Machine Learning Tool for Opioid Overdose

(DEMONSTRATE Trial)

Recruiting at 1 trial location

Overseen By Debbie L Wilson, PhD

Age: 18+

Sex: Any

Trial Phase: Academic

Sponsor: University of Pittsburgh

Must be taking: Opioids

Disqualifiers: Malignant cancer, Hospice care

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

Compensation: Varies

Number of Visits: Unknown

2000 Participants Needed

Trial Summary

What is the purpose of this trial?

This clinical trial aims to evaluate the pilot implementation of a machine-learning (ML)-driven clinical decision support (CDS) tool designed to predict opioid overdose risk within the electronic health record (EHR) system at UF Health Internal Medicine and Family Medicine clinics in Gainesville, Florida. The study will use a pre- versus post-implementation design to compare outcomes within clinics, focusing on measures such as naloxone prescribing rates and opioid overdose occurrences. Researchers will also assess the usability, acceptability, and feasibility of the CDS tool through qualitative interviews with primary care clinicians (PCPs) in the participating clinics.

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 evaluating a tool to predict opioid overdose risk.

What data supports the effectiveness of the Overdose Prevention Alert (OPA) treatment for opioid overdose?

Research shows that smartphone algorithms can detect opioid overdose events with high accuracy, identifying key symptoms like breathing problems. This suggests that technology-based alerts, like OPA, could effectively help prevent fatal overdoses by notifying people who can provide immediate help. ^{1 2 3 4 5}

Is the Machine Learning Tool for Opioid Overdose safe for humans?

The research articles focus on developing and validating machine learning models to predict opioid overdose risk, but they do not provide specific safety data for human use of the tool itself. ^{1 2 3 5 6}

How is the Overdose Prevention Alert (OPA) treatment different from other opioid overdose treatments?

The Overdose Prevention Alert (OPA) treatment is unique because it uses a machine learning tool to predict and prevent opioid overdoses by analyzing data from prescription drug monitoring programs and electronic health records, rather than directly treating an overdose with medication like naloxone. ^{1 2 3 7 8}

Research Team

Wei-Hsuan Lo-Ciganic, PhD

Principal Investigator

Division of General Internal Medicine, School of Medicine, University of Pittsburgh, Pittsburgh, PA

Eligibility Criteria

This trial is for patients at UF Health Internal Medicine and Family Medicine clinics in Gainesville, Florida. It's focused on those who may be at risk of opioid overdose due to various conditions like drug abuse or mental disorders. Specific eligibility criteria are not provided.

Inclusion Criteria

For PCP level outcomes assessment: PCPs practicing in any of the 9 participating clinics (6 UF Health Family Medicine clinics and 3 UF Health Internal Medicine) in Gainesville, Florida.

I am over 18, got an opioid prescription last year, and am at high risk for overdose according to a special computer program.

Exclusion Criteria

Patients who had malignant cancer diagnosis or hospice care prior to study enrollment.

Timeline

Screening

Participants are screened for eligibility to participate in the trial

2-4 weeks

Implementation

Implementation of the ML-driven CDS tool within the EHR system at UF Health clinics

6 months

Ongoing integration and feedback sessions

Evaluation

Assessment of the usability, acceptance, and feasibility of the CDS tool through mixed-method evaluations

6 months

Interviews and online questionnaires with PCPs

Follow-up

Participants are monitored for safety and effectiveness after implementation

12 months

Treatment Details

Interventions

• Overdose Prevention Alert (OPA)

Trial Overview The study tests a machine-learning tool that predicts opioid overdose risk within the electronic health record system. It compares outcomes before and after implementation, looking at naloxone prescriptions and overdose rates.

Participant Groups

Group I: Overdose Prevention Alert (OPA) Intervention Arm Experimental Treatment 1 Intervention

The intervention arm will receive a ML CDS tool that provides interruptive alerts for patients at elevated risk of opioid overdose, triggered when a clinician signs an opioid order.

Who Is Running the Clinical Trial?

University of Pittsburgh

Lead Sponsor

Trials

1,820

Recruited

16,360,000+

National Institute on Drug Abuse (NIDA)

Collaborator

Trials

2,658

Recruited

3,409,000+

Applied Decision Science

Collaborator

Trials

1

Recruited

2,000+

References

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

Machine learning for phenotyping opioid overdose events. [2020]

2. Ireland pubmed.ncbi.nlm.nih.gov

Development and validation of an overdose risk prediction tool using prescription drug monitoring program data. [2023]

3. England pubmed.ncbi.nlm.nih.gov

Using natural language processing of clinical text to enhance identification of opioid-related overdoses in electronic health records data. [2021]

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

Opioid overdose detection using smartphones. [2020]

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

Assessing opioid overdose risk: a review of clinical prediction models utilizing patient-level data. [2022]

6. Ireland pubmed.ncbi.nlm.nih.gov

A predictive risk model for nonfatal opioid overdose in a statewide population of buprenorphine patients. [2023]

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

Methodological approaches for the prediction of opioid use-related epidemics in the United States: a narrative review and cross-disciplinary call to action. [2021]

8. England pubmed.ncbi.nlm.nih.gov

Preventing Overdose Using Information and Data from the Environment (PROVIDENT): protocol for a randomized, population-based, community intervention trial. [2023]