Advancing accuracy in breath testing for lung cancer: strategies for improving diagnostic precision in imbalanced data

• Published in: Respiratory research Vol. 25; no. 1; pp. 32 - 10
• Main Authors: Chen, Ke-Cheng, Kuo, Shuenn-Wen, Shie, Ruei-Hao, Yang, Hsiao-Yu
• Format: Journal Article
• Language: English
• Published: England BioMed Central Ltd 16.01.2024; BioMed Central; BMC
• Subjects: Accuracy; Algorithms; Analysis; Breath tests; Breath Tests - methods; Breathomics; Carbon nanotubes; Care and treatment; Case-Control Studies; Chemical sensors; Datasets; Decision trees; Diagnosis; Diagnostic systems; Diagnostic tests; Electronic Nose; Electronic noses; Exhalation; Humans; Humidity; Imbalanced learning; Lung cancer; Lung Neoplasms - diagnosis; Machine learning; Medical screening; Metabolites; Methods; Minority & ethnic groups; Neural networks; Pathology; Prediction models; Sample size; Sensitivity analysis; Sensor arrays; Sensors; Standard deviation; Support vector machines; VOCs; Volatile metabolite; Volatile Organic Compounds; Taiwan; United States > US; Volatile metabolite; Imbalanced learning; Breathomics; Electronic nose
• ISSN: 1465-993X; 1465-9921; 1465-993X
• DOI: 10.1186/s12931-024-02668-7

Breath testing using an electronic nose has been recognized as a promising new technique for the early detection of lung cancer. Imbalanced data are commonly observed in electronic nose studies, but methods to address them are rarely reported. The objectives of this study were to assess the accuracy of electronic nose screening for lung cancer with imbalanced learning and to select the best mechanical learning algorithm. We conducted a case‒control study that included patients with lung cancer and healthy controls and analyzed metabolites in exhaled breath using a carbon nanotube sensor array. The study used five machine learning algorithms to build predictive models and a synthetic minority oversampling technique to address imbalanced data. The diagnostic accuracy of lung cancer was assessed using pathology reports as the gold standard. We enrolled 190 subjects between 2020 and 2023. A total of 155 subjects were used in the final analysis, which included 111 lung cancer patients and 44 healthy controls. We randomly divided samples into one training set, one internal validation set, and one external validation set. In the external validation set, the summary sensitivity was 0.88 (95% CI 0.84-0.91), the summary specificity was 1.00 (95% CI 0.85-1.00), the AUC was 0.96 (95% CI 0.94-0.98), the pAUC was 0.92 (95% CI 0.89-0.96), and the DOR was 207.62 (95% CI 24.62-924.64). Electronic nose screening for lung cancer is highly accurate. The support vector machine algorithm is more suitable for analyzing chemical sensor data from electronic noses.