Using a machine-learning flag to prompt pharmacogenetic testing in children.

Timely Ordering of Pharmacogenetic Testing in Pediatric Oncology

Not applicable Interventional The Hospital for Sick Children · NCT06902688

This project tests whether a computer model can help doctors offer genetic drug testing to hospitalized children (6 months–18 years) who are likely to be prescribed certain medications within the next three months.

Quick facts

PhaseNot applicable
Study typeInterventional
Enrollment275 (estimated)
Ages6 Months to 18 Years
SexAll
SponsorThe Hospital for Sick Children Academic / other
Locations1 site (Toronto, Ontario)
Trial IDNCT06902688 on ClinicalTrials.gov

What this trial studies

A machine-learning model runs each morning after admission to predict whether a patient will receive one of several pre-selected 'targeted' medications within the next three months. When the model flags a patient as high-risk, the research or pharmacogenomics team notifies the clinical team and offers pharmacogenetic testing to the patient and family. Testing and any genotype-guided medication changes follow an associated pharmacogenetic protocol and focus on systemically administered drugs. The trial enrolls non-ICU pediatric inpatients who have not previously had pharmacogenetic testing or received a targeted medication.

Who should consider this trial

Good fit: Hospitalized patients aged 6 months to 18 years at The Hospital for Sick Children who are not in the ICU, have not previously had pharmacogenetic testing or received a targeted medication, and are expected to remain hospitalized past the day of admission.

Not a fit: Patients already tested genetically, patients who have already received a targeted medication, current ICU patients, or those discharged the same day are excluded and unlikely to benefit from this intervention.

Why it matters

Potential benefit: If successful, this approach could increase the number of children with genetic test results available before starting certain drugs so clinicians can choose safer drugs or doses.

How similar studies have performed: Pharmacogenetic-guided prescribing has shown benefits in some settings, but using a machine-learning model to proactively identify pediatric inpatients for testing is relatively new and unproven.

Eligibility criteria

Show full inclusion / exclusion criteria
Inclusion Criteria:

* Inpatient at The Hospital for Sick Children
* Between 6 months to 18 years old

Exclusion Criteria:

* Prior pharmacogenetic testing and/or prior receipt of a targeted medication
* Current Intensive Care Unit (ICU) admission
* Expected hospital discharge is prior to midnight on the day of admission

Where this trial is running

Toronto, Ontario

Study contacts

How to participate

  1. Review the eligibility criteria above with your treating physician.
  2. Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
  3. Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.
Conditions Machine LearningPrediction ModelsPediatricsPrecision Medicineprecision medicinemachine learningpharmacogeneticsprediction models
Last reviewed 2026-06-09 by the Find a Trial editorial team. Information on this page is for educational purposes and is not medical advice. Always consult qualified healthcare professionals about clinical trial participation.