Lifestyle Modification or Medication to Improve Condition of Patients With Asymptomatic Heart Failure - Monitoring and Management of OptiVol Alert to Reduce Heart Failure Hospitalization II (MOMOTARO II) Study

Clinical Utility of Machine Learning-Derived Vocal Biomarkers in the Management of Heart Failure

Background

This study aimed to systematically evaluate voice symptoms during heart failure (HF) treatments and to exploratorily extract HF-related vocal biomarkers.

Methods and Results

This single-center, prospective study longitudinally acquired 839 audio files from 59 patients with acute decompensated HF. Patients' voices were analyzed along with conventional HF indicators (New York Heart Association [NYHA] class, presence of pulmonary congestion and pleural effusion on chest X-ray, and B-type natriuretic peptide [BNP]) and GOKAN scores based on the assessment of a cardiologist. Machine-learning (ML) models to estimate HF conditions were created using a Light Gradient Boosting Machine. Voice analysis identified 27 acoustic features that correlated with conventional HF indicators and GOKAN scores. When creating ML models based on the acoustic features, there was a significant correlation between actual and ML-derived BNP levels (r=0.49; P<0.001). ML models also identified good diagnostic accuracies in determining HF conditions characterized by NYHA class ≥2, BNP ≥300 pg/mL, presence of pulmonary congestion or pleural effusion on chest X-ray, and decompensated HF (defined as NYHA class ≥2 and BNP levels ≥300 pg/mL; accuracy: 75.1%, 69.1%, 68.7%, 66.4%, and 80.4%, respectively).

Conclusions

The present study successfully extracted HF-related acoustic features that correlated with conventional HF indicators. Although the data are preliminary, ML models based on acoustic features (vocal biomarkers) have the potential to infer various HF conditions, which warrant future studies.

Developing Multidisciplinary Management of Heart Failure in the Super-Aging Society of Japan

The Japanese population is rapidly aging because of its long life expectancy and low birth rate; additionally, the number of patients with heart failure (HF) is increasing to the extent that HF is now considered a pandemic. According to a recent HF registry study, Japanese patients with HF have both medical and care-related problems. Although hospitalization is used to provide medical services, and institutionalization is used to provide care for frail older adults, it can be difficult to distinguish between them. In this context, multidisciplinary management of HF has become increasingly important in preventing hospital readmissions and maintaining a patient's quality of life. Academia has promoted an increase in the number of certified HF nurses and educators. Researchers have issued numerous guidelines or statements on topics such as cardiac rehabilitation, nutrition, and palliative care, in addition to the diagnosis and treatment of acute and chronic HF. Moreover, the Japanese government has created incentives through various medical and long-term care systems adjustments to increase collaboration between these two fields. This review summarizes current epidemiological registries that focus not only on medical but also care-related problems and the 10 years of multidisciplinary management experience in Japanese medical and long-term care systems.

Serum NT-proBNP levels and histopathological myocardial fibrosis in autopsied cases from a Japanese community: The Hisayama Study

BACKGROUND

natriuretic peptide is associated with myocardial fibrosis in animal models and among patients with heart disease. However, it remains unclear whether serum N-terminal pro-B-type peptide (NT-proBNP) levels are associated with histopathologically proven myocardial fibrosis among individuals without apparent heart disease. This study aimed to evaluate the association between serum NT-proBNP levels and the histopathologically estimated myocardial fibrotic area in autopsied samples from a community.

METHODS

we selected 63 cases without apparent heart disease with available data of serum NT-proBNP concentrations within six years before death (average age: 82 years; male: 52%) from autopsied cases in a community, and evaluated the percentage areas of myocardial fibrosis in four cardiac segments from each case (i.e. 252 cardiac segments in total). The association between serum NT-proBNP levels and the percentage area of myocardial fibrosis was estimated using a linear mixed model for repeated measures.

RESULTS

serum NT-proBNP levels were positively correlated with myocardial fibrotic area [Pearson's correlation coefficient: r = 0.49 (95% confidence interval: 0.28-0.66), p <0.001]. Serum NT-proBNP levels were significantly associated with the percentage areas of myocardial fibrosis after adjusting for potential confounding factors. There was no evidence of heterogeneity in the association between the subgroups with and without reduced estimated glomerular filtration rate (<60 mL/min/1.73 m²).

CONCLUSIONS

the present study demonstrated that elevated serum NT-proBNP levels were associated with the histopathologically measured myocardial fibrotic area in autopsied cases from a community. These findings may help clarify the association between elevated serum NT-proBNP levels and myocardial fibrosis and their influence on prognosis.

Remote monitoring for heart failure management during COVID-19 pandemic

BACKGROUND

COVID-19 pandemic impacted on heart failure patients' lifestyle and quality of life, affecting both physical activity levels and state of health.

METHODS

Demographic data and device records were extracted for patients with heart failure in the 16 weeks at the turn of lockdown during pandemic. To explore the variability across the lockdown period, a week-to-week analysis was performed. Patients were interviewed to investigate physical activity and psychological insights. The primary endpoint was the variation in physical activity at the turn of lockdown.

RESULTS

At our facility, 2225 patients implanted with a cardiac device were screened and data were collected for 211 patients fulfilling the inclusion criteria. Patients' physical activity significantly decreased in the lockdown period compared with the control period (active time per day 8.0% vs. 10.8%; relative reduction [RRR] 25.9%; p < 0.0001). A small decrease was noted for mean heart rate (70.1 vs. 71.7 beats per minute [bpm]; RRR 2.2%; p < 0.0001), while thoracic impedance slightly increased (82.2 vs. 82.7 ohm; RRR 0.6%; p = 0.001). Patients' physical activity decreased from week 7 to week 11 (10.9% vs. 6.9%; RRR 36.7%; P < 0.0001) with an increase between week 11 and week 16 (6.9% vs. 8.5%; RRR 18.8%; P < 0.0001). Patients' perceptions about physical activity showed a very low correlation with remote monitoring-assessed physical activity levels (r2 = 0.035, p = 0.039).

CONCLUSIONS

Telemedicine and remote monitoring can explore the impact of COVID-19 pandemic on vital signs and physical activity levels of heart failure patients, playing a crucial role in the prediction of heart failure worsening during circumstances discouraging outpatient visits.