Not provided
| ID | Type | Description | Link |
|---|---|---|---|
| 1R61DA057629 | U.S. NIH Grant/Contract | View source |
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
| Name | Class |
|---|---|
| National Institute on Drug Abuse (NIDA) | NIH |
Not provided
Not provided
Not provided
Not provided
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:
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.
Not provided
Not provided
Not provided
Not provided
| Label | Type | Description | Intervention Names |
|---|---|---|---|
| Patients with OUD | Experimental | Patients with opioid use disorder identified through C-DOSETaP system |
|
| Name | Type | Description | Arm Group Labels | Other Names |
|---|---|---|---|---|
| OUD screening | Other | Completed screening for opioid use disorder |
| |
| Measure | Description | Time Frame |
|---|---|---|
| Number of people screened for OUD | Aggregate rate of data-driven OUD screening across the health system | Rolling measure of annual rates (12 months) measured over the implementation period. |
| Continuity of care for patients with OUD | Continuity of care will be assessed through appointment follow-up and completion of referral to the next care site within 30 days. | 30 days and 12 months |
| Utilization of MOUD across the health system | MOUD use will be measured as the number of patients actively on MOUD as a proportion of all patients within the health system and of those with documented OUD within the health system as defined by International Classification of Diseases, 10th Revision, Clinical Modification (ICD-10-CM) codes. | Baseline and 12 months |
| Measure | Description | Time Frame |
|---|---|---|
| Regional opioid-related mortality | Quarterly opioid-related mortality rate by zip codes served by the primary institution reported to the Illinois Department of Public Health | Baseline and 12 months |
| Regional OUD Screening |
Not provided
Inclusion Criteria
Exclusion Criteria
- Children younger than age 16
Not provided
Not provided
Not provided
Not provided
Not provided
| Name | Role | Phone | Extension | |
|---|---|---|---|---|
| Niranjan S. Karnik, MD, PhD | Contact | (312) 273-0185 | nkarnik@uic.edu | |
| Neeraj Chhabra, MD | Contact | neeraj1@uic.edu |
| Name | Affiliation | Role |
|---|---|---|
| Niranjan S. Karnik, MD, PhD | UIC, College of Medicine | Principal Investigator |
| Neeraj Chhabra, MD | UIC, College of Medicine | Principal Investigator |
| Facility | Status | City | State | ZIP | Country | Contacts |
|---|---|---|---|---|---|---|
| University of Illinois Hospitals and Clinics (UI Health) | Chicago | Illinois | 60608 | United States |
| PubMed Identifier | Type | Citation | Retractions |
|---|---|---|---|
| 35623797 | Background | 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. | |
| 39711725 | Background | 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. |
| Label | URL |
|---|---|
| The AI.Health4All Center, University of Illinois at Chicago | View source |
Not provided
A de-identified research dataset will be submitted to NIH data repository per the approved Data Management and Sharing Plan following R33 completion.
Not provided
Not provided
Not provided
Not provided
Not provided
| ID | Term |
|---|---|
| D009293 | Opioid-Related Disorders |
| ID | Term |
|---|---|
| D000079524 | Narcotic-Related Disorders |
| D019966 | Substance-Related Disorders |
| D064419 | Chemically-Induced Disorders |
| D001523 | Mental Disorders |
Not provided
Not provided
| ID | Term |
|---|---|
| D003266 | Continuity of Patient Care |
| ID | Term |
|---|---|
| D005791 | Patient Care |
| D013812 | Therapeutics |
| D006296 | Health Services |
| D005159 | Health Care Facilities Workforce and Services |
Not provided
Not provided
The C-DOSETaP system represents a health system-level approach to OUD screening, treatment engagement, and patient retention, which comprises multiple clinical contexts, including inpatient hospital-based care, emergency care, primary care, and specialist outpatient care. Screening activities across these domains will take advantage of digital AI classifiers using EHR data in the inpatient and emergency settings and self-report measures in the outpatient clinics. Results from the opioid misuse screeners will be integrated into local clinical workflows and data aggregated to a digital dashboard for use by the health system's OUD Command Center (OCC) to track referrals for OUD care, follow-up care, and prescriptions. Automated flags will alert the OCC for signs potentially indicative of patient dropout from OUD treatment including missed appointments by more than 48 hours, missed prescriptions, and and lack of any follow-up data. Flags will trigger outreach by peer-recovery specialists.
Not provided
Not provided
Not provided
Not provided
| MOUD |
| Other |
Medication treatment for opioid use disorder |
|
| Continuity of care | Other | Facilitation of outpatient treatment linkages |
|
Quarterly opioid-related screening rates by zip codes served by the primary institution reported to the Illinois Department of Public Health
| Baseline and 12 months |
| Regional MOUD utilization | Quarterly MOUD utilization rates by zip codes served by the primary institution reported to the Illinois Department of Public Health | Baseline and 12 months |
| 41785519 | Background | 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. |
| D011320 | Primary Health Care |
| D003191 | Comprehensive Health Care |
| D010346 | Patient Care Management |
| D006298 | Health Services Administration |