Cargando…

Generative transfer learning for measuring plausibility of EHR diagnosis records

OBJECTIVE: Due to a complex set of processes involved with the recording of health information in the Electronic Health Records (EHRs), the truthfulness of EHR diagnosis records is questionable. We present a computational approach to estimate the probability that a single diagnosis record in the EHR...

Descripción completa

Detalles Bibliográficos
Autores principales: Estiri, Hossein, Vasey, Sebastien, Murphy, Shawn N
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Oxford University Press 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7936395/
https://www.ncbi.nlm.nih.gov/pubmed/33043366
http://dx.doi.org/10.1093/jamia/ocaa215
_version_ 1783661185206321152
author Estiri, Hossein
Vasey, Sebastien
Murphy, Shawn N
author_facet Estiri, Hossein
Vasey, Sebastien
Murphy, Shawn N
author_sort Estiri, Hossein
collection PubMed
description OBJECTIVE: Due to a complex set of processes involved with the recording of health information in the Electronic Health Records (EHRs), the truthfulness of EHR diagnosis records is questionable. We present a computational approach to estimate the probability that a single diagnosis record in the EHR reflects the true disease. MATERIALS AND METHODS: Using EHR data on 18 diseases from the Mass General Brigham (MGB) Biobank, we develop generative classifiers on a small set of disease-agnostic features from EHRs that aim to represent Patients, pRoviders, and their Interactions within the healthcare SysteM (PRISM features). RESULTS: We demonstrate that PRISM features and the generative PRISM classifiers are potent for estimating disease probabilities and exhibit generalizable and transferable distributional characteristics across diseases and patient populations. The joint probabilities we learn about diseases through the PRISM features via PRISM generative models are transferable and generalizable to multiple diseases. DISCUSSION: The Generative Transfer Learning (GTL) approach with PRISM classifiers enables the scalable validation of computable phenotypes in EHRs without the need for domain-specific knowledge about specific disease processes. CONCLUSION: Probabilities computed from the generative PRISM classifier can enhance and accelerate applied Machine Learning research and discoveries with EHR data.
format Online
Article
Text
id pubmed-7936395
institution National Center for Biotechnology Information
language English
publishDate 2020
publisher Oxford University Press
record_format MEDLINE/PubMed
spelling pubmed-79363952021-03-10 Generative transfer learning for measuring plausibility of EHR diagnosis records Estiri, Hossein Vasey, Sebastien Murphy, Shawn N J Am Med Inform Assoc Research and Applications OBJECTIVE: Due to a complex set of processes involved with the recording of health information in the Electronic Health Records (EHRs), the truthfulness of EHR diagnosis records is questionable. We present a computational approach to estimate the probability that a single diagnosis record in the EHR reflects the true disease. MATERIALS AND METHODS: Using EHR data on 18 diseases from the Mass General Brigham (MGB) Biobank, we develop generative classifiers on a small set of disease-agnostic features from EHRs that aim to represent Patients, pRoviders, and their Interactions within the healthcare SysteM (PRISM features). RESULTS: We demonstrate that PRISM features and the generative PRISM classifiers are potent for estimating disease probabilities and exhibit generalizable and transferable distributional characteristics across diseases and patient populations. The joint probabilities we learn about diseases through the PRISM features via PRISM generative models are transferable and generalizable to multiple diseases. DISCUSSION: The Generative Transfer Learning (GTL) approach with PRISM classifiers enables the scalable validation of computable phenotypes in EHRs without the need for domain-specific knowledge about specific disease processes. CONCLUSION: Probabilities computed from the generative PRISM classifier can enhance and accelerate applied Machine Learning research and discoveries with EHR data. Oxford University Press 2020-10-12 /pmc/articles/PMC7936395/ /pubmed/33043366 http://dx.doi.org/10.1093/jamia/ocaa215 Text en © The Author(s) 2020. Published by Oxford University Press on behalf of the American Medical Informatics Association. http://creativecommons.org/licenses/by-nc-nd/4.0/ This is an Open Access article distributed under the terms of the Creative Commons Attribution-NonCommercial-NoDerivs licence (http://creativecommons.org/licenses/by-nc-nd/4.0/), which permits non-commercial reproduction and distribution of the work, in any medium, provided the original work is not altered or transformed in any way, and that the work is properly cited. For commercial re-use, please contact journals.permissions@oup.com
spellingShingle Research and Applications
Estiri, Hossein
Vasey, Sebastien
Murphy, Shawn N
Generative transfer learning for measuring plausibility of EHR diagnosis records
title Generative transfer learning for measuring plausibility of EHR diagnosis records
title_full Generative transfer learning for measuring plausibility of EHR diagnosis records
title_fullStr Generative transfer learning for measuring plausibility of EHR diagnosis records
title_full_unstemmed Generative transfer learning for measuring plausibility of EHR diagnosis records
title_short Generative transfer learning for measuring plausibility of EHR diagnosis records
title_sort generative transfer learning for measuring plausibility of ehr diagnosis records
topic Research and Applications
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7936395/
https://www.ncbi.nlm.nih.gov/pubmed/33043366
http://dx.doi.org/10.1093/jamia/ocaa215
work_keys_str_mv AT estirihossein generativetransferlearningformeasuringplausibilityofehrdiagnosisrecords
AT vaseysebastien generativetransferlearningformeasuringplausibilityofehrdiagnosisrecords
AT murphyshawnn generativetransferlearningformeasuringplausibilityofehrdiagnosisrecords