EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Machine learning model for predicting malnutrition risk in lung cancer patients after thoracoscopic resection: a multi-center study

Machine learning-Modell zur Vorhersage des Malnutritionsrisikos bei Lungenkrebspatient:innen nach thorakoskopischer Resektion: multizentrische Studie

Tianfeng Chen, Ruilan Pan, Ling Liang, Limei Xu, Mingyue Yang, Xiujuan Deng, Ping Wang

Frontiers in Oncology · 09.02.2026 · 16

DOI: 10.3389/fonc.2026.1727595 ↗

Auf einen Blick

Eine erklärbare ML-Analyse sagte das Risiko für postoperative Mangelernährung nach thorakoskopischer Resektion bei Lungenkrebs vorher. Das XGBoost-Modell zeigte die beste Leistung.

Fragestellung

Kann ein erklärbares Machine-Learning-Modell das Malnutritionsrisiko bei Lungenkrebspatient:innen nach thorakoskopischer Resektion vorhersagen?

Methode

Retrospektive Analyse mit externer prospektiver Validierung; acht ML-Modelle wurden verglichen, die Leistung mit DCA und ROC-Kurven bewertet, Interpretierbarkeit mit SHAP.

Ergebnisse

Im Gesamtkollektiv lag die Inzidenz der postoperativen Mangelernährung bei 11,3 % (159/1, 407). XGBoost erreichte AUC 0.845 (95% CI: 0.771–0.919) im Testset und 0.886 (95% CI: 0.841–0.932) in der externen Validierung.

Schlussfolgerung der Autor:innen

Das XGBoost-basierte erklärbare ML-Modell sagte das Malnutritionsrisiko effektiv voraus und verband Vorhersageleistung mit Interpretierbarkeit.

Kernaussagen

  • Postoperative Mangelernährung: 11,3 % (159/1, 407)
  • XGBoost: AUC 0.845 im Testset und 0.886 extern
  • SHAP machte die Risikofaktoren besser interpretierbar

Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Oncology, online erschienen am 09.02.2026. Verfasst von Tianfeng Chen und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of Nursing, Guangdong Medical University, Dongguan, Guangdong, China. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

Auf einen BlickAbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Early detection of malnutrition is critical for timely intervention in lung cancer patients undergoing thoracoscopic resection. Existing black-box prediction models lack clinical interpretability, limiting trust and application. The present study was conducted to predict malnutrition risk by establishing an explainable machine learning (ML) model and evaluate the model performance across several sites, so as to develop a web-based application to aid clinical decision-making.

Methods

A retrospective analysis was conducted on 1, 134 lung cancer patients who underwent thoracoscopic resection at Dongguan People’s Hospital between October 2021 and October 2024, consisting of a training set (n = 795) and a testing set (n = 339). Meanwhile, an external validation cohort (n=273) was prospectively enrolled at the Affiliated Hospital of Guangdong Medical University from March to June of 2025. Furthermore, univariate and multivariate analyses were employed to determine the individual risk variables for post-operative malnutrition. This study constructed eight ML models using Gradient Boosting Machine (GBM), Neural Network, Logistic Regression, Extreme Gradient Boosting (XGBoost), Random Forest, K-Nearest Neighbors (KNN), Adaptive Boosting (AdaBoost), and Support Vector Machine (SVM). The performance of the established models was assessed by decision curve analysis (DCA) and receiver operating characteristic (ROC) curves. Meanwhile, feature contributions and visualize model outputs were quantified using the SHapley Additive exPlanations (SHAP) method to enhance clinical interpretability. Consequently, a web-based risk calculator was created to assist in personalized forecasting.

Results

Among 1, 407 total patients, post-operative malnutrition incidence was 11.3% (159/1, 407). Multivariate analysis identified seven independent risk factors: albumin (ALB), Nutritional Risk Screening 2002 score, age, intraoperative blood loss, total drainage volume, Basic Activities of Daily Living (BADL) score, and serum potassium (K). The XGBoost model outperformed others, with AUC 0.845 (95% CI: 0.771–0.919) in the testing set and 0.886 (95% CI: 0.841–0.932) in external validation. SHAP analysis clarified the relative importance of risk factors, improving interpretability.

Conclusion

The XGBoost-based explainable ML model effectively predicts malnutrition risk in lung cancer patients after thoracoscopic resection. Integrating high predictive performance with interpretability, it supports clinical risk stratification and personalized nutritional interventions to improve post-operative outcomes. A publicly available web-based calculator facilitates easy clinical application.

Schlagwörter

Stichwörter der Autor:innen

SHAPlung cancermachine learningmalnutritionthoracoscopic resection

Autor:innen und Institutionen

  • School of Nursing, Guangdong Medical University, Dongguan, Guangdong, China.
  • Department of Thoracic Surgery, Affiliated Hospital of Guangdong Medical University, Zhanjiang, Guangdong, China.
  • Dongguan School of Clinical Medicine, Guangdong Medical University (Dongguan People's Hospital), Dongguan, Guangdong, China.

Zitieren

APA

Chen, T., Pan, R., Liang, L., Xu, L., Yang, M., Deng, X., & Wang, P. (2026). Machine learning model for predicting malnutrition risk in lung cancer patients after thoracoscopic resection: a multi-center study. Frontiers in Oncology, 16. https://doi.org/10.3389/fonc.2026.1727595

Vancouver

Chen T, Pan R, Liang L, Xu L, Yang M, Deng X, et al. Machine learning model for predicting malnutrition risk in lung cancer patients after thoracoscopic resection: a multi-center study. Frontiers in Oncology. 2026;16. doi:10.3389/fonc.2026.1727595

BibTeX
@article{Chen2026,
  author = {Chen, Tianfeng and Pan, Ruilan and Liang, Ling and Xu, Limei and Yang, Mingyue and Deng, Xiujuan and Wang, Ping},
  title = {Machine learning model for predicting malnutrition risk in lung cancer patients after thoracoscopic resection: a multi-center study},
  journal = {Frontiers in Oncology},
  year = {2026},
  volume = {16},
  doi = {10.3389/fonc.2026.1727595}
}
Kostenlos starten →