Age-dependent topic modeling of comorbidities in UK Biobank identifies disease subtypes with differential genetic risk.
Xilin Jiang et al. Nat Genet 2023 10
From the abstract: " The analysis of longitudinal data from electronic health records (EHRs) has the potential to improve clinical diagnoses and enable personalized medicine, motivating efforts to identify disease subtypes from patient comorbidity information. Here we introduce an age-dependent topic modeling (ATM) method that provides a low-rank representation of longitudinal records of hundreds of distinct diseases in large EHR datasets. "
Power of Public Investment in Curated Big Health Data.
Paula Anne Newman-Casey et al. JAMA Ophthalmol 2023 9
From the paper: "Public investment from the US and the UK in creating the UK Biobank and the All of Us databases has resulted in the generation of critical new knowledge to better understand human health. Both projects have created publicly available data sets to encourage researchers to leverage large quantities of data to identify patterns and advance health care. Moreover, each database has its unique strengths. The UK Biobank data set goes deep into genomics, metabolomics, brain, heart, and ocular imaging, providing granular and specific measurements to inform many fields of study. The All of Us data set includes biospecimens, linkages to electronic health records, and survey results."
A Test of Automated Use of Electronic Health Records to Aid in Diagnosis of Genetic Disease
T Cassini et al, Genetics in Medicine, August 22, 2023
Automated use of electronic health records may aid in decreasing the diagnostic delay for rare diseases. The phenotype risk score (PheRS) is a weighted aggregate of syndromically related phenotypes that measures the similarity between an individual’s conditions and features of a disease. For some diseases, there are individuals without a diagnosis of that disease who have scores similar to diagnosed patients. These individuals may have that disease but not yet be diagnosed.
The shaky foundations of large language models and foundation models for electronic health records
M Wornow et al, NPJ Digital Medicine, July 29, 2023
The success of foundation models such as ChatGPT and AlphaFold has spurred significant interest in building similar models for electronic medical records (EMRs) to improve patient care and hospital operations. However, recent hype has obscured critical gaps in our understanding of these models’ capabilities. In this narrative review, we examine 84 foundation models trained on non-imaging EMR data (i.e., clinical text and/or structured data) and create a taxonomy delineating their architectures, training data, and potential use cases. We find that most models are trained on small, narrowly-scoped clinical datasets.