Embracing AI to enhance EP: Insights from cardiologist Jagmeet Singh

Singh highlighted the proliferation of AI algorithms in EP. There are now more than 122 FDA-cleared AI algorithms specific to cardiology, and a large number of these are related to automated analysis of electrocardiograms (ECGs). Singh pointed out the significant advancements of AI in ECG, which now allow for the diagnosis of conditions ranging from atrial fibrillation to sudden cardiac death. He said AI's integration into clinical procedures, including augmented reality (AR) and virtual reality (VR) for procedural guidance, is becoming more prevalent.

AI enhances cardiac remote monitoring capabilities

The accessibility and convenience of AI-powered devices were also discussed. 

Singh said the accessibility, convenience the effectiveness of wearable, clinical-grade cardiac monitor technologies are replacing traditional Holter monitors and providing automated alerts to healthcare providers. 

"Wearables I think will eventually cannibalize implantable devices," Singh predicted. He emphasizing the role of AI in managing and interpreting the vast amount of data generated by these devices to reduce false positives and clinician burnout.

These newer, wearable cardiac monitors under the watch of AI 24/7 has also led to a growing trend of same-day discharges and home monitoring strategies that allow patients to recover in their own homes while still having their telemetry closely monitored remotely. 

"This not only makes fiscal sense but also translates into better clinical outcomes," Singh explained.

Looking ahead, Singh foresees AI evolving into device technology with fully integrated closed-loop alert systems.

The growing role of generative AI in EP

Generative AI tools such as ChatGPT that can take a set of note, data or conversations and convert them into digested reports or even convert complex EP explanations into laymen's terms is a large, growing next frontier in EP. Generative AI is already cleared by the FDA in reporting system released by Nuance that can record an entire patient encounter and then autocomplete a patient visit report, including key testing metrics, recommendations for the patient and patient comments or concerns. Singh said this level of generative AI is now being applied to EP reports.

"I think having AI based algorithms to help us understand all that data that comes from the wearables, whether it's an ECG or whether it's heart rate or physical activity or autonomic state besides oxygen saturation and all the other things that you can measure. I think that data requires some sort of generative AI approach to make it explainable to the patient as well as the physician, and then also close the loop in how you actually can use that to manage patients," Singh explained. 

He said AI device monitoring is being used to reduce the false positive results and eliminate the non-actionable data to the clinicians only see what is really important not only can help speed workflows, but also reduce physician and clinician burnout. 

Patients will have more tools to understand their health conditions, reducing the need for constant physician intervention. He also highlighted the potential of generative AI to provide empathetic responses and personalized care, further enhancing patient experience and boosting clinical efficiency.

"AI may be a black box, but if it enhances that interpersonal skill sets of patients being able to communicate with their data because of generative AI, I think is the first time now that physicians as well as patients can talk directly to the data and get an answer from that data. How it's going to play out remains to be seen, but we're already seeing stuff happen within our hospitals," Singh explained.

AI will help address health disparities

The discussion also touched on the broader implications of AI for addressing the shortage of cardiologists, particularly in rural areas. Singh believes that digital equity facilitated by AI will lead to global health equity, making high-quality care accessible to underserved populations. And not just in low-income or rural areas of the United States, but helping even larger numbers of patients in remote or resource poor countries across the world.

Singh also chaired sessions at HRS discussing the impact of language models on cardiology and the importance of creating adaptable digital toolkits for various populations. The rapid evolution of cellular networks, such as the upcoming 6G technology, will further enable real-time consultative services and global health initiatives, making advanced cardiac care accessible worldwide. He noted that most patients in the U.S. and around the world now have smart phones, and with high-speed internet connections, that can can led to a major change in telemedicine.

In his keynote about AI and new technology at HRS, Singh introduced the concept of "networkness," envisioning a future where healthcare systems are interconnected, allowing for cross-border patient care driven by patient expectations and regulatory acceptance. This "Uber-ization of healthcare," as he called it, could become a reality with advancements in digital health, ensuring universal health coverage and connectivity.