ML-Based Intervention for Vomiting in Pediatric Cancer

Overseen By Agata Wolochacz, BMSc

Age: Any Age

Sex: Any

Trial Phase: Academic

Sponsor: The Hospital for Sick Children

Disqualifiers: Discharged before prediction time

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

Compensation: Varies

Number of Visits: Unknown

1332 Participants Needed

Trial Summary

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 data supports the effectiveness of the ML-based intervention treatment for vomiting in pediatric cancer?

The research highlights that nausea and vomiting are significant issues for children undergoing cancer treatment, and optimizing treatments can improve their quality of life. While the studies focus on antiemetic (anti-vomiting) medications, they suggest that better understanding and management of these symptoms are crucial, which could indirectly support the potential of ML-based interventions to enhance treatment strategies. ^{1 2 3 4 5}

How does the ML-based intervention for vomiting in pediatric cancer differ from other treatments?

The ML-based intervention is unique because it uses machine learning (a type of artificial intelligence) to predict and manage vomiting in children with cancer, potentially offering a more personalized approach compared to traditional treatments that do not use predictive technology. ^{3 6 7 8 9}

What is the purpose of this trial?

The goal of this single arm trial is to learn if a machine learning (ML) model predicting the risk of vomiting within the next 96 hours will impact vomiting outcomes in inpatient cancer pediatric patients. The main questions it aims to answer are whether an ML model predicting the risk of vomiting within the next 96 hours will: Primary 1. Reduce the proportion with any vomiting within the 96-hour window Secondary 1. Reduce the number of vomiting episodes 2. Increase the proportion receiving care pathway-consistent care 3. Impact on number of administrations and costs of antiemetic medications Newly admitted participants will have a ML model predict the risk of vomiting within the next 96 hours according to their medical admission information. The prediction will be made at 8:30 AM following admission. Pharmacists will be charged with bringing information about patients' vomiting risk to the attention of the medical team and implementing interventions.

Research Team

Lillian Sung, MD, PhD

Principal Investigator

The Hospital for Sick Children

Lawrence Guo, 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

Santiago Arciniegas, MSc

Principal Investigator

The Hospital for Sick Children

Eligibility Criteria

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

I am a child receiving care at SickKids' oncology department.

Exclusion Criteria

I am a pediatric patient at SickKids discharged before the prediction time.

Timeline

Screening

Participants are screened for eligibility to participate in the trial

1-2 weeks

Model Deployment and Intervention

Pharmacists use the ML model to predict vomiting risk and implement care pathway-consistent interventions

96 hours

Daily monitoring

Follow-up

Participants are monitored for safety and effectiveness after intervention

4 weeks

Outcome Evaluation

Outcomes are evaluated for a one-year period pre- and post-deployment

1 year

Treatment Details

Interventions

• ML-based intervention

Trial Overview The study tests if a machine learning model can predict and reduce vomiting in child cancer patients by informing medical teams about vomiting risks within a 96-hour window post-admission, potentially improving care and reducing antiemetic medication costs.

Participant Groups

Group I: ML model Experimental Treatment 1 Intervention

ML model to predict the risk of vomiting within the next 96 hours.

Who Is Running the Clinical Trial?

The Hospital for Sick Children

Lead Sponsor

Trials

724

Recruited

6,969,000+

References

1. England pubmed.ncbi.nlm.nih.gov

Antiemetic medication for prevention and treatment of chemotherapy induced nausea and vomiting in childhood. [2018]

2. England pubmed.ncbi.nlm.nih.gov

Antiemetic medication for prevention and treatment of chemotherapy-induced nausea and vomiting in childhood. [2023]

3. United States pubmed.ncbi.nlm.nih.gov

Predictors of antiemetic alteration in pediatric acute myeloid leukemia. [2021]

4. United States pubmed.ncbi.nlm.nih.gov

Determining the factors affecting chemotherapy-induced nausea and vomiting in children with cancer. [2023]

5. Germany pubmed.ncbi.nlm.nih.gov

Gaps exist between patients' experience and clinicians' awareness of symptoms after chemotherapy: CINV and accompanying symptoms. [2018]

6. China pubmed.ncbi.nlm.nih.gov

[Establishment of naive Bayes classifier-based risk prediction model for chemotherapyinduced nausea and vomiting]. [2021]

7. United States pubmed.ncbi.nlm.nih.gov

Chemotherapy induced nausea and emesis in pediatric cancer patients: external validity of child and parent emesis ratings. [2013]

8. France pubmed.ncbi.nlm.nih.gov

Postoperative vomiting in pediatric oncologic patients: prediction by a fuzzy logic model. [2012]

9. United States pubmed.ncbi.nlm.nih.gov

Measuring nausea and vomiting in adolescents: a feasibility study. [2022]