Machine learning: A non-invasive prediction method for gastric cancer based on a survey of lifestyle behaviors.
Machine learning: A non-invasive prediction method for gastric cancer based on a survey of lifestyle behaviors.
复制标题
机器学习：基于生活方式行为调查的胃癌无创预测方法。
DOI：
10.3389/frai.2022.956385
复制
发表时间：
2022
影响因子：
4
通讯作者：
Wu, Jian
中科院分区：
文献类型：
--
作者：
Jiang, Siqing;Gao, Haojun;He, Jiajin;Shi, Jiaqi;Tong, Yuling;Wu, Jian
胃癌仍然对人类健康构成巨大威胁。对消化道肿瘤的明确诊断和及时治疗具有极其重要的意义。传统的胃癌诊断方法（内窥镜、手术、病理组织提取）通常是侵入性的、昂贵的、耗时的。机器学习方法速度快、成本低，突破了传统方法的局限性，可以应用机器学习方法来诊断胃癌。本工作旨在利用个人行为生活方式和非侵入性特征构建廉价、无创、快速、高精度的胃癌诊断模型。对 3,630 名参与者进行了一项回顾性研究。通过交叉验证和测试集的泛化能力来评估开发的模型（极端梯度提升、决策树、随机森林和逻辑回归）。我们发现，与其他模型相比，使用基于极限梯度提升（XGBoost）算法的指纹开发的模型产生了更好的结果。该测试集的总体准确率为85.7%，AUC为89.6%，敏感性为78.7%，特异性为76.9%，阳性预测值为73.8%，验证了所提出的模型具有显着的医学价值和良好的应用前景。
Gastric cancer remains an enormous threat to human health. It is extremely significant to make a clear diagnosis and timely treatment of gastrointestinal tumors. The traditional diagnosis method (endoscope, surgery, and pathological tissue extraction) of gastric cancer is usually invasive, expensive, and time-consuming. The machine learning method is fast and low-cost, which breaks through the limitations of the traditional methods as we can apply the machine learning method to diagnose gastric cancer. This work aims to construct a cheap, non-invasive, rapid, and high-precision gastric cancer diagnostic model using personal behavioral lifestyles and non-invasive characteristics. A retrospective study was implemented on 3,630 participants. The developed models (extreme gradient boosting, decision tree, random forest, and logistic regression) were evaluated by cross-validation and the generalization ability in our test set. We found that the model developed using fingerprints based on the extreme gradient boosting (XGBoost) algorithm produced better results compared with the other models. The overall accuracy of which test set was 85.7%, AUC was 89.6%, sensitivity 78.7%, specificity 76.9%, and positive predictive values 73.8%, verifying that the proposed model has significant medical value and good application prospects.
登录
查看更多内容
影响因子：
3.7
作者：
Li B;Zhang N;Wang YG;George AW;Reverter A;Li Y
通讯作者：
Li Y
DOI：
10.1016/j.bpg.2021.101731
发表时间：
2021-05-08
影响因子：
3.2
作者：
Leja, Marcis;Line, Aija
通讯作者：
Line, Aija
影响因子：
24.5
作者：
Ono, H;Kondo, H;Yoshida, S
通讯作者：
Yoshida, S
影响因子：
8.5
作者：
Nobre, Joao;Neves, Rui Ferreira
通讯作者：
Neves, Rui Ferreira
影响因子：
3
作者：
Blagus R;Lusa L
通讯作者：
Lusa L