ML-Based Intervention for Vomiting in Pediatric Cancer
What You Need to Know Before You Apply
What is the purpose of this trial?
This trial tests a machine learning (ML) tool to predict and help manage vomiting in children with cancer. The researchers aim to determine if knowing the risk of vomiting over the next four days can reduce its frequency and ensure appropriate care. The trial also examines how the prediction affects the use and cost of anti-vomiting medications. It includes children staying in the oncology unit at SickKids Hospital. Children released from the hospital before the ML prediction will not be included. As an unphased trial, this study provides a unique opportunity for patients to contribute to innovative research that could enhance care for children with cancer.
Will I have to stop taking my current medications?
The trial information does not specify whether you need to stop taking your current medications. It focuses on predicting and managing vomiting risk, so it's best to discuss your current medications with the trial team.
What prior data suggests that this ML-based intervention is safe for pediatric cancer patients?
Research has shown that a machine learning (ML) model has been used to predict vomiting in children with cancer by analyzing past data. Researchers examined old medical records to assess the model's ability to predict which children might vomit. Studies found that the model can identify patterns in these records to determine children at risk of vomiting within the first four days of their hospital stay.
Since this ML model only analyzes existing patient data, it poses no safety concerns like those associated with new drugs or procedures. The model's predictions assist doctors and pharmacists in deciding how to prevent vomiting. No reports indicate that the model causes harm, as it doesn't involve any physical treatment.
Overall, evidence suggests that the ML model is safe to use because it doesn't directly affect patients' bodies.12345Why are researchers excited about this trial?
Unlike traditional treatments for vomiting in pediatric cancer, which often rely on medications like antiemetics to control symptoms after they occur, this new approach uses a machine learning (ML) model to predict the risk of vomiting within the next 96 hours. This predictive capability allows for a proactive rather than reactive approach, potentially enhancing quality of life by preventing episodes before they start. Researchers are excited because this model could personalize and improve care, reducing the need for medication and its associated side effects.
What evidence suggests that this ML-based intervention is effective for reducing vomiting in pediatric cancer patients?
Research has shown that a machine learning (ML) model, used by participants in this trial, can predict the risk of vomiting in children with cancer. This model analyzes data from electronic health records (EHR) to make accurate predictions. It has demonstrated strong ability in identifying at-risk patients, achieving a performance score of over 0.70 out of 1. This tool aims to assist doctors in taking preventive steps, potentially reducing vomiting and improving patient care. Although still in early use, the model's promising results suggest it could be valuable in managing vomiting in young cancer patients.23467
Who Is on the Research Team?
Santiago Arciniegas, MSc
Principal Investigator
The Hospital for Sick Children
Lawrence Guo, PhD
Principal Investigator
The Hospital for Sick Children
Lillian Sung, MD, PhD
Principal Investigator
The Hospital for Sick Children
Lee Dupuis, RPh, PhD
Principal Investigator
The Hospital for Sick Children
Priya Patel, PharmD
Principal Investigator
The Hospital for Sick Children
Adam Yan, MD, MBI
Principal Investigator
The Hospital for Sick Children
Are You a Good Fit for This Trial?
This trial is for pediatric cancer patients admitted to the oncology service at SickKids. It's designed for those who will stay in the hospital long enough to have their vomiting risk predicted after admission, excluding those discharged before prediction time.Inclusion Criteria
Exclusion Criteria
Timeline for a Trial Participant
Screening
Participants are screened for eligibility to participate in the trial
Model Deployment and Intervention
Pharmacists use the ML model to predict vomiting risk and implement care pathway-consistent interventions
Follow-up
Participants are monitored for safety and effectiveness after intervention
Outcome Evaluation
Outcomes are evaluated for a one-year period pre- and post-deployment
What Are the Treatments Tested in This Trial?
Interventions
- ML-based intervention
Find a Clinic Near You
Who Is Running the Clinical Trial?
The Hospital for Sick Children
Lead Sponsor