Machine Learning Model for Pediatric Cardiology

Overseen By Agata Wolochacz, BMSc

Age: < 65

Sex: Any

Trial Phase: Academic

Sponsor: The Hospital for Sick Children

Disqualifiers: Expected discharge same day

No Placebo Group All trial participants will receive the active study treatment (no placebo)

Compensation: Varies

Number of Visits: Unknown

What You Need to Know Before You Apply

What is the purpose of this trial?

This trial tests a machine-learning (ML) tool designed to predict serious heart problems in hospitalized children with heart issues. The goal is to determine if this ML-based intervention prompts doctors to consult with a specialized care team more frequently and quickly, potentially reducing ICU deaths and improving care planning. The trial may suit children currently inpatients at a cardiology department, particularly those at high risk of serious heart events who have not recently been seen by the care team. Results from this new method will be compared to previous practices before the tool's implementation. As an unphased trial, this study offers a unique opportunity to contribute to innovative research that could enhance future heart care for children.

Will I have to stop taking my current medications?

The trial information does not specify whether you need to stop taking your current medications.

What prior data suggests that this machine-learning model is safe for pediatric cardiology patients?

Research has shown that using machine learning (ML) in children's healthcare is generally safe. Various studies have tested these tools to predict serious health issues, such as heart problems, and found no direct harm to patients. For instance, one study developed a tool to assess the risk of critical events in children and reported no negative side effects from the ML model itself.

ML models analyze data to assist doctors in making better decisions. The ML tool does not directly interact with patients in a way that could cause harm; instead, it provides doctors with crucial information to improve patient care.

While further research is always beneficial to confirm safety, current evidence suggests these ML models are safe and well-tolerated for predicting serious heart events in children. ^{1 2 3 4 5}

Why are researchers excited about this trial?

Researchers are excited about this trial because it leverages a machine learning (ML) model to identify pediatric cardiac patients who are at the highest risk of serious outcomes. Unlike traditional methods that rely on fixed criteria and manual assessments, this ML-based intervention adapts and learns from vast amounts of data, potentially improving accuracy in risk prediction. By pinpointing patients who need immediate and intensive care, this approach could lead to more personalized and timely interventions, ultimately enhancing patient outcomes and reducing unnecessary treatments.

What evidence suggests that this ML model is effective for predicting serious cardiac events in pediatric patients?

Studies have shown that computer programs using machine learning can predict serious health problems in children with heart conditions. This trial will use an ML-based intervention to identify cardiac patients at the highest risk of serious cardiac outcomes. Research indicates that these programs help pinpoint patients at high risk for complications after heart surgeries, enabling doctors to act sooner to improve patient care. Early findings suggest that machine learning can assist doctors in deciding when a patient might need extra support, such as consultations for advanced heart therapies. These predictions could lead to better care plans and possibly reduce serious incidents in the intensive care unit (ICU). ^{2 6 7 8 9}

Who Is on the Research Team?

Lillian Sung, MD, PhD

Principal Investigator

The Hospital for Sick Children

Are You a Good Fit for This Trial?

This trial is for pediatric inpatients admitted to cardiology. It's designed to help doctors predict serious heart events and improve care with a machine-learning tool. The study excludes patients who don't meet the specific age and condition requirements.

Inclusion Criteria

I am a child admitted to the hospital for heart-related issues.

Timeline for a Trial Participant

Screening

Participants are screened for eligibility to participate in the trial

2-4 weeks

Pre-deployment Observation

Patient outcomes are observed for a 12-month period before the deployment of the ML model

12 months

Post-deployment Observation

Patient outcomes are observed for a 12-month period following the deployment of the ML model

12 months

Follow-up

Participants are monitored for safety and effectiveness after treatment

3 months

What Are the Treatments Tested in This Trial?

Interventions

• ML-based intervention

Trial Overview The trial tests a machine-learning model that predicts cardiac events in children hospitalized for heart conditions. It checks if this tool helps increase timely consultations, reduce ICU deaths, and improve care planning by comparing outcomes before and after its use.

How Is the Trial Designed?

Group I: ML model Experimental Treatment 1 Intervention

Cardiac patients identified by an ML model for having the highest risk of serious cardiac outcomes.

Who Is Running the Clinical Trial?

The Hospital for Sick Children

Lead Sponsor

Trials

724

Recruited

6,969,000+

Published Research Related to This Trial

Using electronic health records from 21,460 patients, a new personalized algorithm called ML4CAD was developed, which significantly improves health outcomes for managing Coronary Artery Disease (CAD) by predicting adverse events with an 81.5% accuracy.

The ML4CAD algorithm increases the expected time from diagnosis to adverse events by 24.11%, particularly benefiting male and Hispanic patients, and provides physicians with an interactive tool for personalized treatment recommendations.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Personalized treatment for coronary artery disease patients: a machine learning approach. Bertsimas, D., Orfanoudaki, A., Weiner, RB.[2021]

Citations

1. pmc.ncbi.nlm.nih.gov pmc.ncbi.nlm.nih.gov/articles/PMC11020051/

Machine learning prediction model of major adverse ... This study aimed to evaluate the performance of five machine learning (ML) algorithms for predicting four major APOs after pediatric congenital heart surgery

2. withpower.com withpower.com/trial/machine-learning-model-for-pediatric-cardiology-2b242

Machine Learning Model for Pediatric Cardiology The goal of this trial is to determine the effectiveness of a machine-learning (ML) model predicting a serious cardiac event within the next three months, ...

3. clinicaltrials.gov clinicaltrials.gov/study/NCT06886529

NCT06886529 | PACT Involvement in Cardiology Patients The goal of this trial is to determine the effectiveness of a machine-learning (ML) model predicting a serious cardiac event within the next three months, when ...

4. frontiersin.org frontiersin.org/journals/pediatrics/articles/10.3389/fped.2022.930913/full

Machine Learning-Based Systems for the Anticipation of ... We provide a brief overview of the potential of ML technologies to improve the identification of pediatric CHD patients at high-risk for clinical deterioration ...

5. csmedj.org csmedj.org/articles/enhancing-pediatric-congenital-heart-disease-outcomes-the-role-of-machine-learning-models-and-ai-driven-methodologies/csmedj.galenos.2025.2025-7-1

Enhancing Pediatric Congenital Heart Disease Outcomes Contemporary AI implementations have demonstrated potential in optimizing cardiac imaging interpretation, supporting clinical decision-making processes, and ...

6. pmc.ncbi.nlm.nih.gov pmc.ncbi.nlm.nih.gov/articles/PMC11818243/

Machine Learning in Pediatric Healthcare: Current Trends ... This narrative review explores the current trends, applications, challenges, and future directions of ML in pediatric healthcare.

7. jamanetwork.com jamanetwork.com/journals/jamanetworkopen/fullarticle/2834654

Machine Learning for Predicting Critical Events Among ... This cohort study describes the development and testing of the pediatric Critical Event Risk Evaluation and Scoring Tool, a machine learning ...

8. thelancet.com thelancet.com/journals/eclinm/article/PIIS2589-5370(25)00187-7/fulltext

Predicting Cardiovascular deterioration in a paediatric ... Machine learning aided decisions can improve the identification of patient deterioration. Important prior work has predicted outcomes in ...

9. jacc.org jacc.org/doi/10.1016/j.jacadv.2022.100153

Artificial Intelligence in Congenital Heart Disease ML interpretation and prediction using EKG input data are being used for the detection of CHD (Table 1). The described algorithms for pediatric arrhythmia ...