Cargando…

A Deep-Learning Model With the Attention Mechanism Could Rigorously Predict Survivals in Neuroblastoma

BACKGROUND: Neuroblastoma is one of the most devastating forms of childhood cancer. Despite large amounts of attempts in precise survival prediction in neuroblastoma, the prediction efficacy remains to be improved. METHODS: Here, we applied a deep-learning (DL) model with the attention mechanism to...

Descripción completa

Detalles Bibliográficos
Autores principales: Feng, Chenzhao, Xiang, Tianyu, Yi, Zixuan, Meng, Xinyao, Chu, Xufeng, Huang, Guiyang, Zhao, Xiang, Chen, Feng, Xiong, Bo, Feng, Jiexiong
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8317851/
https://www.ncbi.nlm.nih.gov/pubmed/34336652
http://dx.doi.org/10.3389/fonc.2021.653863
_version_ 1783730133058715648
author Feng, Chenzhao
Xiang, Tianyu
Yi, Zixuan
Meng, Xinyao
Chu, Xufeng
Huang, Guiyang
Zhao, Xiang
Chen, Feng
Xiong, Bo
Feng, Jiexiong
author_facet Feng, Chenzhao
Xiang, Tianyu
Yi, Zixuan
Meng, Xinyao
Chu, Xufeng
Huang, Guiyang
Zhao, Xiang
Chen, Feng
Xiong, Bo
Feng, Jiexiong
author_sort Feng, Chenzhao
collection PubMed
description BACKGROUND: Neuroblastoma is one of the most devastating forms of childhood cancer. Despite large amounts of attempts in precise survival prediction in neuroblastoma, the prediction efficacy remains to be improved. METHODS: Here, we applied a deep-learning (DL) model with the attention mechanism to predict survivals in neuroblastoma. We utilized 2 groups of features separated from 172 genes, to train 2 deep neural networks and combined them by the attention mechanism. RESULTS: This classifier could accurately predict survivals, with areas under the curve of receiver operating characteristic (ROC) curves and time-dependent ROC reaching 0.968 and 0.974 in the training set respectively. The accuracy of the model was further confirmed in a validation cohort. Importantly, the two feature groups were mapped to two groups of patients, which were prognostic in Kaplan-Meier curves. Biological analyses showed that they exhibited diverse molecular backgrounds which could be linked to the prognosis of the patients. CONCLUSIONS: In this study, we applied artificial intelligence methods to improve the accuracy of neuroblastoma survival prediction based on gene expression and provide explanations for better understanding of the molecular mechanisms underlying neuroblastoma.
format Online
Article
Text
id pubmed-8317851
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-83178512021-07-29 A Deep-Learning Model With the Attention Mechanism Could Rigorously Predict Survivals in Neuroblastoma Feng, Chenzhao Xiang, Tianyu Yi, Zixuan Meng, Xinyao Chu, Xufeng Huang, Guiyang Zhao, Xiang Chen, Feng Xiong, Bo Feng, Jiexiong Front Oncol Oncology BACKGROUND: Neuroblastoma is one of the most devastating forms of childhood cancer. Despite large amounts of attempts in precise survival prediction in neuroblastoma, the prediction efficacy remains to be improved. METHODS: Here, we applied a deep-learning (DL) model with the attention mechanism to predict survivals in neuroblastoma. We utilized 2 groups of features separated from 172 genes, to train 2 deep neural networks and combined them by the attention mechanism. RESULTS: This classifier could accurately predict survivals, with areas under the curve of receiver operating characteristic (ROC) curves and time-dependent ROC reaching 0.968 and 0.974 in the training set respectively. The accuracy of the model was further confirmed in a validation cohort. Importantly, the two feature groups were mapped to two groups of patients, which were prognostic in Kaplan-Meier curves. Biological analyses showed that they exhibited diverse molecular backgrounds which