
An AI model developed by Johns Hopkins significantly outperforms current risk scores in predicting post-surgical complications using routine ECG data.
Key Details
- 1Johns Hopkins researchers developed AI models to analyze pre-surgical electrocardiograms (ECG).
- 2Models were trained using data from 37,000 surgery patients at Beth Israel Deaconess Medical Center.
- 3The best-performing fusion model predicted serious post-surgical complications with 85% accuracy.
- 4Current clinical risk scoring methods are only about 60% accurate.
- 5The work was federally funded and results were published in the British Journal of Anaesthesia.
- 6The AI can identify previously undetectable signals in ECGs relevant to surgical risk.
Why It Matters

Source
EurekAlert
Related News

AI Accelerates Solid Tumor Drug Development and Personalized Oncology
AI is expediting the timeline and personalization of solid tumor drug development using multi-omics, imaging, and advanced computational models.

MAGIC AI System Enables High-Throughput Cancer Cell Imaging and Analysis
Researchers developed MAGIC, an AI-based system integrating automated microscopy and genomics to study chromosomal abnormalities linked to cancer.

Biodegradable Wearable Sensor with AI Enables Interference-Free Respiration Monitoring
Researchers developed a biodegradable, interference-resistant smart mask sensor with AI-driven respiratory classification capability.