Advances in device-based treatment of heart failure with preserved ejection fraction: evidence from clinical trials

Electrocardiograph analysis for risk assessment of heart failure with preserved ejection fraction: A deep learning model

AIMS

Heart failure with preserved ejection fraction (HFpEF) requires an efficient screening method. We developed a deep learning model (DLM) to screen HFpEF risk using electrocardiograms (ECGs).

METHODS AND RESULTS

A cohort study was conducted utilising data from Cohorts A and B. A convolutional neural network-long short-term memory (CNN-LSTM) DLM was employed. HFpEF risk was determined by left ventricular end-diastolic pressure (LVEDP) and clinical symptoms. The DLM was trained by ECGs. LVEDP for each patient was collected through invasive left ventricular catheterisation. Cohort A and B comprised data from individuals at high risk for HFpEF (LVEDP > 12 mmHg) and low risk for HFpEF (LVEDP ≤ 12 mmHg). The model was trained on Cohort A and prospectively validated on Cohort B.

RESULTS

A total of 238 patients underwent ECG and left ventricular catheterisation for model training in Cohort A, and 117 patients for validation in Cohort B. The DLM achieved 78% accuracy in assessing HFpEF risk in Cohort A, while in Cohort B, it demonstrated 78% accuracy, 71.9% specificity, and 71.7% sensitivity. In the validation Cohort B, the DLM-identified high-risk HFpEF group exhibited significantly higher prevalence of diabetes (22.03%-11.86%, P < 0.01), higher BMI indices (25.92-24.22 kg/cm2, P < 0.01), and lower usage history of calcium channel blockers (CCB) (11.76%-28.81%, P < 0.01) compared with the DLM-identified low-risk HFpEF group. Traditional HFpEF indicators, including B-type natriuretic peptide (BNP) (22-20 pg/mL, P = 0.71) and E/E' (8.25-8.5, P = 0.66), did not exhibit significant differences between the two groups.

CONCLUSIONS

The DLM offers an accurate, cost-effective tool for HFpEF risk assessment, potentially facilitating early detection and improved clinical management.

Invasive haemodynamic assessment in heart failure with preserved ejection fraction

Despite the increasing prevalence and substantial burden of heart failure with preserved ejection fraction (HFpEF), which constitutes up to 50% of all heart failure cases, significant challenges persist in its diagnostic and therapeutic strategies. These difficulties arise primarily from the heterogeneous nature of the condition, the presence of various comorbidities and a wide range of phenotypic variations. Considering these challenges, current international guidelines endorse the utilization of invasive haemodynamic assessments, including resting and exercise haemodynamics, as the gold standard for enhancing diagnostic accuracy in cases where traditional diagnostic methods yield inconclusive results. These assessments are crucial not only for confirming the diagnosis but also for delineating the complex underlying pathophysiology, enabling the development of personalized treatment strategies, and facilitating the precise classification of HFpEF phenotypes. In this review, we summarize the haemodynamic changes observed in patients with HFpEF, comparing resting and exercise-induced parameters to those of normal subjects. Additionally, we discuss the current role of invasive haemodynamics in HFpEF assessment and highlight its utility beyond diagnosis, such as identifying HFpEF comorbidities, guiding phenotype-based personalized therapies and characterizing prognostication. Finally, we address the challenges associated with utilizing invasive haemodynamics and propose future directions, focusing on integrating these assessments into routine HFpEF care.

Current Approaches to Worsening Heart Failure: Pathophysiological and Molecular Insights

Worsening heart failure (WHF) is a severe and dynamic condition characterized by significant clinical and hemodynamic deterioration. It is characterized by worsening HF signs, symptoms and biomarkers, despite the achievement of an optimized medical therapy. It remains a significant challenge in cardiology, as it evolves into advanced and end-stage HF. The hyperactivation of the neurohormonal, adrenergic and renin-angiotensin-aldosterone system are well known pathophysiological pathways involved in HF. Several drugs have been developed to inhibit the latter, resulting in an improvement in life expectancy. Nevertheless, patients are exposed to a residual risk of adverse events, and the exploration of new molecular pathways and therapeutic targets is required. This review explores the current landscape of WHF, highlighting the complexities and factors contributing to this critical condition. Most recent medical advances have introduced cutting-edge pharmacological agents, such as guanylate cyclase stimulators and myosin activators. Regarding device-based therapies, invasive pulmonary pressure measurement and cardiac contractility modulation have emerged as promising tools to increase the quality of life and reduce hospitalizations due to HF exacerbations. Recent innovations in terms of WHF management emphasize the need for a multifaceted and patient-centric approach to address the complex HF syndrome.