Machine-learning tool to predict opioid overdose risk in primary care
Developing and Evaluating a Machine-Learning Opioid Prediction & Risk-Stratification E-Platform (DEMONSTRATE)
This study is testing a new computer tool that helps doctors in Gainesville, Florida, predict which patients might be at risk for an opioid overdose to improve safety and care.
Quick facts
| Phase | Not applicable |
|---|---|
| Study type | Interventional |
| Enrollment | 2000 (estimated) |
| Ages | 18 Years and up |
| Sex | All |
| Sponsor | University of Pittsburgh Academic / other |
| Locations | 1 site (Gainesville, Florida) |
| Trial ID | NCT06810076 on ClinicalTrials.gov |
What this trial studies
This clinical trial evaluates the implementation of a machine-learning clinical decision support tool designed to predict the risk of opioid overdose within electronic health records at UF Health clinics in Gainesville, Florida. The study employs a pre- and post-implementation design to compare outcomes such as naloxone prescribing rates and opioid overdose occurrences. Additionally, it assesses the usability and acceptability of the tool through qualitative interviews with primary care clinicians. The integration process involved collaboration with IT services to ensure secure access to patient health information and a user-centered design approach for the tool's interface.
Who should consider this trial
Good fit: Ideal candidates include patients aged 18 and older who have received an opioid prescription in the past year and are identified as at elevated risk for overdose by the machine-learning algorithm.
Not a fit: Patients with a malignant cancer diagnosis or those receiving hospice care prior to study enrollment may not benefit from this study.
Why it matters
Potential benefit: If successful, this tool could significantly reduce the incidence of opioid overdoses by enabling timely interventions in primary care settings.
How similar studies have performed: Other studies have shown promise in using machine learning for predicting health risks, indicating potential success for this novel approach.
Eligibility criteria
Show full inclusion / exclusion 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
Where this trial is running
Gainesville, Florida
- University of Florida Health Internal Medicine and Family Medicine — Gainesville, Florida, United States (Recruiting)
Study contacts
- Principal investigator: Wei-Hsuan Lo-Ciganic, PhD — Division of General Internal Medicine, School of Medicine, University of Pittsburgh, Pittsburgh, PA
- Study coordinator: Wei-Hsuan Lo-Ciganic, PhD
- Email: cp3@pitt.edu
- Phone: 412-383-2171
How to participate
- Review the eligibility criteria above with your treating physician.
- Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
- Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.