
Heart Beats and Predictive AI
Welcome to News From The Future read to you by the AI Voice Clone of Dr Cath made by eleven labs. This is the start of a new thematic across my work, also known as “What in the AI?” Enjoy! Doctors have developed a groundbreaking AI tool capable of detecting heart disease in less than two seconds. This revolutionary technology is transforming the way heart conditions are diagnosed, using artificial intelligence trained on millions of patient data points to analyze routine electrocardiograms (ECGs) with a level of precision and speed far beyond what the human eye can achieve. Let’s dive into the details of this innovation and its potential impact. The ECG, a century-old tool, has been a cornerstone in diagnosing heart attacks and abnormal heart rhythms. It records the electrical activity of the heart, including its rate and rhythm, but its diagnostic capabilities have traditionally been limited. Detecting heart disease, such as heart failure or heart valve disease, has required an echocardiogram, a type of ultrasound scan. Unfortunately, access to echocardiograms can involve long waiting periods, often lasting months. This delay can be critical, as early diagnosis is essential for effective treatment and improved outcomes in patients with heart conditions. The newly developed AI tool changes the game by analyzing ECG results almost instantaneously to detect signs of heart failure and heart valve disease—two of the most common and serious forms of heart disease. Details of this technological breakthrough were presented at the European Society of Cardiology annual congress in Munich, the largest heart conference in the world. The AI tool’s ability to identify these conditions early could lead to faster treatment, potentially saving lives and improving the quality of life for countless patients. Why is this development so significant? ECGs are among the most frequently performed medical tests globally, with approximately one billion conducted each year. By enhancing the diagnostic capabilities of such a routine test, this AI tool has the potential to make a massive global impact. During a trial involving 67,000 patients in the United States, the AI demonstrated remarkable accuracy, identifying up to 81% of heart failure cases and 90% of heart valve disease cases. These results highlight the tool’s ability to prioritize patients who are most at risk, enabling faster follow-up testing and earlier intervention. Dr. Sonya Babu-Narayan, a consultant cardiologist and clinical director at the British Heart Foundation (BHF), which funded the trial, emphasizes the importance of this innovation. She stated, “It is exciting to see that AI can now deliver a read-out from an ECG in what feels like the blink of an eye.” While acknowledging that the tool isn’t perfect and won’t detect every case, she noted its potential to fast-track high-risk patients for further testing. “When it comes to the heart, earlier diagnosis and treatment saves and improves lives,” she remarked, underscoring the life-changing impact of early detection. It’s important to understand that this AI tool is not intended to replace traditional diagnostic methods. It cannot definitively diagnose or rule out heart failure or heart valve disease on its own. Instead, it serves as a powerful screening tool, flagging patients who are highly likely to have these conditions. Those flagged can then be prioritized for echocardiograms, bypassing long waiting lists. This approach could significantly reduce the time to diagnosis and treatment, providing patients with a crucial head start in managing their conditions. Prof. Fu Siong Ng, a cardiology expert at Imperial College London, highlighted the practical implications of this technology. He explained that patients often face months-long waits for heart ultrasound scans after being referred by their doctors. The AI tool could change this by identifying those at highest risk and prioritizing them for urgent scans. Beyond speeding up the diagnostic process, Ng noted that the tool could also identify heart conditions in patients who underwent an ECG for unrelated reasons. This opportunistic diagnostic capability could be a game-changer, as it would allow hospitals to run the AI model on all ECGs performed, flagging high-risk individuals who might otherwise go unnoticed. The potential applications of this technology extend even further. Dr. Ahmed El-Medany, a BHF clinical research fellow who led the analysis at Imperial College London, described the tool as a “superhuman AI.” He suggested that the next big challenge would be to design portable, handheld AI-led ECG readers for healthcare professionals. Such devices could bring this advanced diagnostic capability to more settings, including remote or resource-limited areas, further expanding the tool’s reach and impact. In addition to its applications in heart health, AI is also making strides in other areas of medical diagnostics. Researchers at the University of Tokyo and the Institute of Science Tokyo have developed an AI-based method for analyzing five-second facial videos to detect undiagnosed high blood pressure and type 2 diabetes. These conditions often go unnoticed in millions of people worldwide, and this innovative approach could bridge that gap. By quickly and accurately identifying these conditions, the AI could pave the way for earlier interventions and better health outcomes. The AI tool’s ability to analyse ECGs with such precision represents a monumental step forward in medical diagnostics. By enhancing the capabilities of a routine test, it has the potential to save countless lives through earlier detection and treatment of heart disease. While it’s not a standalone diagnostic solution, its ability to flag high-risk patients for further testing could revolutionise how we approach heart health. And with ongoing advancements in AI technology, the possibilities for improving healthcare outcomes seem boundless. To summarize, this “superhuman” AI tool offers a glimpse into the future of medical diagnostics. By transforming a common test like the ECG into a powerful diagnostic tool for heart disease, it has the potential to make a profound impact on global health. Whether through faster prioritisation of high-risk patients, opportunistic diagnosis of unsuspected conditions, or eventual deployment in portable devices, the possibilities are vast. Coupled with parallel advancements in AI applications for other diseases, this technology marks the beginning of a new era in healthcare - one where speed, accuracy, and accessibility can redefine patient outcomes. Thank you for listening to this podcast. Please support Dr Cath’s works by buying her books or becoming a paid subscriber to her substack. "News From The Future" with Dr Catherine Ball is a reader-supported publication. To receive new posts and support my work, consider becoming a paid subscriber. This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit drcatherineball.substack.com/subscribe













