{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T06:57:30Z","timestamp":1785826650638,"version":"3.56.0"},"reference-count":17,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T00:00:00Z","timestamp":1761696000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Physiol."],"abstract":"<jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>We developed interpretable machine learning (ML) models to predict the overall survival (OS) of esophageal cancer patients. This approach aims to make our modeling results more interpretable and transparent.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We collected the clinicopathological information of esophageal cancer patients from the SEER database and divided them into training and validation sets at a ratio of 7:3. Meanwhile, we obtained an external validation cohort from the First People\u2019s Hospital of Kashi in Xinjiang, China. Using LASSO and multivariate Cox regression analyses, we identified relevant risk factors and combined them to develop CoxPH and 6 ML models: Random Survival Forest (RSF), Gradient Boosting with Component Linear (GLMboost), decision tree (dt), boosting tree (bt), DeepSurv, and neural multi-task logistic regression (NMTLR). We evaluated the predictive performance of these ML models using the C-index, integral cumulative\/dynamic AUC, integral Brier score, Kolmogorov-Smirnov (KS) test and Cramer-von Mises (CvM) test. For interpretability assessment, we employed three complementary methods: (1) time-dependent variable importance to quantify feature contribution across follow-up periods; (2) partial correlation survival plots to visualize individual variable effects; and (3) aggregated survival SHapley additive interpretation (SurvSHAP) plots with mean absolute deviation metrics to validate feature impact stability at both individual and population levels.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The final ML model consisted of 11 factors: grade, stage, T stage, N stage, M stage, radiotherapy, chemotherapy, bone metastasis, liver metastasis, lung metastasis, and age. Our predictive models demonstrate significant discriminative power; in particular, the NMTLR model performs best. For the training, validation, and external validation sets, the area under the curve (AUC) for one-, three-, and 5-year OS was higher than 0.81, and the integrated Brier score was consistently lower than 0.175. interpretability analyses confirmed consistent predictive logic: M stage, N stage, age, grade, bone metastases, liver metastases, lung metastases and radiotherapy were identified as the most influential predictors via quantifiable SurvSHAP values and time-dependent importance weights, with their effects visually validated through partial correlation survival curves.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The NMTLR prognostic model is the most effective at predicting the OS of esophageal cancer patients. It helps physicians correctly assess patient survival and provides valuable information for diagnosis and prognosis evaluation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fphys.2025.1665383","type":"journal-article","created":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T05:29:38Z","timestamp":1761715778000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Interpretable machine learning models to predict survival in esophageal cancer: a study based on the SEER database and external validation in China"],"prefix":"10.3389","volume":"16","author":[{"given":"Abudouresuli","family":"Tuersun","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Saimaitikari","family":"Abudoubari","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abudoushalamu","family":"Abudouwake","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huerxidan","family":"Tuerdi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abulizi","family":"Maimaitiyiming","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pahatijiang","family":"Nijiati","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ya","family":"Qiu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianquan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,10,29]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"e13872","DOI":"10.1111\/acel.13872","article-title":"Explainable machine learning framework to predict personalized physiological aging","volume":"22","author":"Bernard","year":"2023","journal-title":"Aging Cell."},{"key":"B2","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1186\/s13062-025-00650-x","article-title":"Integrating machine learning models with multi-omics analysis to decipher the prognostic significance of mitotic catastrophe heterogeneity in bladder cancer","volume":"20","author":"Dai","year":"2025","journal-title":"Biol. Direct"},{"key":"B3","doi-asserted-by":"publisher","first-page":"1052","DOI":"10.1016\/j.jtho.2024.03.021","article-title":"The international association for the Study of lung cancer lung cancer staging Project: proposals for revision of the classification of residual tumor after resection for the forthcoming (ninth) edition of the TNM classification of lung cancer","volume":"19","author":"Detterbeck","year":"2024","journal-title":"J. Thorac. Oncol."