Cargando…

Deep learning survival model for colorectal cancer patients (DeepCRC) with Asian clinical data compared with different theories

INTRODUCTION: Colorectal cancer (CRC) is the third most common cancer. Precise prediction of CRC patients’ overall survival (OS) probability could offer advice on its treatment. Neural network (NN) is the first-class algorithm, but a consensus on which NN survival models are better has not been esta...

Descripción completa

Detalles Bibliográficos
Autores principales: Li, Wei, Lin, Shuye, He, Yuqi, Wang, Jinghui, Pan, Yuanming
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Termedia Publishing House 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9897076/
https://www.ncbi.nlm.nih.gov/pubmed/36817685
http://dx.doi.org/10.5114/aoms/156477
_version_ 1784882177698168832
author Li, Wei
Lin, Shuye
He, Yuqi
Wang, Jinghui
Pan, Yuanming
author_facet Li, Wei
Lin, Shuye
He, Yuqi
Wang, Jinghui
Pan, Yuanming
author_sort Li, Wei
collection PubMed
description INTRODUCTION: Colorectal cancer (CRC) is the third most common cancer. Precise prediction of CRC patients’ overall survival (OS) probability could offer advice on its treatment. Neural network (NN) is the first-class algorithm, but a consensus on which NN survival models are better has not been established yet. A predictive model on CRC using Asian data is also lacking. METHODS: We conducted 8 NN survival models of CRC (n = 416) with different theories and compared them using Asian data. RESULTS: DeepSurv performed best with a C-index value of 0.8300 in the training cohort and 0.7681 in the test cohort. CONCLUSIONS: The deep learning survival model for CRC patients (DeepCRC) could predict CRC’s OS accurately.
format Online
Article
Text
id pubmed-9897076
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Termedia Publishing House
record_format MEDLINE/PubMed
spelling pubmed-98970762023-02-16 Deep learning survival model for colorectal cancer patients (DeepCRC) with Asian clinical data compared with different theories Li, Wei Lin, Shuye He, Yuqi Wang, Jinghui Pan, Yuanming Arch Med Sci Research Letter INTRODUCTION: Colorectal cancer (CRC) is the third most common cancer. Precise prediction of CRC patients’ overall survival (OS) probability could offer advice on its treatment. Neural network (NN) is the first-class algorithm, but a consensus on which NN survival models are better has not been established yet. A predictive model on CRC using Asian data is also lacking. METHODS: We conducted 8 NN survival models of CRC (n = 416) with different theories and compared them using Asian data. RESULTS: DeepSurv performed best with a C-index value of 0.8300 in the training cohort and 0.7681 in the test cohort. CONCLUSIONS: The deep learning survival model for CRC patients (DeepCRC) could predict CRC’s OS accurately. Termedia Publishing House 2023-01-13 /pmc/articles/PMC9897076/ /pubmed/36817685 http://dx.doi.org/10.5114/aoms/156477 Text en Copyright: © 2022 Termedia & Banach https://creativecommons.org/licenses/by-nc-sa/4.0/This is an Open Access article distributed under the terms of the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0) License, allowing third parties to copy and redistribute the material in any medium or format and to remix, transform, and build upon the material, provided the original work is properly cited and states its license.
spellingShingle Research Letter
Li, Wei
Lin, Shuye
He, Yuqi
Wang, Jinghui
Pan, Yuanming
Deep learning survival model for colorectal cancer patients (DeepCRC) with Asian clinical data compared with different theories
title Deep learning survival model for colorectal cancer patients (DeepCRC) with Asian clinical data compared with different theories
title_full Deep learning survival model for colorectal cancer patients (DeepCRC) with Asian clinical data compared with different theories
title_fullStr Deep learning survival model for colorectal cancer patients (DeepCRC) with Asian clinical data compared with different theories
title_full_unstemmed Deep learning survival model for colorectal cancer patients (DeepCRC) with Asian clinical data compared with different theories
title_short Deep learning survival model for colorectal cancer patients (DeepCRC) with Asian clinical data compared with different theories
title_sort deep learning survival model for colorectal cancer patients (deepcrc) with asian clinical data compared with different theories
topic Research Letter
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9897076/
https://www.ncbi.nlm.nih.gov/pubmed/36817685
http://dx.doi.org/10.5114/aoms/156477
work_keys_str_mv AT liwei deeplearningsurvivalmodelforcolorectalcancerpatientsdeepcrcwithasianclinicaldatacomparedwithdifferenttheories
AT linshuye deeplearningsurvivalmodelforcolorectalcancerpatientsdeepcrcwithasianclinicaldatacomparedwithdifferenttheories
AT heyuqi deeplearningsurvivalmodelforcolorectalcancerpatientsdeepcrcwithasianclinicaldatacomparedwithdifferenttheories
AT wangjinghui deeplearningsurvivalmodelforcolorectalcancerpatientsdeepcrcwithasianclinicaldatacomparedwithdifferenttheories
AT panyuanming deeplearningsurvivalmodelforcolorectalcancerpatientsdeepcrcwithasianclinicaldatacomparedwithdifferenttheories