Mining Primary Care Electronic Health Records for Automatic Disease Phenotyping: A Transparent Machine Learning Framework
dc.contributor.author | Fernández-Gutiérrez, F | |
dc.contributor.author | Kennedy, JI | |
dc.contributor.author | Cooksey, R | |
dc.contributor.author | Atkinson, M | |
dc.contributor.author | Choy, E | |
dc.contributor.author | Brophy, S | |
dc.contributor.author | Huo, L | |
dc.contributor.author | Zhou, Shang-Ming | |
dc.date.accessioned | 2021-11-05T11:31:39Z | |
dc.date.issued | 2021-10-15 | |
dc.identifier.issn | 2075-4418 | |
dc.identifier.issn | 2075-4418 | |
dc.identifier.other | ARTN 1908 | |
dc.identifier.uri | http://hdl.handle.net/10026.1/18223 | |
dc.description.abstract |
<jats:p>(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.</jats:p> | |
dc.format.extent | 1908-1908 | |
dc.format.medium | Electronic | |
dc.language | en | |
dc.language.iso | en | |
dc.publisher | MDPI AG | |
dc.subject | phenotyping | |
dc.subject | rheumatology | |
dc.subject | cohort identification | |
dc.subject | electronic health records | |
dc.subject | feature selection | |
dc.subject | transparent machine learning | |
dc.subject | text mining | |
dc.subject | big data | |
dc.subject | artificial intelligence | |
dc.title | Mining Primary Care Electronic Health Records for Automatic Disease Phenotyping: A Transparent Machine Learning Framework | |
dc.type | journal-article | |
dc.type | Journal Article | |
plymouth.author-url | https://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000715475700001&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=11bb513d99f797142bcfeffcc58ea008 | |
plymouth.issue | 10 | |
plymouth.volume | 11 | |
plymouth.publication-status | Published online | |
plymouth.journal | Diagnostics | |
dc.identifier.doi | 10.3390/diagnostics11101908 | |
plymouth.organisational-group | /Plymouth | |
plymouth.organisational-group | /Plymouth/Faculty of Health | |
plymouth.organisational-group | /Plymouth/Faculty of Health/School of Nursing and Midwifery | |
plymouth.organisational-group | /Plymouth/REF 2021 Researchers by UoA | |
plymouth.organisational-group | /Plymouth/REF 2021 Researchers by UoA/UoA03 Allied Health Professions, Dentistry, Nursing and Pharmacy | |
plymouth.organisational-group | /Plymouth/Users by role | |
plymouth.organisational-group | /Plymouth/Users by role/Academics | |
dc.publisher.place | Switzerland | |
dcterms.dateAccepted | 2021-10-13 | |
dc.rights.embargodate | 2021-11-9 | |
dc.identifier.eissn | 2075-4418 | |
dc.rights.embargoperiod | Not known | |
rioxxterms.versionofrecord | 10.3390/diagnostics11101908 | |
rioxxterms.licenseref.uri | http://www.rioxx.net/licenses/all-rights-reserved | |
rioxxterms.licenseref.startdate | 2021-10-15 | |
rioxxterms.type | Journal Article/Review |