{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T00:54:20Z","timestamp":1760144060348,"version":"build-2065373602"},"reference-count":67,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2024,3,19]],"date-time":"2024-03-19T00:00:00Z","timestamp":1710806400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["MAKE"],"abstract":"<jats:p>AIM: In this study, we use Artificial Intelligence (AI), including Machine (ML) and Deep Learning (DL), to predict the long-term survival of resectable esophageal cancer (EC) patients in a high-volume surgical center. Our objective is to evaluate the predictive efficacy of AI methods for survival prognosis across different time points of oncological treatment. This involves comparing models trained with clinical data, integrating either Tumor, Node, Metastasis (TNM) classification or tumor biomarker analysis, for long-term survival predictions. METHODS: In this retrospective study, 1002 patients diagnosed with EC between 1996 and 2021 were analyzed. The original dataset comprised 55 pre- and postoperative patient characteristics and 55 immunohistochemically evaluated biomarkers following surgical intervention. To predict the five-year survival status, four AI methods (Random Forest RF, XG Boost XG, Artificial Neural Network ANN, TabNet TN) and Logistic Regression (LR) were employed. The models were trained using three predefined subsets of the training dataset as follows: (I) the baseline dataset (BL) consisting of pre-, intra-, and postoperative data, including the TNM but excluding tumor biomarkers, (II) clinical data accessible at the time of the initial diagnostic workup (primary staging dataset, PS), and (III) the PS dataset including tumor biomarkers from tissue microarrays (PS + biomarkers), excluding TNM status. We used permutation feature importance for feature selection to identify only important variables for AI-driven reduced datasets and subsequent model retraining. RESULTS: Model training on the BL dataset demonstrated similar predictive performances for all models (Accuracy, ACC: 0.73\/0.74\/0.76\/0.75\/0.73; AUC: 0.78\/0.82\/0.83\/0.80\/0.79 RF\/XG\/ANN\/TN\/LR, respectively). The predictive performance and generalizability declined when the models were trained with the PS dataset. Surprisingly, the inclusion of biomarkers in the PS dataset for model training led to improved predictions (PS dataset vs. PS dataset + biomarkers; ACC: 0.70 vs. 0.77\/0.73 vs. 0.79\/0.71 vs. 0.75\/0.69 vs. 0.72\/0.63 vs. 0.66; AUC: 0.77 vs. 0.83\/0.80 vs. 0.85\/0.76 vs. 0.86\/0.70 vs. 0.76\/0.70 vs. 0.69 RF\/XG\/ANN\/TN\/LR, respectively). The AI models outperformed LR when trained with the PS datasets. The important features shared after AI-driven feature selection in all models trained with the BL dataset included histopathological lymph node status (pN), histopathological tumor size (pT), clinical tumor size (cT), age at the time of surgery, and postoperative tracheostomy. Following training with the PS dataset with biomarkers, the important predictive features included patient age at the time of surgery, TP-53 gene mutation, Mesothelin expression, thymidine phosphorylase (TYMP) expression, NANOG homebox protein expression, and indoleamine 2,3-dioxygenase (IDO) expressed on tumor-infiltrating lymphocytes, as well as tumor-infiltrating Mast- and Natural killer cells. CONCLUSION: Different AI methods similarly predict the long-term survival status of patients with EC and outperform LR, the state-of-the-art classification model. Survival status can be predicted with similar predictive performance with patient data at an early stage of treatment when utilizing additional biomarker analysis. This suggests that individual survival predictions can be made early in cancer treatment by utilizing biomarkers, reducing the necessity for the pathological TNM status post-surgery. This study identifies important features for survival predictions that vary depending on the timing of oncological treatment.