EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

An artificial intelligence-based endoscopic ultrasonography risk assessment and stratification for gastric stromal tumors

Shan-Shan Hu, Ze-Yu Cao, Mi Ning, Xin Xiao, Xian-Min Deng, Hong-Ze Zeng, Chan Qiu, Li Zhong, Hang Yi, Ai-Min Liu, Dan-Ping Huang, Zhi-Hang Zhou und 1 weitere

Digestive and Liver Disease · 2026-10 · 58 (10) · 1329-1338

DOI: 10.1016/j.dld.2026.07.084 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Digestive and Liver Disease, 2026-10. Verfasst von Shan-Shan Hu und 12 weiteren Autor:innen. Beteiligte Einrichtung: Department of Gastroenterology and Hepatology, Sichuan Provincial People's Hospital, School of Medicine, University of Electronic Science and Technol…. Hauptthemen laut MEDLINE: Gastrointestinal Stromal Tumors, Endosonography, Artificial Intelligence, Stomach Neoplasms. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 17 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Science and Technology Department of Sichuan Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND: Gastrointestinal stromal tumors (GISTs) are tumors with malignant potential. This research aims to develop an artificial intelligence (AI)-based system for analyzing endoscopic ultrasonography (EUS) visuals and generating risk scores. AIMS: This system is designed to better predict GIST risk levels by identifying risk factors. METHODS: An internal dataset comprising 504 EUS images from 226 patients with pathologically confirmed GISTs was collected from Yuzhong Hospital and Jiangnan Hospital of the Second Affiliated Hospital of Chongqing Medical University, Sichuan Provincial People's Hospital between 2018 and 2024. Multiple AI-based machine learning models were developed and tested. Six machine learning models were compared, and the optimal diagnostic model was selected based on statistical results. RESULTS: For the best-performing model, XGBoost, the internal test set results were as follows: overall accuracy 83.17%, sensitivity 75.68%, specificity 93.72%, positive predictive value (PPV) 73.21%, negative predictive value (NPV) 93.52%, F1 score 0.74, and area under the curve (AUC) 0.97. The external validation set results were: overall accuracy 80.68%, sensitivity 71.53%, specificity 92.72%, PPV 70.44%, NPV 92.78%, F1 score 0.70, and AUC 0.94. CONCLUSIONS: This model utilizes machine learning algorithms on EUS images to accurately predict GIST risk stratification.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Gastrointestinal Stromal TumorsEndosonographyArtificial IntelligenceStomach NeoplasmsHumansRisk AssessmentFemaleMiddle AgedMaleBoosting Machine Learning AlgorithmsMachine LearningAgedPredictive Value of TestsSensitivity and SpecificityAdultPredictive Learning ModelsRisk Factors

Stichwörter der Autor:innen

AIEUSGISTMachine learningRisk stratification

Autor:innen und Institutionen

  • Department of Gastroenterology and Hepatology, Sichuan Provincial People's Hospital, School of Medicine, University of Electronic Science and Technology of China, Chengdu, 610000, Sichuan, China.
  • Department of Gastroenterology, Fuling Hospital of Chongqing University, Chongqing, 400000, China.
  • Department of Gastroenterology, The Second Affiliated Hospital of Chongqing Medical University, Chongqing, 400000, China.
  • Sichuan University of Science & Engineering, Zigong, 643000, Sichuan, China.
  • Department of Gastroenterology, The Second Affiliated Hospital of Sichuan College of Traditional Chinese Medicine & Anzhou District People's Hospital of Mianyang City, Mianyang, 621000, Sichuan, China.
  • Department of Gastroenterology, The Second Affiliated Hospital of Chongqing Medical University, Chongqing, 400000, China. Electronic address: ningbo@hospital.cqmu.edu.cn.

Förderung

  • Science and Technology Department of Sichuan Province

Zitieren

APA

Hu, S. S., Cao, Z. Y., Ning, M., Xiao, X., Deng, X. M., Zeng, H. Z., Qiu, C., Zhong, L., Yi, H., Liu, A. M., Huang, D. P., Zhou, Z. H., & Ning, B. (2026). An artificial intelligence-based endoscopic ultrasonography risk assessment and stratification for gastric stromal tumors. Digestive and Liver Disease, 58(10), 1329-1338. https://doi.org/10.1016/j.dld.2026.07.084

Vancouver

Hu SS, Cao ZY, Ning M, Xiao X, Deng XM, Zeng HZ, et al. An artificial intelligence-based endoscopic ultrasonography risk assessment and stratification for gastric stromal tumors. Digestive and Liver Disease. 2026;58(10):1329-1338. doi:10.1016/j.dld.2026.07.084

BibTeX
@article{Hu2026,
  author = {Hu, Shan-Shan and Cao, Ze-Yu and Ning, Mi and Xiao, Xin and Deng, Xian-Min and Zeng, Hong-Ze and Qiu, Chan and Zhong, Li and Yi, Hang and Liu, Ai-Min and Huang, Dan-Ping and Zhou, Zhi-Hang and Ning, Bo},
  title = {An artificial intelligence-based endoscopic ultrasonography risk assessment and stratification for gastric stromal tumors},
  journal = {Digestive and Liver Disease},
  year = {2026},
  volume = {58},
  number = {10},
  pages = {1329--1338},
  doi = {10.1016/j.dld.2026.07.084}
}
Kostenlos starten →