Substance UseNCT03833804
Data-driven Identification for Substance Misuse
A study testing Processing of clinical notes in the EHR data collected during routine care in people with Substance Use and Substance Abuse, run by University of Wisconsin, Madison at 1 site in United States.
Trial summary
The investigators propose to develop an open-source, publicly available machine learning model that health systems could download and apply to their electronic health record data marts to screen for substance misuse in their patients. Read more about this study
- Who is it for?
- Ages 18 to 89 years
- Conditions the study is for
- Substance Use, Substance Abuse, Substance-Related Disorders
- What is being tested?
- Processing of clinical notes in the EHR data collected during routine care
- Could I receive a placebo?
- No, everyone receives an active treatment
- How many people
- 64,996 participants
- Where
- 1 siteUnited States
- Study dates
- 19 Sep 2022to 19 Sep 2024
- Phase
- Interventional
- Are there results?
- Yes, posted in the registrySummary in the doctors' view
Key requirements
Who can take part, as listed by the sponsor. Only the study team can confirm whether you are eligible, so take this list to your doctor.
- Ages 18 to 89 years
- All sexes
- No healthy volunteers
- Adult, Older adult
Who may be able to join
- Ages 18 years old to 89 years old
- Inpatient status during hospitalization
- Length of stay greater than 24 hours
Who cannot join
- Cannot participate in the usual care SBIRT intervention
- Death or obtunded during first 24 hours of admission
- Discharged against medical advice
- Transferred from another acute care hospital
- Transferred to another acute care hospital
Trial locations and contacts
1 site in 1 country.
United States1 site
Rush University Medical Center
Chicago, Illinois, 60612
About this study
Official title: Data-driven Strategies for Substance Misuse Identification in Hospitalized Patients
The investigators propose to develop an open-source, publicly available machine learning model that health systems could download and apply to their electronic health record data marts to screen for substance misuse in their patients. The investigators hypothesize that the natural language processing algorithm can provide a standardized and interoperable approach for an automated daily screen on all hospitalized patients and provide better implementation fidelity for screening, brief intervention, and referral to treatment.
Read the detailed description
In 2016, nearly 30% hospital discharges in the United States (US) had a major diagnostic category for a substance-use related condition. Substance misuse ranks second among principal diagnoses for unplanned 7-day hospital readmission rates. Despite the availability of Screening, Brief Intervention, and Referral to Treatment (SBIRT) interventions, substance misuse is not part of the admission routine and only a minority of patients are screened for substance misuse in the hospital setting. This is particularly problematic, since among hospitalized inpatients, the prevalence of substance misuse is estimated to be as high as 25%, greater than either the general population or outpatient setting. Practical screening methods tailored for the hospital setting are needed.
In the advent of Meaningful Use in the electronic health record (EHR), efficiency for alcohol detection may be improved by leveraging data collected during usual care. Documentation of substance use is common and occurs in over 96% of provider admission notes, but their free text format renders them difficult to mine and analyze. Natural Language Processing (NLP) and machine learning are subfields of artificial intelligence (AI) that provide a solution to analyze text data in the EHR to identify substance misuse. Modern NLP has fused with machine learning, another sub-field of artificial intelligence focused on learning from data. In particular, the most powerful NLP methods rely on supervised learning, a type of machine learning that takes advantage of current reference standards to make predictions about unseen cases
In the earlier version of an NLP and machine learning tool, the investigators successfully used data from clinical notes collected in the first 24 hours of hospital admission to reach a sensitivity and specificity above 70% for identifying alcohol misuse. With nearly 36 million hospital admissions in 2016, a substance misuse classifier has potential to impact millions.
In this study, the aim is to prospectively implement a substance misuse classifier to examine its effectiveness against current practice of all hospitalized adult patients at a tertiary health system. The health system has a mature screening system to examine substance misuse classifier performance against current practice of questionnaire screening.
The hypothesis is that the substance misuse classifier may provide a standardized, interoperable, and accurate approach to screen hospitalized patients. Successful implementation of the classifier in hospitalized patients is a step towards an automated and comprehensive universal screening system for substance misuse.
