Diagnosis by Volatile Organic Compounds in Exhaled Breath from Lung Cancer Patients Using Support Vector Machine...

Area of Science:

• Analytical Chemistry
• Biomedical Engineering
• Oncology

Background:

• Non-invasive screening for early lung cancer detection is crucial.
• Exhaled breath analysis faces challenges due to low concentrations of volatile organic compounds (VOCs).

Purpose of the Study:

• To develop a highly accurate method for diagnosing lung cancer using exhaled breath analysis.
• To identify specific VOC biomarkers for lung cancer detection.

Main Methods:

• Gas chromatography/mass spectrometry (GC/MS) was used to analyze VOCs in exhaled breath from lung cancer patients and healthy controls.
• Statistical analysis and a support vector machine (SVM) algorithm were employed to identify and classify VOC markers.
• The number of detected VOCs was reduced to identify a minimal set for accurate diagnosis.

Main Results:

• Sixty-eight VOCs were initially detected as potential marker species.
• A combination of five specific VOCs (acetonitrile, isoprene, 1-propanol, methanol, and hydrogen cyanide) demonstrated significant diagnostic capability.
• The selected VOC panel achieved an 89.0% screening accuracy for lung cancer detection.

Conclusions:

• A panel of five VOCs in exhaled breath can accurately screen for lung cancer.
• This finding supports the development of a desktop GC-sensor system for non-invasive lung cancer diagnosis.
• The identified VOC biomarkers offer a promising avenue for early disease detection.