},{"key":"B4","doi-asserted-by":"publisher","first-page":"658","DOI":"10.1007\/s12094-022-02801-2","article-title":"SEOM-GEMCAD-TTD clinical Guideline for the diagnosis and treatment of esophageal cancer (2021)","volume":"24","author":"Fern\u00e1ndez-Montes","year":"2022","journal-title":"Clin. Transl. Oncol."},{"key":"B5","doi-asserted-by":"publisher","first-page":"1078","DOI":"10.1007\/s11605-023-05643-7","article-title":"Preoperative esophageal stenting and 5-Year survival in patients undergoing esophagectomy for esophageal cancer: a population-based nationwide Study from Finland","volume":"27","author":"Helminen","year":"2023","journal-title":"J. Gastrointest. Surg."},{"key":"B6","doi-asserted-by":"publisher","first-page":"1691","DOI":"10.1007\/s00432-022-04063-5","article-title":"Machine learning for optimized individual survival prediction in resectable upper gastrointestinal cancer","volume":"149","author":"Jung","year":"2023","journal-title":"J. Cancer Res. Clin. Oncol."},{"key":"B7","doi-asserted-by":"publisher","first-page":"6452","DOI":"10.21037\/jtd-24-742","article-title":"Nomogram model for predicting long-term survival in esophageal cancer patients with metastasis after treatment: a SEER-based study","volume":"16","author":"Li","year":"2024","journal-title":"J. Thorac. Dis."},{"key":"B8","doi-asserted-by":"publisher","first-page":"649","DOI":"10.1053\/j.gastro.2022.05.054","article-title":"The global landscape of esophageal squamous cell carcinoma and esophageal adenocarcinoma incidence and mortality in 2020 and projections to 2040: new estimates from GLOBOCAN 2020","volume":"163","author":"Morgan","year":"2022","journal-title":"Gastroenterology"},{"key":"B9","doi-asserted-by":"publisher","first-page":"631","DOI":"10.2174\/1389450122999210104205732","article-title":"Artificial intelligence, big data and machine learning approaches in precision medicine and drug Discovery","volume":"22","author":"Nayarisseri","year":"2021","journal-title":"Curr. Drug Targets"},{"key":"B10","doi-asserted-by":"publisher","first-page":"e24797","DOI":"10.1016\/j.heliyon.2024.e24797","article-title":"Design of risk prediction model for esophageal cancer based on machine learning approach","volume":"10","author":"Nopour","year":"2024","journal-title":"Heliyon"},{"key":"B11","doi-asserted-by":"publisher","first-page":"950","DOI":"10.1002\/bco2.425","article-title":"Machine learning analysis for detecting late recurrence and loss to follow-up after renal cell carcinoma surgery","volume":"5","author":"Sato","year":"2024","journal-title":"BJUI Compass"},{"key":"B12","doi-asserted-by":"publisher","first-page":"1056","DOI":"10.1053\/j.gastro.2021.11.040","article-title":"Artificial intelligence and deep learning for upper gastrointestinal Neoplasia","volume":"162","author":"Sharma","year":"2022","journal-title":"Gastroenterology"},{"key":"B13","doi-asserted-by":"publisher","first-page":"209","DOI":"10.3322\/caac.21660","article-title":"Global cancer statistics 2020:GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries","volume":"71","author":"Sung","year":"2021","journal-title":"CA Cancer J. Clin."},{"key":"B14","doi-asserted-by":"publisher","first-page":"511","DOI":"10.3390\/bioengineering12050511","article-title":"Development, validation, and deployment of a time-dependent machine learning model for predicting one-year mortality risk in critically ill patients with heart failure","volume":"12","author":"Wang","year":"2025","journal-title":"Bioeng. (Basel)"},{"key":"B15","doi-asserted-by":"publisher","first-page":"9457","DOI":"10.1111\/jcmm.15618","article-title":"A transcriptomic study for identifying cardia- and non-cardia-specific gastric cancer prognostic factors using genetic algorithm-based methods","volume":"24","author":"Xin","year":"2020","journal-title":"J. Cell. Mol. Med."},{"key":"B16","doi-asserted-by":"publisher","first-page":"1068198","DOI":"10.3389\/fonc.2022.1068198","article-title":"Development and validation of a machine learning model for survival risk stratification after esophageal cancer surgery","volume":"12","author":"Xu","year":"2022","journal-title":"Front. Oncol."},{"key":"B17","doi-asserted-by":"publisher","first-page":"e297","DOI":"10.1002\/mco2.297","article-title":"Timely assessment of 5-year relative survival of esophageal cancer patients in Taizhou, Zhejiang province","volume":"4","author":"Zhang","year":"","journal-title":"MedComm"}],"container-title":["Frontiers in Physiology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fphys.2025.1665383\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T05:29:38Z","timestamp":1761715778000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fphys.2025.1665383\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,29]]},"references-count":17,"alternative-id":["10.3389\/fphys.2025.1665383"],"URL":"https:\/\/doi.org\/10.3389\/fphys.2025.1665383","relation":{},"ISSN":["1664-042X"],"issn-type":[{"value":"1664-042X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,29]]},"article-number":"1665383"}}