<\/jats:p>","DOI":"10.3390\/make6010032","type":"journal-article","created":{"date-parts":[[2024,3,19]],"date-time":"2024-03-19T05:23:31Z","timestamp":1710825811000},"page":"679-698","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Analyzing the Impact of Oncological Data at Different Time Points and Tumor Biomarkers on Artificial Intelligence Predictions for Five-Year Survival in Esophageal Cancer"],"prefix":"10.3390","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6998-2255","authenticated-orcid":false,"given":"Leandra","family":"Lukomski","sequence":"first","affiliation":[{"name":"Department of General, Visceral and Cancer Surgery, Faculty of Medicine and University Hospital of Cologne, Kerpener Stra\u00dfe 62, 50937 Cologne, Germany"}]},{"given":"Juan","family":"Pisula","sequence":"additional","affiliation":[{"name":"Data science of Bioimages Lab, Center for Molecular Medicine Cologne (CMMC), Faculty of Medicine and University Hospital of Cologne, Robert-Koch-Stra\u00dfe 21, 50937 Cologne, Germany"}]},{"given":"Naita","family":"Wirsik","sequence":"additional","affiliation":[{"name":"Department of General, Visceral and Cancer Surgery, Faculty of Medicine and University Hospital of Cologne, Kerpener Stra\u00dfe 62, 50937 Cologne, Germany"}]},{"given":"Alexander","family":"Damanakis","sequence":"additional","affiliation":[{"name":"Department of General, Visceral and Cancer Surgery, Faculty of Medicine and University Hospital of Cologne, Kerpener Stra\u00dfe 62, 50937 Cologne, Germany"}]},{"given":"Jin-On","family":"Jung","sequence":"additional","affiliation":[{"name":"Department of General, Visceral and Cancer Surgery, Faculty of Medicine and University Hospital of Cologne, Kerpener Stra\u00dfe 62, 50937 Cologne, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7133-3538","authenticated-orcid":false,"given":"Karl","family":"Knipper","sequence":"additional","affiliation":[{"name":"Department of General, Visceral and Cancer Surgery, Faculty of Medicine and University Hospital of Cologne, Kerpener Stra\u00dfe 62, 50937 Cologne, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6829-7379","authenticated-orcid":false,"given":"Rabi","family":"Datta","sequence":"additional","affiliation":[{"name":"Department of General, Visceral and Cancer Surgery, Faculty of Medicine and University Hospital of Cologne, Kerpener Stra\u00dfe 62, 50937 Cologne, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8700-069X","authenticated-orcid":false,"given":"Wolfgang","family":"Schr\u00f6der","sequence":"additional","affiliation":[{"name":"Department of General, Visceral and Cancer Surgery, Faculty of Medicine and University Hospital of Cologne, Kerpener Stra\u00dfe 62, 50937 Cologne, Germany"}]},{"given":"Florian","family":"Gebauer","sequence":"additional","affiliation":[{"name":"Department of General, Visceral and Cancer Surgery, Helios University Hospital Wuppertal, University Witten\/Herdecke, Heusnerstra\u00dfe 40, 42283 Wuppertal, Germany"}]},{"given":"Thomas","family":"Schmidt","sequence":"additional","affiliation":[{"name":"Department of General, Visceral and Cancer Surgery, Faculty of Medicine and University Hospital of Cologne, Kerpener Stra\u00dfe 62, 50937 Cologne, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3537-6011","authenticated-orcid":false,"given":"Alexander","family":"Quaas","sequence":"additional","affiliation":[{"name":"Institute of Pathology, Faculty of Medicine and University Hospital of Cologne, Kerpener Stra\u00dfe 62, 50937 Cologne, Germany"}]},{"given":"Katarzyna","family":"Bozek","sequence":"additional","affiliation":[{"name":"Data science of Bioimages Lab, Center for Molecular Medicine Cologne (CMMC), Faculty of Medicine and University Hospital of Cologne, Robert-Koch-Stra\u00dfe 21, 50937 Cologne, Germany"}]},{"given":"Christiane","family":"Bruns","sequence":"additional","affiliation":[{"name":"Department of General, Visceral and Cancer Surgery, Faculty of