An Uncharted Path: How Clinicians are Implementing Artificial Intelligence Across Cardiology

Artificial intelligence (AI) is a burgeoning industry, evolving in practically every direction as it continues to develop. AI-based algorithms are being implemented in countless fields, medicine not least among them. Cardiology in particular has seen a wide range of AI innovations in the past 5 years alone, from screening and analyzing patient characteristics to streamlining clinician workflows.

In this feature article, the editorial team at HCPLive sat down with Manish Wadhwa, MD, a cardiologist and electrophysiologist with San Diego Arrhythmia Associates, Charalambos Antoniades, MD, PhD, director of the Acute Multidisciplinary Imaging & Interventional Centre and BHF chair of cardiovascular medicine at the University of Oxford, and Sadiya Khan, MD, MSc, the Magerstadt Professor of Cardiovascular Epidemiology at Northwestern University Feinberg, to discuss how AI is already implemented into cardiovascular care – as well as the debates over equity and access that naturally spring up around these devices.

Existing Integration and Future Directions

A recent publication in Nature from May 2026 highlighted the extent to which AI is already integrated into cardiovascular care, analyzing the impact these algorithms have had on real-world patient outcomes. Examining categories such as workflow efficiency, patient engagement, and clinical outcomes, the study found that the use of AI algorithms, more specifically machine learning and deep learning, substantially increased all 3 metrics.1

Several clinical trials have also been published, and many more are ongoing, investigating the place AI may take in cardiovascular care. The ORFAN-MAESTRIA trial, for example, shone a spotlight on a particular algorithm’s efficacy in identifying indicators and measuring risk of cardioembolic stroke and atrial fibrillation. Using standard computed tomography (CT) scans, this program is capable of fully automated phenotyping of the peri-left atrial (LA) space, detecting LA myopathy before symptoms appear.2

AI has also found a home in implantable devices, such as the ILR ECG Analyzer from Implicity, which received approval from the US Food and Drug Administration (FDA) in August 2026. This algorithm serves as a secondary filter for alerts generated by implantable cardiac monitors (ICMs), helping clinicians and patients alike by filtering out false positive alerts. Not only can this reduce the number of alerts flooding a given clinician’s inbox, but it also serves to help optimize the way clinicians spend their time, allowing them to aid more patients in need.3

Potential Roadblocks and Concerns

However, for all the benefits AI can provide to clinicians and patients, it remains a thorny issue among the public. Questions regarding data privacy and equitable access have sprung up across a variety of medical specialties, exacerbated by the fact that AI algorithms are in many ways subservient to the data on which they are trained. Any biases present in these data, including disparities in race or gender among patients, could remain as the algorithm is moved into day-to-day use.4

Additionally, medical AI models often work with an immense amount of patient data, including imaging, genetic information, and patient history. This could make these data more vulnerable to breaches or unauthorized access. Many clinicians have discussed the need for stricter cybersecurity measures and guidelines before these programs are made capable of handling this sensitive information.4

Despite these concerns, however, AI has already proven itself beneficial in myriad ways for cardiology clinics and clinicians. Be it through simplifying workflows, providing an extra layer of confirmation for alerts or indicators of disease, or simply categorizing patient data more efficiently, these algorithms have begun to integrate themselves in many aspects of practice. With the speed at which the technology is evolving, it is difficult to call AI integration into cardiology, and medicine writ large, anything but inevitable.

Editors’ Note: Antoniades reports disclosures with AstraZeneca, Caristo Diagnostics, Lexicon, Novo Nordisk, Sanofi, Silence Therapeutics, and others. Khan reports no relevant disclosures. Wadhwa reports his position as a clinical advisor for Implicity.

References

1. Lin YE, Yang SM, Huang CJ, et al. Impact of artificial intelligence on cardiovascular workflow, engagement, and outcomes: a systematic review. npj Digit. Med. 9, 536 (2026). https://doi.org/10.1038/s41746-026-02690-7

2. Livingston R. ORFAN-MAESTRIA: AI Predicts Cardioembolic Stroke, Atrial Fibrillation from CT Scans. HCPLive. September 6, 2026. Accessed September 23, 2026. https://www.hcplive.com/view/orfan-maestria-ai-predicts-cardioembolic-stroke-atrial-fibrillation-from-ct-scans

3. Livingston R. FDA-Cleared, AI-Assisted ECG Analyzer Algorithm Reduces False Positives in ICMs. HCPLive. August 21, 2026. Accessed September 23, 2026. https://www.hcplive.com/view/fda-cleared-ai-assisted-ecg-analyzer-algorithm-reduces-false-positives-in-icms

4. Livingston R. Equitable and Ethical AI Use in Cardiology: Addressing Biases and Privacy Concerns. HCPLive. September 11, 2026. Accessed September 23, 2026. https://www.hcplive.com/view/equitable-and-ethical-ai-use-in-cardiology-addressing-biases-and-privacy-concerns