Liu Feiyuan, Long Qiaoyun, He Hui, Dong Shaowei, Zhao Li, Zou Chang, Wu Weiqing
Department of Scientific Research, The First Affiliated Hospital, Southern University of Science and Technology, Shenzhen People's Hospital, Shenzhen, China.
Department of Clinical Research Center, The First Affiliated Hospital, Southern University of Science and Technology, Shenzhen People's Hospital, Shenzhen, China.
Front Pharmacol. 2021 Mar 17;12:635481. doi: 10.3389/fphar.2021.635481. eCollection 2021.
The fecal immunochemical test (FIT) is a widely used strategy for colorectal cancer (CRC) screening with moderate sensitivity. To further increase the sensitivity of FIT in identifying colorectal neoplasia, in this study, we established a classifier model by combining FIT result and other demographic and clinical features. A total of 4,477 participants were examined with FIT and those who tested positive (over 100 ng/ml) were followed up by a colonoscopy examination. Demographic and clinical information of participants including four domains (basic information, clinical history, diet habits and life styles) that consist of 15 features were retrieved from questionnaire surveys. A mean decrease accuracy (MDA) score was used to select features that are mostly related to CRC. Five different algorithms including logistic regression (LR), classification and regression tree (CART), support vector machine (SVM), artificial neural network (ANN) and random forest (RF) were used to generate a classifier model, through a 10X cross validation process. Area under curve (AUC) and normalized mean squared error (NMSE) were used in the evaluation of the performance of the model. The top six features that are mostly related to CRC include age, gender, history of intestinal adenoma or polyposis, smoking history, gastrointestinal discomfort symptom and fruit eating habit were selected. LR algorithm was used in the generation of the model. An AUC score of 0.92 and an NMSE score of 0.076 were obtained by the final classifier model in separating normal individuals from participants with colorectal neoplasia. Our results provide a new "Funnel" strategy in colorectal neoplasia screening via adding a classifier model filtering step between FIT and colonoscopy examination. This strategy minimizes the need of colonoscopy examination while increases the sensitivity of FIT-based CRC screening.
粪便免疫化学检测（FIT）是一种广泛应用于结直肠癌（CRC）筛查的方法，其灵敏度中等。为了进一步提高FIT在识别结直肠肿瘤方面的灵敏度，在本研究中，我们通过结合FIT结果以及其他人口统计学和临床特征建立了一个分类模型。共有4477名参与者接受了FIT检测，检测结果呈阳性（超过100 ng/ml）的参与者随后接受了结肠镜检查。通过问卷调查获取了参与者的人口统计学和临床信息，包括由15个特征组成的四个领域（基本信息、临床病史、饮食习惯和生活方式）。使用平均准确性下降（MDA）分数来选择与CRC最相关的特征。通过10倍交叉验证过程，使用了包括逻辑回归（LR）、分类与回归树（CART）、支持向量机（SVM）、人工神经网络（ANN）和随机森林（RF）在内的五种不同算法来生成分类模型。使用曲线下面积（AUC）和归一化均方误差（NMSE）来评估模型的性能。选择了与CRC最相关的前六个特征，包括年龄、性别、肠道腺瘤或息肉病史、吸烟史、胃肠道不适症状和水果饮食习惯。使用LR算法生成模型。最终的分类模型在区分正常个体和结直肠肿瘤参与者时，获得了0.92的AUC分数和0.076的NMSE分数。我们的研究结果通过在FIT和结肠镜检查之间增加一个分类模型过滤步骤，为结直肠肿瘤筛查提供了一种新的“漏斗”策略。该策略在增加基于FIT的CRC筛查灵敏度的同时，最大限度地减少了结肠镜检查的需求。
