Backdoor Adjustment of Confounding by Provenance for Robust Text Classification of Multi-institutional Clinical Notes.
AMIA Annu Symp Proc
; 2023: 923-932, 2023.
Article
in En
| MEDLINE
| ID: mdl-38222433
ABSTRACT
Natural Language Processing (NLP) methods have been broadly applied to clinical tasks. Machine learning and deep learning approaches have been used to improve the performance of clinical NLP. However, these approaches require sufficiently large datasets for training, and trained models have been shown to transfer poorly across sites. These issues have led to the promotion of data collection and integration across different institutions for accurate and portable models. However, this can introduce a form of bias called confounding by provenance. When source-specific data distributions differ at deployment, this may harm model performance. To address this issue, we evaluate the utility of backdoor adjustment for text classification in a multi-site dataset of clinical notes annotated for mentions of substance abuse. Using an evaluation framework devised to measure robustness to distributional shifts, we assess the utility of backdoor adjustment. Our results indicate that backdoor adjustment can effectively mitigate for confounding shift.
Full text:
1
Collection:
01-internacional
Database:
MEDLINE
Main subject:
Substance-Related Disorders
/
Electronic Health Records
Type of study:
Clinical_trials
/
Prognostic_studies
Limits:
Humans
Language:
En
Journal:
AMIA Annu Symp Proc
Journal subject:
INFORMATICA MEDICA
Year:
2023
Document type:
Article
Affiliation country:
Country of publication: