Chicago Data-driven Opioid Use Disorder Screening, Engagement, Treatment and Planning System

Overview

This study, called the Chicago Data-driven Opioid use disorder Screening, Engagement, Treatment and Planning (C-DOSETaP) System, tests a new system of clinical care for patients with opioid use disorder (OUD) across a large health system. The main questions this study aims to answer are: 1. Does the C-DOSETaP System increase screening for patients with OUD; 2. Does the C-DOSETaP System improve continuity of health care for patients with OUD; 3. Does the C-DOSETaP System increase use of medications for opioid use disorder; and 4. Does the C-DOSETaP System reduce the number of opioid-related deaths in the neighborhoods served.

Detailed description

The Chicago Data-driven Opioid use disorder Screening, Engagement, Treatment and Planning (C-DOSETaP) System, tests an innovative approach leveraging healthcare data harmonization, digital tools, and clinical workflows to improve the care for patients with opioid use disorder (OUD) across a large health system serving a population heavily affected by the opioid overdose epidemic. The C-DOSETaP system will implement a diverse set of screening tools across the health systems' numerous clinical domains, improve healthcare engagement and utilization of OUD treatments, and pursue a data-forward approach leveraging electronic health record (EHR) data to track care delivery and engage with patients at risk for treatment dropout or failure.

The investigators hypothesize that implementation of the C-DOSETaP system alongside a locally developed system-level opioid response plan will result in: 1) increased OUD screening rates; 2) improved continuity of care; 3) increased utilization of medications for opioid use disorder (MOUD); and 4) reduced mortality in neighborhoods served by the primary study institution.

Primary Outcomes Three dimensions of OUD treatment and engagement will be assessed as primary outcomes for the study. The investigators will measure: 1) screening rates; 2) continuity of care; and 3) use of MOUD across the health system. Screening rates will be measured as the proportion of all patients with encounters in the health system that have a completed screening for opioid misuse within the preceding 12 months. Continuity of care will be assessed by appointment follow-up and completed referral to the next care site. Use of MOUD will be measured as the number of patients actively on MOUD as a proportion of all patients with documented OUD within the health system as defined by International Classification of Diseases, 10th Revision, Clinical Modification (ICD-10-CM) codes.

Secondary Outcomes The investigators plan to evaluate aggregate impact of interventions and primary measures on OUD mortality reported in neighborhoods served by the primary study institution during the phased stepped wedge rollout across system-associated clinics. The secondary outcomes for this phase include quarterly opioid-related mortality by zip codes served by the primary institution.

Interventions

• Other OUD screening
  Completed screening for opioid use disorder
• Other MOUD
  Medication treatment for opioid use disorder
• Other Continuity of care
  Facilitation of outpatient treatment linkages

Primary outcome measures

• Number of people screened for OUD [Time frame: Rolling measure of annual rates (12 months) measured over the implementation period.]
• Continuity of care for patients with OUD [Time frame: 30 days and 12 months]
• Utilization of MOUD across the health system [Time frame: Baseline and 12 months]

Secondary outcome measures (3)

• Regional opioid-related mortality [Time frame: Baseline and 12 months]
• Regional OUD Screening [Time frame: Baseline and 12 months]
• Regional MOUD utilization [Time frame: Baseline and 12 months]

Eligibility criteria

Inclusion criteria

• Participant must be a patient seen at the University of Illinois Hospital and Clinics
• Adults and adolescents age 16 or older

Exclusion criteria

\- Children younger than age 16

Criteria are shown verbatim from the registry (in English). Final eligibility is always assessed by the study center.

Healthy volunteers: Yes

Study design

Allocation

N/A

Model

Single group

Masking

Open label

Primary purpose

Health services research

Study locations

United States · 1 center

• University of Illinois Hospitals and Clinics (UI Health) — Chicago

Publications

• Afshar M, Sharma B, Dligach D, Oguss M, Brown R, Chhabra N, Thompson HM, Markossian T, Joyce C, Churpek MM, Karnik NS. Development and multimodal validation of a substance misuse algorithm for referral to treatment using artificial intelligence (SMART-AI): a retrospective deep learning study. Lancet Digit Health. 2022 Jun;4(6):e426-e435. doi: 10.1016/S2589-7500(22)00041-3. PMID 35623797
• Shahid U, Parde N, Smith DL, Dickinson G, Bianco J, Thorpe D, Hota M, Afshar M, Karnik NS, Chhabra N. Development and Evaluation of Machine Learning Models for the Detection of Emergency Department Patients with Opioid Misuse from Clinical Notes. medRxiv [Preprint]. 2024 Dec 12:2024.12.11.24318875. doi: 10.1101/2024.12.11.24318875. PMID 39711725
• Chhablani C, Shahid U, Parde N, Muslmani S, Hu H, Thorpe D, Afshar M, Karnik N, Chhabra N. Machine learning models to detect opioid misuse in emergency department patients at triage. Am J Emerg Med. 2026 Jun;104:17-23. doi: 10.1016/j.ajem.2026.02.037. Epub 2026 Feb 26. PMID 41785519

Identifiers

NCT: NCT07498322 · 2024-0243 · 1R61DA057629

Primary sources (government registries)

• ClinicalTrials.gov (US NIH)

View this study on ClinicalTrials.gov ↗