Data AnalysisVerified

Reviewed and published by trentmaziarz, June 30, 2026. Discovered and drafted by our automated research pipeline.

Boston Children's Hospital, in collaboration with MITRE, deployed machine learning algorithms in its pediatric cardiac catheterization lab that predict the risk of patient harm before procedures, allowing clinical staff to assess risk levels and make pre-procedure decisions. The framework, called GRACE (Generating Risk Reduction Analytics for Complex Cardiac Care Environments), was used the day before catheter procedures.

Details

The GRACE/GR2AC3E initiative applied supervised machine learning techniques to electronic health record data from patients undergoing congenital cardiac catheterization at Boston Children's Hospital, using data from 2019 to 2020. The models analyzed patient-level, procedural-level, and system-level characteristics to predict clinically meaningful adverse events. A published peer-reviewed study (JSCAI, December 2024) described the methodology and performance of LASSO and Random Forest models. The framework enables staff to classify patients as high-, medium-, or low-risk the day before a procedure and plan accordingly.

Products affected

GRACE / GR2AC3E risk prediction framework

Sources & Evidence

Academic Paper

Generating Risk Reduction Analytics in Complex Cardiac Care Environments (GR2AC3E): Risk Prediction in Congenital Catheterization

Journal of the Society for Cardiovascular Angiography & Interventions·Dec 2024

https://www.jscai.org/article/S2772-9303(24)02100-8/fulltext

News Article

Delivering GRACE: AI and Analytics to Reduce Risk in Children's Healthcare

MITRE·May 2023

https://www.mitre.org/news-insights/impact-story/delivering-grace-ai-and-analytics-reduce-risk-childrens-healthcare

Cite this record

Trace Foundation. (2026). Boston Children's Hospital: Boston Children's Hospital, in collaboration with MITRE, deployed machine learning algorithms in its pediatric cardiac catheterization lab that predict the risk of patient harm before procedures, allowing clinical staff to assess risk levels and make pre-procedure decisions. The framework, called GRACE (Generating Risk Reduction Analytics for Complex Cardiac Care Environments), was used the day before catheter procedures (data as of 2026-06-30) [Data set record]. AI Trace. https://www.aitrace.org/r/practice/82e81767-0203-4edd-bc6f-6f6a06054d61. Accessed October 5, 2026.

Stable link: https://www.aitrace.org/r/practice/82e81767-0203-4edd-bc6f-6f6a06054d61
Data as of: June 30, 2026
Last verified: Not recorded

How to cite AI Trace

Other practices by Boston Children's Hospital

OtherBoston Children's Hospital integrated OpenAI's ChatGPT for Healthcare, an enterprise-grade, HIPAA-compliant AI workspace, rolling it out to clinical, research, and administrative staff as one of the platform's earliest adopters at launch in January 2026. The platform is powered by GPT-5 models evaluated through physician-led testing.Data AnalysisBoston Children's Hospital deployed VirtualHip, a fully automated AI tool integrated across its Adolescent and Young Adult Hip Preservation Program clinic, which converts routine 2D medical images into detailed 3D hip models and provides clinicians with diagnostic and treatment guidance within about one hour. It is described as the first fully automated AI tool of its kind deployed across a US hip clinic.ProductivityBoston Children's Hospital deployed an AI system that analyzes clinical notes and estimates how sick each patient is to improve how operating room time is allocated. This allows surgical schedules to be planned further in advance, increasing the number of patients who can receive timely care.

Have evidence about Boston Children's Hospital's AI practices? Submit a report.

Report a Sighting →