Various Approaches for Predicting Stroke Prognosis using Magnetic Resonance Imaging Text Records

Heo, Tak-Sung; Kim, Chul-Ho; Choi, Jeong-Myeong; Jeong, Yeongseok; Kim, Yu-Seop

doi:10.18653/v1/2020.clinicalnlp-1.1

Cited by 4 publications

(1 citation statement)

References 14 publications

(13 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Pandey et al (2020) used a convolutional neural network to extract findings from radiology reports of heart failure patients and predict all-cause mortality with CPH. Heo et al (2020) performed stroke prognosis based on the document-level and sentence-level representations of MRI records. Our work extends this line of research by using contextual deep representations of clinical texts to perform survival analysis.…”

Section: Related Workmentioning

confidence: 99%

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

Lee¹,

Sholle²,

Beecy³

et al. 2021

Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

View full text Add to dashboard Cite

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.

show abstract

Section: Related Workmentioning

confidence: 99%