Vijay S. Nori1, Christopher A. Hane1, William H. Crown1, Rhoda Au2, William J. Burke3, Darshak M. Sanghavi1, Paul Bleicher1
1OptumLabs, Optum, Cambridge, MA, USA
2Department of Anatomy and Neurobiology, Boston University School of Medicine, Boston, MA, USA
3Psychiatry, Banner Alzheimer's Institute, Phoenix, AZ, USA
Tóm tắt
AbstractIntroductionThe study objective was to build a machine learning model to predict incident mild cognitive impairment, Alzheimer's Disease, and related dementias from structured data using administrative and electronic health record sources.MethodsA cohort of patients (n = 121,907) and controls (n = 5,307,045) was created for modeling using data within 2 years of patient's incident diagnosis date. Additional cohorts 3–8 years removed from index data are used for prediction. Training cohorts were matched on age, gender, index year, and utilization, and fit with a gradient boosting machine, lightGBM.ResultsIncident 2‐year model quality on a held‐out test set had a sensitivity of 47% and area‐under‐the‐curve of 87%. In the 3‐year model, the learned labels achieved 24% (71%), which dropped to 15% (72%) in year 8.DiscussionThe ability of the model to discriminate incident cases of dementia implies that it can be a worthwhile tool to screen patients for trial recruitment and patient management.
