1. Generative transfer learning for measuring plausibility of EHR diagnosis records
- Author
-
Hossein Estiri, Shawn N. Murphy, and Sebastien Vasey
- Subjects
genetic structures ,AcademicSubjects/SCI01060 ,generative models ,Computer science ,Health Informatics ,transfer learning ,Machine learning ,computer.software_genre ,Research and Applications ,Machine Learning ,03 medical and health sciences ,0302 clinical medicine ,Joint probability distribution ,health services administration ,Diagnosis ,data quality ,Humans ,Disease ,030212 general & internal medicine ,health care economics and organizations ,AcademicSubjects/MED00580 ,030304 developmental biology ,Probability ,0303 health sciences ,business.industry ,Professional-Patient Relations ,Biobank ,electronic health records ,Data quality ,Scalability ,Artificial intelligence ,Health information ,Supervised Machine Learning ,AcademicSubjects/SCI01530 ,Transfer of learning ,business ,computer ,Classifier (UML) ,diagnosis records ,Delivery of Health Care ,Generative grammar - Abstract
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.
- Published
- 2020