Machine learning technique-based four-autoantibody test for early detection of esophageal squamous cell carcinoma: a multicenter, retrospective study with a nested case–control study

Abstract Background Autoantibodies represent promising diagnostic blood-based biomarkers that may be generated prior to the first clinically detectable signs of cancers. In present study, we aimed to identify a novel optimized autoantibody panel with high diagnostic accuracy for clinical and preclin...

Full description

Saved in:
Bibliographic Details
Main Authors: Yi-Wei Xu, Yu-Hui Peng, Can-Tong Liu, Hao Chen, Ling-Yu Chu, Hai-Lu Chen, Zhi-Yong Wu, Wen-Qiang Wei, Li-Yan Xu, Fang-Cai Wu, En-Min Li
Format: Article
Language:English
Published: BMC 2025-04-01
Series:BMC Medicine
Subjects:
Online Access:https://doi.org/10.1186/s12916-025-04066-2
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850172465396842496
author Yi-Wei Xu
Yu-Hui Peng
Can-Tong Liu
Hao Chen
Ling-Yu Chu
Hai-Lu Chen
Zhi-Yong Wu
Wen-Qiang Wei
Li-Yan Xu
Fang-Cai Wu
En-Min Li
author_facet Yi-Wei Xu
Yu-Hui Peng
Can-Tong Liu
Hao Chen
Ling-Yu Chu
Hai-Lu Chen
Zhi-Yong Wu
Wen-Qiang Wei
Li-Yan Xu
Fang-Cai Wu
En-Min Li
author_sort Yi-Wei Xu
collection DOAJ
description Abstract Background Autoantibodies represent promising diagnostic blood-based biomarkers that may be generated prior to the first clinically detectable signs of cancers. In present study, we aimed to identify a novel optimized autoantibody panel with high diagnostic accuracy for clinical and preclinical esophageal squamous cell carcinoma (ESCC) using machine learning (ML) algorithms. Methods We identified potential autoantibodies against tumor-associated antigens with serological proteome analysis. Serum autoantibody levels were measured by ELISA. Using a training set (n = 531), 102 models based on ML algorithms were constructed, and Partial Least Squares Generalized Linear Models (plsRglm) was selected out using receiver operating characteristics (ROC), Kolmogorov–Smirnov (K-S) test, and Population Stability Index (PSI), and further validated through an internal validation set (n = 413), external validation set 1 (n = 371), and external validation set 2 (n = 202). Then, we validated the ability of plsRglm model in predicting preclinical ESCC by a nested case–control study (24 preclinical ESCCs and 112 matched controls) within a population-based prospective cohort study. Results ROC analysis, K-S test, and PSI showed that plsRglm model based on four autoantibodies (ALDOA, ENO1, p53, and NY-ESO-1) exhibited the better diagnostic performance and robustness, which provided a high diagnostic accuracy in diagnosing ESCC with the respective AUCs (sensitivities and specificities) of 0.860 (68.8% and 90.4%) in the training set, 0.826 (65.3% and 89.1%) in the internal validation set, and 0.851 (69.2% and 87.3%) in the external validation set 1. For early-stage ESCC, this signature also maintained diagnostic performance [0.817 (62.3% and 90.4%) in the training set; 0.842 (62.5% and 89.1%) in the internal validation set; 0.854 (63.2% and 87.3%) in the external validation set 1; and 0.850 (67.3% and 90.1%) in the external validation set 2]. In the nested case–control study, this plsRglm model could detect the presence of preclinical ESCC with the AUC of 0.723, sensitivity of 54.2%, and specificity of 86.6%. Conclusions Our findings indicated that the plsRglm model based on four autoantibodies might help identify preclinical and early-stage ESCC.
