Incorporating Risk Factor Embeddings in Pre-trained Transformers Improves Sentiment Prediction in Psychiatric Discharge Summaries

Xiyu Ding, Mei-Hua Hall, Timothy Miller


Abstract
Reducing rates of early hospital readmission has been recognized and identified as a key to improve quality of care and reduce costs. There are a number of risk factors that have been hypothesized to be important for understanding re-admission risk, including such factors as problems with substance abuse, ability to maintain work, relations with family. In this work, we develop Roberta-based models to predict the sentiment of sentences describing readmission risk factors in discharge summaries of patients with psychosis. We improve substantially on previous results by a scheme that shares information across risk factors while also allowing the model to learn risk factor-specific information.
Anthology ID:
2020.clinicalnlp-1.4
Volume:
Proceedings of the 3rd Clinical Natural Language Processing Workshop
Month:
November
Year:
2020
Address:
Online
Venues:
ClinicalNLP | EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
35–40
Language:
URL:
https://aclanthology.org/2020.clinicalnlp-1.4
DOI:
10.18653/v1/2020.clinicalnlp-1.4
Bibkey:
Cite (ACL):
Xiyu Ding, Mei-Hua Hall, and Timothy Miller. 2020. Incorporating Risk Factor Embeddings in Pre-trained Transformers Improves Sentiment Prediction in Psychiatric Discharge Summaries. In Proceedings of the 3rd Clinical Natural Language Processing Workshop, pages 35–40, Online. Association for Computational Linguistics.
Cite (Informal):
Incorporating Risk Factor Embeddings in Pre-trained Transformers Improves Sentiment Prediction in Psychiatric Discharge Summaries (Ding et al., ClinicalNLP 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.clinicalnlp-1.4.pdf
Video:
 https://slideslive.com/38939823