Obesity in heart failure: impact on survival and treatment modalities

Machine learning models in heart failure with mildly reduced ejection fraction patients

Objective

Heart failure with mildly reduced ejection fraction (HFmrEF) has been recently recognized as a unique phenotype of heart failure (HF) in current practical guideline. However, risk stratification models for mortality and HF re-hospitalization are still lacking. This study aimed to develop and validate a novel machine learning (ML)-derived model to predict the risk of mortality and re-hospitalization for HFmrEF patients.

Methods

We assessed the risks of mortality and HF re-hospitalization in HFmrEF (45–49%) patients enrolled in the TOPCAT trial. Eight ML-based models were constructed, including 72 candidate variables. The Harrell concordance index (C-index) and DeLong test were used to assess discrimination and the improvement in discrimination between models, respectively. Calibration of the HF risk prediction model was plotted to obtain bias-corrected estimates of predicted versus observed values.

Results

Least absolute shrinkage and selection operator (LASSO) Cox regression was the best-performing model for 1- and 6-year mortality, with a highest C-indices at 0.83 (95% CI: 0.68–0.94) over a maximum of 6 years of follow-up and 0.77 (95% CI: 0.64–0.89) for the 1-year follow-up. The random forest (RF) showed the best discrimination for HF re-hospitalization, scoring 0.80 (95% CI: 0.66–0.94) and 0.85 (95% CI: 0.71–0.99) at the 6- and 1-year follow-ups, respectively. For risk assessment analysis, Kansas City Cardiomyopathy Questionnaire (KCCQ) subscale scores were the most important predictor of readmission outcome in the HFmrEF patients.

Conclusion

ML-based models outperformed traditional models at predicting mortality and re-hospitalization in patients with HFmrEF. The results of the risk assessment showed that KCCQ score should be paid increasing attention to in the management of HFmrEF patients.

High-protein vs. standard-protein diets in overweight and obese patients with heart failure and diabetes mellitus: findings of the Pro-HEART trial

AIMS

The intermediate-term effects of dietary protein on cardiometabolic risk factors in overweight and obese patients with heart failure and diabetes mellitus are unknown. We compared the effect of two calorie-restricted diets on cardiometabolic risk factors in this population.

METHODS AND RESULTS

In this randomized controlled study, 76 overweight and obese (mean weight, 107.8 ± 20.8 kg) patients aged 57.7 ± 9.7 years, 72.4% male, were randomized to a high-protein (30% protein, 40% carbohydrates, and 30% fat) or standard-protein diet (15% protein, 55% carbohydrates, and 30% fat) for 3 months. Reductions in weight and cardiometabolic risks were evaluated at 3 months. Both diets were equally effective in reducing weight (3.6 vs. 2.9 kg) and waist circumference (1.9 vs. 1.3 cm), but the high-protein diet decreased to a greater extent glycosylated haemoglobin levels (0.7% vs. 0.1%, P = 0.002), cholesterol (16.8 vs. 0.9 mg/dL, P = 0.031), and triglyceride (25.7 vs. 5.7 mg/dL, P = 0.032), when compared with the standard-protein diet. The high-protein diet also significantly improved both systolic and diastolic blood pressure than the standard-protein diet (P < 0.001 and P = 0.040, respectively).

CONCLUSIONS

Both energy-restricted diets reduced weight and visceral fat. However, the high-protein diet resulted in greater reductions in cardiometabolic risks relative to a standard-protein diet. These results suggest that a high-protein diet may be more effective in reducing cardiometabolic risk in this population, but further trials of longer duration are needed.