Clinicians from all specialties use AI to answer cardiology questions
Cardiologists and other clinicians are using artificial intelligence (AI) tools more and more on the job to guide treatment decisions and manage care, according to new data published in JAMA.[1]
For this study, researchers tracked the use of OpenEvidence, an AI-enabled clinical information platform designed to be used by healthcare providers. They used a large language model to evaluate a random sample of user activity from January 2024 to June 2026.
“Unlike traditional clinical resources, AI-enabled tools synthesize available evidence in response to a clinician’s specific question, changing how clinicians access a body of medical knowledge that has long exceeded what any individual can retain,” wrote first author Vishal R. Patel, MD, a researcher with Harvard Medical School, and colleagues. “Policymakers, professional societies, and health systems are developing guidelines around the use of AI in clinical practice, yet these efforts have proceeded without empirical data on how these tools are used. The same is true of efforts to evaluate how well these tools perform, which have focused primarily on diagnostic accuracy and medical knowledge recall, without evidence on the tasks clinicians actually bring to them.”
Overall, more than 950,000 clinicians—and more than 556,000 physicians—submitted a total of 271 million queries from January 2024 to June 2026. More than 19,000 (3.5%) of those clinicians were cardiologists or cardiology care professionals.
Nurse practitioners and physician assistants tied for submitting the most queries per active user month (44.5) followed by physicians (37.1). Physicians in the early part of their careers were much more likely to submit queries than veteran physicians.
Diving into the different healthcare specialties, oncology/hematology, internal medicine physicians were the most likely to submit queries. Family medicine, infectious disease, gastroenterology and neurology were the other specialties associated with submitting an above-average number of queries.
Cardiology specialists, meanwhile, were linked to submitting a below-average number of queries.
What, exactly, were these queries focused on? Overall, clinical decision-making was the most common reason users would access this AI-enabled resource. Treatment/management was the No. 2 reason.
When looking specifically at cardiology care professionals, the most common reasons for submitting queries were:
- Treatment and management questions (28.1%)
- Medication information questions (13.6%)
- Disease information questions (11.6%)
- Tests and imaging information questions (10.7%)
- Literature search questions (6.2%)
- Risks and prognosis questions (5.1%)
Another popular reason for using the AI software was to confirm the contents of practice guidelines. Among all specialties, cardiology was associated with the second highest percentage of queries specifically focused on practice guidelines (3.6%).
The study’s authors also noted that cardiology was a common topic for all OpenEvidence users. In fact, cardiology was a popular topic among users in internal medicine, clinical care, family medicine, pulmonology, emergency medicine, radiology and surgery.
“Clinicians predominantly sought information on treatment and medication decisions, and physicians frequently queried outside their own specialty, patterns that diverge from the diagnostic tasks emphasized in current evaluations of clinical AI,” the authors wrote. “These findings highlight the growing role of AI-enabled clinical information platforms in clinical practice and suggest that efforts to evaluate, teach, and integrate AI in clinical medicine should be informed by empirical studies of its use in actual practice.”
Click here to read the full study in JAMA.
Michael has more than 19 years of experience as a professional writer and editor. He has written at length about cardiology, radiology, artificial intelligence and other key healthcare topics.