could be linked to the prognosis of the patients. CONCLUSIONS: In this study, we applied artificial intelligence methods to improve the accuracy of neuroblastoma survival prediction based on gene expression and provide explanations for better understanding of the molecular mechanisms underlying neuroblastoma. Frontiers Media S.A. 2021-07-14 /pmc/articles/PMC8317851/ /pubmed/34336652 http://dx.doi.org/10.3389/fonc.2021.653863 Text en Copyright © 2021 Feng, Xiang, Yi, Meng, Chu, Huang, Zhao, Chen, Xiong and Feng https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Oncology
Feng, Chenzhao
Xiang, Tianyu
Yi, Zixuan
Meng, Xinyao
Chu, Xufeng
Huang, Guiyang
Zhao, Xiang
Chen, Feng
Xiong, Bo
Feng, Jiexiong
A Deep-Learning Model With the Attention Mechanism Could Rigorously Predict Survivals in Neuroblastoma
title A Deep-Learning Model With the Attention Mechanism Could Rigorously Predict Survivals in Neuroblastoma
title_full A Deep-Learning Model With the Attention Mechanism Could Rigorously Predict Survivals in Neuroblastoma
title_fullStr A Deep-Learning Model With the Attention Mechanism Could Rigorously Predict Survivals in Neuroblastoma
title_full_unstemmed A Deep-Learning Model With the Attention Mechanism Could Rigorously Predict Survivals in Neuroblastoma
title_short A Deep-Learning Model With the Attention Mechanism Could Rigorously Predict Survivals in Neuroblastoma
title_sort deep-learning model with the attention mechanism could rigorously predict survivals in neuroblastoma
topic Oncology
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8317851/
https://www.ncbi.nlm.nih.gov/pubmed/34336652
http://dx.doi.org/10.3389/fonc.2021.653863
work_keys_str_mv AT fengchenzhao adeeplearningmodelwiththeattentionmechanismcouldrigorouslypredictsurvivalsinneuroblastoma
AT xiangtianyu adeeplearningmodelwiththeattentionmechanismcouldrigorouslypredictsurvivalsinneuroblastoma
AT yizixuan adeeplearningmodelwiththeattentionmechanismcouldrigorouslypredictsurvivalsinneuroblastoma
AT mengxinyao adeeplearningmodelwiththeattentionmechanismcouldrigorouslypredictsurvivalsinneuroblastoma
AT chuxufeng adeeplearningmodelwiththeattentionmechanismcouldrigorouslypredictsurvivalsinneuroblastoma
AT huangguiyang adeeplearningmodelwiththeattentionmechanismcouldrigorouslypredictsurvivalsinneuroblastoma
AT zhaoxiang adeeplearningmodelwiththeattentionmechanismcouldrigorouslypredictsurvivalsinneuroblastoma
AT chenfeng adeeplearningmodelwiththeattentionmechanismcouldrigorouslypredictsurvivalsinneuroblastoma
AT xiongbo adeeplearningmodelwiththeattentionmechanismcouldrigorouslypredictsurvivalsinneuroblastoma
AT fengjiexiong adeeplearningmodelwiththeattentionmechanismcouldrigorouslypredictsurvivalsinneuroblastoma
AT fengchenzhao deeplearningmodelwiththeattentionmechanismcouldrigorouslypredictsurvivalsinneuroblastoma
AT xiangtianyu deeplearningmodelwiththeattentionmechanismcouldrigorouslypredictsurvivalsinneuroblastoma
AT yizixuan deeplearningmodelwiththeattentionmechanismcouldrigorouslypredictsurvivalsinneuroblastoma
AT mengxinyao deeplearningmodelwiththeattentionmechanismcouldrigorouslypredictsurvivalsinneuroblastoma
AT chuxufeng deeplearningmodelwiththeattentionmechanismcouldrigorouslypredictsurvivalsinneuroblastoma
AT huangguiyang deeplearningmodelwiththeattentionmechanismcouldrigorouslypredictsurvivalsinneuroblastoma
AT zhaoxiang deeplearningmodelwiththeattentionmechanismcouldrigorouslypredictsurvivalsinneuroblastoma
AT chenfeng deeplearningmodelwiththeattentionmechanismcouldrigorouslypredictsurvivalsinneuroblastoma
AT xiongbo deeplearningmodelwiththeattentionmechanismcouldrigorouslypredictsurvivalsinneuroblastoma
AT fengjiexiong deeplearningmodelwiththeattentionmechanismcouldrigorouslypredictsurvivalsinneuroblastoma