Medicine and University Hospital of Cologne, Kerpener Stra\u00dfe 62, 50937 Cologne, Germany"}]},{"given":"Felix","family":"Popp","sequence":"additional","affiliation":[{"name":"Department of General, Visceral and Cancer Surgery, Faculty of Medicine and University Hospital of Cologne, Kerpener Stra\u00dfe 62, 50937 Cologne, Germany"}]}],"member":"1968","published-online":{"date-parts":[[2024,3,19]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1038\/s41591-018-0300-7","article-title":"High-performance medicine: The convergence of human and artificial intelligence","volume":"25","author":"Topol","year":"2019","journal-title":"Nat. Med."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"685","DOI":"10.1007\/s12525-021-00475-2","article-title":"Machine learning and deep learning","volume":"31","author":"Janiesch","year":"2021","journal-title":"Electron. Mark."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"6240","DOI":"10.21037\/jtd-21-1107","article-title":"Application of machine learning approaches to predict the 5-year survival status of patients with esophageal cancer","volume":"13","author":"Gong","year":"2021","journal-title":"J. Thorac. Dis."},{"key":"ref_4","doi-asserted-by":"crossref","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":"2022","journal-title":"J. Cancer Res. Clin. Oncol."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1596","DOI":"10.1002\/cncr.20938","article-title":"Prediction of survival in patients with esophageal carcinoma using artificial neural networks","volume":"103","author":"Sato","year":"2005","journal-title":"Cancer"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Alaskar, H., and Saba, T. (2021). Machine Learning and Deep Learning: A Comparative Review, Springer.","DOI":"10.1007\/978-981-33-6307-6_15"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"622364","DOI":"10.3389\/frai.2021.622364","article-title":"Human- versus Artificial Intelligence","volume":"4","author":"Korteling","year":"2021","journal-title":"Front. Artif. Intell."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"706","DOI":"10.1038\/s41416-021-01485-9","article-title":"Advances in the curative management of oesophageal cancer","volume":"126","author":"Bolger","year":"2022","journal-title":"Br. J. Cancer"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1948","DOI":"10.1016\/S0140-6736(18)32557-1","article-title":"Perioperative chemotherapy with fluorouracil plus leucovorin, oxaliplatin, and docetaxel versus fluorouracil or capecitabine plus cisplatin and epirubicin for locally advanced, resectable gastric or gastro-oesophageal junction adenocarcinoma (FLOT4): A randomised, phase 2\/3 trial","volume":"393","author":"Homann","year":"2019","journal-title":"Lancet"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1995","DOI":"10.1200\/JCO.20.03614","article-title":"Ten-Year Outcome of Neoadjuvant Chemoradiotherapy Plus Surgery for Esophageal Cancer: The Randomized Controlled CROSS Trial","volume":"39","author":"Eyck","year":"2021","journal-title":"J. Clin. Oncol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"119","DOI":"10.21037\/acs.2017.03.14","article-title":"8th edition AJCC\/UICC staging of cancers of the esophagus and esophagogastric junction: Application to clinical practice","volume":"6","author":"Rice","year":"2017","journal-title":"Ann. Cardiothorac. Surg."},{"key":"ref_12","unstructured":"Robert Koch Institute, and The Association of Population-Based Cancer Registries in Germany (2022). Cancer in Germany 2017\/2018, Robert Koch Institute."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"7","DOI":"10.3322\/caac.21708","article-title":"Cancer statistics, 2022","volume":"72","author":"Siegel","year":"2022","journal-title":"CA A Cancer J. Clin."},{"key":"ref_14","unstructured":"Leitlinienprogramm Onkologie (Deutsche Krebsgesellschaft, D.K., AWMF) (2024, March 14). Diagnostik und Therapie der Plattenepithelkarzinome und Adenokarzinome des \u00d6sophagus, Langversion 4.0. AWMF-Registernummer: 021-023OL 2023. Available online: https:\/\/www.leitlinienprogramm-onkologie.de\/leitlinien\/oesophaguskarzinom\/."