Predicting Sleep Disorders with Machine Learning from Patient Records.

A new machine-learning algorithm can accurately predict whether a person is at risk of sleep disorders by analyzing demographics, lifestyle data, physical exam results, and laboratory values. Age, weight, and depression are three factors the AI technology identified as being significant predictors of insomnia. The study used the machine learning model XGBoost to analyze publicly available data on 7,929 patients in the US who completed the National Health and Nutrition Examination Survey. The authors conclude that machine learning methods may be effective first steps in screening patients for sleep disorder risk without relying on physician judgement or bias.