Artificial intelligence in endoscopic ultrasonography: risk stratification of gastric gastrointestinal stromal tumors.

IF 4.2 3区医学

Therapeutic Advances in Gastroenterology Pub Date : 2023-05-30 eCollection Date: 2023-01-01 DOI:10.1177/17562848231177156

Yi Lu, Lu Chen, Jiachuan Wu, Limian Er, Huihui Shi, Weihui Cheng, Ke Chen, Yuan Liu, Bingfeng Qiu, Qiancheng Xu, Yue Feng, Nan Tang, Fuchuan Wan, Jiachen Sun, Min Zhi

{"title":"Artificial intelligence in endoscopic ultrasonography: risk stratification of gastric gastrointestinal stromal tumors.","authors":"Yi Lu, Lu Chen, Jiachuan Wu, Limian Er, Huihui Shi, Weihui Cheng, Ke Chen, Yuan Liu, Bingfeng Qiu, Qiancheng Xu, Yue Feng, Nan Tang, Fuchuan Wan, Jiachen Sun, Min Zhi","doi":"10.1177/17562848231177156","DOIUrl":null,"url":null,"abstract":"Background: Previous studies have identified useful endoscopic ultrasonography (EUS) features to predict the malignant potential of gastrointestinal stromal tumors (GISTs). However, the results of the studies were not consistent. Artificial intelligence (AI) has shown promising results in medicine.Objectives: We aimed to build a risk stratification EUS-AI model to predict the malignancy potential of GISTs.Design: This was a retrospective study with external validation.Methods: We developed two models using EUS images from two hospitals to predict the GIST risk category. Model 1 was the four-category risk EUS-AI model, and Model 2 was the two-category risk EUS-AI model. The diagnostic performance of the models was validated with external cohorts.Results: A total of 1320 images (880 were very low-risk, 269 were low-risk, 68 were intermediate-risk, and 103 were high-risk) were finally chosen for building the models and test sets, and a total of 656 images (211 were very low-risk, 266 were low-risk, 88 were intermediate-risk, and 91 were high-risk) were chosen for external validation. The overall accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) for the four-category risk EUS-AI model in the external validation sets by tumor were 74.50%, 55.00%, 79.05%, 53.49%, and 81.63%, respectively. The accuracy, sensitivity, specificity, PPV, and NPV for the two-category risk EUS-AI model for the prediction of very low-risk GISTs in the external validation sets by tumor were 86.25%, 94.44%, 79.55%, 79.07%, and 94.59%, respectively.Conclusion: We developed a EUS-AI model for the risk stratification of GISTs with promising results, which may complement current clinical practice in the management of GISTs.Registration: The study has been registered in the Chinese Clinical Trial Registry (No. ChiCTR2100051191).","PeriodicalId":23022,"journal":{"name":"Therapeutic Advances in Gastroenterology","volume":"16 ","pages":"17562848231177156"},"PeriodicalIF":4.2000,"publicationDate":"2023-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ftp.ncbi.nlm.nih.gov/pub/pmc/oa_pdf/c3/59/10.1177_17562848231177156.PMC10233610.pdf","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Therapeutic Advances in Gastroenterology","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1177/17562848231177156","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2023/1/1 0:00:00","PubModel":"eCollection","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 0

Abstract

Background: Previous studies have identified useful endoscopic ultrasonography (EUS) features to predict the malignant potential of gastrointestinal stromal tumors (GISTs). However, the results of the studies were not consistent. Artificial intelligence (AI) has shown promising results in medicine.

Objectives: We aimed to build a risk stratification EUS-AI model to predict the malignancy potential of GISTs.

Design: This was a retrospective study with external validation.

Methods: We developed two models using EUS images from two hospitals to predict the GIST risk category. Model 1 was the four-category risk EUS-AI model, and Model 2 was the two-category risk EUS-AI model. The diagnostic performance of the models was validated with external cohorts.

Results: A total of 1320 images (880 were very low-risk, 269 were low-risk, 68 were intermediate-risk, and 103 were high-risk) were finally chosen for building the models and test sets, and a total of 656 images (211 were very low-risk, 266 were low-risk, 88 were intermediate-risk, and 91 were high-risk) were chosen for external validation. The overall accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) for the four-category risk EUS-AI model in the external validation sets by tumor were 74.50%, 55.00%, 79.05%, 53.49%, and 81.63%, respectively. The accuracy, sensitivity, specificity, PPV, and NPV for the two-category risk EUS-AI model for the prediction of very low-risk GISTs in the external validation sets by tumor were 86.25%, 94.44%, 79.55%, 79.07%, and 94.59%, respectively.

Conclusion: We developed a EUS-AI model for the risk stratification of GISTs with promising results, which may complement current clinical practice in the management of GISTs.

Registration: The study has been registered in the Chinese Clinical Trial Registry (No. ChiCTR2100051191).

Abstract Image

查看原文本刊更多论文

内窥镜超声造影中的人工智能：胃肠道间质瘤的风险分层。

背景：以往的研究发现了一些有用的内镜超声波（EUS）特征，可用于预测胃肠道间质瘤（GIST）的恶性潜能。然而，这些研究的结果并不一致。人工智能（AI）已在医学领域取得了可喜的成果：我们旨在建立一个预测 GISTs 恶性潜能的 EUS-AI 风险分层模型：设计：这是一项带有外部验证的回顾性研究：我们利用两家医院的 EUS 图像建立了两个模型，用于预测 GIST 的风险类别。模型 1 是四类风险 EUS-AI 模型，模型 2 是两类风险 EUS-AI 模型。结果：最终选择了 1320 张图像（880 张极低风险、269 张低风险、68 张中风险和 103 张高风险）建立模型和测试集，并选择了 656 张图像（211 张极低风险、266 张低风险、88 张中风险和 91 张高风险）进行外部验证。在外部验证组中，按肿瘤分类的四类风险 EUS-AI 模型的总体准确性、灵敏度、特异性、阳性预测值（PPV）和阴性预测值（NPV）分别为 74.50%、55.00%、79.05%、53.49% 和 81.63%。在外部验证集中，两类风险EUS-AI模型按肿瘤预测极低风险GIST的准确性、敏感性、特异性、PPV和NPV分别为86.25%、94.44%、79.55%、79.07%和94.59%：我们建立了一个用于GIST风险分层的EUS-AI模型，并取得了可喜的成果，该模型可以补充目前临床实践中对GIST的管理：该研究已在中国临床试验注册中心注册（编号：ChiCTR2100051191）。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Therapeutic Advances in Gastroenterology Medicine-Gastroenterology

自引率

2.40%

发文量

103

期刊介绍： Therapeutic Advances in Gastroenterology is an open access journal which delivers the highest quality peer-reviewed original research articles, reviews, and scholarly comment on pioneering efforts and innovative studies in the medical treatment of gastrointestinal and hepatic disorders. The journal has a strong clinical and pharmacological focus and is aimed at an international audience of clinicians and researchers in gastroenterology and related disciplines, providing an online forum for rapid dissemination of recent research and perspectives in this area. The editors welcome original research articles across all areas of gastroenterology and hepatology. The journal publishes original research articles and review articles primarily. Original research manuscripts may include laboratory, animal or human/clinical studies – all phases. Letters to the Editor and Case Reports will also be considered.