format Article
id doaj-art-48ff57b1c9b741379c0fcafcb059fcca
institution OA Journals
issn 1741-7015
language English
publishDate 2025-04-01
publisher BMC
record_format Article
series BMC Medicine
spelling doaj-art-48ff57b1c9b741379c0fcafcb059fcca2025-08-20T02:20:05ZengBMCBMC Medicine1741-70152025-04-0123111510.1186/s12916-025-04066-2Machine learning technique-based four-autoantibody test for early detection of esophageal squamous cell carcinoma: a multicenter, retrospective study with a nested case–control studyYi-Wei Xu0Yu-Hui Peng1Can-Tong Liu2Hao Chen3Ling-Yu Chu4Hai-Lu Chen5Zhi-Yong Wu6Wen-Qiang Wei7Li-Yan Xu8Fang-Cai Wu9En-Min Li10Department of Clinical Laboratory Medicine, Esophageal Cancer Prevention and Control Research Center, Chaoshan Branch of State Key Laboratory for Esophageal Cancer Prevention and Treatment, Cancer Hospital of Shantou University Medical CollegeDepartment of Clinical Laboratory Medicine, Esophageal Cancer Prevention and Control Research Center, Chaoshan Branch of State Key Laboratory for Esophageal Cancer Prevention and Treatment, Cancer Hospital of Shantou University Medical CollegeDepartment of Clinical Laboratory Medicine, Esophageal Cancer Prevention and Control Research Center, Chaoshan Branch of State Key Laboratory for Esophageal Cancer Prevention and Treatment, Cancer Hospital of Shantou University Medical CollegeState Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Sun Yat-Sen University Cancer CenterDepartment of Clinical Laboratory Medicine, Esophageal Cancer Prevention and Control Research Center, Chaoshan Branch of State Key Laboratory for Esophageal Cancer Prevention and Treatment, Cancer Hospital of Shantou University Medical CollegeDepartment of Surgical Oncology, Shantou Central HospitalDepartment of Surgical Oncology, Shantou Central HospitalDepartment of Cancer Epidemiology, National Cancer Center/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical CollegeInstitute of Oncological Pathology, Shantou University Medical CollegeDepartment of Radiation Oncology, Esophageal Cancer Prevention and Control Research Center, Cancer Hospital of Shantou University Medical CollegeEsophageal Cancer Prevention and Control Research Center, Chaoshan Branch of State Key Laboratory for Esophageal Cancer Prevention and Treatment, Cancer Hospital of Shantou University Medical CollegeAbstract Background Autoantibodies represent promising diagnostic blood-based biomarkers that may be generated prior to the first clinically detectable signs of cancers. In present study, we aimed to identify a novel optimized autoantibody panel with high diagnostic accuracy for clinical and preclinical esophageal squamous cell carcinoma (ESCC) using machine learning (ML) algorithms. Methods We identified potential autoantibodies against tumor-associated antigens with serological proteome analysis. Serum autoantibody levels were measured by ELISA. Using a training set (n = 531), 102 models based on ML algorithms were constructed, and Partial Least Squares Generalized Linear Models (plsRglm) was selected out using receiver operating characteristics (ROC), Kolmogorov–Smirnov (K-S) test, and Population Stability Index (PSI), and further validated through an internal validation set (n = 413), external validation set 1 (n = 371), and external validation set 2 (n = 202). Then, we validated the ability of plsRglm model in predicting preclinical ESCC by a nested case–control study (24 preclinical ESCCs and 112 matched controls) within a population-based prospective cohort study. Results ROC analysis, K-S test, and PSI showed that plsRglm model based on four autoantibodies (ALDOA, ENO1, p53, and NY-ESO-1) exhibited the better diagnostic performance and robustness, which provided a high diagnostic accuracy in diagnosing ESCC with the respective AUCs (sensitivities and specificities) of 0.860 (68.8% and 90.4%) in the training set, 0.826 (65.3% and 89.1%) in the internal validation set, and 0.851 (69.2% and 87.3%) in the external validation set 1. For early-stage ESCC, this signature also maintained diagnostic performance [0.817 (62.3% and 90.4%) in the training set; 0.842 (62.5% and 89.1%) in the internal validation set; 0.854 (63.2% and 87.3%) in the external validation set 1; and 0.850 (67.3% and 90.1%) in the external validation set 2]. In the nested case–control study, this plsRglm model could detect the presence of preclinical ESCC with the AUC of 0.723, sensitivity of 54.2%, and specificity of 86.6%. Conclusions Our findings indicated that the plsRglm model based on four autoantibodies might help identify preclinical and early-stage ESCC.https://doi.org/10.1186/s12916-025-04066-2AutoantibodyEsophageal cancerEarly detectionMachine learning
