124 306

Cited 2 times in

Deep-Learning-Based Natural Language Processing of Serial Free-Text Radiological Reports for Predicting Rectal Cancer Patient Survival

Authors
 Sunkyu Kim  ;  Choong-Kun Lee  ;  Yonghwa Choi  ;  Eun Sil Baek  ;  Jeong Eun Choi  ;  Joon Seok Lim  ;  Jaewoo Kang  ;  Sang Joon Shin 
Citation
 FRONTIERS IN ONCOLOGY, Vol.11 : 747250, 2021-11 
Journal Title
FRONTIERS IN ONCOLOGY
Issue Date
2021-11
Keywords
MRI ; deep learning ; natural language processing (NLP) ; rectal cancer ; survival prediction
Abstract
Most electronic medical records, such as free-text radiological reports, are unstructured; however, the methodological approaches to analyzing these accumulating unstructured records are limited. This article proposes a deep-transfer-learning-based natural language processing model that analyzes serial magnetic resonance imaging reports of rectal cancer patients and predicts their overall survival. To evaluate the model, a retrospective cohort study of 4,338 rectal cancer patients was conducted. The experimental results revealed that the proposed model utilizing pre-trained clinical linguistic knowledge could predict the overall survival of patients without any structured information and was superior to the carcinoembryonic antigen in predicting survival. The deep-transfer-learning model using free-text radiological reports can predict the survival of patients with rectal cancer, thereby increasing the utility of unstructured medical big data.
Files in This Item:
T202125776.pdf Download
DOI
10.3389/fonc.2021.747250
Appears in Collections:
1. College of Medicine (의과대학) > Dept. of Internal Medicine (내과학교실) > 1. Journal Papers
1. College of Medicine (의과대학) > Dept. of Radiology (영상의학교실) > 1. Journal Papers
Yonsei Authors
Shin, Sang Joon(신상준) ORCID logo https://orcid.org/0000-0001-5350-7241
Lee, Choong-kun(이충근) ORCID logo https://orcid.org/0000-0001-5151-5096
Lim, Joon Seok(임준석) ORCID logo https://orcid.org/0000-0002-0334-5042
URI
https://ir.ymlib.yonsei.ac.kr/handle/22282913/188179
사서에게 알리기
  feedback

qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Browse

Links