Data-driven Identification for Substance Misuse

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.

Study Overview

• Status: Recruiting
• Conditions: Substance-Related Disorders; Substance Use; Substance Abuse
• Intervention / Treatment: Other: Processing of clinical notes in the EHR data collected during routine care

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 Type: Interventional
• Enrollment (Estimated): 34800
• Phase: Not Applicable

Contacts and Locations

• Study Contact: Name: Majid Afshar, MD; Phone Number: 3125459462; Email: majid.afshar@wisc.edu

Study Locations

• United States
  • Illinois
    • Chicago, Illinois, United States, 60612
      • Recruiting
      • Rush University Medical Center
      • Contact: Ali Keshavarzian; Email: ali_keshavarzian@rush.edu
      • Contact: Jenna Nikolaides; Email: jenna_nikolaides@rush.edu

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: 18 years to 89 years (Adult, Older Adult)
• Accepts Healthy Volunteers: No

Description

Inclusion Criteria:

• Ages 18 years old to 89 years old
• Inpatient status during hospitalization
• Length of stay greater than 24 hours

Exclusion Criteria:

• 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

Study Plan

How is the study designed?

Design Details

• Primary Purpose: Screening
• Allocation: N/A
• Interventional Model: Single Group Assignment
• Masking: None (Open Label)

Number of Arms

1

Arms and Interventions

Participant Group / Arm	Intervention / Treatment
Experimental: NLP (natural language processing) pre-screen; 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.	Other: Processing 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.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
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.	54 months

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
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.	12 months enrollment with 6 months follow-up for rehospitalization

Collaborators and Investigators

• Sponsor: University of Wisconsin, Madison
• Collaborators: Rush University Medical Center

Publications and helpful links

General 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.

Helpful Links

• login page but full code not finalized for publishing

Study record dates

Study Major Dates

• Study Start (Actual): February 1, 2023
• Primary Completion (Estimated): January 30, 2025
• Study Completion (Estimated): March 30, 2025

Study Registration Dates

• First Submitted: February 6, 2019
• First Submitted That Met QC Criteria: February 6, 2019
• First Posted (Actual): February 7, 2019

Study Record Updates

• Last Update Posted (Estimated): January 25, 2024
• Last Update Submitted That Met QC Criteria: January 23, 2024
• Last Verified: January 1, 2024

More Information

Terms related to this study

• Keywords: machine learning; artificial intelligence; opioid use disorder; clinical decision support; natural language processing; unhealthy alcohol use; illicit drug use
• Additional Relevant MeSH Terms: Mental Disorders; Chemically-Induced Disorders; Substance-Related Disorders
• Other Study ID Numbers: 2021-0509; A534285 (Other Identifier: UW Madison); SMPH/MEDICINE (Other Identifier: UW Madison)

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: YES
• IPD Plan 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.
• IPD Sharing Time Frame: 12 months after completion of study and available for at least five years on github.com
• IPD Sharing Supporting Information Type: ANALYTIC_CODE

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No