Background Inflammation and skeletal muscle wasting often coexist in elderly populations, but few studies have examined their relationship in elderly heart failure (HF) patients. This study examined the relationship between inflammation and increased skeletal muscle proteolysis, reduced skeletal mass and strength, and their prognostic implications in elderly HF patients (> 65 years) using a random forest approach. Methods We prospectively enrolled consecutive elderly HF patients (n = 78) and age- and sex-matched control subjects (n = 83). We measured the interleukin (IL)-6, C-reactive protein (CRP), and B-type natriuretic peptide (BNP) levels, lower limb muscle mass and strength, and 6-min walk distance. The amount of muscle proteolysis was determined by urinary 3-methylhystidine, normalized by creatinine (3-MH/Cr). The composite endpoint was defined as all-cause death or hospitalizations due to worsening HF. Results Compared to controls, elderly HF patients had a significantly higher IL-6, CRP, BNP, and 3-MH/Cr, and exhibited a reduced lower limb muscle mass and strength. A correlation analysis demonstrated significant positive correlations between the inflammatory cytokine levels and 3-MH/Cr and BNP, and negative correlations with the lower limb muscle mass and strength, and 6-min walk distance. During a median follow-up of 2.4-years, 24 patients reached the endpoint. A random forest model revealed that inflammatory cytokines, skeletal muscle wasting, and the BNP had greater effects on the risk prediction. The algorithm achieved an area under the receiver operating characteristic curve of 0.887 (95% CI, 0.772–1.000). Conclusion This study provided evidence of the association between inflammation and increased skeletal muscle proteolysis, reduced skeletal mass and strength, and their prognostic roles in elderly HF patients.

Background Machine learning (ML) has emerged as a promising tool for risk stratification. However, few studies have applied ML to risk assessment of patients with atrial fibrillation (AF). Hypothesis We aimed to compare the performance of random forest (RF), logistic regression (LR), and conventional risk schemes in predicting the outcomes of AF. Methods We analyzed data from 7406 nonvalvular AF patients (median age 71 years, female 29.2%) enrolled in a nationwide AF registry (J‐RHYTHM Registry) and who were followed for 2 years. The endpoints were thromboembolisms, major bleeding, and all‐cause mortality. Models were generated from potential predictors using an RF model, stepwise LR model, and the thromboembolism (CHADS2 and CHA2DS2‐VASc) and major bleeding (HAS‐BLED, ORBIT, and ATRIA) scores. Results For thromboembolisms, the C‐statistic of the RF model was significantly higher than that of the LR model (0.66 vs. 0.59, p = .03) or CHA2DS2‐VASc score (0.61, p < .01). For major bleeding, the C‐statistic of RF was comparable to the LR (0.69 vs. 0.66, p = .07) and outperformed the HAS‐BLED (0.61, p < .01) and ATRIA (0.62, p < .01) but not the ORBIT (0.67, p = .07). The C‐statistic of RF for all‐cause mortality was comparable to the LR (0.78 vs. 0.79, p = .21). The calibration plot for the RF model was more aligned with the observed events for major bleeding and all‐cause mortality. Conclusions The RF model performed as well as or better than the LR model or existing clinical risk scores for predicting clinical outcomes of AF.