In order to bring you the best possible user experience, this site uses Javascript. If you are seeing this message, it is likely that the Javascript option in your browser is disabled. For optimal viewing of this site, please ensure that Javascript is enabled for your browser.
Did you know that your browser is out of date? To get the best experience using our website we recommend that you upgrade to a newer version. Learn more.

Generative AI: A Transformative Force in Cardiovascular Care?

Artificial Intelligence (Machine Learning, Deep Learning)
Hospital Information Systems, Electronic Records, Clinical Decision Support
Patient Engagement and Personalized Health

The field of artificial intelligence (AI) has been rapidly advancing, and its impact on healthcare, also in cardiology, is becoming increasingly evident. A recent comprehensive review by Jain et al. provides an insightful overview of the current state and potential future applications of AI in cardiovascular care.(1) A record-breaking number of AI algorithms were approved by the FDA last year, with cardiology being the second most prominent field after imaging.(2) And a new subset of AI, generative AI (GenAI), may further revolutionize the way we deliver cardiovascular care.

GenAI is different from traditional AI in that it can generate content, such as summaries of text and answers to questions, rather than merely analyzing existing data. Medical large language models (LLMs) have already demonstrated their potential by achieving high scores on standardized tests. But can they truly impact clinical reality? Reports suggest that GenAI could have a substantial impact on healthcare, initially focusing on high-potential, low-risk applications like generating summaries of clinical notes.(2,3) As expertise and trust in GenAI grow, its application in diagnostics and therapy is expected to follow. Later, multimodal foundation models that combine data from various sources, such as imaging, genetics, and electronic health records (EHR) can provide a more comprehensive understanding of a patient's health status and enable more accurate predictions and personalized treatment plans.(1,4)

But already in the short-term, the potential benefits of GenAI in cardiovascular care are numerous. It can automate administrative tasks, assist in planning, support research, and enhance patient self-management. 

Importantly, by streamlining workflows and reducing bureaucracy, GenAI can significantly improve job satisfaction among healthcare professionals. This would address one of the most pressing issues in healthcare today: the exodus of professionals from their jobs due to burnout and dissatisfaction. Examples include automating referral letters, summarizing clinical notes, and automating the numerous clicks required by users of EHR systems.(5)

Furthermore, GenAI can empower patients to take a more active role in their healthcare. Patients can use LLM-powered chatbots to interact with their EHR, prepare for appointments, and record and transcribe conversations with their healthcare professionals. Giving patients control over their EHR and the ability to communicate with it in their own words and at their own pace can improve self-management and adherence to therapy.(6)

However, the implementation of GenAI in cardiovascular care is not without challenges. There is a need for high-quality datasets, rigorous evaluation, and collaboration among stakeholders to ensure the safe and effective deployment of GenAI. Human oversight and responsibility are essential, and initial solutions should focus on low-risk applications while ensuring healthcare professional responsibility (“human-in-the-loop”). To successfully integrate GenAI into cardiovascular care, cardiologists and academics must actively engage in its development and implementation. Education and training programs are necessary to help healthcare professionals effectively utilize GenAI in their practice. A balanced approach that recognizes both the benefits and challenges of GenAI is crucial for its responsible implementation in cardiology.

In our daily news feeds, GenAI is perhaps somewhat overhyped. But even if its quality plateaus soon, ending its hitherto exponential growth in performance, it will still provide a basis for significant changes. Current quality levels of transcription and summarization, for example, are already sufficient to accurately capture a patient-doctor interaction and summarize it for an EHR. The current requirement is for companies to develop these solutions, for hospitals to acknowledge the time savings, for insurance companies to reward the cost savings, and for patients and healthcare professionals to appreciate the opportunity to look into each other's eyes, without the distraction of that screen which now is only barely angled away.

While challenges exist, the benefits of GenAI in cardiology are too significant to ignore, and it may revolutionize cardiovascular care delivery by automating tasks, improving patient self-management, and enhancing job satisfaction. By actively engaging in the development and implementation of GenAI, and adopting a balanced approach that prioritizes safety and responsibility, we can explore its potential to transform the way we deliver cardiovascular care and ultimately improve patient outcomes.

References


  1. Jain S, Elias P, Poterucha T, Randazzo M, Lopez Jimenez F, Khera R, et al. Artificial Intelligence in Cardiovascular Care — Part 2: Applications: JACC Review Topic of the Week. Journal of the American College of Cardiology [Internet]. 2024 Apr 7 [cited 2024 May 16]; Available from: https://www.sciencedirect.com/science/article/pii/S0735109724067445
  2. Nestor Maslej, Loredana Fattorini, Raymond Perrault, Vanessa Parli, Anka Reuel, Erik Brynjolfsson, John Etchemendy, Katrina Ligett, Terah Lyons, James Manyika, Juan Carlos Niebles, Yoav Shoham, Russell Wald, and Jack Clark. The AI Index 2024 Annual Report [Internet]. Stanford, CA, USA: AI Index Steering Committee, Institute for Human-Centered AI, Stanford University; 2024 Apr [cited 2024 May 21]. Available from: https://aiindex.stanford.edu/report/
  3. Berger E, Dries M. Bain. 2023 [cited 2024 May 21]. Beyond Hype: Getting the Most Out of Generative AI in Healthcare Today. Available from: https://www.bain.com/insights/getting-the-most-out-of-generative-ai-in-healthcare/
  4. Moor M, Banerjee O, Abad ZSH, Krumholz HM, Leskovec J, Topol EJ, et al. Foundation models for generalist medical artificial intelligence. Nature. 2023 Apr;616(7956):259–65.
  5. Cluitmans M. Digital assistants: A welcome antidote to healthcare bureaucracy [Internet]. 2023 [cited 2024 May 21]. Available from: https://www.transformingmed.tech/p/digital-assistants-a-welcome-antidote
  6. DeBronkart D. #PatientsUseAI: Patients are end users of AI [Internet]. Patients Use AI. 2024 [cited 2024 May 21]. Available from: https://patientsuseai.substack.com/p/patientsuseai-patients-are-end-users
The content of this article reflects the personal opinion of the author/s and is not necessarily the official position of the European Society of Cardiology.

Contact us

ESC Working Group on e-Cardiology

European Society of Cardiology

European Heart House
Les Templiers
2035 Route des Colles
CS 80179 Biot

06903, Sophia Antipolis, FR

Tel: +33.4.92.94.76.00