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"39","DOI":"10.2147\/CMAR.S101169","article-title":"Multidisciplinary management for esophageal and gastric cancer","volume":"8","author":"Boniface","year":"2016","journal-title":"Cancer Manag. Res."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"759","DOI":"10.1016\/S0140-6736(21)01234-4","article-title":"Pembrolizumab plus chemotherapy versus chemotherapy alone for first-line treatment of advanced oesophageal cancer (KEYNOTE-590): A randomised, placebo-controlled, phase 3 study","volume":"398","author":"Sun","year":"2021","journal-title":"Lancet"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1090","DOI":"10.1016\/S1470-2045(15)00040-6","article-title":"Neoadjuvant chemoradiotherapy plus surgery versus surgery alone for oesophageal or junctional cancer (CROSS): Long-term results of a randomised controlled trial","volume":"16","author":"Shapiro","year":"2015","journal-title":"Lancet Oncol."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"2287","DOI":"10.1007\/s00432-022-04025-x","article-title":"Fructose-1,6-bisphosphatase 1 (FBP1) is an independent biomarker associated with a favorable prognosis in esophageal adenocarcinoma","volume":"148","author":"Damanakis","year":"2022","journal-title":"J. Cancer Res. Clin. Oncol."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1016\/j.tranon.2019.10.013","article-title":"PIK3CA and KRAS Amplification in Esophageal Adenocarcinoma and their Impact on the Inflammatory Tumor Microenvironment and Prognosis","volume":"13","author":"Essakly","year":"2020","journal-title":"Transl. Oncol."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"2319","DOI":"10.1007\/s00432-020-03295-7","article-title":"Lymphocyte activation gene-3 (LAG3) mRNA and protein expression on tumour infiltrating lymphocytes (TILs) in oesophageal adenocarcinoma","volume":"146","author":"Gebauer","year":"2020","journal-title":"J. Cancer Res. Clin. Oncol."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Hoppe, S., Meder, L., Gebauer, F., Ullrich, R.T., Zander, T., Hillmer, A.M., Buettner, R., Plum, P., Puppe, J., and Malter, W. (2022). Trophoblast Cell Surface Antigen 2 (TROP2) as a Predictive Bio-Marker for the Therapeutic Efficacy of Sacituzumab Govitecan in Adenocarcinoma of the Esophagus. Cancers, 14.","DOI":"10.3390\/cancers14194789"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"2862647","DOI":"10.1155\/2020\/2862647","article-title":"Indoleamine 2,3-Dioxygenase (IDO) Expression Is an Independent Prognostic Marker in Esophageal Adenocarcinoma","volume":"2020","author":"Loeser","year":"2020","journal-title":"J. Immunol. Res."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"115179","DOI":"10.18632\/oncotarget.23112","article-title":"High protein and mRNA expression levels of TUBB3 (class III \u00df-tubulin) are associated with aggressive tumor features in esophageal adenocarcinomas","volume":"8","author":"Loeser","year":"2017","journal-title":"Oncotarget"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"18411","DOI":"10.1038\/s41598-020-75085-7","article-title":"Integrin alpha V (ITGAV) expression in esophageal adenocarcinoma is associated with shortened overall-survival","volume":"10","author":"Loeser","year":"2020","journal-title":"Sci. Rep."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Loeser, H., W\u00f6lwer, C.B., Alakus, H., Chon, S.H., Zander, T., Buettner, R., Hillmer, A.M., Bruns, C.J., Schroeder, W., and Gebauer, F. (2020). Y Chromosome Loss is a Frequent Event in Barrett\u2019s Adenocarcinoma and Associated with Poor Outcome. Cancers, 12.","DOI":"10.3390\/cancers12071743"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1758835920917571","DOI":"10.1177\/1758835920917571","article-title":"Mesothelin expression in esophageal adenocarcinoma and squamous cell carcinoma and its possible impact on future treatment strategies","volume":"12","author":"Moentenich","year":"2020","journal-title":"Ther. Adv. Med. Oncol."