Ignite Creation Date:
2025-12-24 @ 7:57 PM
Ignite Modification Date:
2026-01-24 @ 5:57 PM
Study NCT ID:
NCT03833804
Status:
COMPLETED
Last Update Posted:
2025-10-24
First Post:
2019-02-06
Is NOT Gene Therapy:
True
Has Adverse Events:
True
Brief Title:
Data-driven Identification for Substance Misuse
Sponsor:
Organization:
Raw JSON
{'hasResults': True, 'derivedSection': {'miscInfoModule': {'versionHolder': '2025-12-24'}, 'conditionBrowseModule': {'meshes': [{'id': 'D019966', 'term': 'Substance-Related Disorders'}, {'id': 'D009293', 'term': 'Opioid-Related Disorders'}], 'ancestors': [{'id': 'D064419', 'term': 'Chemically-Induced Disorders'}, {'id': 'D001523', 'term': 'Mental Disorders'}, {'id': 'D000079524', 'term': 'Narcotic-Related Disorders'}]}}, 'resultsSection': {'moreInfoModule': {'pointOfContact': {'email': 'mafshar@medicine.wisc.edu', 'phone': '608-263-1792', 'title': 'Majid Afshar, MD', 'organization': 'UW School of Medicine and Public Health'}, 'certainAgreement': {'piSponsorEmployee': True}}, 'adverseEventsModule': {'timeFrame': 'No plan per protocol to collect adverse events data.', 'description': 'Investigators did not plan per protocol to examine all-cause mortality outside of the discharge disposition (data reported in baseline characteristics), serious adverse events, or other adverse events. Adverse Events and Deaths were not collected.', 'eventGroups': [{'id': 'EG000', 'title': 'Usual Care', 'description': 'data collected before study intervention', 'otherNumAtRisk': 0, 'deathsNumAtRisk': 0, 'otherNumAffected': 0, 'seriousNumAtRisk': 0, 'deathsNumAffected': 0, 'seriousNumAffected': 0}, {'id': 'EG001', 'title': 'SMART-AI: NLP (Natural Language Processing) Pre-screen', 'description': '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.\n\nProcessing of clinical notes in the EHR data collected during routine care: Clinical notes collected in the first day of hospital admission during usual care as input to natural language processing and machine learning algorithm.', 'otherNumAtRisk': 0, 'deathsNumAtRisk': 0, 'otherNumAffected': 0, 'seriousNumAtRisk': 0, 'deathsNumAffected': 0, 'seriousNumAffected': 0}], 'frequencyThreshold': '0'}, 'outcomeMeasuresModule': {'outcomeMeasures': [{'type': 'PRIMARY', 'title': 'Proportion of Patients That Had a Universal Screen Positive and Received SBIRT (Screening, Brief Intervention, or Referral to Treatment)', 'denoms': [{'units': 'Participants', 'counts': [{'value': '31432', 'groupId': 'OG000'}, {'value': '33564', 'groupId': 'OG001'}]}], 'groups': [{'id': 'OG000', 'title': 'Usual Care', 'description': 'Before intervention'}, {'id': 'OG001', 'title': 'SMART-AI', 'description': '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.\n\nProcessing of clinical notes in the EHR data collected during routine care: Clinical notes collected in the first day of hospital admission during usual care as input to natural language processing and machine learning algorithm.'}], 'classes': [{'categories': [{'measurements': [{'value': '1189', 'groupId': 'OG000'}, {'value': '1144', 'groupId': 'OG001'}]}]}], 'analyses': [{'pValue': '0.20', 'groupIds': ['OG000', 'OG001'], 'paramType': 'z-test', 'ciNumSides': 'TWO_SIDED', 'paramValue': '0.86', 'statisticalMethod': 'One-sided independent samples z-test', 'nonInferiorityType': 'NON_INFERIORITY', 'nonInferiorityComment': 'The investigators conducted a noninferiority analysis using a prespecified margin of 0.5%. The noninferiority margin was selected based on expert input from addiction medicine clinicians and implementation scientists, who agreed that a 0.5% absolute difference in the composite intervention rate would be clinically acceptable given the workflow and scalability benefits of automation. The margin was chosen to reflect a reasonable balance between clinical impact and operational gain.'