- Conditions
- Substance Use, Substance Abuse, Substance-Related Disorders
- Being tested
- Processing of clinical notes in the EHR data collected during routine care
- Keywords
- natural language processing, machine learning, artificial intelligence, clinical decision support, unhealthy alcohol use, opioid use disorder, illicit drug use
- Medical subject headings
- Substance-Related Disorders, Opioid-Related Disorders
What participants receive
What participants receive. In a randomised study each person is assigned to one group by chance.
Processing of clinical notes in the EHR data collected during routine careOther
Clinical notes collected in the first day of hospital admission during usual care as input to natural language processing and machine learning algorithm.
| Study group | Role | What they receive |
|---|---|---|
| SMART-AI: NLP (natural language processing) pre-screen | Experimental | Automated processing of clinical notes collected during routine care in first 24 hours of hospital admission to identify individuals at-risk for substance misuse to receive standard-of-care full screening and assessment, brief intervention, or referral to treatment (SBIRT) intervention. Receives: Other: Processing of clinical notes in the EHR data collected during routine care |
| Usual Care | No intervention | Data collected before the intervention began |
What is being measured
The primary outcome is the main question the study is designed to answer.
Proportion of Patients That Had a Universal Screen Positive and Received SBIRT (Screening, Brief Intervention, or Referral to Treatment)
The primary outcome is the proportion of patients who received SBIRT after a positive universal screen for being at risk for substance misuse. The design is an interrupted time-series prospective observational study.
Measured: 24 months
Secondary outcomes (1)
All-cause Re-hospitalizations Following 6-months From the Index Hospital Encounter
We will compare healthcare utilization outcomes in all patients between pre- and post-periods controlling for all patient demographic and clinical characteristics.
Measured: 12 months enrollment with 6 months follow-up for rehospitalization
Timeline
From the start of the study to its completion; the mark is today. Estimated dates are the sponsor’s plan.
- First posted7 Feb 2019
- Study start19 Sep 2022
- Primary completion19 Sep 2024
- Study completion19 Sep 2024
Resources
- Official record on ClinicalTrials.govThe registry entry this page is built from, with its full change history.
- Posted resultsParticipant flow, outcome measures and adverse events reported by the sponsor.
- Publications (3)Papers the sponsor has linked to this study.
- Other trials for Substance UseStudies of the same condition, open and under way.
- What the trial phases meanHow a treatment moves from first tests in people to approval.
More details
For doctors and researchers: how the study is designed, who runs it, and its registry IDs.
Study design
- Study type
- Interventional
- Phase
- Phase N/A
- Primary purpose
- Screening
- Allocation
- Not applicable
- Intervention model
- Sequential
- Model description
- Quasi-experimental design as an interrupted time series
- Masking
- None (open label)
- Enrolment
- 64,996 participants (actual)
Sponsor and investigators
- Lead sponsor
- University of Wisconsin, Madison
- Sponsor type
- University, hospital or other
- Collaborators
- Rush University Medical Center, National Institute on Drug Abuse (NIDA)
- Responsible party
- Sponsor
IDs, dates and publications
- ClinicalTrials.gov ID
- NCT03833804
- Sponsor's protocol ID
- 2022-0983
- Other IDs
- A534285, SMPH/MEDICINE, 1R01DA051464
- Status last verified
- Oct 2025
- First submitted
- 6 Feb 2019
- Last updated
- 24 Oct 2025
- Results posted
- Yes, on ClinicalTrials.gov
- Data monitoring committee
- Yes
- FDA-regulated drug
- No
- FDA-regulated device
- No
- Individual data sharing
- Yes: The patient data are protected health information and unavailable to public but the algorithm will be shared. The investigators will serialize our best models developed using either pickle (a Python native mechanism for object serialization) or joblib (https://pythonhosted.org/joblib/) and write software that will be capable of reloading them and making predictions. The software will be distributed via github.com or similar web-based software hosting service.