},{"key":"ref_27","first-page":"3665","article-title":"Claudin 18.2 expression in esophageal adenocarcinoma and its potential impact on future treatment strategies","volume":"19","author":"Moentenich","year":"2020","journal-title":"Oncol. Lett."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Plum, P.S., Gebauer, F., Kr\u00e4mer, M., Alakus, H., Berlth, F., Chon, S.H., Schiffmann, L., Zander, T., B\u00fcttner, R., and H\u00f6lscher, A.H. (2019). HER2\/neu (ERBB2) expression and gene amplification correlates with better survival in esophageal adenocarcinoma. BMC Cancer, 19.","DOI":"10.1186\/s12885-018-5242-4"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"1031","DOI":"10.1007\/s00432-020-03486-2","article-title":"GATA binding protein 6 (GATA6) is co-amplified with PIK3CA in patients with esophageal adenocarcinoma and is linked to neoadjuvant therapy","volume":"147","author":"Plum","year":"2021","journal-title":"J. Cancer Res. Clin. Oncol."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"1731","DOI":"10.1007\/s00432-018-2698-1","article-title":"Upregulation of insulin-like growth factor II mRNA-binding protein 3 (IMP3) has negative prognostic impact on early invasive (pT1) adenocarcinoma of the esophagus","volume":"144","author":"Plum","year":"2018","journal-title":"J. Cancer Res. Clin. Oncol."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"154","DOI":"10.1016\/j.tranon.2018.09.007","article-title":"Genomic Characterization of TP53-Wild-Type Esophageal Carcinoma","volume":"12","author":"Quaas","year":"2019","journal-title":"Transl. Oncol."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"1213","DOI":"10.1007\/s10120-021-01197-2","article-title":"Sex-specific prognostic effect of CD66b-positive tumor-infiltrating neutrophils (TANs) in gastric and esophageal adenocarcinoma","volume":"24","author":"Quaas","year":"2021","journal-title":"Gastric Cancer"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"569475","DOI":"10.3389\/fonc.2021.569475","article-title":"Occurrence of High Microsatellite-Instability\/Mismatch Repair Deficiency in Nearly 2,000 Human Adenocarcinomas of the Gastrointestinal Tract, Pancreas, and Bile Ducts: A Study From a Large German Comprehensive Cancer Center","volume":"11","author":"Quaas","year":"2021","journal-title":"Front. Oncol."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Schallenberg, S., Bork, J., Essakly, A., Alakus, H., Buettner, R., Hillmer, A.M., Bruns, C., Schroeder, W., Zander, T., and Loeser, H. (2020). Loss of the SWI\/SNF-ATPase subunit members SMARCF1 (ARID1A), SMARCA2 (BRM), SMARCA4 (BRG1) and SMARCB1 (INI1) in oesophageal adenocarcinoma. BMC Cancer, 20.","DOI":"10.1186\/s12885-019-6425-3"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Schiffmann, L.M., G\u00f6bel, H., L\u00f6ser, H., Schorn, F., Werthenbach, J.P., Fuchs, H.F., Plum, P.S., Bludau, M., Zander, T., and Schr\u00f6der, W. (2019). Elevated X-linked inhibitor of apoptosis protein (XIAP) expression uncovers detrimental prognosis in subgroups of neoadjuvant treated and T-cell rich esophageal adenocarcinoma. BMC Cancer, 19.","DOI":"10.1186\/s12885-019-5722-1"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"1115","DOI":"10.1007\/s10120-021-01195-4","article-title":"Optimized PD-L1 scoring of gastric cancer","volume":"24","author":"Eschbach","year":"2021","journal-title":"Gastric Cancer"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"1601","DOI":"10.1007\/s12094-021-02556-2","article-title":"Distribution of tumor-infiltrating-T-lymphocytes and possible tumor-escape mechanisms avoiding immune cell attack in locally advanced adenocarcinomas of the esophagus","volume":"23","author":"Schoemmel","year":"2021","journal-title":"Clin. Transl. Oncol."