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

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 ser...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Sunkyu Kim, Choong-kun Lee, Yonghwa Choi, Eun Sil Baek, Jeong Eun Choi, Joon Seok Lim, Jaewoo Kang, Sang Joon Shin
Formato:	article
Lenguaje:	EN
Publicado:	Frontiers Media S.A. 2021
Materias:	rectal cancer MRI deep learning survival prediction natural language processing (NLP) Neoplasms. Tumors. Oncology. Including cancer and carcinogens RC254-282
Acceso en línea:	https://doaj.org/article/580e429283964cb4bcd085c2ffc223f1
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:580e429283964cb4bcd085c2ffc223f1
record_format	dspace
spelling	oai:doaj.org-article:580e429283964cb4bcd085c2ffc223f12021-11-17T05:51:39ZDeep-Learning-Based Natural Language Processing of Serial Free-Text Radiological Reports for Predicting Rectal Cancer Patient Survival2234-943X10.3389/fonc.2021.747250https://doaj.org/article/580e429283964cb4bcd085c2ffc223f12021-11-01T00:00:00Zhttps://www.frontiersin.org/articles/10.3389/fonc.2021.747250/fullhttps://doaj.org/toc/2234-943XMost 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.Sunkyu KimChoong-kun LeeChoong-kun LeeYonghwa ChoiEun Sil BaekJeong Eun ChoiJoon Seok LimJaewoo KangSang Joon ShinSang Joon ShinFrontiers Media S.A.articlerectal cancerMRIdeep learningsurvival predictionnatural language processing (NLP)Neoplasms. Tumors. Oncology. Including cancer and carcinogensRC254-282ENFrontiers in Oncology, Vol 11 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	rectal cancer MRI deep learning survival prediction natural language processing (NLP) Neoplasms. Tumors. Oncology. Including cancer and carcinogens RC254-282
spellingShingle	rectal cancer MRI deep learning survival prediction natural language processing (NLP) Neoplasms. Tumors. Oncology. Including cancer and carcinogens RC254-282 Sunkyu Kim Choong-kun Lee Choong-kun Lee Yonghwa Choi Eun Sil Baek Jeong Eun Choi Joon Seok Lim Jaewoo Kang Sang Joon Shin Sang Joon Shin Deep-Learning-Based Natural Language Processing of Serial Free-Text Radiological Reports for Predicting Rectal Cancer Patient Survival
description	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.
format	article
author	Sunkyu Kim Choong-kun Lee Choong-kun Lee Yonghwa Choi Eun Sil Baek Jeong Eun Choi Joon Seok Lim Jaewoo Kang Sang Joon Shin Sang Joon Shin
author_facet	Sunkyu Kim Choong-kun Lee Choong-kun Lee Yonghwa Choi Eun Sil Baek Jeong Eun Choi Joon Seok Lim Jaewoo Kang Sang Joon Shin Sang Joon Shin
author_sort	Sunkyu Kim
title	Deep-Learning-Based Natural Language Processing of Serial Free-Text Radiological Reports for Predicting Rectal Cancer Patient Survival
title_short	Deep-Learning-Based Natural Language Processing of Serial Free-Text Radiological Reports for Predicting Rectal Cancer Patient Survival
title_full	Deep-Learning-Based Natural Language Processing of Serial Free-Text Radiological Reports for Predicting Rectal Cancer Patient Survival
title_fullStr	Deep-Learning-Based Natural Language Processing of Serial Free-Text Radiological Reports for Predicting Rectal Cancer Patient Survival
title_full_unstemmed	Deep-Learning-Based Natural Language Processing of Serial Free-Text Radiological Reports for Predicting Rectal Cancer Patient Survival
title_sort	deep-learning-based natural language processing of serial free-text radiological reports for predicting rectal cancer patient survival
publisher	Frontiers Media S.A.
publishDate	2021
url	https://doaj.org/article/580e429283964cb4bcd085c2ffc223f1
work_keys_str_mv	AT sunkyukim deeplearningbasednaturallanguageprocessingofserialfreetextradiologicalreportsforpredictingrectalcancerpatientsurvival AT choongkunlee deeplearningbasednaturallanguageprocessingofserialfreetextradiologicalreportsforpredictingrectalcancerpatientsurvival AT choongkunlee deeplearningbasednaturallanguageprocessingofserialfreetextradiologicalreportsforpredictingrectalcancerpatientsurvival AT yonghwachoi deeplearningbasednaturallanguageprocessingofserialfreetextradiologicalreportsforpredictingrectalcancerpatientsurvival AT eunsilbaek deeplearningbasednaturallanguageprocessingofserialfreetextradiologicalreportsforpredictingrectalcancerpatientsurvival AT jeongeunchoi deeplearningbasednaturallanguageprocessingofserialfreetextradiologicalreportsforpredictingrectalcancerpatientsurvival AT joonseoklim deeplearningbasednaturallanguageprocessingofserialfreetextradiologicalreportsforpredictingrectalcancerpatientsurvival AT jaewookang deeplearningbasednaturallanguageprocessingofserialfreetextradiologicalreportsforpredictingrectalcancerpatientsurvival AT sangjoonshin deeplearningbasednaturallanguageprocessingofserialfreetextradiologicalreportsforpredictingrectalcancerpatientsurvival AT sangjoonshin deeplearningbasednaturallanguageprocessingofserialfreetextradiologicalreportsforpredictingrectalcancerpatientsurvival
_version_	1718425858865102848

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

Ejemplares similares