Cargando…

A hybrid CNN-RNN approach for survival analysis in a Lung Cancer Screening study

In this study, we present a hybrid CNN-RNN approach to investigate long-term survival of subjects in a lung cancer screening study. Subjects who died of cardiovascular and respiratory causes were identified whereby the CNN model was used to capture imaging features in the CT scans and the RNN model...

Descripción completa

Detalles Bibliográficos
Autores principales: Lu, Yaozhi, Aslani, Shahab, Zhao, An, Shahin, Ahmed, Barber, David, Emberton, Mark, Alexander, Daniel C., Jacob, Joseph
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Elsevier 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10432611/
https://www.ncbi.nlm.nih.gov/pubmed/37600411
http://dx.doi.org/10.1016/j.heliyon.2023.e18695
_version_ 1785091460295557120
author Lu, Yaozhi
Aslani, Shahab
Zhao, An
Shahin, Ahmed
Barber, David
Emberton, Mark
Alexander, Daniel C.
Jacob, Joseph
author_facet Lu, Yaozhi
Aslani, Shahab
Zhao, An
Shahin, Ahmed
Barber, David
Emberton, Mark
Alexander, Daniel C.
Jacob, Joseph
author_sort Lu, Yaozhi
collection PubMed
description In this study, we present a hybrid CNN-RNN approach to investigate long-term survival of subjects in a lung cancer screening study. Subjects who died of cardiovascular and respiratory causes were identified whereby the CNN model was used to capture imaging features in the CT scans and the RNN model was used to investigate time series and thus global information. To account for heterogeneity in patients' follow-up times, two different variants of LSTM models were evaluated, each incorporating different strategies to address irregularities in follow-up time. The models were trained on subjects who underwent cardiovascular and respiratory deaths and a control cohort matched to participant age, gender, and smoking history. The combined model can achieve an AUC of 0.76 which outperforms humans at cardiovascular mortality prediction. The corresponding F1 and Matthews Correlation Coefficient are 0.63 and 0.42 respectively. The generalisability of the model is further validated on an ‘external’ cohort. The same models were applied to survival analysis with the Cox Proportional Hazard model. It was demonstrated that incorporating the follow-up history can lead to improvement in survival prediction. The Cox neural network can achieve an IPCW C-index of 0.75 on the internal dataset and 0.69 on an external dataset. Delineating subjects at increased risk of cardiorespiratory mortality can alert clinicians to request further more detailed functional or imaging studies to improve the assessment of cardiorespiratory disease burden. Such strategies may uncover unsuspected and under-recognised pathologies thereby potentially reducing patient morbidity.
format Online
Article
Text
id pubmed-10432611
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Elsevier
record_format MEDLINE/PubMed
spelling pubmed-104326112023-08-18 A hybrid CNN-RNN approach for survival analysis in a Lung Cancer Screening study Lu, Yaozhi Aslani, Shahab Zhao, An Shahin, Ahmed Barber, David Emberton, Mark Alexander, Daniel C. Jacob, Joseph Heliyon Research Article In this study, we present a hybrid CNN-RNN approach to investigate long-term survival of subjects in a lung cancer screening study. Subjects who died of cardiovascular and respiratory causes were identified whereby the CNN model was used to capture imaging features in the CT scans and the RNN model was used to investigate time series and thus global information. To account for heterogeneity in patients' follow-up times, two different variants of LSTM models were evaluated, each incorporating different strategies to address irregularities in follow-up time. The models were trained on subjects who underwent cardiovascular and respiratory deaths and a control cohort matched to participant age, gender, and smoking history. The combined model can achieve an AUC of 0.76 which outperforms humans at cardiovascular mortality prediction. The corresponding F1 and Matthews Correlation Coefficient are 0.63 and 0.42 respectively. The generalisability of the model is further validated on an ‘external’ cohort. The same models were applied to survival analysis with the Cox Proportional Hazard model. It was demonstrated that incorporating the follow-up history can lead to improvement in survival prediction. The Cox neural network can achieve an IPCW C-index of 0.75 on the internal dataset and 0.69 on an external dataset. Delineating subjects at increased risk of cardiorespiratory mortality can alert clinicians to request further more detailed functional or imaging studies to improve the assessment of cardiorespiratory disease burden. Such strategies may uncover unsuspected and under-recognised pathologies thereby potentially reducing patient morbidity. Elsevier 2023-08-03 /pmc/articles/PMC10432611/ /pubmed/37600411 http://dx.doi.org/10.1016/j.heliyon.2023.e18695 Text en © 2023 The Author(s) https://creativecommons.org/licenses/by/4.0/This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Research Article
Lu, Yaozhi
Aslani, Shahab
Zhao, An
Shahin, Ahmed
Barber, David
Emberton, Mark
Alexander, Daniel C.
Jacob, Joseph
A hybrid CNN-RNN approach for survival analysis in a Lung Cancer Screening study
title A hybrid CNN-RNN approach for survival analysis in a Lung Cancer Screening study
title_full A hybrid CNN-RNN approach for survival analysis in a Lung Cancer Screening study
title_fullStr A hybrid CNN-RNN approach for survival analysis in a Lung Cancer Screening study
title_full_unstemmed A hybrid CNN-RNN approach for survival analysis in a Lung Cancer Screening study
title_short A hybrid CNN-RNN approach for survival analysis in a Lung Cancer Screening study
title_sort hybrid cnn-rnn approach for survival analysis in a lung cancer screening study
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10432611/
https://www.ncbi.nlm.nih.gov/pubmed/37600411
http://dx.doi.org/10.1016/j.heliyon.2023.e18695
work_keys_str_mv AT luyaozhi ahybridcnnrnnapproachforsurvivalanalysisinalungcancerscreeningstudy
AT aslanishahab ahybridcnnrnnapproachforsurvivalanalysisinalungcancerscreeningstudy
AT zhaoan ahybridcnnrnnapproachforsurvivalanalysisinalungcancerscreeningstudy
AT shahinahmed ahybridcnnrnnapproachforsurvivalanalysisinalungcancerscreeningstudy
AT barberdavid ahybridcnnrnnapproachforsurvivalanalysisinalungcancerscreeningstudy
AT embertonmark ahybridcnnrnnapproachforsurvivalanalysisinalungcancerscreeningstudy
AT alexanderdanielc ahybridcnnrnnapproachforsurvivalanalysisinalungcancerscreeningstudy
AT jacobjoseph ahybridcnnrnnapproachforsurvivalanalysisinalungcancerscreeningstudy
AT luyaozhi hybridcnnrnnapproachforsurvivalanalysisinalungcancerscreeningstudy
AT aslanishahab hybridcnnrnnapproachforsurvivalanalysisinalungcancerscreeningstudy
AT zhaoan hybridcnnrnnapproachforsurvivalanalysisinalungcancerscreeningstudy
AT shahinahmed hybridcnnrnnapproachforsurvivalanalysisinalungcancerscreeningstudy
AT barberdavid hybridcnnrnnapproachforsurvivalanalysisinalungcancerscreeningstudy
AT embertonmark hybridcnnrnnapproachforsurvivalanalysisinalungcancerscreeningstudy
AT alexanderdanielc hybridcnnrnnapproachforsurvivalanalysisinalungcancerscreeningstudy
AT jacobjoseph hybridcnnrnnapproachforsurvivalanalysisinalungcancerscreeningstudy