Development of Classification Rules for a Screening Diagnostics of Lung Cancer Patients Based on the Spectral Analysis of Metabolic Profiles in the Exhaled Air

Abstract

The pattern recognition technique was used for the development of classification rules for a screening diagnostics of lung cancer (LC) patients, based on the spectral analysis of metabolic profiles in the exhaled air, measured by the IR laser photoacoustic spectroscopy (LPAS). The study involved LC, chronic obstructive pulmonary disease, pneumonia patients, and healthy volunteers. The analysis of the measured spectra of exhaled air samples was based first on reduction of the dimension of the feature space using principal component analysis (PCA); thereafter the dichotomous classification was carried out using the support vector machine (SVM). The approaches to differential diagnostics based on the set of SVM classifiers usage are presented.

Types of spectroscopy and microscopy techniques for cancer diagnosis: a review

“…The experimental data analysis was carried out using a support vector machine (SVM) which is a differential classification predictive machine learning. Informative feature extraction was realized by PCA, and the model provided up to 90% binary classification accuracy [125,127,128]. The PAS was used to monitor breast cancer development [129] with frequency-doubled 281-nm excitation source using an Nd:YAG and dye laser.…”

Laser photoacoustic spectroscopy applications in breathomics

“…These "One-vs-One" classifiers allow one to construct differential diagnosis rules. One of the possible approaches to this task is enumeration of these classifiers for a feature vector of an object under study [20]. Below the differential diagnostics rule was based on the result of "One-vs-One" classifications, which was appeared more times.…”