Early identification of older individuals at risk of mobility decline with machine learning

•Among the tested algorithms, random forest presented the best performances.•Performing separate predictions for each task leads to improved results.•The task with the best prediction was the difficulty of crouching and kneeling.•Age, schooling, back pain and hypertension were some of most important predictors. : The early identification of individuals at risk of mobility decline can improve targeted strategies of prevention. : To evaluate the predictive performance of machine learning (ML) algorithms in identifying older individuals at risk of future mobility decline. : We used data from the SABE Study (Health, Well-being and Aging Study), a representative sample of people aged 60 years and more, living in the Municipality of São Paulo, Brazil. Mobility decline was assessed 5 years after admission in the study by self-reported difficulty to walk a block, climb steps, being able to stoop, crouch and kneel, or lifting or carrying weights greater than 5 kg. Popular machine learning algorithms were trained in 70% of the sample with 10-fold cross-validation, and predictive performance metrics were obtained from applying the trained algorithms to the other 30% (test set). : Of the 1,615 individuals, 48% developed difficulty in at least one of the four tasks, 32% in stooping, crouching and kneeling, and 30% in carrying weights. The random forest algorithm had the best predictive performance for most outcomes. The tasks that the algorithm was able to predict with better performance were crouching and kneeling (AUC-ROC: 0.81[0.76–0.85]), and lifting or carrying weights (AUC-ROC: 0.80[0.75–0.84]). Age was the most important variable for the algorithms, followed by education and back pain, according to the SHAP (SHapley Additive exPlanations) values. : Applications of ML algorithms are a promising tool to identify older patients at risk of mobility decline, with the potential of improving targeted preventive programs.