Cargando…

Predicting Overall Survival for Patients with Malignant Mesothelioma Following Radiotherapy via Interpretable Machine Learning

SIMPLE SUMMARY: Malignant pleural mesothelioma (MPM) is a rare cancer arising from the cells of the thoracic pleura of the lungs. It has a poor prognosis and is often fatal, with a reported 5-year survival rate of less than 5%. Post-surgery radiotherapy is recommended for patients with resectable di...

Descripción completa

Detalles Bibliográficos
Autores principales: Wang, Zitian, Li, Vincent R., Chu, Fang-I, Yu, Victoria, Lee, Alan, Low, Daniel, Moghanaki, Drew, Lee, Percy, Qi, X. Sharon
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10416916/
https://www.ncbi.nlm.nih.gov/pubmed/37568732
http://dx.doi.org/10.3390/cancers15153916
_version_ 1785087892552417280
author Wang, Zitian
Li, Vincent R.
Chu, Fang-I
Yu, Victoria
Lee, Alan
Low, Daniel
Moghanaki, Drew
Lee, Percy
Qi, X. Sharon
author_facet Wang, Zitian
Li, Vincent R.
Chu, Fang-I
Yu, Victoria
Lee, Alan
Low, Daniel
Moghanaki, Drew
Lee, Percy
Qi, X. Sharon
author_sort Wang, Zitian
collection PubMed
description SIMPLE SUMMARY: Malignant pleural mesothelioma (MPM) is a rare cancer arising from the cells of the thoracic pleura of the lungs. It has a poor prognosis and is often fatal, with a reported 5-year survival rate of less than 5%. Post-surgery radiotherapy is recommended for patients with resectable disease to improve local control. However, radiation treatment planning for MPM is extremely challenging due to the anatomic complexity, large surface area, unique concave shape, location, and large size of the pleura planning target volume. The aims of this work are: (1) To examine the achieved dosimetric endpoints for a retrospective cohort of MPM patients and to assess associations of these variables with corresponding overall survival (OS) using machine learning methods; (2) To identify key predictors that influence OS via interpretable machine learning algorithms for left- and right-sided mesothelioma patients separately, and to develop and validate predictive models based on identified clinical and dosimetric parameters for predicting OS. ABSTRACT: Purpose/Objectives: Malignant pleural mesothelioma (MPM) is a rare but aggressive cancer arising from the cells of the thoracic pleura with a poor prognosis. We aimed to develop a model, via interpretable machine learning (ML) methods, predicting overall survival for MPM following radiotherapy based on dosimetric metrics as well as patient characteristics. Materials/Methods: Sixty MPM (37 right, 23 left) patients treated on a Tomotherapy unit between 2013 and 2018 were retrospectively analyzed. All patients received 45 Gy (25 fractions). The multivariable Cox regression (Cox PH) model and Survival Support Vector Machine (sSVM) were applied to build predictive models of overall survival (OS) based on clinical, dosimetric, and combined variables. Results: Significant differences in dosimetric endpoints for critical structures, i.e., the lung, heart, liver, kidney, and stomach, were observed according to target laterality. The OS was found to be insignificantly different (p = 0.18) between MPM patients who tested left- and right-sided, with 1-year OS of 77.3% and 75.0%, respectively. With Cox PH regression, considering dosimetric variables for right-sided patients alone, an increase in PTV_Min, Total_Lung_PTV_Mean, Contra_Lung_Volume, Contra_Lung_V20, Esophagus_Mean, and Heart_Volume had a greater hazard to all-cause death, while an increase in Total_Lung_PTV_V20, Contra_Lung_V5, and Esophagus_Max had a lower hazard to all-cause death. Considering clinical variables alone, males and increases in N stage had greater hazard to all-cause death; considering both clinical and dosimetric variables, increases in N stage, PTV_Mean, PTV_Min, and esophagus_Mean had greater hazard to all-cause death, while increases in T stage and Heart_V30 had lower hazard to all-cause-death. In terms of C-index, the Cox PH model and sSVM performed similarly and fairly well when considering clinical and dosimetric variables independently or jointly. Conclusions: Clinical and dosimetric variables may predict the overall survival of mesothelioma patients, which could guide personalized treatment planning towards a better treatment response. The identified predictors and their impact on survival offered additional value for translational application in clinical practice.
format Online
Article
Text
id pubmed-10416916
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-104169162023-08-12 Predicting Overall Survival for Patients with Malignant Mesothelioma Following Radiotherapy via Interpretable Machine Learning Wang, Zitian Li, Vincent R. Chu, Fang-I Yu, Victoria Lee, Alan Low, Daniel Moghanaki, Drew Lee, Percy Qi, X. Sharon Cancers (Basel) Article SIMPLE SUMMARY: Malignant pleural mesothelioma (MPM) is a rare cancer arising from the cells of the thoracic pleura of the lungs. It has a poor prognosis and is often fatal, with a reported 5-year survival rate of less than 5%. Post-surgery radiotherapy is recommended for patients with resectable disease to improve local control. However, radiation treatment planning for MPM is extremely challenging due to the anatomic complexity, large surface area, unique concave shape, location, and large size of the pleura