PACT Involvement in Cardiology Patients

Early PACT Involvement in Cardiology Patients Using Machine Learning

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 compared pre- versus post-deployment, in pediatric cardiac inpatients. The main questions it aims to answer are whether deployment of the ML model:

1. Increases PACT consultation within the next three months among admissions without PACT involvement in the previous 100 days
2. Increases PACT consultation or visit within the next three months among those who experience a serious cardiac event during this period
3. Decreases time to PACT consultation or visit among those seen by PACT during this period
4. Decreases the incidence of death in the intensive care unit (ICU)
5. Increases documentation of goals of care

High-risk cardiology patients will be identified by an ML model each morning. If the patient has been seen by the PACT team within the past year, the update will go to the PACT team members. If the patient hasn't been seen by the PACT team, the email will be sent to the cardiology physician in charge of the patient. This physician will decide whether a PACT consultation is necessary based on their clinical judgment. If so, a referral will be made using the usual process. Outcomes of the identified patients will be compared pre- and post-deployment.

Study Overview

• Status: Recruiting
• Conditions: Machine Learning; Pediatric Cardiology; Cardiovascular Outcome; Pediatric Palliative Care
• Intervention / Treatment: Other: ML-based intervention

Detailed Description

At The Hospital for Sick Children (SickKids), the collaboration between cardiology and palliative care is much stronger than other centers, with routine involvement in patients being considered for heart transplant. Despite this, earlier involvement of palliative care would be advantageous. Our cardiology co-investigators identified patients who would benefit from earlier palliative care team involvement as those receiving advanced heart therapies (defined as ventricular assist device (VAD) and being wait listed for heart transplant) and those who die. The study team created a clinical deployment environment named SickKids Enterprise-wide Data in Azure Repository (SEDAR). [1] SEDAR is a modular and robust approach to deliver foundational data that is re-usable across multiple ML projects. It offers validated EHR data in a standardized and curated schema. ML is a promising approach to identify cardiac patients at the highest risk of these serious cardiac outcomes who may benefit from earlier palliative care team involvement. To assess the effectiveness of this approach, patient outcomes will be compared pre- and post-deployment of the ML model. The pre-period will include patients admitted for a 12-month period before deployment (starting 15 months prior to deployment). The post-period will include patients admitted for a 12-month period following deployment starting 3 months post-deployment start.

• Study Type: Interventional
• Enrollment (Estimated): 1000
• Phase: Not Applicable

Contacts and Locations

• Study Contact: Name: Lillian Sung, MD, PhD; Phone Number: 4168135287; Email: lillian.sung@sickkids.ca
• Study Contact Backup: Name: Agata Wolochacz, BMSc; Phone Number: 309976 4168137654; Email: agata.wolochacz@sickkids.ca

Study Locations

• Canada
  • Toronto, Canada, M5G1X8
    • Recruiting
    • The Hospital for Sick Children
    • Contact: Lillian Sung, MD, PhD; Phone Number: 416-813-5287; Email: lillian.sung@sickkids.ca

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Child; Adult
• Accepts Healthy Volunteers: No

Description

Inclusion Criteria:

• Pediatric inpatients admitted to cardiology

Exclusion Criteria:

• Expected to be discharged prior to midnight on the day of admission

Study Plan

How is the study designed?

Design Details

• Primary Purpose: Supportive Care
• Allocation: N/A
• Interventional Model: Single Group Assignment
• Masking: None (Open Label)

Number of Arms

1

Arms and Interventions

Participant Group / Arm	Intervention / Treatment
Experimental: ML model; Cardiac patients identified by an ML model for having the highest risk of serious cardiac outcomes.	Other: ML-based intervention; ML model predicting a serious cardiac event in cardiac patients, defined as VAD procedure, being wait listed for heart transplant or death within the next three months.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Proportion of admissions with PACT consultation within the next three months among admissions without PACT involvement in the previous 100 days	The primary outcome will be the proportion of admissions with PACT consultation within the next three months among admissions without PACT involvement in the previous 100 days. This variable will be measured using SEDAR.	Time of enrolment to 3 months

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
PACT consultation or visit within the next three months among those with a positive model prediction	PACT consultation or visit within the next three months among those with a positive model prediction will be measured using SEDAR.	Time of enrolment to 3 months
Time to PACT consultation or visit among those seen by PACT	Time to PACT consultation or visit among those seen by PACT will be measured using SEDAR.	Time of enrolment to 3 months
Death in the ICU	Death in the ICU will be measured using SEDAR.	Time of enrolment to 3 months
Documentation of goals of care	Goals of care will be abstracted via chart review.	Time of enrolment to 3 months

Collaborators and Investigators

• Sponsor: The Hospital for Sick Children
• Investigators: Principal Investigator: Lillian Sung, MD, PhD, The Hospital for Sick Children

Publications and helpful links

General Publications

• Patel P, Robinson PD, Phillips R, Baggott C, Devine K, Gibson P, Guilcher GMT, Holdsworth MT, Neumann E, Orsey AD, Spinelli D, Thackray J, van de Wetering M, Cabral S, Sung L, Dupuis LL. Treatment of breakthrough and prevention of refractory chemotherapy-induced nausea and vomiting in pediatric cancer patients: Clinical practice guideline update. Pediatr Blood Cancer. 2023 Aug;70(8):e30395. doi: 10.1002/pbc.30395. Epub 2023 May 13.

Study record dates

Study Major Dates

• Study Start (Actual): October 16, 2025
• Primary Completion (Estimated): June 28, 2027
• Study Completion (Estimated): October 16, 2027

Study Registration Dates

• First Submitted: March 13, 2025
• First Submitted That Met QC Criteria: March 13, 2025
• First Posted (Actual): March 20, 2025

Study Record Updates

• Last Update Posted (Actual): April 23, 2026
• Last Update Submitted That Met QC Criteria: April 22, 2026
• Last Verified: April 1, 2026

More Information

Terms related to this study

• Keywords: machine learning; quality of life; pediatric; cardiovascular outcomes; prediction models
• Other Study ID Numbers: 3433

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No
• product manufactured in and exported from the U.S.: No