EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Predicting postoperative malnutrition in patients with oral cancer: development of an XGBoost model with SHAP analysis and web-based application

Vorhersage postoperativer Mangelernährung bei Patient:innen mit Mundkrebs: Entwicklung eines XGBoost-Modells mit SHAP-Analyse und webbasierter Anwendung

Lixia Kuang, Jingya Yu, Yunyu Zhou, Yu Zhang, Guangman Wang, Fangmin Zhang, Grace Paka Lubamba, Xiaoqin Bi

Frontiers in Oncology · 12.05.2025 · 15

DOI: 10.3389/fonc.2025.1564459 ↗

Auf einen Blick

In einer prospektiven Studie mit 487 Patient:innen mit Mundkrebs sagte ein XGBoost-Modell postoperative Mangelernährung gut vorher. Die AUC lag bei 0,872 im Trainingssatz und 0,840 im Validierungssatz.

Fragestellung

Kann ein XGBoost-Modell postoperative Mangelernährung bei Patient:innen mit Mundkrebs vorhersagen?

Methode

Prospektive Studie in einem tertiären Krankenhaus in China; 487 postoperative Patient:innen mit Mundkrebs; Vergleich von LR, SVM, LGBM und XGBoost; Bewertung mit NRS-2002, GLIM, SHAP, Kalibrierung und DCA.

Ergebnisse

251 von 487 Patient:innen (51,54 %) hatten postoperative Mangelernährung. Sieben Prädiktoren wurden identifiziert: Geschlecht, T-Stadium, Rekonstruktion, Diabetes, Alter, Lymphozytenzahl und Gesamtcholesterin.

Schlussfolgerung der Autor:innen

Dies sei die erste Entwicklung eines XGBoost-basierten Modells zur Vorhersage postoperativer Mangelernährung bei Patient:innen mit Mundkrebs. SHAP und ein Web-Tool erhöhten laut Autor:innen die klinische Anwendbarkeit.

Kernaussagen

  • Postoperative Mangelernährung bei 51,54 % der 487 Patient:innen
  • XGBoost: AUC 0,872 im Training und 0,840 in der Validierung
  • Sieben Prädiktoren; SHAP-Analyse und Web-Tool integriert

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 12.05.2025. Verfasst von Lixia Kuang und 7 weiteren Autor:innen. Beteiligte Einrichtung: State Key Laboratory of Oral Diseases & National Center for Stomatology & National Clinical Research Center for Oral Diseases & Department of Orthogn…. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

Auf einen BlickAbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Postoperative malnutrition, which significantly affects recovery and overall quality of life, is a critical concern for patients with oral cancer. Timely identification of patients at nutritional risk is essential for implementing appropriate interventions, thereby improving postoperative outcomes.

Methods

This prospective study, which was conducted at a tertiary hospital in China between August 2023 and May 2024, included 487 postoperative oral cancer patients. The dataset was divided into a training set (70%) and a validation set (30%). Predictive models were developed via four supervised machine learning algorithms: logistic regression (LR), support vector machine (SVM), light gradient boosting machine (LGBM), and extreme gradient boosting (XGBoost). Nutritional risk was assessed via the Nutritional Risk Screening 2002 (NRS-2002) tool and diagnosed via the Global Leadership Initiative on Malnutrition (GLIM) criteria. Model performance was evaluated on the basis of discrimination, calibration, and clinical applicability, with SHAP analysis used for interpretability. Statistical analysis was conducted via R software, with appropriate tests for continuous and categorical variables.

Results

Of the 487 oral cancer patients, 251 (51.54%) experienced postoperative malnutrition. The study cohort was split into a training set comprising 340 patients and a validation set comprising 147 patients. Seven key predictors were identified, including sex, T stage, repair and reconstruction, diabetes status, age, lymphocyte count, and total cholesterol (TC) level. The XGBoost model demonstrated an area under the curve (AUC) of 0.872 (95% CI: 0.836–0.909) in the training set and 0.840 (95% CI: 0.777–0.904) in the validation set. Calibration curves confirmed the model’s robust fit, and decision curve analysis (DCA) indicated substantial clinical benefit.

Conclusion

This study represents the first development of an XGBoost-based model for predicting postoperative malnutrition in patients with oral cancer. The integration of SHAP for model interpretability, along with the creation of an intuitive web tool, enhances the model’s clinical applicability. This approach can significantly reduce malnutrition-related complications and improve recovery outcomes for oral cancer patients.

Schlagwörter

Stichwörter der Autor:innen

Shapley Additive exPlanations (SHAPs)machine learningmalnutritionoral neoplasmspostoperative complications

Autor:innen und Institutionen

  • State Key Laboratory of Oral Diseases & National Center for Stomatology & National Clinical Research Center for Oral Diseases & Department of Orthognathic and Temporomandibular Joint (TMJ) Surgery, West China Hospital o…
  • Department of Hepatobiliary, Chongqing Fuling Hospital, School of Medicine, Chongqing University, Chongqing, China.
  • West China School of Nursing, Sichuan University, Chengdu, China.
  • School of Stomatology, North Sichuan Medical College, Nanchong, Sichuan, China.
  • State Key Laboratory of Oral Diseases & National Center for Stomatology & National Clinical Research Center for Oral Diseases & Department of Head and Neck Oncology, West China Hospital of Stomatology, Sichuan Universit…
  • Department of Oral and Maxillofacial Surgery, University Clinics of Kinshasa, Faculty of Dental Medicine, University of Kinshasa, Kinshasa, Democratic Republic of Congo.

Zitieren

APA

Kuang, L., Yu, J., Zhou, Y., Zhang, Y., Wang, G., Zhang, F., Lubamba, G. P., & Bi, X. (2025). Predicting postoperative malnutrition in patients with oral cancer: development of an XGBoost model with SHAP analysis and web-based application. Frontiers in Oncology, 15. https://doi.org/10.3389/fonc.2025.1564459

Vancouver

Kuang L, Yu J, Zhou Y, Zhang Y, Wang G, Zhang F, et al. Predicting postoperative malnutrition in patients with oral cancer: development of an XGBoost model with SHAP analysis and web-based application. Frontiers in Oncology. 2025;15. doi:10.3389/fonc.2025.1564459

BibTeX
@article{Kuang2025,
  author = {Kuang, Lixia and Yu, Jingya and Zhou, Yunyu and Zhang, Yu and Wang, Guangman and Zhang, Fangmin and Lubamba, Grace Paka and Bi, Xiaoqin},
  title = {Predicting postoperative malnutrition in patients with oral cancer: development of an XGBoost model with SHAP analysis and web-based application},
  journal = {Frontiers in Oncology},
  year = {2025},
  volume = {15},
  doi = {10.3389/fonc.2025.1564459}
}
Kostenlos starten →