23% and 97.75% for AS, comparable with expert knowledge-driven methods. (4) Conclusions: This framework could potentially be used as an efficient tool for identifying patients with a condition of interest from EHRs, helping clinicians in clinical decision-support process.
phenotyping, rheumatology, cohort identification, electronic health records, feature selection, transparent machine learning, text mining, big data, artificial intelligence
Faculty of Medicine, Health and Life Sciences
The authors acknowledge the supports from the Farr Institute of Health Informatics Research (MR/K006525/1) and Health Data Research UK (NIWA1). This research was also supported
by “Major Project of National Social Science Foundation of China (16ZDA0092)” and “Guangxi
University ‘Digital ASEAN Cloud Big Data Security and Mining Technology’ Innovation Team”