planning target volume. The aims of this work are: (1) To examine the achieved dosimetric endpoints for a retrospective cohort of MPM patients and to assess associations of these variables with corresponding overall survival (OS) using machine learning methods; (2) To identify key predictors that influence OS via interpretable machine learning algorithms for left- and right-sided mesothelioma patients separately, and to develop and validate predictive models based on identified clinical and dosimetric parameters for predicting OS. ABSTRACT: Purpose/Objectives: Malignant pleural mesothelioma (MPM) is a rare but aggressive cancer arising from the cells of the thoracic pleura with a poor prognosis. We aimed to develop a model, via interpretable machine learning (ML) methods, predicting overall survival for MPM following radiotherapy based on dosimetric metrics as well as patient characteristics. Materials/Methods: Sixty MPM (37 right, 23 left) patients treated on a Tomotherapy unit between 2013 and 2018 were retrospectively analyzed. All patients received 45 Gy (25 fractions). The multivariable Cox regression (Cox PH) model and Survival Support Vector Machine (sSVM) were applied to build predictive models of overall survival (OS) based on clinical, dosimetric, and combined variables. Results: Significant differences in dosimetric endpoints for critical structures, i.e., the lung, heart, liver, kidney, and stomach, were observed according to target laterality. The OS was found to be insignificantly different (p = 0.18) between MPM patients who tested left- and right-sided, with 1-year OS of 77.3% and 75.0%, respectively. With Cox PH regression, considering dosimetric variables for right-sided patients alone, an increase in PTV_Min, Total_Lung_PTV_Mean, Contra_Lung_Volume, Contra_Lung_V20, Esophagus_Mean, and Heart_Volume had a greater hazard to all-cause death, while an increase in Total_Lung_PTV_V20, Contra_Lung_V5, and Esophagus_Max had a lower hazard to all-cause death. Considering clinical variables alone, males and increases in N stage had greater hazard to all-cause death; considering both clinical and dosimetric variables, increases in N stage, PTV_Mean, PTV_Min, and esophagus_Mean had greater hazard to all-cause death, while increases in T stage and Heart_V30 had lower hazard to all-cause-death. In terms of C-index, the Cox PH model and sSVM performed similarly and fairly well when considering clinical and dosimetric variables independently or jointly. Conclusions: Clinical and dosimetric variables may predict the overall survival of mesothelioma patients, which could guide personalized treatment planning towards a better treatment response. The identified predictors and their impact on survival offered additional value for translational application in clinical practice. MDPI 2023-08-01 /pmc/articles/PMC10416916/ /pubmed/37568732 http://dx.doi.org/10.3390/cancers15153916 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Wang, Zitian
Li, Vincent R.
Chu, Fang-I
Yu, Victoria
Lee, Alan
Low, Daniel
Moghanaki, Drew
Lee, Percy
Qi, X. Sharon
Predicting Overall Survival for Patients with Malignant Mesothelioma Following Radiotherapy via Interpretable Machine Learning
title Predicting Overall Survival for Patients with Malignant Mesothelioma Following Radiotherapy via Interpretable Machine Learning
title_full Predicting Overall Survival for Patients with Malignant Mesothelioma Following Radiotherapy via Interpretable Machine Learning
title_fullStr Predicting Overall Survival for Patients with Malignant Mesothelioma Following Radiotherapy via Interpretable Machine Learning
title_full_unstemmed Predicting Overall Survival for Patients with Malignant Mesothelioma Following Radiotherapy via Interpretable Machine Learning
title_short Predicting Overall Survival for Patients with Malignant Mesothelioma Following Radiotherapy via Interpretable Machine Learning
title_sort predicting overall survival for patients with malignant mesothelioma following radiotherapy via interpretable machine learning
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10416916/
https://www.ncbi.nlm.nih.gov/pubmed/37568732
http://dx.doi.org/10.3390/cancers15153916
work_keys_str_mv AT wangzitian predictingoverallsurvivalforpatientswithmalignantmesotheliomafollowingradiotherapyviainterpretablemachinelearning
AT livincentr predictingoverallsurvivalforpatientswithmalignantmesotheliomafollowingradiotherapyviainterpretablemachinelearning
AT chufangi predictingoverallsurvivalforpatientswithmalignantmesotheliomafollowingradiotherapyviainterpretablemachinelearning
AT yuvictoria predictingoverallsurvivalforpatientswithmalignantmesotheliomafollowingradiotherapyviainterpretablemachinelearning
AT leealan predictingoverallsurvivalforpatientswithmalignantmesotheliomafollowingradiotherapyviainterpretablemachinelearning
AT lowdaniel predictingoverallsurvivalforpatientswithmalignantmesotheliomafollowingradiotherapyviainterpretablemachinelearning
AT moghanakidrew predictingoverallsurvivalforpatientswithmalignantmesotheliomafollowingradiotherapyviainterpretablemachinelearning
AT leepercy predictingoverallsurvivalforpatientswithmalignantmesotheliomafollowingradiotherapyviainterpretablemachinelearning
AT qixsharon predictingoverallsurvivalforpatientswithmalignantmesotheliomafollowingradiotherapyviainterpretablemachinelearning