Nothing Special   »   [go: up one dir, main page]

Leveraging Deep Representations of Radiology Reports in Survival Analysis for Predicting Heart Failure Patient Mortality

Hyun Gi Lee, Evan Sholle, Ashley Beecy, Subhi Al’Aref, Yifan Peng


Abstract
Utilizing clinical texts in survival analysis is difficult because they are largely unstructured. Current automatic extraction models fail to capture textual information comprehensively since their labels are limited in scope. Furthermore, they typically require a large amount of data and high-quality expert annotations for training. In this work, we present a novel method of using BERT-based hidden layer representations of clinical texts as covariates for proportional hazards models to predict patient survival outcomes. We show that hidden layers yield notably more accurate predictions than predefined features, outperforming the previous baseline model by 5.7% on average across C-index and time-dependent AUC. We make our work publicly available at https://github.com/bionlplab/heart_failure_mortality.
Anthology ID:
2021.naacl-main.358
Volume:
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
June
Year:
2021
Address:
Online
Editors:
Kristina Toutanova, Anna Rumshisky, Luke Zettlemoyer, Dilek Hakkani-Tur, Iz Beltagy, Steven Bethard, Ryan Cotterell, Tanmoy Chakraborty, Yichao Zhou
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4533–4538
Language:
URL:
https://aclanthology.org/2021.naacl-main.358
DOI:
10.18653/v1/2021.naacl-main.358
Bibkey:
Cite (ACL):
Hyun Gi Lee, Evan Sholle, Ashley Beecy, Subhi Al’Aref, and Yifan Peng. 2021. Leveraging Deep Representations of Radiology Reports in Survival Analysis for Predicting Heart Failure Patient Mortality. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 4533–4538, Online. Association for Computational Linguistics.
Cite (Informal):
Leveraging Deep Representations of Radiology Reports in Survival Analysis for Predicting Heart Failure Patient Mortality (Lee et al., NAACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.naacl-main.358.pdf
Video:
 https://aclanthology.org/2021.naacl-main.358.mp4
Code
 bionlplab/heart_failure_mortality
Data
BLUECheXpert