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.

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.

Inclusion Criteria:

• Pediatric inpatients admitted to cardiology

Exclusion Criteria:

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