TAN Shiyan 1 , ZENG Qiong 2 , XIANG Hongxia 1 , WANG Qian 1 , FU Xi 1,3 , HE Jiawei 1 , YOU Liting 4 , MA Qiong 1 , YOU Fengming 1,3 , REN Yifeng 1,3
  • 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, Jiangshu, 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;
  • 4. Department of Laboratory Medicine, West China Hospital, Sichuan University, Chengdu, 610041, P. R. China;
YOU Fengming, Email: yfmdoc@163.com; REN Yifeng, Email: ryftcm.dr@yahoo.com
Pulmonary nodules; electronic nose; machine learning; Traditional Chinese Medicine (TCM) syndrome elements; breath odor map
10.7507/1007-4848.202407045
Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables References Cited by

Purpose  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 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.