Developing and Evaluating a Machine-Learning Opioid Overdose Prediction & Risk-Stratification Tool in Primary Care

Launched by UNIVERSITY OF PITTSBURGH · Jan 30, 2025

Keywords

ClinConnect Summary

This clinical trial is testing a new tool that uses machine learning to help doctors predict which patients might be at risk for an opioid overdose. The tool will be integrated into the electronic health records at UF Health clinics in Gainesville, Florida. By comparing data before and after the tool is implemented, researchers aim to see if it helps increase the number of patients receiving naloxone (a medication that can reverse an overdose) and reduce actual overdose incidents. They will also gather feedback from doctors to understand how easy and helpful the tool is to use.

To be part of this study, doctors working in any of the 13 participating clinics can participate, while patients must be at least 18 years old, have received an opioid prescription in the past year, and be identified as at risk for overdose by the tool. However, patients with a cancer diagnosis or those in hospice care cannot participate. If eligible, participants can expect to contribute to an important effort aimed at improving patient safety and care regarding opioid use.

Gender

ALL

Eligibility criteria

• Inclusion Criteria:
• • For PCP level outcomes assessment
• • PCPs
• • practicing in any of the 13 participating clinics (10 UF Health Family Medicine clinics and 3 UF Health Internal Medicine) in Gainesville, Florida.
• For patient level outcomes assessment:
• • Inclusion criteria: Patients who seen in any of the 9 participating UF Health clinics who
• • are aged ≥18 years
• • received any opioid prescription in the past year prior to their clinic visit.
• • are identified as being at elevated risk for overdose by the ML algorithm. Exclusion Criteria: Patients who
• • had malignant cancer diagnosis or hospice care prior to study enrollment