摘要
目的评估非特异性检验指标组成的预测模型在胃癌早期诊断中的可行性。方法从上海长海医院的电子病案系统数据库中,共纳入2010年1月1日至2019年4月30日的24615例病例记录,包括10497例胃癌,5198例胃癌前疾病,和8920名健康体检。通过分层随机抽样,将研究人群分为验证集、训练集和测试集。对所有实验室变量进行数据处理和质量控制后,通过梯度增强决策树、随机森林、支持向量机和人工神经元网络这4种机器学习算法,选择随机森林作为最优机器学习算法和诊断效能分组,使用后向逐步回归法训练数据,构建最佳特征模型采用受试者工作特征(ROC)曲线评价模型的诊断效能。结果本研究建立了由22个常规检验项目组成的诊断模型V22,诊断早期胃癌的ROC曲线下面积(AUC)为0.808,敏感度为85.7%;特异度为91.9%。对癌胚抗原(CEA)阴性胃癌,V22也显示出较高的诊断准确率0.813,AUC为0.801。结论V22是一个有临床应用价值的胃癌辅助诊断模型,可以很好的区分早期胃癌和由健康组和癌前疾病组成的对照组,对早期胃癌的检出率优于传统的肿瘤标志物CEA。
Objective To evaluate the feasibility of a predictire model composed of non-specific test indexes in early diagnosis of gastric cancer.Methods From the database of electronic medical record system of Shanghai Changhai Hospital,a total of 24615 case records were included from January 1,2010 to April 30,2019,including 10497 cases of gastric cancer,5198 cases of precancerous diseases,and 8920 cases of health examination.Through stratified random sampling,the study population was divided into validation set,training set and test set.After data processing and quality control for all laboratory variables,the optimal machine learning algorithm and diagnostic efficiency grouping were selected through four machine learning algorithms,induding the gradient boosting decision tree,random forest,support vector machine,and artificial neural network,and the data were trained by backward stepwise regression method to build the best feature model.Result In this study,a diagnostic model V22 consisting of 22 routine testing parameters was established.V22 could distinguish early gastric cancer from control group composed of healthy group and precancerous disease,AUC was 0.808,the sensitivity was 85.7%,and the specificity was 91.9%.For CEA negative gastric cancer,V22 also showed high diagnostic accuracy,AUC was 0.801.Conclusion V22 was a valuable model for the diagnosis of gastric cancer.V22 was an auxiliary diagnostic model of gastric cancer with clinical application value,which could well distinguish early gastric cancer from the control group composed of healthy group and precancerous disease,and the detection rate of early gastric cancer was better than the traditional tumor marker CEA.
作者
贾音
孙婷婷
刘海东
秦琴
朱俊
熊康
康金松
蓝欢
伍小凤
聂明明
刘善荣
Jia Yin;Sun Tingting;Liu Haidong;Qin Qin;Zhu Jun;Xiong Kang;Kang Jinsong;Lan Huan;Wu Xiaofeng;Nie Mingming;Liu Shanrong(Department of Laboratory Medicine,the First Affiliated Hospital of Navy Military Medical University,Shanghai 200433,China;Department of Gastrointestinal Surgery,the First Affiliated Hospital of Navy Military Medical University,Shanghai 200433,China)
出处
《中华检验医学杂志》
CAS
CSCD
北大核心
2021年第3期197-203,共7页
Chinese Journal of Laboratory Medicine
基金
上海市优秀学科带头人(18XD1405300)。
关键词
人工智能
胃肿瘤
大数据
实验诊断
Artificial intelligence
Stomach neoplasms
Big data
Laboratory diagnosis
