tlyonlogo
会员中心

最近浏览的商品：

0去询价篮结算
询价篮中还没有商品，赶紧选购吧！
当前位置: 首页 > 技术文献 > 应用文献 > 电子鼻联合机器学习对肺结节良恶性及中医证素呼气图谱辨识的单中心观察性研究
文章分类
公司动态
 公司新闻
 喜讯
新闻资讯
 行业要闻
 纪事
实验技术
 前处理
 电化学
 光谱
 气相色谱GC
 液相HPLC
 离子色谱
 离子迁移谱/质谱
 物性检测
 食品分析
 药物分析
 果蔬采后
 分子生物
 动物生理
 实验室建设
 光学测量
技术文献
 解决方案
 使用手册
 产品样本
 应用文献
 论文文集
价格目录
招聘启事
学术会议
浏览历史

电子鼻联合机器学习对肺结节良恶性及中医证素呼气图谱辨识的单中心观察性研究
来源: Shiyan TAN et al  发布日期: 2025-02-24  访问量: 15

导
读		 目的探讨电子鼻结合机器学习识别肺良恶性结节呼吸气味图和中医证候要素的能力。方法研究设计为单中心观察性研究。收集了2023年4月至2024年3月成都中医药大学医院心胸外科收治的108例肺结节患者的一般数据和4项诊断信息。采用辨证论治方法分析患者的中医病位和性质分布特征。使用Cyranose 320电子鼻收集口腔呼气的气味特征，并采用随机森林（RF）、K近邻（KNN）、逻辑回归（LR）、支持向量机（SVM）和极限梯度增强（XGBoost）等五种机器学习算法来识别良恶性肺结节和不同中医证候的呼气特征
标签: 电子鼻、呼气、肺良恶结节、机器学习
 

Recognition of breath odor map of benign and malignant pulmonary nodules and Traditional Chinese Medicine syndrome elements based on electronic nose combined with machine learning: An observational study in a single center

Shiyan TAN 1 ; Qiong ZENG 2 ; Hongxia XIANG 3 ; Qian WANG 3 ; Xi FU 4 ; Jiawei HE 1 ; Liting YOU 5 ; Qiong MA 1 ; Fengming YOU 4 ; Yifeng REN 4
 

1. Hospital of Chengdu University of Traditional Chinese Medicine, Chengdu, 610075, P. R. China
2. Jiangsu Provincial Military Region Xuzhou Fifth Retired Cadre Rest Center, Xuzhou, 221000, Jiangsu, P. R. China
3. Hospital of Chengdu University of Traditional Chinese Medicine, Chengdu, 610075, P. R. China 2.
4. 1. Hospital of Chengdu University of Traditional Chinese Medicine, Chengdu, 610075, P. R. China 3.TCM Regulating Metabolic Diseases Key Laboratory of Sichuan Province, Hospital of Chengdu University of Traditional Chinese Medicine, Chengdu, 610075, P. R. China
5. Department of Laboratory Medicine, West China Hospital, Sichuan University, Chengdu, 610041, P. R. China
 

Abstract:
Objective To explore the recognition capabilities of electronic nose combined with machine learning in identifying the breath odor map of benign and malignant pulmonary nodules and Traditional Chinese Medicine (TCM) syndrome elements. Methods The study design was a single-center observational study. General data and four diagnostic information were collected from 108 patients with pulmonary nodules admitted to the Department of Cardiothoracic Surgery of Hospital of Chengdu University of TCM from April 2023 to March 2024. The patients' TCM disease location and nature distribution characteristics were analyzed using the syndrome differentiation method. The Cyranose 320 electronic nose was used to collect the odor profiles of oral exhalation, and five machine learning algorithms including random forest (RF), K-nearest neighbor (KNN), logistic regression (LR), support vector machine (SVM), and eXtreme gradient boosting (XGBoost) were employed to identify the exhaled breath profiles of benign and malignant pulmonary nodules and different TCM syndromes. Results (1) The common disease locations in pulmonary nodules were ranked in descending order as liver, lung, and kidney; the common disease natures were ranked in descending order as Yin deficiency, phlegm, dampness, Qi stagnation, and blood deficiency. (2) The electronic nose combined with the RF algorithm had the best efficacy in identifying the exhaled breath profiles of benign and malignant pulmonary nodules, with an AUC of 0.91, accuracy of 86.36%, specificity of 75.00%, and sensitivity of 92.85%. (3) The electronic nose combined with RF, LR, or XGBoost algorithms could effectively identify the different TCM disease locations and natures of pulmonary nodules, with classification accuracy, specificity, and sensitivity generally exceeding 80.00%.Conclusion Electronic nose combined with machine learning not only has the potential capabilities to differentiate the benign and malignant pulmonary nodules, but also provides new technologies and methods for the objective diagnosis of TCM syndromes in pulmonary nodules.
 
目的 探究电子鼻联合机器学习对肺结节良恶性及中医证素呼气图谱的辨识效能。方法 研究设计为单中心观察性研究。收集2023年4月—2024年3月期间就诊于成都中医药大学附属医院心胸外科住院部108例肺结节患者的一般资料及四诊信息，通过证素辨证的方法分析患者中医病位、病性分布特点，运用Cyranose 320电子鼻采集口腔呼气的气味图谱，基于随机森林（random forest，RF）、K最近邻（K-nearest neighbor，KNN）、逻辑回归（logistic regression，LR）、支持向量机（support vector machine，SVM）、极端梯度提升（eXtreme gradient boosting，XGBoost）5种机器学习算法辨识肺结节良恶性及不同中医证素的呼气图谱。结果 （1）肺结节常见病位证素从高到低依次是肝、肺、肾；常见病性证素从高到低依次是阴虚、痰、湿、气滞、血虚。（2）电子鼻联合RF算法对肺结节良恶性呼气图谱辨识效能最佳，受试者工作特征曲线下面积（AUC）为0.91，准确度为86.36%，特异度为75.00%，灵敏度为92.85%。（3）电子鼻联合RF、LR或XGBoost算法能较好辨识肺结节不同病位、病性证素，其分类准确度、特异度及灵敏度普遍≥80.00%。结论  电子鼻联合机器学习不仅具备鉴别肺结节良恶性的潜力，亦可为肺结节中医客观化病证诊断提供新技术与新方法。

 


*本文内容非商业广告，仅供专业人士参考!

相关产品
相关文章