},{"key":"ref_38","first-page":"2825","article-title":"Scikit-learn: Machine Learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"ref_40","first-page":"1063","article-title":"Analysis of a random forests model","volume":"13","author":"Biau","year":"2012","journal-title":"J. Mach. Learn. Res."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Chen, T., and Guestrin, C. (2016, January 13\u201317). XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.","DOI":"10.1145\/2939672.2939785"},{"key":"ref_42","unstructured":"Meyers, R.A. (2003). Encyclopedia of Physical Science and Technology, Academic Press. [3rd ed.]."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Howard, J., and Gugger, S. (2020). Fastai: A Layered API for Deep Dearning. Information, 11.","DOI":"10.3390\/info11020108"},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Arik, S.\u00d6., and Pfister, T. (2021, January 2\u20139). TabNet: Attentive Interpretable Tabular Learning. Proceedings of the AAAI Conference on Artificial Intelligence, Online.","DOI":"10.1609\/aaai.v35i8.16826"},{"key":"ref_45","unstructured":"Dreamquark (2022, October 21). Pytorch_Tabnet. Available online: https:\/\/dreamquark-ai.github.io\/tabnet\/index.html."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Kleinbaum, D.G. (1994). Logistic Regression: A Self-Learning Text, Springer.","DOI":"10.1007\/978-1-4757-4108-7"},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Akiba, T., Sano, S., Yanase, T., Ohta, T., and Koyama, M. (2019, January 4\u20138). Optuna: A next-generation hyperparameter optimization framework. Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, Anchorage, AK, USA.","DOI":"10.1145\/3292500.3330701"},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"1340","DOI":"10.1093\/bioinformatics\/btq134","article-title":"Permutation importance: A corrected feature importance measure","volume":"26","author":"Altmann","year":"2010","journal-title":"Bioinformatics"},{"key":"ref_49","unstructured":"Mueller, Z. (2022, November 03). Walkwithfastai. Available online: https:\/\/walkwithfastai.com\/Regression_and_Permutation_Importance."},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"McKinney, W. (2010, January 28\u201330). Data structures for statistical computing in python. Proceedings of the 9th Python in Science Conference, Austin, TX, USA.","DOI":"10.25080\/Majora-92bf1922-00a"},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1038\/s41586-020-2649-2","article-title":"Array programming with NumPy","volume":"585","author":"Harris","year":"2020","journal-title":"Nature"},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1109\/MCSE.2007.55","article-title":"Matplotlib: A 2D graphics environment","volume":"9","author":"Hunter","year":"2007","journal-title":"Comput. Sci. Eng."},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"1087","DOI":"10.1016\/j.jclinepi.2006.01.014","article-title":"Review: A gentle introduction to imputation of missing values","volume":"59","author":"Donders","year":"2006","journal-title":"J. Clin. Epidemiol."},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1097\/SLA.0000000000002693","article-title":"Artificial Intelligence in Surgery: Promises and Perils","volume":"268","author":"Hashimoto","year":"2018","journal-title":"Ann. Surg."},{"key":"ref_55","doi-asserted-by":"crossref","first-page":"528","DOI":"10.1111\/apt.16778","article-title":"Systematic review with meta-analysis: Artificial intelligence in the diagnosis of oesophageal diseases","volume":"55","author":"Visaggi","year":"2022","journal-title":"Aliment. Pharmacol. Ther."},{"key":"ref_56","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1038\/nmeth.4642","article-title":"Statistics versus machine learning","volume":"15","author":"Bzdok","year":"2018","journal-title":"Nat. Methods"},{"key":"ref_57","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1097\/SLA.0000000000004794","article-title":"The AUGIS Survival Predictor: Prediction of Long-term and Conditional Survival after Esophagectomy Using Random Survival Forests","volume":"277","author":"Rahman","year":"2021","journal-title":"Ann. Surg."