}], 'paramType': 'COUNT_OF_PARTICIPANTS', 'timeFrame': '24 months', 'description': '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.', 'unitOfMeasure': 'Participants', 'reportingStatus': 'POSTED'}, {'type': 'SECONDARY', 'title': 'All-cause Re-hospitalizations Following 6-months From the Index Hospital Encounter', 'denoms': [{'units': 'Participants', 'counts': [{'value': '31432', 'groupId': 'OG000'}, {'value': '33564', 'groupId': 'OG001'}]}], 'groups': [{'id': 'OG000', 'title': 'Usual Care', 'description': 'Before intervention'}, {'id': 'OG001', 'title': 'SMART-AI', 'description': '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.\n\nProcessing of clinical notes in the EHR data collected during routine care: Clinical notes collected in the first day of hospital admission during usual care as input to natural language processing and machine learning algorithm.'}], 'classes': [{'categories': [{'measurements': [{'value': '9584', 'groupId': 'OG000'}, {'value': '10241', 'groupId': 'OG001'}]}]}], 'paramType': 'COUNT_OF_PARTICIPANTS', 'timeFrame': '12 months enrollment with 6 months follow-up for rehospitalization', 'description': 'We will compare healthcare utilization outcomes in all patients between pre- and post-periods controlling for all patient demographic and clinical characteristics.', 'unitOfMeasure': 'Participants', 'reportingStatus': 'POSTED'}]}, 'participantFlowModule': {'groups': [{'id': 'FG000', 'title': 'Usual Care', 'description': 'Before intervention'}, {'id': 'FG001', 'title': 'NLP (Natural Language Processing) Pre-screen', 'description': '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.\n\nProcessing of clinical notes in the EHR data collected during routine care: Clinical notes collected in the first day of hospital admission during usual care as input to natural language processing and machine learning algorithm.'}], 'periods': [{'title': 'Usual Care Data Collection (2022-2023)', 'milestones': [{'type': 'STARTED', 'achievements': [{'groupId': 'FG000', 'numSubjects': '31432'}, {'groupId': 'FG001', 'numSubjects': '0'}]}, {'type': 'COMPLETED', 'achievements': [{'groupId': 'FG000', 'numSubjects': '31432'}, {'groupId': 'FG001', 'numSubjects': '0'}]}, {'type': 'NOT COMPLETED', 'achievements': [{'groupId': 'FG000', 'numSubjects': '0'}, {'groupId': 'FG001', 'numSubjects': '0'}]}]}, {'title': 'SMART-AI Data Collection (2023-2024)', 'milestones': [{'type': 'STARTED', 'achievements': [{'groupId': 'FG000', 'numSubjects': '0'}, {'groupId': 'FG001', 'numSubjects': '33564'}]}, {'type': 'COMPLETED', 'achievements': [{'groupId': 'FG000', 'numSubjects': '0'}, {'groupId': 'FG001', 'numSubjects': '33564'}]}, {'type': 'NOT COMPLETED', 'achievements': [{'groupId': 'FG000', 'numSubjects': '0'}, {'groupId': 'FG001', 'numSubjects': '0'}]}]}], 'preAssignmentDetails': 'The comparison groups are pre-intervention and intervention. data from 31432 people were assessed prior to the intervention in 2022-2023 and data from 33564 people were assessed with the intervention from 2023-2024: data from 64996 people were assessed in total.'}, 'baselineCharacteristicsModule': {'denoms': [{'units': 'Participants', 'counts': [{'value': '31432', 'groupId': 'BG000'}, {'value': '33564', 'groupId': 'BG001'}, {'value': '64996', 'groupId': 'BG002'}]}], 'groups': [{'id': 'BG000', 'title': 'Usual Care', 'description': 'Before intervention'}, {'id': 'BG001', 'title': 'NLP (Natural Language Processing) Pre-screen: SMART-AI', 'description': '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.