Agradecimentos: This work was supported by CAPES, CNPq, INEO, and FAPESP (2018/22214-6). Flavio M. Shimizu thanks the support by CNPq and FAPESP (2012/15543-7). Acelino C. Sá thanks the support by CNPq (153855/2018-5). Daniel C. Braz thanks the Mato Grosso do Sul State University (UEMS) for the...

Agradecimentos: This work was supported by CAPES, CNPq, INEO, and FAPESP (2018/22214-6). Flavio M. Shimizu thanks the support by CNPq and FAPESP (2012/15543-7). Acelino C. Sá thanks the support by CNPq (153855/2018-5). Daniel C. Braz thanks the Mato Grosso do Sul State University (UEMS) for the training program

Abstract: The diagnosis of cancer and other diseases using data from non-specific sensors - such as the electronic tongues (e-tongues) -is challenging owing to the lack of selectivity, in addition to the variability of biological samples. In this study, we demonstrate that impedance data obtained...

Abstract: The diagnosis of cancer and other diseases using data from non-specific sensors - such as the electronic tongues (e-tongues) -is challenging owing to the lack of selectivity, in addition to the variability of biological samples. In this study, we demonstrate that impedance data obtained with an e-tongue in saliva samples can be used to diagnose cancer in the mouth. Data taken with a single-response microfluidic e-tongue applied to the saliva of 27 individuals were treated with multidimensional projection techniques and non-supervised and supervised machine learning algorithms. The distinction between healthy individuals and patients with cancer on the floor of mouth or oral cavity could only be made with supervised learning. Accuracy above 80% was obtained for the binary classification (YES or NO for cancer) using a Support Vector Machine (SVM) with radial basis function kernel and Random Forest. In the classification considering the type of cancer, the accuracy dropped to ca. 70%. The accuracy tended to increase when clinical information such as alcohol consumption was used in conjunction with the e-tongue data. With the random forest algorithm, the rules to explain the diagnosis could be identified using the concept of Multidimensional Calibration Space. Since the training of the machine learning algorithms is believed to be more efficient when the data of a larger number of patients are employed, the approach presented here is promising for computer-assisted diagnosis

COORDENAÇÃO DE APERFEIÇOAMENTO DE PESSOAL DE NÍVEL SUPERIOR - CAPES

CONSELHO NACIONAL DE DESENVOLVIMENTO CIENTÍFICO E TECNOLÓGICO - CNPQ

153855/2018-5

FUNDAÇÃO DE AMPARO À PESQUISA DO ESTADO DE SÃO PAULO - FAPESP

2012/15543-7; 2018/22214-6

Fechado