},{"key":"ref_58","unstructured":"Molnar, C., K\u00f6nig, G., Herbinger, J., Freiesleben, T., Dandl, S., Scholbeck, C.A., Casalicchio, G., Grosse-Wentrup, M., and Bischl, B. (2020). International Workshop on Extending Explainable AI beyond Deep Models and Classifiers, Springer."},{"key":"ref_59","doi-asserted-by":"crossref","first-page":"1970","DOI":"10.1200\/JCO.2001.19.7.1970","article-title":"Esophageal cancer: The mode of lymphatic tumor cell spread and its prognostic significance","volume":"19","author":"Hosch","year":"2001","journal-title":"J. Clin. Oncol."},{"key":"ref_60","doi-asserted-by":"crossref","first-page":"365","DOI":"10.1097\/SLA.0b013e31815aaadf","article-title":"The number of metastatic lymph nodes and the ratio between metastatic and examined lymph nodes are independent prognostic factors in esophageal cancer regardless of neoadjuvant chemoradiation or lymphadenectomy extent","volume":"247","author":"Mariette","year":"2008","journal-title":"Ann. Surg."},{"key":"ref_61","doi-asserted-by":"crossref","first-page":"1918","DOI":"10.1016\/S0003-4975(01)03203-9","article-title":"Transthoracic esophagectomy with radical mediastinal and abdominal lymph node dissection and cervical esophagogastrostomy for esophageal carcinoma","volume":"72","author":"Swanson","year":"2001","journal-title":"Ann. Thorac. Surg."},{"key":"ref_62","doi-asserted-by":"crossref","first-page":"2025","DOI":"10.1038\/s41416-023-02232-y","article-title":"Combined regression score predicts outcome after neoadjuvant treatment of oesophageal cancer","volume":"128","author":"Damanakis","year":"2023","journal-title":"Br. J. Cancer"},{"key":"ref_63","doi-asserted-by":"crossref","first-page":"347","DOI":"10.1002\/ijc.33544","article-title":"Nanog is a promising chemoresistant stemness marker and therapeutic target by iron chelators for esophageal cancer","volume":"149","author":"Narusaka","year":"2021","journal-title":"Int. J. Cancer"},{"key":"ref_64","doi-asserted-by":"crossref","first-page":"1947","DOI":"10.1002\/cncr.10418","article-title":"Prognostic significance of serum thymidine phosphorylase concentration in esophageal squamous cell carcinoma","volume":"94","author":"Shimada","year":"2002","journal-title":"Cancer"},{"key":"ref_65","doi-asserted-by":"crossref","unstructured":"Lv, L., Pan, K., Li, X.D., She, K.L., Zhao, J.J., Wang, W., Chen, J.G., Chen, Y.B., Yun, J.P., and Xia, J.C. (2011). The accumulation and prognosis value of tumor infiltrating IL-17 producing cells in esophageal squamous cell carcinoma. PLoS ONE, 6.","DOI":"10.1371\/journal.pone.0018219"},{"key":"ref_66","doi-asserted-by":"crossref","first-page":"940","DOI":"10.1136\/jcp.54.12.940","article-title":"The prognostic relevance of angiogenesis and mast cells in squamous cell carcinoma of the oesophagus","volume":"54","author":"Elpek","year":"2001","journal-title":"J. Clin. Pathol."},{"key":"ref_67","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1007\/s12029-013-9550-2","article-title":"Prognostic value of tumor-infiltrating mast cells in outcome of patients with esophagus squamous cell carcinoma","volume":"45","author":"Fakhrjou","year":"2014","journal-title":"J. Gastrointest. Cancer"}],"container-title":["Machine Learning and Knowledge Extraction"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2504-4990\/6\/1\/32\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T14:15:44Z","timestamp":1760105744000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-4990\/6\/1\/32"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,19]]},"references-count":67,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,3]]}},"alternative-id":["make6010032"],"URL":"https:\/\/doi.org\/10.3390\/make6010032","relation":{},"ISSN":["2504-4990"],"issn-type":[{"type":"electronic","value":"2504-4990"}],"subject":[],"published":{"date-parts":[[2024,3,19]]}}}