An infrared spectroscopic blood test for non-small cell lung carcinoma and subtyping into pulmonary squamous cell carcinoma or adenocarcinoma

Abstract

Abstract. BACKGROUND:Lung cancer is the leading cause of death for male and female cancer patients alike. Early diagnosis improves prognosis. A blood test would be a valuable support. OBJECTIVE: Infrared spectroscopy provides a label-free biochemical fingerprint of a sample. A study was conducted on 161 patients with initial cancer suspicion to identify and verify spectral biomarker candidate patterns to detect non-small cell lung carcinoma (NSCLC). METHODS: Blood serum and plasma samples were analysed with an automated FTIR spectroscopic system. Two pattern recognition algorithms and two classifiers were applied. Monte Carlo cross validation was performed with linear discriminant analysis and random forest classification. RESULTS: Marker patterns for the discrimination of cancer from clinically relevant disease control patients were identified in FTIR spectra of blood samples. An accuracy of up to 79% was achieved. Squamous cell and adenocarcinoma patients were separable with an accuracy of 80%. CONCLUSIONS: The study demonstrates the applicability of FTIR spectroscopic blood testing for lung cancer detection. Evidence for cancer subtype discrimination is given. With an improved performance, the method could be developed as a routine diagnostic tool for blood testing detecting NSCLC.

Comments on recent reports on infrared spectral detection of disease markers in blood components

“…Thus, recent reports detailing the detection of specific disease in dried blood serum or plasma samples, such as the detection of cancer of the brain , prostate , bladder , lung , breast ovary , liver and bile duct , may have to be re‐evaluated in terms of their claims of detecting a specific disease. Rather, these reports may have detected a disease‐induced change in the AGR that may be much larger than signals expected for specific disease markers.…”

PRFFECT: A versatile tool for spectroscopists

“…Tester) we provide a robust methodology to make it easier to test different pre- The Random Forest (RF) machine learning algorithm is widely used in many different fields of research, including cheminformatics, [10,11] bioinformatics, [12], and ecology, [13]. Within the field of biomedical spectroscopy, RF has been used in the annotation of lung cancer subtypes [14] and in the diagnosis of nonsmall cell lung carcinoma, [15] urinary bladder cancer, [16], hyperlipidemia [17], and brain tumours [7]. RF has proven to be a robust and accurate technique for developing spectral diagnostic models, giving excellent classification results without over-fitting.…”

Application of Fourier Transform-Infrared Spectroscopy as a Tool for Early Cancer Detection

“…It was suggested that FTIR in sputum cells showed high sensitivity and specificity in diagnosing the disease within a small range of significant wave numbers [10] . Another study was performed on 161 patients with initial cancer suspicion with the FTIR analysis of blood sample to identify non-small cell lung carcinoma (NSCLC) [43] . Biochemical differences between blood samples of control and lung carcinoma patients were detected in the spectra and an accuracy of 80% was achieved in separation of squamous cell and adenocarcinoma patients.…”