Physical performance strongly predicts all-cause mortality risk in a real-world population of older diabetic patients: machine learning approach for mortality risk stratification

Abstract

BackgroundPrognostic risk stratification in older adults with type 2 diabetes (T2D) is important for guiding decisions concerning advance care planning.Materials and methodsA retrospective longitudinal study was conducted in a real-world sample of older diabetic patients afferent to the outpatient facilities of the Diabetology Unit of the IRCCS INRCA Hospital of Ancona (Italy). A total of 1,001 T2D patients aged more than 70 years were consecutively evaluated by a multidimensional geriatric assessment, including physical performance evaluated using the Short Physical Performance Battery (SPPB). The mortality was assessed during a 5-year follow-up. We used the automatic machine-learning (AutoML) JADBio platform to identify parsimonious mathematical models for risk stratification.ResultsOf 977 subjects included in the T2D cohort, the mean age was 76.5 (SD: 4.5) years and 454 (46.5%) were men. The mean follow-up time was 53.3 (SD:15.8) months, and 209 (21.4%) patients died by the end of the follow-up. The JADBio AutoML final model included age, sex, SPPB, chronic kidney disease, myocardial ischemia, peripheral artery disease, neuropathy, and myocardial infarction. The bootstrap-corrected concordance index (c-index) for the final model was 0.726 (95% CI: 0.687–0.763) with SPPB ranked as the most important predictor. Based on the penalized Cox regression model, the risk of death per unit of time for a subject with an SPPB score lower than five points was 3.35 times that for a subject with a score higher than eight points (P-value <0.001).ConclusionAssessment of physical performance needs to be implemented in clinical practice for risk stratification of T2D older patients.

Intra-Individual Variations in How Insulin Sensitivity Responds to Long-Term Exercise: Predictions by Machine Learning Based on Large-Scale Serum Proteomics

“…In our data, baseline serum protein levels effectively distinguished between insulin sensitivity non-responders and responders using an ML algorithm constructed and validated in two independent data sets. Our results are in line with a growing body of research indicating that ML is an efficient tool to improve risk stratification and treatment responses in type 2 diabetes [18][19][20]. It is tempting to speculate that our ML algorithm could be used in future studies to a priori define individuals who may not improve their insulin sensitivity in response to exercise, allowing assignment of other interventions, such as weight loss by diet and/or drugs, e.g., to test for non-inferiority against the group assigned to exercise in terms of improved insulin sensitivity.…”

“…Machine learning (ML) may be applied to predict individual responses based on large amounts of complex data [ 17 ] and to sub-type patients with type 2 diabetes [ 18 ]. Furthermore, ML has identified physical performance as the strongest risk factor for mortality in older patients with type 2 diabetes [ 19 ] and identified non-responders to metformin treatment using large-scale serum metabolomics [ 20 ]. Explainable ML algorithms, such as random forest [ 21 ], may also efficiently identify persons who benefit from physical activity [ 15 ].…”