« Previous Abstract[Analysis of Peroxyacetyl Nitrate and Ozone During a Typical Photochemical Pollution Process at the Panyu Atmospheric Composition Station]    Next Abstract"Distinguishing between Decaffeinated and Regular Coffee by HS-SPME-GCxGC-TOFMS, Chemometrics, and Machine Learning" »

Lung Cancer

Title:		Breath profile as composite biomarkers for lung cancer diagnosis
Author(s):		Zou Y; Wang Y; Jiang Z; Zhou Y; Chen Y; Hu Y; Jiang G; Xie D;
Address:		"School of Electronic Information and Electrical Engineering, Changsha University, Changsha 410003, China. Research Center for Healthcare Data Science, Zhijiang Lab, Hangzhou, China. Tianhe Culture Chain Technologies Co Ltd., Changsha, 410008, China. Zhejiang Sir Run Run Shaw Hospital, Department of Medicine, Zhejiang University, Hangzhou 310027, China"
Journal Title:		Lung Cancer
Year:		2021
Volume:		20210130
Issue:
Page Number:		206 - 213
DOI:		10.1016/j.lungcan.2021.01.020
ISSN/ISBN:		1872-8332 (Electronic) 0169-5002 (Linking)
Abstract:		"OBJECTIVES: Lung cancer is continuously the leading cause of cancer related death, resulting from the lack of specific symptoms at early stage. A large-scale screening method may be the key point to find asymptomatic patients, leading to the reduction of mortality. METHODS: An alternative method combining breath test and a machine learning algorithm is proposed. 236 breath samples were analyzed by TD-GCMS. Breath profile of each sample is composed of 308 features extracted from chromatogram. Gradient boost decision trees algorithm was employed to recognize lung cancer patients. Bootstrap is performed to simulate real diagnostic practice, with which we evaluated the confidence of our methods. RESULTS: An accuracy of 85 % is shown in 6-fold cross validations. In statistical bootstrap, 72 % samples are marked as 'confident', and the accuracy of confident samples is 93 % throughout the cross validations. CONCLUSION: We have proposed such a non-invasive, accurate and confident method that might contribute to large-scale screening of lung cancer. As a consequence, more asymptomatic patients with early lung cancer may be detected"
Keywords:		"Biomarkers Biomarkers, Tumor Breath Tests Exhalation Humans *Lung Neoplasms/diagnosis *Volatile Organic Compounds Bootstrap statistics Exhaled breath analysis Gradient boost decision trees algorithm Lung cancer;"
Notes:		"MedlineZou, Yingchang Wang, Yu Jiang, Zaile Zhou, Yuan Chen, Ying Hu, Yanjie Jiang, Guobao Xie, Duan eng Research Support, Non-U.S. Gov't Ireland 2021/02/11 Lung Cancer. 2021 Apr; 154:206-213. doi: 10.1016/j.lungcan.2021.01.020. Epub 2021 Jan 30"