Machine learning models to predict onset of dementia: A label learning approach

IntroductionThe 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 2years of patient's incident diagnosis date. Additional cohorts 3-8years 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 year8. 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.