Department of the First Clinical Medical College, Gansu University of Traditional Chinese Medicine, Lanzhou, People's Republic of China.
Department of General Surgery, Gansu Provincial Hospital, Lanzhou, People's Republic of China.
BMC Med Inform Decis Mak. 2023 Oct 13;23(1):214. doi: 10.1186/s12911-023-02324-y.
The most prevalent mesenchymal-derived gastrointestinal cancers are gastric stromal tumors (GSTs), which have the highest incidence (60-70%) of all gastrointestinal stromal tumors (GISTs). However, simple and effective diagnostic and screening methods for GST remain a great challenge at home and abroad. This study aimed to build a GST early warning system based on a combination of machine learning algorithms and routine blood, biochemical and tumour marker indicators.
In total, 697 complete samples were collected from four hospitals in Gansu Province, including 42 blood indicators from 318 pretreatment GST patients, 180 samples of gastric polyps and 199 healthy individuals. In this study, three algorithms, gradient boosting machine (GBM), random forest (RF), and logistic regression (LR), were chosen to build GST prediction models for comparison. The performance and stability of the models were evaluated using two different validation techniques: 5-fold cross-validation and external validation. The DeLong test assesses significant differences in AUC values by comparing different ROC curves, the variance and covariance of the AUC value.
The AUC values of both the GBM and RF models were higher than those of the LR model, and this difference was statistically significant (P < 0.05). The GBM model was considered to be the optimal model, as a larger area was enclosed by the ROC curve, and the axes indicated robust model classification performance according to the accepted model discriminant. Finally, the integration of 8 top-ranked blood indices was proven to be able to distinguish GST from gastric polyps and healthy people with sensitivity, specificity and area under the curve of 0.941, 0.807 and 0.951 for the cross-validation set, respectively.
The GBM demonstrated powerful classification performance and was able to rapidly distinguish GST patients from gastric polyps and healthy individuals. This identification system not only provides an innovative strategy for the diagnosis of GST but also enables the exploration of hidden associations between blood parameters and GST for subsequent studies on the prevention and disease surveillance management of GST. The GST discrimination system is available online for free testing of doctors and high-risk groups at https://jzlyc.gsyy.cn/bear/mobile/index.html .
最常见的间充质来源的胃肠道癌症是胃间质瘤（GST），其在所有胃肠道间质瘤（GIST）中的发病率最高（60-70%）。然而，国内外对于 GST 仍然缺乏简单有效的诊断和筛查方法。本研究旨在建立一个基于机器学习算法和常规血液、生化和肿瘤标志物指标相结合的 GST 预警系统。
本研究共收集了来自甘肃省 4 家医院的 697 例完整样本，包括 318 例 GST 患者治疗前的 42 项血液指标、180 例胃息肉样本和 199 例健康个体。本研究选择了三种算法，梯度提升机（GBM）、随机森林（RF）和逻辑回归（LR），用于构建 GST 预测模型进行比较。使用两种不同的验证技术：5 折交叉验证和外部验证来评估模型的性能和稳定性。通过比较不同的 ROC 曲线来评估 AUC 值的 DeLong 检验，评估 AUC 值的方差和协方差。
GBM 和 RF 模型的 AUC 值均高于 LR 模型，差异具有统计学意义（P<0.05）。GBM 模型被认为是最优模型，因为 ROC 曲线所包围的区域更大，根据可接受的模型判别，坐标轴表明了稳健的模型分类性能。最后，证明整合 8 个排名最高的血液指标能够区分 GST 与胃息肉和健康人群，在交叉验证集的敏感性、特异性和 AUC 分别为 0.941、0.807 和 0.951。
GBM 表现出强大的分类性能，能够快速区分 GST 患者与胃息肉和健康个体。该识别系统不仅为 GST 的诊断提供了一种创新策略，还可以探索血液参数与 GST 之间的隐藏关联，为 GST 的预防和疾病监测管理的后续研究提供参考。GST 鉴别系统可在 https://jzlyc.gsyy.cn/bear/mobile/index.html 上免费供医生和高危人群进行在线测试。
