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

What You Need to Know Before You Apply

What is the purpose of this trial?

This trial tests a tool that helps doctors predict who might be at risk for an opioid overdose. Specific health clinics are using it to determine if it can increase safe practices, such as prescribing naloxone, a medication that reverses overdoses. Researchers are also evaluating whether doctors find the Overdose Prevention Alert (OPA) tool easy and helpful to use. Patients prescribed opioids in the last year and flagged by the tool as higher risk for overdose might be suitable participants. As an unphased trial, this study offers patients the chance to contribute to innovative research that could enhance overdose prevention strategies.

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 prior data suggests that this machine-learning tool is safe for use in predicting opioid overdose risk?

Research has shown that the Overdose Prevention Alert (OPA) tool is a computer program designed to predict and prevent opioid overdoses by analyzing data. As a software tool, its safety concerns differ from those of medications, focusing instead on accurately identifying individuals at risk without causing unnecessary worry.

The current study phase is labeled "Not Applicable," indicating a focus on evaluating the tool's effectiveness and usability rather than traditional safety testing. This suggests the tool poses low risk, as it does not involve direct physical treatment of patients.

The study will assess the tool's performance in real-life situations by determining if it aids doctors in prescribing naloxone (a drug used to reverse opioid overdoses) and reduces actual overdose cases. Researchers will also gather feedback from doctors regarding the tool's ease of use and acceptability. This feedback ensures the tool is not only effective but also safe for everyday medical use. ^{1 2 3 4 5}

Why are researchers excited about this trial?

Researchers are excited about the Overdose Prevention Alert (OPA) because it represents a novel approach to tackling opioid overdoses by leveraging machine learning. Unlike traditional methods that rely on historical patient data and manual risk assessment, OPA uses a machine learning clinical decision support tool to provide real-time alerts for clinicians when they are prescribing opioids to patients at high risk of overdose. This proactive and data-driven approach could significantly enhance the ability to prevent overdoses before they occur, offering a smarter and more responsive way to address the opioid crisis.

What evidence suggests that this machine learning tool is effective for predicting opioid overdose risk?

Research shows that the Overdose Prevention Alert (OPA), provided to participants in this trial, uses a smart computer program to predict and prevent opioid overdoses by analyzing patient information. This tool identifies individuals at high risk of an overdose, allowing doctors to take preventive measures. Early results suggest that similar computer programs have successfully predicted health issues. By alerting doctors, the OPA tool aims to increase the use of naloxone, a medicine that can reverse an opioid overdose, and reduce the number of overdoses. Although specific data on OPA is limited, the method relies on proven risk prediction strategies. ^{3 6 7 8 9}

Who Is on the Research Team?

Wei-Hsuan Lo-Ciganic, PhD

Principal Investigator

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

Are You a Good Fit for This Trial?

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 for a Trial Participant

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

What Are the Treatments Tested in This Trial?

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.

How Is the Trial Designed?

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+

Citations

1. pmc.ncbi.nlm.nih.gov pmc.ncbi.nlm.nih.gov/articles/PMC8450721/

Multi-informant Implementation and Intervention Outcomes ... This study evaluated 16 OEND trainings conducted at different Opioid Overdose Prevention Programs in New York City.

2. withpower.com withpower.com/trial/machine-learning-tool-for-opioid-overdose-715d4

Machine Learning Tool for Opioid Overdose 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 ...

3. sciencedirect.com sciencedirect.com/science/article/pii/S1098301524000731

Economic Evaluations of Establishing Opioid Overdose ... Health outcomes primarily included overdose mortality outcomes or HIV/hepatitis C virus infections averted. Most studies used mathematical modeling and ...

4. cdc.gov cdc.gov/overdose-prevention/media/pdfs/2018-evidence-based-strategies.pdf

Evidence-Based Strategies for Preventing Opioid Overdose Examples of strategies shown ineffective by research and data include: arrest and incarceration, compulsory treatment, rapid detox without ...

5. nejm.org nejm.org/doi/full/10.1056/NEJMra1807054

Prevention of Opioid Overdose In this review, we focus on prescriber strategies for overdose prevention in three groups of patients: those who have not received previous opioid therapy.

6. cdc.gov cdc.gov/overdose-prevention/data-research/facts-stats/index.html

Data Resources | Overdose Prevention View fatal and nonfatal overdose data dashboards, and pharmacy dispensing rate maps.

7. pmc.ncbi.nlm.nih.gov pmc.ncbi.nlm.nih.gov/articles/PMC9859116/

Overdose Detection Technologies to Reduce Solitary ... The hotline is monitored 24/7 and offers added anonymous protection for people who use drugs alone to prevent solitary overdose deaths, also ...

8. library.samhsa.gov library.samhsa.gov/sites/default/files/overdose-prevention-response-kit-pep23-03-00-001.pdf

SAMHSA Overdose Prevention and Response Toolkit 1 In addition, provisional data from CDC now show that overdose deaths have declined throughout 2024, with a projected decline of nearly 27% in ...

9. health.ny.gov health.ny.gov/diseases/aids/general/opioid_overdose_prevention/

New York State's Opioid Overdose Prevention Program These data include county-level quarterly reports recommended by the New York State Heroin and Opioid Task Force and specified in amendments to Public Health ...