Predicting chronic opioid use among patients with osteoarthritis using electronic health record data.
Jeff T MohlNikita StempniewiczJohn K CuddebackDavid M KentElizabeth A MacLeanLance NichollsChristopher KerriganElizabeth L CieminsPublished in: Arthritis care & research (2022)
We found that EHR-based predictive models could estimate the risk of future COU among OA patients to help inform care decisions. Black-box methods did not have significant advantages over more interpretable models. Care should be taken when extending all models into organizations not included in model training due to high variability in performance across held-out organizations.
Keyphrases
- electronic health record
- healthcare
- clinical decision support
- end stage renal disease
- palliative care
- quality improvement
- ejection fraction
- knee osteoarthritis
- chronic kidney disease
- adverse drug
- rheumatoid arthritis
- pain management
- peritoneal dialysis
- transcription factor
- affordable care act
- machine learning
- big data
- virtual reality