New Research Shows AI-enabled Digital Stethoscope Can Better Diagnose Heart Disease

• Blockchain Council
• September 13, 2024

New research conducted by Mayo Clinic reveals the transformative potential of artificial intelligence (AI) in improving the diagnosis of peripartum cardiomyopathy, a condition that can have life-threatening consequences for women during pregnancy or shortly after childbirth. Researchers have demonstrated that using an AI-enabled digital stethoscope that captures electrocardiogram (ECG) data and heart sounds can identify twice as many cases of peripartum cardiomyopathy as standard care. This breakthrough not only offers hope for early detection and treatment but also highlights the importance of AI in healthcare.

Peripartum cardiomyopathy presents a unique challenge as its symptoms, such as shortness of breath when lying down, swelling of hands and feet, weight gain, and rapid heartbeat, often mimic normal pregnancy discomforts. Distinguishing between the two is critical for the well-being of both the mother and child.

Dr. Demilade Adedinsewo, a cardiologist at Mayo Clinic, led this groundbreaking research, which took place in Nigeria, a country with the highest reported incidence of peripartum cardiomyopathy. The study involved 1,195 women receiving pregnancy care, with half undergoing AI-guided screening using the digital stethoscope and the other half receiving traditional obstetric care alongside a clinical ECG. An echocardiogram confirmed the cases where the AI-enabled digital stethoscope predicted peripartum cardiomyopathy. The results were striking, with 4% of pregnant and postpartum women in the AI intervention group diagnosed with cardiomyopathy, compared to 2% in the control group, revealing that half of the cases had gone undetected with standard care.

Moving beyond Nigeria, GP clinics in London and Wales are embarking on a pioneering trial to improve the diagnosis of heart failure using AI-powered tools. Led by researchers at Imperial College London and funded by a £1.2 million award from the National Institute for Health and Care Research (NIHR), the TRICORDER program aims to deploy AI-enabled smart stethoscopes to 100 primary care practices. This represents the first sector-wide utilization of AI in primary care and could potentially revolutionize heart failure diagnosis.

Heart failure, a condition where the heart struggles to pump blood effectively, carries a higher risk of death than many cancers and poses a substantial burden on healthcare systems. In the UK, it affects 2% of the population and consumes 4% of the NHS budget. Previous research by the Imperial College London team demonstrated that combining an AI algorithm with a smart stethoscope (Eko DUO) enabled immediate heart failure diagnosis with remarkable sensitivity (91%) and specificity (80%), surpassing the accuracy of invasive and costly routine diagnostic tests.

The TRICORDER program will assess whether providing GPs with AI stethoscopes can lead to earlier heart failure detection, reducing emergency hospital admissions and cutting costs for the NHS. More than 200 GP practices, covering over three million patients in Northwest London and North Wales, will participate in the randomized allocation of AI stethoscopes or standard care. Patients examined with the AI stethoscope will undergo a brief, non-invasive heart examination using the Eko digital stethoscope and app powered by AI. If potential signs of cardiac disease are detected, GPs can promptly initiate further tests and life-saving treatments.

Professor Nicholas Peters from the National Heart and Lung Institute at Imperial College London emphasized the urgent need for improved heart failure detection, as emergency admissions for heart failure cost the UK over £2 billion annually, with 80% of diagnoses occurring during emergency admissions. The TRICORDER program, if successful, could save the healthcare system £2,400 per patient and significantly enhance the chances of early intervention and better patient outcomes.

Currently, the gold standard for heart failure detection is a blood test (NT-proBNP). However, relying solely on this test often leads to delayed diagnosis and treatment for those in need. The widespread use of AI tools in primary care holds the potential to transform heart disease outcomes for millions in the UK, ensuring earlier diagnoses and improved quality of life.

Connor Landgraf, Co-founder and CEO of Eko Health expressed the importance of accurate and early heart disease detection, emphasizing the positive impact of technology on patients’ lives. The deployment of AI-enabled heart disease detection technology across the UK underscores the critical role AI plays in revolutionizing healthcare.

TRICORDER represents a collaborative effort between The NHS North West London Integrated Care System, Betsi Cadwaladr University Health Board, and Imperial College London. The initial study received funding from various sources, including the Artificial Intelligence in Health and Care Award from the NHS Accelerated Access Collaborative, Imperial College Healthcare NHS Trust, Imperial Health Charity, Imperial Biomedical Research Centre of the National Institute for Health Research, and the British Heart Foundation.

The recent advancements in AI-enabled digital stethoscopes offer new hope for the early detection and treatment of heart-related conditions during pregnancy and beyond. Additionally, the TRICORDER program’s innovative use of AI in primary care has the potential to revolutionize heart failure diagnosis, reducing healthcare costs and improving patient outcomes on a massive scale. These breakthroughs underscore the transformative power of AI in healthcare and its potential to save lives and resources.