Machine learning based obesity and aging related signature for predicting the prognosis and immunotherapy benefit in stomach adenocarcinoma

Abstract Background Stomach adenocarcinoma (STAD) is one of most common cancers with high invasiveness and poor prognosis. Obesity and aging are correlated with higher risk for cancer development and worse prognosis in certain types of malignancies. Methods An integrative approach incorporating 10 m...

Full description

Saved in:
Bibliographic Details
Main Authors: Yongheng Chen, Xiaoxia Yu, Wencan Xu, Anqi Huang, Zhengbing Li
Format: Article
Language:English
Published: Springer 2025-07-01
Series:Discover Oncology
Subjects:
Online Access:https://doi.org/10.1007/s12672-025-03054-5
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849238579039961088
author Yongheng Chen
Xiaoxia Yu
Wencan Xu
Anqi Huang
Zhengbing Li
author_facet Yongheng Chen
Xiaoxia Yu
Wencan Xu
Anqi Huang
Zhengbing Li
author_sort Yongheng Chen
collection DOAJ
description Abstract Background Stomach adenocarcinoma (STAD) is one of most common cancers with high invasiveness and poor prognosis. Obesity and aging are correlated with higher risk for cancer development and worse prognosis in certain types of malignancies. Methods An integrative approach incorporating 10 machine learning methods was employed to develop an obesity and aging-related signature (ORS) using data from the TCGA, GSE15459, GSE26253, GSE62254, and GSE84437 datasets. To assess the predictive value of ORS for immunotherapy benefits, we utilized several indicating scores and three immunotherapy datasets (GSE91061, GSE78220, and IMvigor210). Results The predictive model developed using the LASSO method achieved the highest average C-index and was identified as the optimal ORS. This ORS served as an independent risk factor for the clinical outcomes of STAD patients, demonstrating robust performance in predicting overall survival rates. In the TCGA cohort, the area under the curve values for the 1-, 3-, and 5-year receiver operator characteristic curves were 0.871, 0.803, and 0.768, respectively. Patients with low ORS score exhibited higher gene set scores for immune-activated cells, increased cytolytic activity, and enhanced T cell co-stimulation. Additionally, low ORS score was associated with a reduced tumor immune dysfunction and exclusion score, decreased immune escape score, elevated PD1 and CTLA4 immunophenoscore, higher tumor mutation burden, improved response rates, and better prognosis in STAD. Conversely, the IC50 values for common chemotherapy and targeted therapy regimens were lower in the high ORS score group. Conclusion The current study developed an optimal ORS in STAD, which could be used for predicting the prognosis, stratifying risk and guiding treatment for STAD patients.
format Article
id doaj-art-dfd71c5d68674bc7907a1f055db46695
institution Kabale University
issn 2730-6011
language English
publishDate 2025-07-01
publisher Springer
record_format Article
series Discover Oncology
spelling doaj-art-dfd71c5d68674bc7907a1f055db466952025-08-20T04:01:34ZengSpringerDiscover Oncology2730-60112025-07-0116111310.1007/s12672-025-03054-5Machine learning based obesity and aging related signature for predicting the prognosis and immunotherapy benefit in stomach adenocarcinomaYongheng Chen0Xiaoxia Yu1Wencan Xu2Anqi Huang3Zhengbing Li4Department of Geriatrics, the First Affiliated Hospital of Shantou University Medical CollegeDepartment of Hospice, the First Affiliated Hospital of Shantou University Medical CollegeDepartment of Endocrinology and Metabolism, the First Affiliated Hospital of Shantou University Medical CollegeDepartment of Endocrinology and Metabolism, the First Affiliated Hospital of Shantou University Medical CollegeDepartment of Endocrinology and Metabolism, the First Affiliated Hospital of Shantou University Medical CollegeAbstract Background Stomach adenocarcinoma (STAD) is one of most common cancers with high invasiveness and poor prognosis. Obesity and aging are correlated with higher risk for cancer development and worse prognosis in certain types of malignancies. Methods An integrative approach incorporating 10 machine learning methods was employed to develop an obesity and aging-related signature (ORS) using data from the TCGA, GSE15459, GSE26253, GSE62254, and GSE84437 datasets. To assess the predictive value of ORS for immunotherapy benefits, we utilized several indicating scores and three immunotherapy datasets (GSE91061, GSE78220, and IMvigor210). Results The predictive model developed using the LASSO method achieved the highest average C-index and was identified as the optimal ORS. This ORS served as an independent risk factor for the clinical outcomes of STAD patients, demonstrating robust performance in predicting overall survival rates. In the TCGA cohort, the area under the curve values for the 1-, 3-, and 5-year receiver operator characteristic curves were 0.871, 0.803, and 0.768, respectively. Patients with low ORS score exhibited higher gene set scores for immune-activated cells, increased cytolytic activity, and enhanced T cell co-stimulation. Additionally, low ORS score was associated with a reduced tumor immune dysfunction and exclusion score, decreased immune escape score, elevated PD1 and CTLA4 immunophenoscore, higher tumor mutation burden, improved response rates, and better prognosis in STAD. Conversely, the IC50 values for common chemotherapy and targeted therapy regimens were lower in the high ORS score group. Conclusion The current study developed an optimal ORS in STAD, which could be used for predicting the prognosis, stratifying risk and guiding treatment for STAD patients.https://doi.org/10.1007/s12672-025-03054-5Stomach adenocarcinomaAgingObesityMachine learningImmunotherapy
spellingShingle Yongheng Chen
Xiaoxia Yu
Wencan Xu
Anqi Huang
Zhengbing Li
Machine learning based obesity and aging related signature for predicting the prognosis and immunotherapy benefit in stomach adenocarcinoma
Discover Oncology
Stomach adenocarcinoma
Aging
Obesity
Machine learning
Immunotherapy
title Machine learning based obesity and aging related signature for predicting the prognosis and immunotherapy benefit in stomach adenocarcinoma
title_full Machine learning based obesity and aging related signature for predicting the prognosis and immunotherapy benefit in stomach adenocarcinoma
title_fullStr Machine learning based obesity and aging related signature for predicting the prognosis and immunotherapy benefit in stomach adenocarcinoma
title_full_unstemmed Machine learning based obesity and aging related signature for predicting the prognosis and immunotherapy benefit in stomach adenocarcinoma
title_short Machine learning based obesity and aging related signature for predicting the prognosis and immunotherapy benefit in stomach adenocarcinoma
title_sort machine learning based obesity and aging related signature for predicting the prognosis and immunotherapy benefit in stomach adenocarcinoma
topic Stomach adenocarcinoma
Aging
Obesity
Machine learning
Immunotherapy
url https://doi.org/10.1007/s12672-025-03054-5
work_keys_str_mv AT yonghengchen machinelearningbasedobesityandagingrelatedsignatureforpredictingtheprognosisandimmunotherapybenefitinstomachadenocarcinoma
AT xiaoxiayu machinelearningbasedobesityandagingrelatedsignatureforpredictingtheprognosisandimmunotherapybenefitinstomachadenocarcinoma
AT wencanxu machinelearningbasedobesityandagingrelatedsignatureforpredictingtheprognosisandimmunotherapybenefitinstomachadenocarcinoma
AT anqihuang machinelearningbasedobesityandagingrelatedsignatureforpredictingtheprognosisandimmunotherapybenefitinstomachadenocarcinoma
AT zhengbingli machinelearningbasedobesityandagingrelatedsignatureforpredictingtheprognosisandimmunotherapybenefitinstomachadenocarcinoma