EUVIMEDEUVIMED entdecken
Multizentrische StudieKohortenstudieOpen Access · CC BY 4.0

Machine learning models for predicting postoperative peritoneal metastasis after hepatocellular carcinoma rupture: a multicenter cohort study in China

Feng Xia iD, Qian Chen, Zhicheng Liu, Qiao Zhang, Bin Guo, Feimu Fan, Zhiyuan Huang, Jun Zheng, Hengyi Gao, Guobing Xia, Li Ren, Hongliang Mei und 4 weitere

The Oncologist · 2025

DOI: 10.1093/oncolo/oyae341 ↗

Kurz gefasst

Multizentrische Studie in der Zeitschrift The Oncologist, 2025. Verfasst von Feng Xia und 15 weiteren Autor:innen. Beteiligte Einrichtung: Department of Hepatic Surgery, Tongji Hospital, Tongji Medical College of Huazhong University of Science and Technology, Wuhan, Hubei, People's Repub…. Hauptthemen laut MEDLINE: Carcinoma, Hepatocellular, Liver Neoplasms, Peritoneal Neoplasms, Machine Learning. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of Hubei Province, Hengrui Hepatobiliary and Pancreatic Malignant Tumor Research Fund-Youth Research Fund, Key project of science and technology in Hubei Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Peritoneal metastasis (PM) after the rupture of hepatocellular carcinoma (HCC) is a critical issue that negatively affects patient prognosis. Machine learning models have shown great potential in predicting clinical outcomes; however, the optimal model for this specific problem remains unclear.

Methods

Clinical data were collected and analyzed from 522 patients with ruptured HCC who underwent surgery at 7 different medical centers. Patients were assigned to the training, validation, and test groups in a random manner, with a distribution ratio of 7:1.5:1.5. Overall, 78 (14.9%) patients experienced postoperative PM. Five different types of models, including logistic regression, support vector machines, classification trees, random forests, and deep learning (DL) models, were trained using these data and evaluated based on their receiver operating characteristic curve and area under the curve (AUC) values and F1 scores.

Results

The DL models achieved the highest AUC values (10-fold training cohort: 0.943, validation set: 0.928, and test set: 0.892) and F1 scores (10-fold training set: 0.917, validation cohort: 0.908, and test set:0.899) The results of the analysis indicate that tumor size, timing of hepatectomy, alpha-fetoprotein levels, and microvascular invasion are the most important predictive factors closely associated with the incidence of postoperative PM.

Conclusion

The DL model outperformed all other machine learning models in predicting postoperative PM after the rupture of HCC based on clinical data. This model provides valuable information for clinicians to formulate individualized treatment plans that can improve patient outcomes.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Carcinoma, HepatocellularLiver NeoplasmsPeritoneal NeoplasmsMachine LearningHumansMaleFemaleMiddle AgedChinaPrognosisCohort StudiesAgedAdult

Stichwörter der Autor:innen

machine learningmetastasisperitoneumprognostic factorsrupture hepatocellular carcinoma

Autor:innen und Institutionen

  • Department of Hepatic Surgery, Tongji Hospital, Tongji Medical College of Huazhong University of Science and Technology, Wuhan, Hubei, People's Republic of China.
  • Department of Emergency Medicine, Zhongshan People's Hospital Affiliated to Guangdong Medical University, Zhongshan, Guangdong, People's Republic of China.
  • Department of Science and Education, Shenzhen Baoan District People's Hospital, Shenzhen, Guangdong, People's Republic of China.
  • Department of Hepatobiliary and Pancreatic Surgery, Shenzhen Longhua District People's Hospital, Shenzhen, Guangdong, People's Republic of China.
  • Department of Hepatobiliary and Pancreatic Surgery, Huangshi Central Hospital, Hubei Polytechnic University, Huangshi, Hubei, People's Republic of China.
  • Department of Hepatobiliary Surgery, Affiliated Hospital of Qinghai University, Xining, Qinghai, People's Republic of China.

ORCID-Profile: Feng Xia, Peng Zhu

Förderung

  • Natural Science Foundation of Hubei Province
  • Hengrui Hepatobiliary and Pancreatic Malignant Tumor Research Fund-Youth Research Fund
  • Key project of science and technology in Hubei Province
  • General Project of Health Commission of Hubei Province

Zitieren

APA

Xia, F., Chen, Q., Liu, Z., Zhang, Q., Guo, B., Fan, F., Huang, Z., Zheng, J., Gao, H., Xia, G., Ren, L., Mei, H., Chen, X., Cheng, Q., Zhang, B., & Zhu, P. (2025). Machine learning models for predicting postoperative peritoneal metastasis after hepatocellular carcinoma rupture: a multicenter cohort study in China. The Oncologist. https://doi.org/10.1093/oncolo/oyae341

Vancouver

Xia F, Chen Q, Liu Z, Zhang Q, Guo B, Fan F, et al. Machine learning models for predicting postoperative peritoneal metastasis after hepatocellular carcinoma rupture: a multicenter cohort study in China. The Oncologist. 2025. doi:10.1093/oncolo/oyae341

BibTeX
@article{Xia2025,
  author = {Xia, Feng and Chen, Qian and Liu, Zhicheng and Zhang, Qiao and Guo, Bin and Fan, Feimu and Huang, Zhiyuan and Zheng, Jun and Gao, Hengyi and Xia, Guobing and Ren, Li and Mei, Hongliang and Chen, Xiaoping and Cheng, Qi and Zhang, Bixiang and Zhu, Peng},
  title = {Machine learning models for predicting postoperative peritoneal metastasis after hepatocellular carcinoma rupture: a multicenter cohort study in China},
  journal = {The Oncologist},
  year = {2025},
  doi = {10.1093/oncolo/oyae341}
}
Kostenlos starten →