Raghareutai Kajornvit, Tanchotsrinon Watcharaporn, Sattayalertyanyong Onuma, Kaosombatwattana Uayporn
Division of Gastroenterology, Department of Medicine, Faculty of Medicine Siriraj Hospital, Mahidol University, Bangkok, 10700, Thailand.
Siriraj Informatics and Data Innovation Center, Siriraj Hospital, Mahidol University, Bangkok, Thailand.
BMC Med Inform Decis Mak. 2025 Mar 24;25(1):145. doi: 10.1186/s12911-025-02969-x.
Acute upper gastrointestinal bleeding (UGIB) is common in clinical practice and has a wide range of severity. Along with medical therapy, endoscopic intervention is the mainstay treatment for hemostasis in high-risk rebleeding lesions. Predicting the need for endoscopic intervention would be beneficial in resource-limited areas for selective referral to an endoscopic center. The proposed risk stratification scores had limited accuracy. We developed a machine learning model to predict the need for endoscopic intervention in patients with acute UGIB.
A prospectively collected database of UGIB patients from 2011 to 2020 was retrospectively reviewed. Patients older than 18 years diagnosed with UGIB who underwent endoscopy were included. Data comprised demographic characteristics, clinical presentation, and laboratory parameters. The cleaned data was used for model development and validation in Python. We conducted 80%-20% split sample training and test sets. The training set was used for supervised learning of 15 models using a stratified 5-fold cross-validation process. The model with the highest AUROC was then internally validated with the test set to evaluate performance.
Of 1389 patients, 615 (44.3%) of the cohorts received the endoscopic intervention (293 variceal- and 336 nonvariceal-bleeding interventions). Eighteen features, including demographic characteristics, clinical presentation, and laboratory parameters, were selected as input for 15 machine learning models. The result revealed that the linear discriminant analysis model could achieve the highest AUROC of 0.74 to predict endoscopic intervention. The model was validated with the test set, in which the AUROC was increased from 0.74 to 0.81. Finally, the model was deployed as a web application by Streamlit.
Our machine learning model can identify patients with acute UGIB who need endoscopic intervention with good performance. This may help primary care physicians prioritize patients who need referrals and optimize resource allocation in resource-limited areas. Further development and identification of more specific features might improve prediction performance.
None (Retrospective cohort study) PATIENT & PUBLIC INVOLVEMENT: None.
急性上消化道出血（UGIB）在临床实践中很常见，严重程度范围广泛。除药物治疗外，内镜干预是高危再出血病变止血的主要治疗方法。预测内镜干预的需求对于资源有限地区选择性转诊至内镜中心将是有益的。现有的风险分层评分准确性有限。我们开发了一种机器学习模型来预测急性UGIB患者对内镜干预的需求。
回顾性分析2011年至2020年前瞻性收集的UGIB患者数据库。纳入年龄大于18岁、诊断为UGIB且接受内镜检查的患者。数据包括人口统计学特征、临床表现和实验室参数。清理后的数据用于在Python中进行模型开发和验证。我们进行了80%-20%的样本拆分训练集和测试集。训练集用于使用分层5折交叉验证过程对15个模型进行监督学习。然后用测试集对具有最高曲线下面积（AUROC）的模型进行内部验证以评估性能。
在1389例患者中，615例（44.3%）接受了内镜干预（293例静脉曲张出血和336例非静脉曲张出血干预）。18个特征，包括人口统计学特征、临床表现和实验室参数，被选为15个机器学习模型的输入。结果显示，线性判别分析模型预测内镜干预的AUROC最高可达0.74。该模型在测试集中进行验证，其AUROC从0.74提高到0.81。最后，该模型通过Streamlit部署为一个网络应用程序。
我们的机器学习模型能够很好地识别需要内镜干预的急性UGIB患者。这可能有助于初级保健医生对需要转诊的患者进行优先排序，并在资源有限的地区优化资源分配。进一步开发和识别更具体的特征可能会提高预测性能。
无（回顾性队列研究）患者及公众参与：无。