\n\nProcessing of clinical notes in the EHR data collected during routine care: Clinical notes collected in the first day of hospital admission during usual care as input to natural language processing and machine learning algorithm.'}, {'id': 'BG002', 'title': 'Total', 'description': 'Total of all reporting groups'}], 'measures': [{'title': 'Age, Continuous', 'classes': [{'denoms': [{'units': 'Participants', 'counts': [{'value': '31432', 'groupId': 'BG000'}, {'value': '33564', 'groupId': 'BG001'}, {'value': '64996', 'groupId': 'BG002'}]}], 'categories': [{'measurements': [{'value': '56', 'spread': '19', 'groupId': 'BG000'}, {'value': '56', 'spread': '19', 'groupId': 'BG001'}, {'value': '56', 'spread': '19', 'groupId': 'BG002'}]}]}], 'paramType': 'MEAN', 'unitOfMeasure': 'years', 'dispersionType': 'STANDARD_DEVIATION'}, {'title': 'Sex: Female, Male', 'classes': [{'denoms': [{'units': 'Participants', 'counts': [{'value': '31432', 'groupId': 'BG000'}, {'value': '33564', 'groupId': 'BG001'}, {'value': '64996', 'groupId': 'BG002'}]}], 'categories': [{'title': 'Female', 'measurements': [{'value': '18458', 'groupId': 'BG000'}, {'value': '19421', 'groupId': 'BG001'}, {'value': '37879', 'groupId': 'BG002'}]}, {'title': 'Male', 'measurements': [{'value': '12974', 'groupId': 'BG000'}, {'value': '14143', 'groupId': 'BG001'}, {'value': '27117', 'groupId': 'BG002'}]}]}], 'paramType': 'COUNT_OF_PARTICIPANTS', 'unitOfMeasure': 'Participants'}, {'title': 'Race/Ethnicity, Customized', 'classes': [{'denoms': [{'units': 'Participants', 'counts': [{'value': '31432', 'groupId': 'BG000'}, {'value': '33564', 'groupId': 'BG001'}, {'value': '64996', 'groupId': 'BG002'}]}], 'categories': [{'title': 'White', 'measurements': [{'value': '10524', 'groupId': 'BG000'}, {'value': '11097', 'groupId': 'BG001'}, {'value': '21621', 'groupId': 'BG002'}]}, {'title': 'Black', 'measurements': [{'value': '11139', 'groupId': 'BG000'}, {'value': '11650', 'groupId': 'BG001'}, {'value': '22789', 'groupId': 'BG002'}]}, {'title': 'Hispanic', 'measurements': [{'value': '7363', 'groupId': 'BG000'}, {'value': '8061', 'groupId': 'BG001'}, {'value': '15424', 'groupId': 'BG002'}]}, {'title': 'Asian', 'measurements': [{'value': '1047', 'groupId': 'BG000'}, {'value': '1064', 'groupId': 'BG001'}, {'value': '2111', 'groupId': 'BG002'}]}, {'title': 'Other', 'measurements': [{'value': '1058', 'groupId': 'BG000'}, {'value': '1318', 'groupId': 'BG001'}, {'value': '2376', 'groupId': 'BG002'}]}, {'title': 'Unknown', 'measurements': [{'value': '301', 'groupId': 'BG000'}, {'value': '374', 'groupId': 'BG001'}, {'value': '675', 'groupId': 'BG002'}]}]}], 'paramType': 'COUNT_OF_PARTICIPANTS', 'unitOfMeasure': 'Participants'}, {'title': 'Region of Enrollment', 'classes': [{'title': 'United States', 'denoms': [{'units': 'Participants', 'counts': [{'value': '31432', 'groupId': 'BG000'}, {'value': '33564', 'groupId': 'BG001'}, {'value': '64996', 'groupId': 'BG002'}]}], 'categories': [{'measurements': [{'value': '31432', 'groupId': 'BG000'}, {'value': '33564', 'groupId': 'BG001'}, {'value': '64996', 'groupId': 'BG002'}]}]}], 'paramType': 'NUMBER', 'unitOfMeasure': 'participants'}, {'title': 'Patient Class', 'classes': [{'denoms': [{'units': 'Participants', 'counts': [{'value': '31432', 'groupId': 'BG000'}, {'value': '33564', 'groupId': 'BG001'}, {'value': '64996', 'groupId': 'BG002'}]}], 'categories': [{'title': 'Inpatient', 'measurements': [{'value': '24231', 'groupId': 'BG000'}, {'value': '25992', 'groupId': 'BG001'}, {'value': '50223', 'groupId': 'BG002'}]}, {'title': 'Observation', 'measurements': [{'value': '7201', 'groupId': 'BG000'}, {'value': '7572', 'groupId': 'BG001'}, {'value': '14773', 'groupId': 'BG002'}]}]}], 'paramType': 'COUNT_OF_PARTICIPANTS', 'unitOfMeasure': 