Groundbreaking DAMSUN-HF Study Demonstrates AI-Enhanced Heart Failure Detection
A new study conducted in Sub-Saharan Africa has demonstrated that Eko Health’s AI-enabled stethoscope can identify heart failure with specialist-level sensitivity at the point of care. The DAMSUN-HF study, conducted in clinical settings across Ghana and neighboring regions, evaluated the device’s ability to detect reduced ejection fraction (EF) — a key indicator of heart failure — using artificial intelligence to interpret auscultation data in real time.
Heart failure remains a leading cause of morbidity worldwide, and timely, accurate diagnosis is essential for effective management. Traditional auscultation can be challenging, particularly in low-resource settings where access to advanced imaging like echocardiography is limited. The DAMSUN-HF study addresses this gap by leveraging AI to augment the clinician’s ear, enhancing diagnostic confidence without requiring immediate access to high-end imaging.
What the DAMSUN-HF Study Found
The study enrolled patients presenting with symptoms suggestive of heart failure. Clinicians used Eko Health’s AI-enabled stethoscope to perform auscultation, with the AI algorithm analyzing acoustic signatures and clinical context to estimate the likelihood of reduced EF. The results showed high sensitivity in identifying patients with reduced EF at the point of care, which implies that clinicians using the tool could reliably triage and manage suspected heart failure cases more effectively on-site.
Key metrics reported by the investigators indicate that AI-assisted auscultation matched or exceeded the diagnostic performance of standard, yet resource-intensive, methods in many scenarios. This level of accuracy is particularly impactful in Sub-Saharan Africa, where access to echocardiography or cardiology specialists is unevenly distributed and travel to tertiary centers can delay care.
Implications for Clinical Practice
By enabling near-specialist detection of reduced EF at the bedside, the AI-enabled stethoscope supports faster clinical decisions, earlier treatment initiation, and improved patient outcomes. For health systems, this technology offers a scalable solution to expand diagnostic capacity without a proportional increase in specialists or infrastructure. In settings where healthcare resources are stretched, such tools can streamline workflow, reduce unnecessary referrals, and help prioritize patients who need advanced imaging or inpatient care.
Importantly, the DAMSUN-HF findings align with a growing body of evidence that AI can augment frontline clinicians without replacing the need for comprehensive cardiovascular assessment. The platform complements echocardiography and cardiology input by enhancing the initial evaluation and ensuring that high-risk patients are identified promptly.
What Sets Eko’s Solution Apart?
Eko Health’s stethoscope integrates advanced AI with high-fidelity acoustic sensing to support decision-making at the point of care. The system is designed for real-time interpretation, offering clinicians a probabilistic assessment of reduced EF alongside standard auscultatory findings. In regions with limited access to cardiology services, this capability can be a game-changing adjunct that informs treatment pathways, triage, and referrals.
Future Directions and Adoption
Researchers and healthcare providers involved in the DAMSUN-HF study emphasize the importance of broader validation across diverse populations and settings. Ongoing efforts aim to assess long-term clinical outcomes, integration with existing health information systems, and strategies to ensure equitable access to AI-assisted diagnostics.
As Eko Health continues to expand its footprint in Africa and other resource-limited regions, the DAMSUN-HF study adds to a growing momentum around AI-enabled auscultation as a practical, scalable tool for improving cardiovascular care where it is needed most.
About the Study and Access
The DAMSUN-HF study represents a collaborative effort among researchers, clinicians, and patient communities in Sub-Saharan Africa. Results point to meaningful improvements in diagnostic precision at the point of care and set the stage for broader adoption of AI-assisted auscultation in routine practice.
