-
Notifications
You must be signed in to change notification settings - Fork 2
EHR Clinical KP
Source: Multiomics EHR KP
The Electronic Health Record (EHR) Clinical KP is created and maintained by the Multiomics Provider team from the Institute for Systems Biology in Seattle, WA. This KP provides a knowledge graph pointing from risk factors to a variety health outcomes (diseases, phenotypes, medication exposure). We use data from over 28 million EHRs to train a large collection of interpretable machine learning models which are integrated into a single large knowledge graph. The edges of the graph are generated by running ~300 logistic regression models for clinical conditions with features including age, sex, medical conditions and medications as nodes to predict associations with disease outcome.
Example: This KP provides information derived from usage patterns of medication use in regular healthcare. For example, methylprednisone is associated with multiple sclerosis.
High-level description of data source(s): Providence Health Systems and Affiliates (PSHA), which cares for patients through 51 hospitals and 1085 clinics across seven states in the US, including Alaska, California, Montana, New Mexico, Oregon, Texas, and Washington. We conduct analysis under IRB-approved protocols using data from over 28 million EHRs. We develop interpretable machine learning models to analysis associations between medical conditions and patterns of medication use. The associations observed from those models are integrated into a knowledge graph.
Key methodologic metrics provided on edges: For each edge, this KG provides the regression coefficient/log odds ratio, confidence interval, p-value, AUROC, total sample size of patients in that model, age range of patients, and the year range of the electronic health records from which data is extracted.
Regulatory requirement(s) and/or restriction(s) on data use and/or user consideration(s): Institute for Systems Biology partnership with Providence/Swedish Health Alliance (please email data-access@isbscience.org for more information)
Knowledge Sources Accessed: N/A
Wiki URL: https://github.com/NCATSTranslator/Translator-All/wiki/Multiomics-EHR-Risk-KP