Publications
Afshar M, Phillips A, Karnik N, Mueller J, To D, Gonzalez R, Price R, Cooper R, Joyce C, Dligach D. Natural language processing and machine learning to identify alcohol misuse from the electronic health record in trauma patients: development and internal validation. J Am Med Inform Assoc. 2019 Mar 1;26(3):254-261. doi: 10.1093/jamia/ocy166.
PubMed 30602031Rojas JC, Joyce C, Markossian TW, Chaudhari V, McClintic MR, Castro F, Fairgrieve AJ, Dligach D, Oguss MK, Churpek MM, Nikolaides J, Afshar M. Clinical Implementation of an AI Algorithm for Substance Misuse Screening in Hospitalized Adults. medRxiv [Preprint]. 2025 Nov 19:2025.11.17.25340323. doi: 10.1101/2025.11.17.25340323.
PubMed 41332823Joyce C, Markossian TW, Nikolaides J, Ramsey E, Thompson HM, Rojas JC, Sharma B, Dligach D, Oguss MK, Cooper RS, Afshar M. The Evaluation of a Clinical Decision Support Tool Using Natural Language Processing to Screen Hospitalized Adults for Unhealthy Substance Use: Protocol for a Quasi-Experimental Design. JMIR Res Protoc. 2022 Dec 19;11(12):e42971. doi: 10.2196/42971.
PubMed 36534461
Study at a glance
From the registry record, last updated by the sponsor on 24 Oct 2025. Recruitment status is as the sponsor reported it: confirm with the study team.
- Official title
- Data-driven Strategies for Substance Misuse Identification in Hospitalized Patients
- ClinicalTrials.gov ID
- NCT03833804
- Acronym / sponsor ID
- 2022-0983
- Conditions
- Substance Use, Substance Abuse, Substance-Related Disorders
- Keywords
- natural language processing, machine learning, artificial intelligence, clinical decision support, unhealthy alcohol use, opioid use disorder, illicit drug use
- Study type
- Interventional
- Recruitment status
- Completed
- Enrolment
- 64,996 participants (actual)
- Lead sponsor
- University of Wisconsin, MadisonUniversity, hospital or other
- Collaborators
- Rush University Medical Center, National Institute on Drug Abuse (NIDA)
- Study start
- 19 Sep 2022 (actual)
- Primary completion
- 19 Sep 2024 (actual)
- Study completion
- 19 Sep 2024 (actual)
- First posted
- 7 Feb 2019 (actual)
- Results
- Posted 24 Oct 2025
Clinical summary
The research question as the sponsor registered it. This describes what the study plans to test, not what it found.
The investigators propose to develop an open-source, publicly available machine learning model that health systems could download and apply to their electronic health record data marts to screen for substance misuse in their patients. The investigators hypothesize that the natural language processing algorithm can provide a standardized and interoperable approach for an automated daily screen on all hospitalized patients and provide better implementation fidelity for screening, brief intervention, and referral to treatment.
Detailed description
In 2016, nearly 30% hospital discharges in the United States (US) had a major diagnostic category for a substance-use related condition. Substance misuse ranks second among principal diagnoses for unplanned 7-day hospital readmission rates. Despite the availability of Screening, Brief Intervention, and Referral to Treatment (SBIRT) interventions, substance misuse is not part of the admission routine and only a minority of patients are screened for substance misuse in the hospital setting. This is particularly problematic, since among hospitalized inpatients, the prevalence of substance misuse is estimated to be as high as 25%, greater than either the general population or outpatient setting. Practical screening methods tailored for the hospital setting are needed.
In the advent of Meaningful Use in the electronic health record (EHR), efficiency for alcohol detection may be improved by leveraging data collected during usual care. Documentation of substance use is common and occurs in over 96% of provider admission notes, but their free text format renders them difficult to mine and analyze. Natural Language Processing (NLP) and machine learning are subfields of artificial intelligence (AI) that provide a solution to analyze text data in the EHR to identify substance misuse. Modern NLP has fused with machine learning, another sub-field of artificial intelligence focused on learning from data. In particular, the most powerful NLP methods rely on supervised learning, a type of machine learning that takes advantage of current reference standards to make predictions about unseen cases
In the earlier version of an NLP and machine learning tool, the investigators successfully used data from clinical notes collected in the first 24 hours of hospital admission to reach a sensitivity and specificity above 70% for identifying alcohol misuse. With nearly 36 million hospital admissions in 2016, a substance misuse classifier has potential to impact millions.
