Leveraging Precision Medicine Analytics to Optimize Inflammation Reduction and Enhance Physical Function in Older Adults

Background Chronic inflammation in older adults is a key contributor to functional decline and mortality. Although anti-inflammatory medications have shown limited success in improving physical function, emerging targeted approaches offer new promise. We applied machine learning to identify clusters of older adults with shared patterns of inflammatory and cardiometabolic dysregulation and evaluated their responses to specific interventions. Methods We conducted a secondary analysis of the Enabling Reduction of low-grade Inflammation in Seniors (ENRGISE) multicenter, double-blind, placebo-controlled, factorial trial. This trial assessed the effects of losartan, omega-3, combination therapy, or placebo on interleukin-6 (IL-6) levels and 400-meter walking speed. Key variables were selected using LASSO, followed by linear regression to identify those significantly affecting the outcome slope. The optimal intervention was defined as the one that maximized the estimated slope improvement. Results We included 287 participants (47.4% female; mean age 77.6 ± 5.4 years) with a baseline IL-6 of 4.81 pg/mL. If all participants had received the recommended interventions, the estimated mean IL-6 slope would be -0.70 pg/mL/year (95% CI:-3.71, 1.41), compared to -0.51 pg/mL/year (-1.47, 0.35) among those randomized. The estimated improvement in walking speed was +0.0017 m/s/year (-0.0336, 0.0407) for the recommended interventions versus +0.0015 m/s/year (-0.0145,0.0154) observed in the trial. For grip strength, the slope was -1.02 kg/year (-2.63,0.57) for the recommended group and -1.02 kg/year (-1.79,-0.45) for the trial group. Conclusion Although results were not significant, our findings suggest that tailored interventions based on individuals’ unique profiles may yield more favorable effects compared to non-tailored approaches. However, further powered studies should continue to explore precision medicine analytics and their potential to help identify more effective and personalized interventions.