1332 Participants Needed

ML-Based Intervention for Vomiting in Pediatric Cancer

LS
AW
Overseen ByAgata Wolochacz, BMSc
Age: Any Age
Sex: Any
Trial Phase: Academic
Sponsor: The Hospital for Sick Children
No Placebo GroupAll trial participants will receive the active study treatment (no placebo)

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.12345

Why 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?

SA

Santiago Arciniegas, MSc

Principal Investigator

The Hospital for Sick Children

LG

Lawrence Guo, PhD

Principal Investigator

The Hospital for Sick Children

LS

Lillian Sung, MD, PhD

Principal Investigator

The Hospital for Sick Children

LD

Lee Dupuis, RPh, PhD

Principal Investigator

The Hospital for Sick Children

PP

Priya Patel, PharmD

Principal Investigator

The Hospital for Sick Children

AY

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

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 for a Trial Participant

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

What Are the Treatments Tested in This Trial?

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.
How Is the Trial Designed?
1Treatment groups
Experimental Treatment
Group I: ML modelExperimental Treatment1 Intervention

Find a Clinic Near You

Who Is Running the Clinical Trial?

The Hospital for Sick Children

Lead Sponsor

Trials
724
Recruited
6,969,000+

Citations

1.pubmed.ncbi.nlm.nih.govpubmed.ncbi.nlm.nih.gov/41174551/
Development and prospective evaluation of a machine ...We found that data in the EHR could be used to develop a retrospective ML model to predict vomiting among pediatric oncology and HCT ...
NCT06886451 | Vomiting Prevention in Children With CancerThe 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 ...
Development and prospective evaluation of a machine ...We found that data in the EHR could be used to develop a retrospective ML model to predict vomiting among pediatric oncology and HCT inpatients.
AI Model Predicts Vomiting in Pediatric CancerThe model demonstrated robust predictive power, with an area-under-the-receiver-operating-characteristic curve (AUROC) exceeding 0.70 in both ...
A deep learning-based system for automatic detection of ...The Automatic Emesis Detection (AED) tool for the quantification of emesis in S. murinus, achieving an overall accuracy of 98.92%.
Development and prospective evaluation of a machine ...We found that data in the EHR could be used to develop a retrospective ML model to predict vomiting among pediatric oncology and HCT inpatients.
Development and prospective evaluation of a machine ...Conclusions We found that data in the EHR could be used to develop a retrospective ML model to predict vomiting among pediatric oncology and HCT ...
Unbiased ResultsWe believe in providing patients with all the options.
Your Data Stays Your DataWe only share your information with the clinical trials you're trying to access.
Verified Trials OnlyAll of our trials are run by licensed doctors, researchers, and healthcare companies.
Terms of Service·Privacy Policy·Cookies·Security