2022
DOI: 10.1111/ajt.17059
|View full text |Cite
|
Sign up to set email alerts
|

Artificial intelligence to identify harmful alcohol use after early liver transplant for alcohol-associated hepatitis

Abstract: Early liver transplantation (LT) for alcohol-associated hepatitis (AH) is the fastest growing indication for LT, but prediction of harmful alcohol use post-LT remains limited. Among 10 ACCELERATE-AH centers, we examined psychosocial evaluations from consecutive LT recipients for AH from 2006 to 2017. A multidisciplinary panel used content analysis to develop a maximal list of psychosocial variables. We developed an artificial intelligence model to predict post-LT harmful alcohol use. The cohort included traini… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1

Citation Types

0
17
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
9

Relationship

0
9

Authors

Journals

citations
Cited by 16 publications
(17 citation statements)
references
References 24 publications
0
17
0
Order By: Relevance
“…This was surprising given that prior literature has found numerous psychosocial factors to be associated with alcohol use in the post-liver transplant population. 16 A possible explanation could be that some prior studies were based on self-reported alcohol use, and perhaps there are certain factors associated with whether a person is willing to self-report alcohol use in certain settings, but not many factors associated with actual alcohol use when an objective tool such as PEth is used to identify recent alcohol intake. 17 follow-up appointments and readmission rates.…”
Section: Discussionmentioning
confidence: 99%
“…This was surprising given that prior literature has found numerous psychosocial factors to be associated with alcohol use in the post-liver transplant population. 16 A possible explanation could be that some prior studies were based on self-reported alcohol use, and perhaps there are certain factors associated with whether a person is willing to self-report alcohol use in certain settings, but not many factors associated with actual alcohol use when an objective tool such as PEth is used to identify recent alcohol intake. 17 follow-up appointments and readmission rates.…”
Section: Discussionmentioning
confidence: 99%
“…Lee et al [ 152 ] developed an artificial intelligence model to predict post-LT harmful alcohol consumption in patients who underwent early liver transplant for alcohol associated hepatitis, using variables generated through content analysis: These variables included the identification of a primary support person, the presence of young children or grandchildren living with the patient, being a home caregiver for children or elderly relatives, opioid abuse, and being religious; this model could predict harmful alcohol consumption in the external validation set with a positive predictive value of 0.82 (95%CI: 0.625–1.000) and a negative predictive value of 0.81 (95%CI: 0.803–0.819), with and AUC of 0.69, indicating potential for AI to assist in the discovery of novel predictors of post-LT hazardous alcohol use, which may be used as a tool to tailor therapies for alcohol use disorder based on a projected likelihood of relapse.…”
Section: Disease Recurrencementioning
confidence: 99%
“…Several scoring systems have also been developed to better risk-stratify patients with ALD with regards to posttransplant alcohol use in addition to psychosocial assessments for transplant and traditional screening tools for AUD (Table 2) [32,52,55,56 ▪ ,68–71,72 ▪ ,73 ▪ ,74–79]. A recent retrospective case–control study found that patients who underwent early liver transplantation compared with controls declined secondary to low insight into AUD had significantly more favorable Michigan Alcoholism Prognostic Scale (MAPS), High-Risk Alcoholism Relapse (HRAR), Stanford Integrated Psychosocial Assessment for Transplantation (SIPAT), Alcohol Relapse Risk Assessment (ARRA), and Hopkins Psychosocial Scale (HPSS) scores, but Sustained Alcohol Use Post-LT (SALT) and Alcohol Use Disorders Identification Test (AUDIT-C) scores were not predictive [72 ▪ ].…”
Section: Alcohol Use Disordermentioning
confidence: 99%
“…71,72 Liver transplantation for alcoholic hepatitis Durkin and Bittermann 1087-2418 Copyright © 2022 Wolters Kluwer Health, Inc. All rights reserved.…”
mentioning
confidence: 99%