Search

BACKGROUND: A better understanding of performance in functional mobility tasks related to the mortality patterns for the different causes of death for the Brazilian older population is still a challenge. OBJECTIVE: To analyze if gait speed and chair stand test performance are associated with mortality in older adults, and if the overall mobility status changes the effect of other mortality risk factors. METHODS: The data were from SABE (Health, Well-being and Aging Study), a multiple-cohort study conducted in São Paulo, Brazil, with a representative sample of people aged 60 and more. Cox regression models were used to analyze 10-year all-cause and cause-specific mortality with consideration for gait speed and the chair stand test. RESULTS: Of the 1411 participants, 26% died during the follow-up. The performance in the chair stand test had a more consistent association with mortality (hazard ratio (HR)=1.03, 95%CI: 1.00, 1.05) than gait speed. Being unable to perform the test also increased the risk to die by all-cause (HR=1.71, 95%CI: 1.21, 2.42) and by diseases of the circulatory system (HR=2.14, 95%CI: 1.25, 3.65). The stratified analysis of mobility performance changed the effects of some of the mortality risk factors, such as cognitive impairment and multimorbidity. CONCLUSIONS: The chair stand test could be a better choice than 3-meters walking test as a mortality predictor. In addition, the impact of cognitive decline and multimorbidity were greater among those with reduced mobility, supporting the development of preventive interventions and public policies targeted at more vulnerable groups of older adults.

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.