In this study, the aim is to prospectively implement a substance misuse classifier to examine its effectiveness against current practice of all hospitalized adult patients at a tertiary health system. The health system has a mature screening system to examine substance misuse classifier performance against current practice of questionnaire screening.
The hypothesis is that the substance misuse classifier may provide a standardized, interoperable, and accurate approach to screen hospitalized patients. Successful implementation of the classifier in hospitalized patients is a step towards an automated and comprehensive universal screening system for substance misuse.
Study design
- Primary purpose
- Screening
- Allocation
- Not applicable
- Intervention model
- Sequential
- Masking
- None (open label)
- Number of arms
- 2
- Model description
- Quasi-experimental design as an interrupted time series
| Arm | Type | Receives |
|---|---|---|
| SMART-AI: NLP (natural language processing) pre-screen | Experimental | Other: Processing of clinical notes in the EHR data collected during routine careAutomated processing of clinical notes collected during routine care in first 24 hours of hospital admission to identify individuals at-risk for substance misuse to receive standard-of-care full screening and assessment, brief intervention, or referral to treatment (SBIRT) intervention. |
| Usual Care | No intervention | –Data collected before the intervention began |
Who may qualify
- Ages
- 18 to 89 years
- Sex
- All
- Healthy volunteers
- Not accepted
- Age groups
- Adult, Older adult
Key inclusion criteria (3 listed)
- Ages 18 years old to 89 years old
- Inpatient status during hospitalization
- Length of stay greater than 24 hours
Key exclusion criteria (5 listed)
- Cannot participate in the usual care SBIRT intervention
- Death or obtunded during first 24 hours of admission
- Discharged against medical advice
- Transferred from another acute care hospital
- Transferred to another acute care hospital
Eligibility is decided by the study team after screening; this overview does not establish that a patient qualifies. Full inclusion and exclusion criteria.
Interventions
| Intervention | Type | Arms |
|---|---|---|
| Processing of clinical notes in the EHR data collected during routine careClinical notes collected in the first day of hospital admission during usual care as input to natural language processing and machine learning algorithm. | Other | SMART-AI: NLP (natural language processing) pre-screen |
Primary outcome
Proportion of Patients That Had a Universal Screen Positive and Received SBIRT (Screening, Brief Intervention, or Referral to Treatment)
Time frame: 24 months
The primary outcome is the proportion of patients who received SBIRT after a positive universal screen for being at risk for substance misuse. The design is an interrupted time-series prospective observational study.
1 secondary outcome
All-cause Re-hospitalizations Following 6-months From the Index Hospital Encounter
Time frame: 12 months enrollment with 6 months follow-up for rehospitalization
Results and safety
Loading the posted results from ClinicalTrials.gov…
Research links
- Official record on ClinicalTrials.govLast updated by the sponsor 24 Oct 2025.
- Posted resultsParticipant flow, baseline, all outcome measures and adverse events.
- Results publication: PubMed 30602031Afshar M, Phillips A, Karnik N, Mueller J, To D, Gonzalez R, Price R, Cooper R, Joyce C, Dligach D. Natural language processing and machine learning to identify alcohol misuse from the electronic health record in trauma patients: development and internal validation. J Am Med Inform Assoc. 2019 Mar 1;26(3):254-261. doi: 10.1093/jamia/ocy166.
- Derived from this study: PubMed 41332823Rojas JC, Joyce C, Markossian TW, Chaudhari V, McClintic MR, Castro F, Fairgrieve AJ, Dligach D, Oguss MK, Churpek MM, Nikolaides J, Afshar M. Clinical Implementation of an AI Algorithm for Substance Misuse Screening in Hospitalized Adults. medRxiv [Preprint]. 2025 Nov 19:2025.11.17.25340323. doi: 10.1101/2025.11.17.25340323.
