Artificial Intelligence at Mayo Clinic

2026-07-27 · Source: Emerj Artificial Intelligence Research · Field: Health & Wellbeing — Clinical Care & Medical Practice, Medical Devices & Health Technology, Healthcare Systems & Policy · Depth: Intermediate, medium

Summary

Mayo Clinic, a leading nonprofit academic medical center, is extensively integrating artificial intelligence into its operations, with over 200 AI projects underway. In 2025, the organization, which employed nearly 85,000 people and posted \$473 million in operating income, integrated 22 AI-enabled Mayo Clinic Platform solutions into clinical practice and closed nearly 200 new AI, biopharma, and diagnostics agreements. The Mayo Clinic Platform, launched in 2019, has amassed a research data infrastructure of over 15 million patient records. Two prominent AI applications include AI-enabled ECG screening for early disease detection, which has increased diagnoses of low ejection fraction by 32% in the EAGLE trial and is FDA-cleared, and AI-powered chart review using "Record Time" to reduce physician prep time by 5-30 minutes per visit.

Key takeaway

For healthcare executives evaluating AI investments, prioritize solutions that integrate seamlessly into existing clinical workflows to maximize adoption and impact. Your focus should be on leveraging internal historical data for early disease detection, as demonstrated by Mayo's 32% increase in diagnoses for low ejection fraction. Additionally, consider AI tools like "Record Time" to automate administrative tasks, freeing up physician time for direct patient care and improving operational efficiency.

Key insights

Large-scale, data-driven AI integration into existing clinical workflows significantly enhances early disease detection and administrative efficiency.

Principles

• AI adoption thrives when integrated into existing workflows.
• Deep historical data is key for high-quality AI models.
• Focus AI on well-defined administrative bottlenecks.

Method

Mayo Clinic trained a neural network on 625,000 paired ECG and echocardiogram records to detect electrical patterns linked to weakened heart pumps, then validated it in a prospective trial.

In practice

• Use AI to screen routine ECGs for asymptomatic heart conditions.
• Implement AI for chronological organization and summarization of external patient records.

Topics

• Healthcare AI
• Clinical Decision Support
• ECG Analysis
• Electronic Health Records
• Early Disease Detection
• Medical Data Platforms

Best for: Executive, AI Product Manager, Director of AI/ML, Research Scientist, Consultant

Related on AIssential

• 😺 Mayo's AI spotted cancer 3 years before doctors did — AI is demonstrating superior diagnostic and triage capabilities in medicine, even with incomplete information.
• AI could ease the burden of hospital discharge summaries - Stanford Medicine — AI tools can reduce physician burnout in clinical documentation, even without significant time savings.
• From Data Integration to Decision Intelligence: The Next Transformation in Clinical and Commercial… — AI-powered decision intelligence transforms fragmented healthcare data into predictive insights for operational workflows.
• AI stethoscope trial highlights the perils of implementation gaps — AI diagnostic tools require careful integration into clinical workflows to achieve their full potential.
• Validating a Deep Learning Algorithm to Identify Patients with Glaucoma using Systemic Electronic Health Records — An EHR-only deep learning model can effectively pre-screen for glaucoma without specialized imaging.
• Development of an automated, reliable, and clinically meaningful artificial intelligence (AI) tool for diagnosing cardiac disease from conventional cardiovascular magnetic resonance (CMR) images — Automated AI, leveraging LLMs and vision models, significantly enhances cardiac disease diagnosis from CMR images.

See Counsel's argued verdicts on the open AI decisions leaders are weighing →

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Emerj Artificial Intelligence Research.