AI Supports Continuous Care in Congenital Heart Disease
- Main idea: Researchers are developing a machine learning model to predict which patients with congenital heart disease are likely to have gaps in their care.This aims to improve...
- * predictive Factors: The model identifies factors like socioeconomic status, insurance status, and severity of disease as important predictors of care gaps.
- * The research was presented at the American Heart Association Scientific Sessions (November 7-10,2025,new Orleans).
Here’s a breakdown of the key details from the provided text:
Main idea: Researchers are developing a machine learning model to predict which patients with congenital heart disease are likely to have gaps in their care.This aims to improve long-term outcomes by allowing for targeted interventions.
Key Findings & Details:
* predictive Factors: The model identifies factors like socioeconomic status, insurance status, and severity of disease as important predictors of care gaps. Those with more severe disease or who require frequent follow-up are more likely to remain in consistent care, making those factors important to the model.
* Current Status: the model is still being refined and needs further training.
* Next Steps:
* Improve data collection within electronic medical records (EMRs) regarding social determinants of health.
* Test the model in a controlled EMR setting to predict gaps and track patient outcomes.
* Collaboration: The researchers are working with a social determinants of health team at Nemours.
Source:
* The research was presented at the American Heart Association Scientific Sessions (November 7-10,2025,new Orleans).
* Researcher: Abbas H. Zaidi, MD (cardiology@healio.com)
* Publication: Cardiology Today (Healio)
Additional feature:
* The article promotes ”healio AI,” a tool that allows users to ask clinical questions and access a knowledge base including PubMed, trials, guidelines, and Healio’s news coverage.