spellingShingle Yi-Wei Xu
Yu-Hui Peng
Can-Tong Liu
Hao Chen
Ling-Yu Chu
Hai-Lu Chen
Zhi-Yong Wu
Wen-Qiang Wei
Li-Yan Xu
Fang-Cai Wu
En-Min Li
Machine learning technique-based four-autoantibody test for early detection of esophageal squamous cell carcinoma: a multicenter, retrospective study with a nested case–control study
BMC Medicine
Autoantibody
Esophageal cancer
Early detection
Machine learning
title Machine learning technique-based four-autoantibody test for early detection of esophageal squamous cell carcinoma: a multicenter, retrospective study with a nested case–control study
title_full Machine learning technique-based four-autoantibody test for early detection of esophageal squamous cell carcinoma: a multicenter, retrospective study with a nested case–control study
title_fullStr Machine learning technique-based four-autoantibody test for early detection of esophageal squamous cell carcinoma: a multicenter, retrospective study with a nested case–control study
title_full_unstemmed Machine learning technique-based four-autoantibody test for early detection of esophageal squamous cell carcinoma: a multicenter, retrospective study with a nested case–control study
title_short Machine learning technique-based four-autoantibody test for early detection of esophageal squamous cell carcinoma: a multicenter, retrospective study with a nested case–control study
title_sort machine learning technique based four autoantibody test for early detection of esophageal squamous cell carcinoma a multicenter retrospective study with a nested case control study
topic Autoantibody
Esophageal cancer
Early detection
Machine learning
url https://doi.org/10.1186/s12916-025-04066-2
work_keys_str_mv AT yiweixu machinelearningtechniquebasedfourautoantibodytestforearlydetectionofesophagealsquamouscellcarcinomaamulticenterretrospectivestudywithanestedcasecontrolstudy
AT yuhuipeng machinelearningtechniquebasedfourautoantibodytestforearlydetectionofesophagealsquamouscellcarcinomaamulticenterretrospectivestudywithanestedcasecontrolstudy
AT cantongliu machinelearningtechniquebasedfourautoantibodytestforearlydetectionofesophagealsquamouscellcarcinomaamulticenterretrospectivestudywithanestedcasecontrolstudy
AT haochen machinelearningtechniquebasedfourautoantibodytestforearlydetectionofesophagealsquamouscellcarcinomaamulticenterretrospectivestudywithanestedcasecontrolstudy
AT lingyuchu machinelearningtechniquebasedfourautoantibodytestforearlydetectionofesophagealsquamouscellcarcinomaamulticenterretrospectivestudywithanestedcasecontrolstudy
AT hailuchen machinelearningtechniquebasedfourautoantibodytestforearlydetectionofesophagealsquamouscellcarcinomaamulticenterretrospectivestudywithanestedcasecontrolstudy
AT zhiyongwu machinelearningtechniquebasedfourautoantibodytestforearlydetectionofesophagealsquamouscellcarcinomaamulticenterretrospectivestudywithanestedcasecontrolstudy
AT wenqiangwei machinelearningtechniquebasedfourautoantibodytestforearlydetectionofesophagealsquamouscellcarcinomaamulticenterretrospectivestudywithanestedcasecontrolstudy
AT liyanxu machinelearningtechniquebasedfourautoantibodytestforearlydetectionofesophagealsquamouscellcarcinomaamulticenterretrospectivestudywithanestedcasecontrolstudy
AT fangcaiwu machinelearningtechniquebasedfourautoantibodytestforearlydetectionofesophagealsquamouscellcarcinomaamulticenterretrospectivestudywithanestedcasecontrolstudy
AT enminli machinelearningtechniquebasedfourautoantibodytestforearlydetectionofesophagealsquamouscellcarcinomaamulticenterretrospectivestudywithanestedcasecontrolstudy