Non-Invasive Lung Cancer Diagnostics through Metabolites in Exhaled Breath: Influence of the Disease Variability and Comorbidities.
Azamat Z TemerdashevElina M GashimovaVladimir A PorkhanovIgor S PolyakovDmitry V PerunovEkaterina V DmitrievaPublished in: Metabolites (2023)
Non-invasive, simple, and fast tests for lung cancer diagnostics are one of the urgent needs for clinical practice. The work describes the results of exhaled breath analysis of 112 lung cancer patients and 120 healthy individuals using gas chromatography-mass spectrometry (GC-MS). Volatile organic compound (VOC) peak areas and their ratios were considered for data analysis. VOC profiles of patients with various histological types, tumor localization, TNM stage, and treatment status were considered. The effect of non-pulmonary comorbidities (chronic heart failure, hypertension, anemia, acute cerebrovascular accident, obesity, diabetes) on exhaled breath composition of lung cancer patients was studied for the first time. Significant correlations between some VOC peak areas and their ratios and these factors were found. Diagnostic models were created using gradient boosted decision trees (GBDT) and artificial neural network (ANN). The performance of developed models was compared. ANN model was the most accurate: 82-88% sensitivity and 80-86% specificity on the test data.
Keyphrases
- neural network
- data analysis
- gas chromatography mass spectrometry
- type diabetes
- clinical practice
- gas chromatography
- blood pressure
- liver failure
- insulin resistance
- metabolic syndrome
- cardiovascular disease
- pulmonary hypertension
- chronic kidney disease
- weight loss
- ms ms
- drug induced
- weight gain
- aortic dissection
- big data
- high fat diet induced
- machine learning
- decision making
- body mass index
- mass spectrometry
- skeletal muscle
- deep learning
- structural basis
- acute respiratory distress syndrome
- simultaneous determination
- extracorporeal membrane oxygenation