'Participants'}, {'title': 'Admission Type', 'classes': [{'denoms': [{'units': 'Participants', 'counts': [{'value': '31432', 'groupId': 'BG000'}, {'value': '33564', 'groupId': 'BG001'}, {'value': '64996', 'groupId': 'BG002'}]}], 'categories': [{'title': 'Elective', 'measurements': [{'value': '13753', 'groupId': 'BG000'}, {'value': '14652', 'groupId': 'BG001'}, {'value': '28405', 'groupId': 'BG002'}]}, {'title': 'Emergency', 'measurements': [{'value': '17679', 'groupId': 'BG000'}, {'value': '18912', 'groupId': 'BG001'}, {'value': '36591', 'groupId': 'BG002'}]}]}], 'paramType': 'COUNT_OF_PARTICIPANTS', 'unitOfMeasure': 'Participants'}, {'title': 'Elixhauser Comorbidity', 'classes': [{'denoms': [{'units': 'Participants', 'counts': [{'value': '30668', 'groupId': 'BG000'}, {'value': '32672', 'groupId': 'BG001'}, {'value': '63340', 'groupId': 'BG002'}]}], 'categories': [{'measurements': [{'value': '2.8', 'spread': '4.8', 'groupId': 'BG000'}, {'value': '2.9', 'spread': '4.9', 'groupId': 'BG001'}, {'value': '2.9', 'spread': '4.8', 'groupId': 'BG002'}]}]}], 'paramType': 'MEAN', 'unitOfMeasure': 'comorbidities', 'dispersionType': 'STANDARD_DEVIATION', 'populationDescription': 'Elixhauser Comorbidity was unknown for some participants.'}, {'title': 'Length of Stay (LOS)', 'classes': [{'denoms': [{'units': 'Participants', 'counts': [{'value': '31432', 'groupId': 'BG000'}, {'value': '33564', 'groupId': 'BG001'}, {'value': '64996', 'groupId': 'BG002'}]}], 'categories': [{'measurements': [{'value': '5.1', 'spread': '6.5', 'groupId': 'BG000'}, {'value': '4.9', 'spread': '6.4', 'groupId': 'BG001'}, {'value': '5.0', 'spread': '6.5', 'groupId': 'BG002'}]}]}], 'paramType': 'MEAN', 'unitOfMeasure': 'days', 'dispersionType': 'STANDARD_DEVIATION'}, {'title': 'Insurance', 'classes': [{'denoms': [{'units': 'Participants', 'counts': [{'value': '31432', 'groupId': 'BG000'}, {'value': '33564', 'groupId': 'BG001'}, {'value': '64996', 'groupId': 'BG002'}]}], 'categories': [{'title': 'Medicaid', 'measurements': [{'value': '8728', 'groupId': 'BG000'}, {'value': '8714', 'groupId': 'BG001'}, {'value': '17442', 'groupId': 'BG002'}]}, {'title': 'Medicare', 'measurements': [{'value': '13111', 'groupId': 'BG000'}, {'value': '14364', 'groupId': 'BG001'}, {'value': '27475', 'groupId': 'BG002'}]}, {'title': 'Private', 'measurements': [{'value': '7438', 'groupId': 'BG000'}, {'value': '8038', 'groupId': 'BG001'}, {'value': '15476', 'groupId': 'BG002'}]}, {'title': 'Self Pay', 'measurements': [{'value': '431', 'groupId': 'BG000'}, {'value': '666', 'groupId': 'BG001'}, {'value': '1097', 'groupId': 'BG002'}]}, {'title': 'Other', 'measurements': [{'value': '204', 'groupId': 'BG000'}, {'value': '186', 'groupId': 'BG001'}, {'value': '390', 'groupId': 'BG002'}]}, {'title': 'Unknown', 'measurements': [{'value': '1520', 'groupId': 'BG000'}, {'value': '1596', 'groupId': 'BG001'}, {'value': '3116', 'groupId': 'BG002'}]}]}], 'paramType': 'COUNT_OF_PARTICIPANTS', 'unitOfMeasure': 'Participants'}, {'title': 'Discharge', 'classes': [{'denoms': [{'units': 'Participants', 'counts': [{'value': '31432', 'groupId': 'BG000'}, {'value': '33564', 'groupId': 'BG001'}, {'value': '64996', 'groupId': 'BG002'}]}], 'categories': [{'title': 'Home', 'measurements': [{'value': '21176', 'groupId': 'BG000'}, {'value': '23335', 'groupId': 'BG001'}, {'value': '44511', 'groupId': 'BG002'}]}, {'title': 'Home / Home Health', 'measurements': [{'value': '5739', 'groupId': 'BG000'}, {'value': '5528', 'groupId': 'BG001'}, {'value': '11267', 'groupId': 'BG002'}]}, {'title': 'Skilled Nursing Facility / Rehab', 'measurements': [{'value': '2760', 'groupId': 'BG000'}, {'value': '2812', 'groupId': 'BG001'}, {'value': '5572', 'groupId': 'BG002'}]}, {'title': 