Development and validation of a machine-learning model for preoperative risk of gastric gastrointestinal stromal tumors.

Autor:	Liang SQ; Department of Gastroenterology, Affiliated Hospital of North Sichuan Medical College, Nanchong, Sichuan, China., Cui YT; Department of Gastroenterology, Affiliated Hospital of North Sichuan Medical College, Nanchong, Sichuan, China., Hu GB; Department of Gastroenterology, Affiliated Hospital of North Sichuan Medical College, Nanchong, Sichuan, China., Guo HY; Department of Gastroenterology, Affiliated Hospital of North Sichuan Medical College, Nanchong, Sichuan, China., Chen XR; Department of Gastroenterology, Affiliated Hospital of North Sichuan Medical College, Nanchong, Sichuan, China., Zuo J; Department of Gastroenterology, Affiliated Hospital of North Sichuan Medical College, Nanchong, Sichuan, China., Qi ZR; Department of Gastroenterology, Affiliated Hospital of North Sichuan Medical College, Nanchong, Sichuan, China., Wang XF; Department of Gastroenterology, Affiliated Hospital of North Sichuan Medical College, Nanchong, Sichuan, China; Digestive Endoscopy Center, Affiliated Hospital of North Sichuan Medical College, Nanchong, Sichuan, China. Electronic address: 2750853458@qq.com.
Jazyk:	angličtina
Zdroj:	Journal of gastrointestinal surgery : official journal of the Society for Surgery of the Alimentary Tract [J Gastrointest Surg] 2024 Oct 22. Date of Electronic Publication: 2024 Oct 22.
DOI:	10.1016/j.gassur.2024.10.019
Abstrakt:	Background: Gastrointestinal stromal tumors (GISTs) have malignant potential, and treatment varies according to risk. However, no specific protocols exist to preoperatively assess the malignant potential of gastric stromal tumors (gGISTs). This study aimed to use machine learning (ML) to develop and validate clinically relevant preoperative models to predict the malignant potential of gGISTs. Methods: We screened patients diagnosed with gGISTs at the Affiliated Hospital of North Sichuan Medical College. We employed the Least Absolute Shrinkage and Selection Operator (LASSO) and logistic regression to identify risk factors. Subsequently, an ensemble of ML models was deployed to determine the optimal classifier. Additionally, we harnessed SHapley Additive exPlanations (SHAP) for tailored risk profiling. Results: We enrolled 318 patients with gGISTs. Utilizing LASSO regression and multifactorial logistic regression, we analyzed the training dataset, revealing that the presence of endoscopic ultrasound (EUS) high-risk features, tumor border clarity, tumor diameter, and monocyte-to-lymphocyte ratio (MLR) were significant predictors of high malignancy risk in gGIST. As determined by our ML approach, the logistic classification model demonstrated optimal performance, with an area under the receiver operating characteristic curve of 0.919 and 0.925 for the training and test sets, respectively. Furthermore, decision curve analysis substantiated the clinical relevance of the model. Conclusion: High-risk EUS features, ill-defined tumor margins, larger tumor diameters, and elevated MLR independently predicted heightened malignant potential in gGIST. We developed logistic regression models based on these factors, which were further interpreted using the SHAP methodology. This analytical approach facilitated personalized therapeutic decision-making for diverse patient populations. (Copyright © 2024. Published by Elsevier Inc.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu