Journal of cardiac failure

Journal of cardiac failure
Audio Summaries

Every issue of Journal of cardiac failure moves the field forward, but reading every paper cover-to-cover isn't realistic. OSLR turns each article into a 3-minute audio summary so you can stay current while you commute, round, or work out.

60 audio summariesNLM Catalog

Specialties

Journal of cardiac failure covers research in these specialties.

Recent summaries

The latest articles summarized from Journal of cardiac failure.

Changes in Ventilation Associated with Worsening Heart Failure in Ambulatory Patients.

Nov 13, 2026

This study used continuous thoracic-impedance data from implanted CRT-D devices in 900 MultiSENSE patients to ask whether breathing patterns change before worsening heart failure in everyday life. Across 130 HF events in 92 patients, respiratory rate rose and tidal volume fell in the 3 days before events, producing a significant increase in the Rapid Shallow Breathing Index (RSBI), a pattern that persisted when only resting periods were analyzed and also appeared with worsening dyspnea between clinic visits. The authors conclude that RSBI may be a sensitive marker of impending HF worsening that could support remote monitoring of ambulatory patients.

Establishing a passive registry of patients with heart failure enabled by natural language processing and language models.

Nov 13, 2026

Disease registries are costly to build and maintain, and key heart failure data such as ejection fraction, NYHA class, and social determinants are often stored as unstructured text in EHRs. This study asks whether natural language processing and large language models can automatically build a passive heart failure registry from a Boston tertiary care system's EHRs, linked to Medicare, Medicaid, and vital statistics data. The authors identified 69,007 patients with HF and successfully extracted EF for over half, NYHA class for 23.4%, and social history for 97.7%, suggesting the approach can support future HF research at low cost.

Artificial Intelligence in Heart Failure: From Earlier Disease Detection to Integrated Care Delivery.

Nov 10, 2026

This review asks how artificial intelligence can improve heart failure care, from earlier detection through chronic management. The authors survey AI tools such as AI-enabled electrocardiography, imaging and EHR-based risk models, clinician decision support, remote medication titration, and wearables. They conclude that AI delivers the most value when embedded in active clinical workflows that drive targeted testing, treatment optimization, and follow-up, rather than operating as passive alerts.

Natural Language Processing for the Adjudication of Heart Failure with Reduced and Preserved Ejection Fraction in the Electronic Health Record.

Nov 10, 2026

This study asks whether a natural language processing (NLP) model can more accurately identify heart failure (HF) cases in electronic health records than administrative billing codes, including across reduced (HFrEF) and preserved (HFpEF) ejection fraction subtypes. Using 500 manually adjudicated cases from about 156,000 Beth Israel Deaconess patients, the fine-tuned NLP model outperformed primary ICD codes (kappa 0.73 vs 0.49; sensitivity 89% vs 52%) and performed robustly across subtypes, where ICD codes were weakest for HFpEF. Applied to the full cohort, the NLP approach identified substantially more HFrEF (84% more) and HFpEF (99% more) candidate cases, suggesting it could meaningfully improve HF ascertainment at scale.

Artificial Intelligence‒Guided Phenotyping of Cardiomyopathies: From Detection to Surveillance.

Nov 10, 2026

This review examines how artificial intelligence can improve the diagnosis, phenotyping, risk stratification, and monitoring of cardiomyopathies, using hypertrophic cardiomyopathy (HCM) and transthyretin amyloid cardiomyopathy (ATTR-CM) as primary examples. The authors ask whether AI applied to multimodal data (history, ECG, imaging, biomarkers, and health records) can detect underdiagnosed disease, quantify its severity, and predict its course. They also propose a forward-looking framework for AI-guided phenotyping that addresses label quality, generalizability, false positives in low-prevalence settings, regulation, and the need for prospective evidence that human-AI collaboration improves patient outcomes.

Explainable Machine Learning for Predicting Incident Heart Failure from Routine Electronic Health Record Data.

Nov 10, 2026

This study asks whether an interpretable machine learning model built from routine electronic health record data can predict 5-year incident heart failure as accurately as established risk equations. The authors developed AIHF models using over 2,000 EHR predictors at Stanford and validated them in a national Veterans Affairs cohort, finding AUCs of roughly 0.74–0.85 with discrimination comparable to PREVENT-HF and PCP-HF. The results suggest that transparent, EHR-based models using longitudinal data could offer a scalable way to identify at-risk patients for HF prevention.

Closing the Artificial Intelligence Implementation Gap for Heart Failure Care: How Recent Science Shapes the Next Steps.

Nov 10, 2026

This review asks why AI models for heart failure often show strong algorithmic performance in studies yet fail to produce measurable clinical benefit when deployed. The authors argue that successful implementation depends less on model accuracy and more on design, evaluation, workflow integration, and governance, and they propose four shifts: designing models backward from clinical decisions, deploying them in higher-pretest-probability settings with actionable workflows, generating evidence through independent, simulation-based, and prospective outcome-focused trials, and moving governance from model-level oversight to system-level accountability.

Digital Phenotyping, Remote Monitoring, and Risk Prediction of Heart Failure in Hypertensive Disorders of Pregnancy: A Systematic Review With Narrative Synthesis.

Nov 10, 2026

This systematic review asks whether digital phenotyping, remote monitoring, EHR-based prediction, and machine learning can identify women at risk of heart failure and other cardiovascular morbidity after hypertensive disorders of pregnancy such as preeclampsia. Of 3,366 screened records, only 6 studies met the criteria, and model discrimination ranged from modest to strong (AUROC about 0.70 to 0.94), with recurrent predictors including severe hypertension, earlier gestational age at delivery, kidney disease, and pre-existing cardiac disease. The authors conclude that clinical, EHR, and remotely monitored data show preliminary promise for risk stratification, but most models lack external validation and prospective testing is needed.

Beyond the Stethoscope: Artificial Intelligence for Heart Failure Diagnosis and Phenotyping.

Nov 10, 2026

This review examines how artificial intelligence applied to routine data, such as electrocardiograms (ECGs) and echocardiograms, could improve heart failure diagnosis and phenotyping. The authors ask whether AI-enabled tools like EchoNext and PRESENT-SHD can enable scalable opportunistic screening for undiagnosed structural heart disease and earlier identification of specific phenotypes, such as transthyretin cardiac amyloidosis. They conclude that successful clinical adoption will require prospective validation, careful workflow integration, and responsible deployment.

Long-Term Adherence and Outcomes in Ambulatory Heart Failure Patients Using the Cordella Pulmonary Artery Sensor System.

Nov 9, 2026

This study analyzed 2-year data from the PROACTIVE-HF trial (N=456) to determine whether patient adherence to transmitting data from the Cordella pulmonary artery sensor and clinician response times were linked to heart failure hospitalizations. Patients with low adherence and clinicians with slower response times had higher hospitalization rates than their high-adherence and fast-response counterparts, but the adherence association was no longer significant after adjusting for baseline differences (adjusted IRR 0.83; P=0.19), while the clinician response association was reported as significant (p=0.02) without an equivalent adjusted analysis in the abstract. The authors conclude that patient engagement with sensor data and responsive clinicians are important for successful remote heart failure management.

Listen to Journal of cardiac failure

14-day free trial. Every new article, summarized in ~3 minutes.