Machine learning and the nomogram as the accurate tools for predicting postoperative malnutrition risk in esophageal cancer patients

Aug 4, 2026

Upload by Skyler

Postoperative malnutrition is a common complication after esophageal cancer surgery and can impair recovery and long-term outcomes. This study developed and validated predictive models to estimate the risk of malnutrition at 1 month after esophagectomy. Using 1,693 curatively operated patients, feature selection relied on LASSO, eight machine learning models were trained, and a nomogram was built with multivariable logistic regression. Random Forest performed best, while the nomogram offered strong interpretability and clinical utility.

LanguageEnglish

CategoryHealthcare

FormatPDF

Pages13

Reading Time33 min

AccessFree to download

Background

Methods

Development and validation cohorts

Feature selection and model construction

Results

Incidence and model performance

Nomogram predictors and evaluation

Conclusion

OPEN ACCESS EDITED BY Jonathan Soldera, University of Caxias do Sul, Brazil REVIEWED BY Dina Keumala Sari, Universitas Sumatera Utara, Indonesia Yanquan Liu, Guangdong Medical University, China *CORRESPONDENCE Xiamei Chen [Amey0113@163.com](Amey0113@163.com)[ ](Amey0113@163.com)Mingfang Yan [ymfdoc@163.com](ymfdoc@163.com)[ ](ymfdoc@163.com)RECEIVED 05 April 2025 ACCEPTED 30 May 2025 PUBLISHED 18 June 2025 CITATION Lin Z, He H, Yan M, Chen X, Chen H and Ke J (2025) Machine learning and thenomogram as the accurate tools for predicting postoperative malnutrition risk in esophageal cancer patients. Front. Nutr. 12:1606470 . doi: 10.3389/fnut.2025.1606470 COPYRIGHT © 2025 Lin, He, Yan, Chen, Chen and Ke. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. TYPE Original Research PUBLISHED 18 June 2025 DOI 10.3389/fnut.2025.1606470 Machine learning and thenomogram as the accurate tools for predicting postoperative malnutrition risk in esophageal cancer patients Zhenmeng Lin 1,2, Hao He 1, Mingfang Yan 2*, Xiamei Chen3*, Hanshen Chen4 and Jianfang Ke 1 1 Department of Thoracic Oncology Surgery, Clinical Oncology School of Fujian Medical University & Fujian Cancer Hospital, Fuzhou, China, 2 Department of Anesthesiology Surgery, Clinical Oncology School of Fujian Medical University, Fujian Cancer Hospital, Fuzhou, China, 3 Department of Operation, Clinical Oncology School of Fujian Medical University & Fujian Cancer Hospital, Fuzhou, Fujian, China, 4 Department of Thoracic Oncology Surgery, First Affiliated Hospital of Fujian Medical University, Fuzhou, China Background: Postoperative malnutrition is a prevalent complication following esophageal cancer surgery, significantly impairing clinical recovery and longterm prognosis. This study aimed to develop and validate predictive models using machine learning algorithms and a nomogram to estimate the risk of malnutrition at 1 month after esophagectomy. Methods: A total of 1,693 patients who underwent curative esophageal cancer surgery were analyzed, with 1,251 patients allocated to the development cohort and 442 to the validation cohort. Feature selection was performed via the least absolute shrinkage and selection operator (LASSO) algorithm. Eight machine learning models were constructed and evaluated, alongside a nomogram developed through multivariable logistic regression. Results: The incidence of postoperative malnutrition was 45.4%(568/1,251) in the development cohort and 50.7%(224/442) in the validation cohort. Among machine learning models, the Random Forest (RF) model demonstrated optimal performance, achieving area under the receiver operating characteristic curve (AUC) values of 0.820 (95% CI: 0.796–0. 845) and 0.805 (95% CI: 0.771–0. 839) in the development and validation cohorts, respectively. The nomogram incorporated five clinically interpretable predictors: female gender, advanced age, low preoperative body mass index (BMI), neoadjuvant therapy history, and preoperative sarcopenia. It showed comparable discriminative ability, with AUCs of 0.801 (95% CI: 0.775–0. 826) and 0.795 (95% CI: 0.764–0. 828) in the respective cohorts (p > 0.05 vs. RF) . Calibration curves revealed strong agreement between predicted and observed outcomes, while decision curve analysis (DCA) confirmed substantial clinical utility across risk thresholds. Conclusion: Both machine learning and the nomogram provide accurate tools for predicting postoperative malnutrition risk in esophageal cancer patients. While RF showed marginally higher predictive performanc

FAQs

What problem does the study address in esophageal cancer patients?

The study focuses on predicting postoperative malnutrition risk one month after esophagectomy, a complication that can worsen recovery and long-term prognosis.

How were the predictive models developed and validated?

Data from 1,693 curatively operated patients were split into a development cohort (1,251) and a validation cohort (442). Feature selection used LASSO, eight machine learning models were evaluated, and a nomogram was created via multivariable logistic regression.

Which model performed best, and how did the nomogram compare?

The Random Forest model showed the highest discriminative performance in both cohorts. The nomogram demonstrated comparable AUC values and better clinical interpretability for individualized risk stratification.

Aug 4, 2026

Upload by Skyler