'Long Term Acute Care', 'measurements': [{'value': '165', 'groupId': 'BG000'}, {'value': '171', 'groupId': 'BG001'}, {'value': '336', 'groupId': 'BG002'}]}, {'title': 'Other Transfer', 'measurements': [{'value': '98', 'groupId': 'BG000'}, {'value': '162', 'groupId': 'BG001'}, {'value': '260', 'groupId': 'BG002'}]}, {'title': 'AMA', 'measurements': [{'value': '412', 'groupId': 'BG000'}, {'value': '385', 'groupId': 'BG001'}, {'value': '797', 'groupId': 'BG002'}]}, {'title': 'Psych', 'measurements': [{'value': '104', 'groupId': 'BG000'}, {'value': '93', 'groupId': 'BG001'}, {'value': '197', 'groupId': 'BG002'}]}, {'title': 'Other / Unknown', 'measurements': [{'value': '50', 'groupId': 'BG000'}, {'value': '74', 'groupId': 'BG001'}, {'value': '124', 'groupId': 'BG002'}]}, {'title': 'Hospice / Expired', 'measurements': [{'value': '928', 'groupId': 'BG000'}, {'value': '1004', 'groupId': 'BG001'}, {'value': '1932', 'groupId': 'BG002'}]}]}], 'paramType': 'COUNT_OF_PARTICIPANTS', 'unitOfMeasure': 'Participants'}]}}, 'documentSection': {'largeDocumentModule': {'largeDocs': [{'date': '2022-04-01', 'size': 561277, 'label': 'Study Protocol and Statistical Analysis Plan', 'hasIcf': False, 'hasSap': True, 'filename': 'Prot_SAP_001.pdf', 'typeAbbrev': 'Prot_SAP', 'uploadDate': '2025-07-22T09:41', 'hasProtocol': True}]}}, 'protocolSection': {'designModule': {'phases': ['NA'], 'studyType': 'INTERVENTIONAL', 'designInfo': {'allocation': 'NA', 'maskingInfo': {'masking': 'NONE', 'maskingDescription': 'No masking as the manual screen is already part of usual care and the automated screen will become usual care in the post-period of the pre-post design.'}, 'primaryPurpose': 'SCREENING', 'interventionModel': 'SEQUENTIAL', 'interventionModelDescription': 'Quasi-experimental design as an interrupted time series'}, 'enrollmentInfo': {'type': 'ACTUAL', 'count': 64996}}, 'statusModule': {'overallStatus': 'COMPLETED', 'startDateStruct': {'date': '2022-09-19', 'type': 'ACTUAL'}, 'expandedAccessInfo': {'hasExpandedAccess': False}, 'statusVerifiedDate': '2025-10', 'completionDateStruct': {'date': '2024-09-19', 'type': 'ACTUAL'}, 'lastUpdateSubmitDate': '2025-10-14', 'studyFirstSubmitDate': '2019-02-06', 'resultsFirstSubmitDate': '2025-09-09', 'studyFirstSubmitQcDate': '2019-02-06', 'lastUpdatePostDateStruct': {'date': '2025-10-24', 'type': 'ESTIMATED'}, 'resultsFirstSubmitQcDate': '2025-10-14', 'studyFirstPostDateStruct': {'date': '2019-02-07', 'type': 'ACTUAL'}, 'resultsFirstPostDateStruct': {'date': '2025-10-24', 'type': 'ESTIMATED'}, 'primaryCompletionDateStruct': {'date': '2024-09-19', 'type': 'ACTUAL'}}, 'outcomesModule': {'primaryOutcomes': [{'measure': 'Proportion of Patients That Had a Universal Screen Positive and Received SBIRT (Screening, Brief Intervention, or Referral to Treatment)', 'timeFrame': '24 months', 'description': '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.'}], 'secondaryOutcomes': [{'measure': 'All-cause Re-hospitalizations Following 6-months From the Index Hospital Encounter', 'timeFrame': '12 months enrollment with 6 months follow-up for rehospitalization', 'description': 'We will compare healthcare utilization outcomes in all patients between pre- and post-periods controlling for all patient demographic and clinical characteristics.'}]}, 'oversightModule': {'oversightHasDmc': True, 'isFdaRegulatedDrug': False, 'isFdaRegulatedDevice': False}, 'conditionsModule': {'keywords': ['natural language processing', 'machine learning', 'artificial intelligence', 'clinical decision support', 'unhealthy alcohol use', 'opioid use disorder', 'illicit drug use'], 'conditions': ['Substance Use', 'Substance Abuse', 'Substance-Related Disorders']}, 'referencesModule': {'references': [{'pmid': '30602031', 'type': 'RESULT', 'citation': '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.'