ABSTRACT
Aims: Although frailty assessment is recommended for guiding treatment strategies and outcome prediction in elderly patients with heart failure (HF), most frailty scales are subjective, and the scores vary among raters. We sought to develop a machine learning-based automatic rating method/system/model of the clinical frailty scale (CFS) for patients with HF. Methods and results: We prospectively examined 417 elderly (≥75 years) with symptomatic chronic HF patients from 7 centres between January 2019 and October 2023. The patients were divided into derivation (n = 194) and validation (n = 223) cohorts. We obtained body-tracking motion data using a deep learning-based pose estimation library, on a smartphone camera. Predicted CFS was calculated from 128 key features, including gait parameters, using the light gradient boosting machine (LightGBM) model. To evaluate the performance of this model, we calculated Cohen's weighted kappa (CWK) and intraclass correlation coefficient (ICC) between the predicted and actual CFSs. In the derivation and validation datasets, the LightGBM models showed excellent agreements between the actual and predicted CFSs [CWK 0.866, 95% confidence interval (CI) 0.807-0.911; ICC 0.866, 95% CI 0.827-0.898; CWK 0.812, 95% CI 0.752-0.868; ICC 0.813, 95% CI 0.761-0.854, respectively]. During a median follow-up period of 391 (inter-quartile range 273-617) days, the higher predicted CFS was independently associated with a higher risk of all-cause death (hazard ratio 1.60, 95% CI 1.02-2.50) after adjusting for significant prognostic covariates. Conclusion: Machine learning-based algorithms of automatically CFS rating are feasible, and the predicted CFS is associated with the risk of all-cause death in elderly patients with HF.
ABSTRACT
AIMS: Iron deficiency (ID) is a common co-morbidity in patients with heart failure (HF). A recent study showed that ID defined by the current guideline criteria was not associated with worse clinical outcomes, and new ID criteria was proposed in patients with HF. However, the external applicability of the new proposed criteria is unclear. We sought to investigate the applicability of the proposed ID criteria in Japanese patients with HF. METHODS AND RESULTS: We prospectively examined 763 patients with chronic HF from a Japanese multicentre registry. The proposed ID criteria were transferrin saturation (TSAT) < 20% and serum iron ≤13 mmol/L and the guideline ID criteria were serum ferritin <100 ng/mL or, when ferritin was 100-299 ng/mL, TSAT <20%. Among all patients (456 male, mean age 71 ± 13 years), 213 (28%) and 444 (58%) met the proposed and guideline ID criteria, respectively. During a median follow-up period of 436 days (interquartile range 297-565), the primary outcome of all-cause mortality occurred in 56 (7%) patients. There was no significant difference in the primary outcome between the patients with and without guideline ID criteria (P = 0.32), whereas patients with serum iron ≤10 µmol/L showed higher mortality (P = 0.002). In multivariable Cox regressions, the proposed ID criteria, but not guideline ID criteria, were independently associated with the risk of all-cause mortality (HR 2.01, 95% CI 1.16-3.51 and HR 1.32, 95% CI 0.76-2.28, respectively), even after adjustment for covariates. CONCLUSIONS: When defined by the proposed criteria and not the guideline criteria, ID was associated with higher mortality in patients with chronic HF, suggesting that the proposed ID criteria is applicable to the Japanese population.
