Outcomes and Cost-Effectiveness of an EHR-Embedded AI Screener for Identifying Hospitalized Adults at Risk for Opioid Use Disorder

Majid Afshar; Felice Resnik; Cara Joyce; Madeline Oguss; Dmitriy Dligach; Elizabeth Burnside; Anne Sullivan; Matthew Churpek; Brian Patterson; Elizabeth Salisbury-Afshar; Frank Liao; Randall Brown; Marlon Mundt

doi:10.21203/rs.3.rs-5200964/v1

Outcomes and Cost-Effectiveness of an EHR-Embedded AI Screener for Identifying Hospitalized Adults at Risk for Opioid Use Disorder

Majid Afshar, Felice Resnik, Cara Joyce, Madeline Oguss, Dmitriy Dligach, Elizabeth Burnside, Anne Sullivan, Matthew Churpek, Brian Patterson, Elizabeth Salisbury-Afshar, Frank Liao, Randall Brown, Marlon Mundt

Research output: Contribution to journal › Article › peer-review

Abstract

UNLABELLED: Hospitalized adults with opioid use disorder (OUD) are at high risk for adverse events and rehospitalizations. This pre-post quasi-experimental study evaluated whether an AI-driven OUD screener embedded in the electronic health record (EHR) was non-inferior to usual care in identifying patients for Addiction Medicine consults, aiming to provide a similarly effective but more scalable alternative to human-led ad hoc consultations. The AI screener analyzed EHR notes in real-time with a convolutional neural network to identify patients at risk and recommend consultation. The primary outcome was the proportion of patients receiving consults, comparing a 16-month pre-intervention period to an 8-month post-intervention period with the AI screener. Consults did not change between periods (1.35% vs 1.51%, p < 0.001 for non-inferiority). The AI screener was associated with a reduction in 30-day readmissions (OR: 0.53, 95% CI: 0.30-0.91, p = 0.02) with an incremental cost of $6,801 per readmission avoided, demonstrating its potential as a scalable, cost-effective solution for OUD care.

CLINICALTRIALSGOV ID: NCT05745480.

Original language	English
Journal	Research square
DOIs	https://doi.org/10.21203/rs.3.rs-5200964/v1
State	Published - Sep 14 2024

Access to Document

10.21203/rs.3.rs-5200964/v1

Cite this

Afshar, M., Resnik, F., Joyce, C., Oguss, M., Dligach, D., Burnside, E., Sullivan, A., Churpek, M., Patterson, B., Salisbury-Afshar, E., Liao, F., Brown, R., & Mundt, M. (2024). Outcomes and Cost-Effectiveness of an EHR-Embedded AI Screener for Identifying Hospitalized Adults at Risk for Opioid Use Disorder. Research square. https://doi.org/10.21203/rs.3.rs-5200964/v1

@article{17dbaa1780dc4af58cbc4917561c0214,

title = "Outcomes and Cost-Effectiveness of an EHR-Embedded AI Screener for Identifying Hospitalized Adults at Risk for Opioid Use Disorder",

abstract = "UNLABELLED: Hospitalized adults with opioid use disorder (OUD) are at high risk for adverse events and rehospitalizations. This pre-post quasi-experimental study evaluated whether an AI-driven OUD screener embedded in the electronic health record (EHR) was non-inferior to usual care in identifying patients for Addiction Medicine consults, aiming to provide a similarly effective but more scalable alternative to human-led ad hoc consultations. The AI screener analyzed EHR notes in real-time with a convolutional neural network to identify patients at risk and recommend consultation. The primary outcome was the proportion of patients receiving consults, comparing a 16-month pre-intervention period to an 8-month post-intervention period with the AI screener. Consults did not change between periods (1.35\% vs 1.51\%, p < 0.001 for non-inferiority). The AI screener was associated with a reduction in 30-day readmissions (OR: 0.53, 95\% CI: 0.30-0.91, p = 0.02) with an incremental cost of \$6,801 per readmission avoided, demonstrating its potential as a scalable, cost-effective solution for OUD care.CLINICALTRIALSGOV ID: NCT05745480.",

author = "Majid Afshar and Felice Resnik and Cara Joyce and Madeline Oguss and Dmitriy Dligach and Elizabeth Burnside and Anne Sullivan and Matthew Churpek and Brian Patterson and Elizabeth Salisbury-Afshar and Frank Liao and Randall Brown and Marlon Mundt",

year = "2024",

month = sep,

day = "14",

doi = "10.21203/rs.3.rs-5200964/v1",

language = "English",

journal = "Research square",

issn = "2693-5015",

}

TY - JOUR

T1 - Outcomes and Cost-Effectiveness of an EHR-Embedded AI Screener for Identifying Hospitalized Adults at Risk for Opioid Use Disorder

AU - Afshar, Majid

AU - Resnik, Felice

AU - Joyce, Cara

AU - Oguss, Madeline

AU - Dligach, Dmitriy

AU - Burnside, Elizabeth

AU - Sullivan, Anne

AU - Churpek, Matthew

AU - Patterson, Brian

AU - Salisbury-Afshar, Elizabeth

AU - Liao, Frank

AU - Brown, Randall

AU - Mundt, Marlon

PY - 2024/9/14

Y1 - 2024/9/14

N2 - UNLABELLED: Hospitalized adults with opioid use disorder (OUD) are at high risk for adverse events and rehospitalizations. This pre-post quasi-experimental study evaluated whether an AI-driven OUD screener embedded in the electronic health record (EHR) was non-inferior to usual care in identifying patients for Addiction Medicine consults, aiming to provide a similarly effective but more scalable alternative to human-led ad hoc consultations. The AI screener analyzed EHR notes in real-time with a convolutional neural network to identify patients at risk and recommend consultation. The primary outcome was the proportion of patients receiving consults, comparing a 16-month pre-intervention period to an 8-month post-intervention period with the AI screener. Consults did not change between periods (1.35% vs 1.51%, p < 0.001 for non-inferiority). The AI screener was associated with a reduction in 30-day readmissions (OR: 0.53, 95% CI: 0.30-0.91, p = 0.02) with an incremental cost of $6,801 per readmission avoided, demonstrating its potential as a scalable, cost-effective solution for OUD care.CLINICALTRIALSGOV ID: NCT05745480.

AB - UNLABELLED: Hospitalized adults with opioid use disorder (OUD) are at high risk for adverse events and rehospitalizations. This pre-post quasi-experimental study evaluated whether an AI-driven OUD screener embedded in the electronic health record (EHR) was non-inferior to usual care in identifying patients for Addiction Medicine consults, aiming to provide a similarly effective but more scalable alternative to human-led ad hoc consultations. The AI screener analyzed EHR notes in real-time with a convolutional neural network to identify patients at risk and recommend consultation. The primary outcome was the proportion of patients receiving consults, comparing a 16-month pre-intervention period to an 8-month post-intervention period with the AI screener. Consults did not change between periods (1.35% vs 1.51%, p < 0.001 for non-inferiority). The AI screener was associated with a reduction in 30-day readmissions (OR: 0.53, 95% CI: 0.30-0.91, p = 0.02) with an incremental cost of $6,801 per readmission avoided, demonstrating its potential as a scalable, cost-effective solution for OUD care.CLINICALTRIALSGOV ID: NCT05745480.

U2 - 10.21203/rs.3.rs-5200964/v1

DO - 10.21203/rs.3.rs-5200964/v1

M3 - Article

C2 - 39483915

SN - 2693-5015

JO - Research square

JF - Research square

ER -