}, {'pmid': '41332823', 'type': 'DERIVED', 'citation': 'Rojas 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.'}, {'pmid': '36534461', 'type': 'DERIVED', 'citation': 'Joyce 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.'}], 'seeAlsoLinks': [{'url': 'https://github.com/', 'label': 'login page but full code not finalized for publishing'}]}, 'descriptionModule': {'briefSummary': '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.', 'detailedDescription': '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.\n\nIn 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\n\nIn 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.\n\nIn 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.\n\nThe 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.'}, 'eligibilityModule': {'sex': 'ALL', 'stdAges': ['ADULT', 'OLDER_ADULT'], 'maximumAge': '89 Years', 'minimumAge': '18 Years', 'healthyVolunteers': False, 'eligibilityCriteria': 'Inclusion Criteria:\n\n* Ages 18 years old to 89 years old\n* Inpatient status during hospitalization\n* Length of stay greater than 24 hours\n\nExclusion Criteria:\n\n* Cannot participate in the usual care SBIRT intervention\n* Death or obtunded during first 24 hours of admission\n* Discharged against medical advice\n* Transferred from another acute care hospital\n* Transferred to another acute care hospital'}, 'identificationModule': {'nctId': 'NCT03833804', 'briefTitle': 'Data-driven Identification for Substance Misuse', 'organization': {'class': 'OTHER', 'fullName': 'University of Wisconsin, Madison'}, 'officialTitle': 'Data-driven Strategies for Substance Misuse Identification in Hospitalized Patients', 'orgStudyIdInfo': {'id': '2022-0983'}, 'secondaryIdInfos': [{'id': 'A534285', 'type': 'OTHER', 'domain': 'UW Madison'}, {'id': 'SMPH/MEDICINE', 'type': 'OTHER', 'domain': 'UW Madison'}, {'id': '1R01DA051464', 'link': 'https://reporter.nih.gov/quickSearch/1R01DA051464', 'type': 'NIH'}]}, 'armsInterventionsModule': {'armGroups': [{'type': 'EXPERIMENTAL', 'label': 'SMART-AI: NLP (natural language processing) pre-screen', 'description': '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.', 'interventionNames': ['Other: Processing of clinical notes in the EHR data collected during routine care']}, {'type': 'NO_INTERVENTION', 'label': 'Usual Care', 'description': 'Data collected before the intervention began'}], 'interventions': [{'name': 'Processing of clinical notes in the EHR data collected during routine care', 'type': 'OTHER', 'description': 'Clinical notes collected in the first day of hospital admission during usual care as input to natural language processing and machine learning algorithm.', 'armGroupLabels': ['SMART-AI: NLP (natural language processing) pre-screen']}]}, 'contactsLocationsModule': {'locations': [{'zip': '60612', 'city': 'Chicago', 'state': 'Illinois', 'country': 'United States', 'facility': 'Rush University Medical Center', 'geoPoint': {'lat': 41.85003, 'lon': -87.65005}}]}, 'ipdSharingStatementModule': {'url': 'http://github.com', 'infoTypes': ['ANALYTIC_CODE'], 'timeFrame': '12 months after completion of study and available for at least five years on github.com', 'ipdSharing': 'YES', 'description': '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.'}, 'sponsorCollaboratorsModule': {'leadSponsor': {'name': 'University of Wisconsin, Madison', 'class': 'OTHER'}, 'collaborators': [{'name': 'Rush University Medical Center', 'class': 'OTHER'}, {'name': 'National Institute on Drug Abuse (NIDA)', 'class': 'NIH'}], 'responsibleParty': {'type': 'SPONSOR'}}}}