Colorectal cancer (CRC) is the third most common type of cancer worldwide and the second most deadly. Recent research efforts have focused on developing non-invasive techniques for CRC detection. In this study, we evaluated the diagnostic capabilities of diffuse reflectance spectroscopy (DRS) for CRC detection by building 6 classification models based on support vector machines (SVMs). Our dataset consists of 2889 diffuse reflectance spectra collected from freshly excised ex vivo tissues of 47 patients over wavelengths ranging from 350 and 1919 nm with source-detector distances of 630-µm and 2500-µm to probe different depths. Quadratic SVMs were used and performance was evaluated using twofold cross-validation on 10 iterations of randomized training and test sets. We achieved (93.5 ± 2.4)% sensitivity, (94.0 ± 1.7)% specificity AUC by probing the superficial colorectal tissue and (96.1 ± 1.8)% sensitivity, (95.7 ± 0.6)% specificity AUC by sampling deeper tissue layers. To the best of our knowledge, this is the first DRS study to investigate the potential of probing deeper tissue layers using larger SDD probes for CRC detection in the luminal wall. The data analysis showed that using a broader spectrum and longer near-infrared wavelengths can improve the diagnostic accuracy of CRC as well as probing deeper tissue layers.

Early diagnosis of COVID-19 in suspected patients is essential for contagion control and damage reduction strategies. We investigated the applicability of attenuated total reflection (ATR) Fourier transform infrared (FTIR) spectroscopy associated with machine learning in oropharyngeal swab suspension fluid to predict COVID-19 positive samples. The study included samples of 243 patients from two Brazilian States. Samples were transported by using different viral transport mediums (liquid 1 or 2). Clinical COVID-19 diagnosis was performed by the RT-PCR. We built a classification model based on partial least squares (PLS) associated with cosine k-nearest neighbours (KNN). Our analysis led to 84% and 87% sensitivity, 66% and 64% specificity, and 76.9% and 78.4% accuracy for samples of liquids 1 and 2, respectively. Based on this proof-of-concept study, we believe this method could offer a simple, label-free, cost-effective solution for high-throughput screening of suspect patients for COVID-19 in health care centres and emergency departments.

Melanoma is the most aggressive skin cancer type. It is characterized by pigmented lesions with high tissue invasion and metastatic potential. The early detection of melanoma is extremely important to improve patient prognosis and survival rate, since it can progress to the deadly metastatic stage. Presently, the melanoma diagnosis is based on the clinical analysis of the macroscopic lesion characteristics such as shape, color, borders following the ABCD rules. The aim of this study is to evaluate the time-resolved fluorescence lifetime of NADH and FAD molecules to detect cutaneous melanoma in an experimental in vivo model. Forty-two lesions were analyzed and the data was classified using linear discriminant analysis, a sensitivity of 99.4%, specificity of 97.4% and accuracy of 98.4% were achieved. These results show the potential of this fluorescence spectroscopy for melanoma detection.

Diabetes mellitus (DM) is a general term for heterogeneous metabolic disorders whose main characteristic is chronic hyperglycemia. Considering that conventional diagnostic methods are currently unable of early DM detection and the number of diabetic patients has been increasing worldwide, there is a clinical need for novel diagnostic approaches. Fourier-transform infrared (FT-IR) spectroscopy technique an alternative non-invasive diagnostic method for real-time evaluation of biofluids such as saliva. This study aims evaluate the feasibility of diagnosing diabetes and periodontitis through saliva samples based on their FT-IR spectra. Our first collection and spectral analysis of samples was a pilot study and comprised a total of 23 patients, 2 healthy, 9 with diabetes and 12 with diabetes and periodontitis. By using weighted KNN as classifier, we have obtained an area under the Receiver Operating Characteristic curve of 0.92 and 0.95 when considering the diabetes or diabetes + periodontitis groups as positive groups, respectively.

Actinic cheilitis is a potentially malignant disorder of the lips. Its first cause is believed to be UV sun radiation. The lesion is highly heterogeneous, making the choice of area to be biopsied difficult. This study exploits the capabilities of time-resolved fluorescence spectroscopy for the identification of the most representative area to be biopsied. A preliminary study was performed on fourteen patients. A classification algorithm was used on data acquired on nine different biopsies. The algorithm discriminated between absent, mild, and moderate dysplasia with a sensitivity of 92.9%, 90.0%, and 80.0%, respectively. The false positive rate for healthy tissue (specificity) was 88.8%.