Mayo AI-ECG flags low EF; 41-year-old recovers to 55%

AI system

System: Mayo Clinic AI-ECG low-ejection-fraction algorithm (AI-ECG dashboard)
Model: Not assessed
Release: Not assessed
Application developer: Mayo Clinic (licensed to Eko and Anumana)
Role: Not assessed
Configuration: Not assessed
Inputs and outputs: Not assessed
Autonomy: Not assessed
Workflow: Routine 12-lead ECGs scored by the low-EF network. A dashboard that clinicians consult during evaluation. Confirmatory echocardiography and guideline-directed therapy.
Human oversight: Not assessed
Relation to AI: The AI-ECG probabilities (97.88% and 98.67%) prompted the echocardiogram and treatment, according to the authors. The source is the developer's own case report. The authors disclose that Mayo licensed the technology and that inventors may receive financial benefit. No independent account of the case exists.
AI contribution: The AI-ECG probabilities (97.88% and 98.67%) prompted the echocardiogram and treatment, according to the authors. The source is the developer's own case report. The authors disclose that Mayo licensed the technology and that inventors may receive financial benefit. No independent account of the case exists.

Studies: Not assessed
Study design: Not assessed
Measurement: Not assessed
Setting and sample: Not assessed
Measures: at four months his ejection fraction had improved to 55%
Comparison: the conventional reading of the same ECGs, which showed only nonspecific abnormalities
Results: Reference: The ECG showed sinus tachycardia, premature ventricular complexes with rightward deviation, and a nonspecific T-wave abnormality (echocardiography then showed a left ventricular ejection fraction of 41%). Result: high probabilities of reduced ejection fraction (97.88% and 98.67%); at a 4-month follow-up visit, the patient had improved left ventricular ejection fraction to 55%.
Additional value from AI: Not assessed
Limitations: Not assessed
Denominators: Not assessed
Materials for replication: Not assessed

Participants: Developer: Mayo Clinic (licensed to Eko and Anumana). Operator: Mayo Clinic, Rochester.
Jurisdictions: Benefit: Rochester, Minnesota, USA. Developer: United States. Operator: United States.
Ownership and control: Not assessed
Dependencies: Not assessed
Cross-border connections: Not assessed
Geopolitical implications: Not assessed

Conditions for replication: The algorithm is deployed in the clinical workflow. Clinicians act on a high probability score.
Replication attempts: 3 follow-up entries. Benefit recurred: 2. Outcome unresolved: 1.
Later findings: 3 April 2024. The Mayo-developed low-ejection-fraction algorithm, licensed to Eko Health and trained on Mayo's ECG dataset, received FDA clearance in early April 2024 for use with Eko's digital stethoscopes, and Mayo authors continued to publish AI-ECG case reports through 2025.
Availability: Not assessed
Institutional decision: Not assessed
Grounds: Not assessed
Action and result: Not assessed
Success criterion: Not assessed

Assessed benefits: People. Organizations. Society.
Depth: People: 3. Organizations: Not assessed. Society: Not assessed.
Reasons: People: New HFrEF identified and treated; ejection fraction 55% at four months. Organizations: No organizational outcome reported for this case. Society: Single case.
Observed or intended: Not assessed
Rubric: Not assessed
Assessor and date: Not assessed
Alternative assessments: Not assessed
Fill: Independently reported

Kind: Not assessed
Related entries: Not assessed
Field: Health; cardiology. Adults presenting with unexplained symptoms and an ECG.
Purpose: Screen 12-lead ECGs for a low left-ventricular ejection fraction with a convolutional neural network
Dates: Date basis unassessed: 2021 (precision unassessed). Updated: 21 October 2026.
Stage: Not assessed
Version: SHA-256: 2c17991dfd34…