- Derived from this study: PubMed 36534461Joyce C, Markossian TW, Nikolaides J, Ramsey E, Thompson HM, Rojas JC, Sharma B, Dligach D, Oguss MK, Cooper RS, Afshar M. The Evaluation of a Clinical Decision Support Tool Using Natural Language Processing to Screen Hospitalized Adults for Unhealthy Substance Use: Protocol for a Quasi-Experimental Design. JMIR Res Protoc. 2022 Dec 19;11(12):e42971. doi: 10.2196/42971.
- login page but full code not finalized for publishingLink provided by the sponsor.
- Individual participant dataSharing planned: Yes. The patient data are protected health information and unavailable to public but the algorithm will be shared. The investigators will serialize our best models developed using either pickle (a Python native mechanism for object serialization) or joblib (https://pythonhosted.org/joblib/) and write software that will be capable of reloading them and making predictions. The software will be distributed via github.com or similar web-based software hosting service.
Related trials for Substance Use
Not yet recruitingEarly Phase 1
Pain Sensitivity, Alcohol-Induced Analgesia, and Heavy Drinking in Individuals With Opioid Use Disorder
Opioid Use Disorder, Alcohol Intoxication
Active, not recruiting
Closed-loop TBS Targeting rPO for the Core Clinical Features of Methamphetamine Use Disorder
Methamphetamine Use Disorder, Substance Use Disorder
RecruitingObservational study
SMART-r: Substance Monitoring and Active Relapse Tracking Repository
Alcoholism, Substance-Related Disorders
Enrolling by invitationObservational study
Development of an Interview-Informed Timeline Follow-Back (TLFB) for Opioid Use in the Era of Fentanyl
Substance Use Disorders (SUDs)
RecruitingObservational study
Olfactory Function and Model-Based Behavior in People Living With HIV and SUD
HIV, Substance Use Disorder
Referral and contact
AzTrials does not enrol participants or take referrals. Contact the study team or a site listed below; they decide who can take part. This study is not recruiting at the moment.
The record lists no contact. Use the official record to reach the sponsor.
1 site in 1 country: see every site and its status.
Questions about this trial
What is this clinical trial studying?
A study testing Processing of clinical notes in the EHR data collected during routine care in people with Substance Use and Substance Abuse, run by University of Wisconsin, Madison at 1 site in United States.
The full registered description is in the About this study section and the official record.
Who may be eligible to take part?
The sponsor lists 3 inclusion and 5 exclusion criteria. Eligibility is decided by the study team after screening, so read the full criteria and contact a listed site.
Is this clinical trial currently recruiting?
The record says: finished, as of the sponsor's last update on 24 Oct 2025. Status can change between updates, so confirm with the study contact before making plans.
Where is the study taking place?
The record lists 1 site in United States. Whether a site is taking part right now should be confirmed with that site. See every site.
What are the possible benefits and risks?
They depend on the study and the treatment, and no study can promise a benefit. The study team explains the known risks during informed consent, before anyone joins; the record itself does not list them.
Are results available for this study?
Yes. Results are posted in the registry (first posted 24 Oct 2025). A summary is in the For doctors view, and the full results are on ClinicalTrials.gov.
How can a doctor refer a patient or contact the research team?
The record lists no contact. The official record names the sponsor, who can be asked directly. AzTrials does not enrol participants or take referrals.
What does the primary outcome measure?
Proportion of Patients That Had a Universal Screen Positive and Received SBIRT (Screening, Brief Intervention, or Referral to Treatment) (time frame: 24 months). It is what the study was designed to measure, not a finding.
Where can I read the original study information?
On the ClinicalTrials.gov record for NCT03833804, which also lists 3 linked publications.
Does a listing mean the treatment is approved or proven to work?
No. A listing means the study is registered. It does not show that the treatment is safe, works, or is approved by a regulator.
How often is this information updated?
AzTrials copies changed records from ClinicalTrials.gov every night and reloads the whole registry every week. The sponsor last updated this record on 24 Oct 2025.