Researchers have developed AI models that analyze EKG and EHR data to predict risk of sudden cardiac arrest in the general population.
Key Details
- 1AI models were trained and validated on a total patient base of approximately 1.7 million individuals.
- 2Models included EKG-only, EHR-only, and combined EKG-EHR approaches; all showed significant predictive ability.
- 3The combined model accurately predicted 153 out of 228 high-risk cases in a real-world cohort (2021-2023).
- 4AI analysis of EKG alone provided nearly equivalent predictive power to more complex models.
- 5The models improved individual risk profiling from 1 in 1,000 to 1 in 100 within the tested population.
- 6Study limitations include data from a single health system and potential demographic or selection biases.
Why It Matters
This research demonstrates the real-world feasibility of AI-powered risk stratification for sudden cardiac arrest using broadly available clinical data. Such tools could help target preventive interventions, potentially reducing mortality from an often unpredictable emergency.
Source
EurekAlert
Related News
•EurekAlert
AI-Powered OCT Enables Rapid 'Optical Biopsy' for Early Endometrial Cancer Detection
A team at Washington University has developed a catheter-based 3D OCT system with AI to quickly and noninvasively detect early endometrial cancers.
•EurekAlert
AI Clinical Reasoning in Diagnostics and Digital Fatigue in Healthcare
Recent JMIR features explore large language models in clinical diagnostics and digital fatigue among healthcare professionals.
•EurekAlert
KAIST, MIT, Microsoft Develop Efficient AI Image Upsampling for Robotics
KAIST, MIT, and Microsoft have created 'Upsample Anything,' a training-free AI method to restore high-resolution visual data from compressed images with up to 16x improved GPU memory efficiency.