Exploring Use of AI Tools for Cardiovascular Risk Prediction in Migraine: Chia-Chun Chiang, MD

WATCH TIME: 5 minutes

“We found that higher outputs from the atrial fibrillation prediction model and larger delta age values were predictive of adverse cardiovascular outcomes in patients with migraine. That suggests AI-ECG can be a very quick and effective tool.”

Migraine, particularly migraine with aura, may be associated with an increased risk of cardiovascular events. Findings from a new retrospective cohort study showed that a higher artificial intelligence-electrocardiogram (AI-ECG) atrial fibrillation (AF) prediction model output and delta age were predictive of adverse vascular outcomes in patients with migraine. Results also revealed that a higher AF prediction model output as predictive of future development of AF. Overall, this data suggests that AI-ECG models could be used to identify patients with migraine who may be at risk for future adverse vascular events.¹

Presented at the recently concluded 2025 American Headache Society (AHS) Annual Meeting, held June 19-22 in Minneapolis, the study included 29,928 adult patients with migraine who had at least 1 digital, standard 12-lead ECG between 2000 and 2020. Conducted by senior author Chia-Chun Chiang, MD, and colleagues, the primary outcome was a composite outcome of adverse vascular events that included acute myocardial infarction, acute ischemic stroke, venous thromboembolism and death. During the study period, researchers reported that 4662 patients with migraine had adverse vascular events (15.6%), and 1384 participants developed new-onset AF (4.6%).

At the 2025 AHS Annual Meeting, Chiang, associate professor of neurology at Mayo Clinic Rochester, sat down with NeurologyLive^® to highlight the findings from the presented study on applying AI tools to assess cardiovascular risk in patients with migraine. She talked about how the study examined a large patient cohort and integrated various clinical and diagnostic factors, including cardiovascular markers and migraine characteristics, to better understand potential risk patterns. Chiang noted that this line of research may help inform future efforts to refine risk prediction models and support earlier intervention strategies in clinical care for migraine.

Click here for more coverage of AHS 2025.

REFERENCES
1. Chiang C. Artificial Intelligence ECG-Based Screening and Prediction Tool to Identify Migraine Patients at Risk for Stroke and CVD (CL). Presented at: 2025 AHS Annual Meeting; June 19-22; Minneapolis, MN. Plenary 2 Session: STROKE