RESUMO

BACKGROUND: Diffuse large B-cell lymphoma (DLBCL) is classified into germinal center-like (GCB) and non-germinal center-like (non-GCB) cell-of-origin groups, entities driven by different oncogenic pathways with different clinical outcomes. DLBCL classification by immunohistochemistry (IHC)-based decision tree algorithms is a simpler reported technique than gene expression profiling (GEP). There is a significant discrepancy between IHC-decision tree algorithms when they are compared to GEP. METHODS: To address these inconsistencies, we applied the machine learning approach considering the same combinations of antibodies as in IHC-decision tree algorithms. Immunohistochemistry data from a public DLBCL database was used to perform comparisons among IHC-decision tree algorithms, and the machine learning structures based on Bayesian, Bayesian simple, Naïve Bayesian, artificial neural networks, and support vector machine to show the best diagnostic model. We implemented the linear discriminant analysis over the complete database, detecting a higher influence of BCL6 antibody for GCB classification and MUM1 for non-GCB classification. RESULTS: The classifier with the highest metrics was the four antibody-based Perfecto-Villela (PV) algorithm with 0.94 accuracy, 0.93 specificity, and 0.95 sensitivity, with a perfect agreement with GEP (κ = 0.88, P < 0.001). After training, a sample of 49 Mexican-mestizo DLBCL patient data was classified by COO for the first time in a testing trial. CONCLUSIONS: Harnessing all the available immunohistochemical data without reliance on the order of examination or cut-off value, we conclude that our PV machine learning algorithm outperforms Hans and other IHC-decision tree algorithms currently in use and represents an affordable and time-saving alternative for DLBCL cell-of-origin identification.

Assuntos

Algoritmos , Perfilação da Expressão Gênica , Centro Germinativo/patologia , Linfoma Difuso de Grandes Células B/classificação , Linfoma Difuso de Grandes Células B/patologia , Aprendizado de Máquina , Adulto , Idoso , Idoso de 80 Anos ou mais , Linfócitos B/patologia , Teorema de Bayes , Árvores de Decisões , Análise Discriminante , Feminino , Perfilação da Expressão Gênica/métodos , Perfilação da Expressão Gênica/estatística & dados numéricos , Humanos , Imuno-Histoquímica/métodos , Imuno-Histoquímica/estatística & dados numéricos , Linfoma Difuso de Grandes Células B/genética , Linfoma Difuso de Grandes Células B/metabolismo , Masculino , Pessoa de Meia-Idade

RESUMO

Deception is considered a psychological process by which one individual deliberately attempts to convince another person to accept as true what the liar knows to be false. This paper presents the use of functional near-infrared spectroscopy for deception detection. This technique measures hemodynamic variations in the cortical regions induced by neural activations. The experimental setup involved a mock theft paradigm with ten subjects, where the subjects responded to a set of questions, with each of their answers belonging to one of three categories: Induced Lies, Induced Truths, and Non-Induced responses. The relative changes of the hemodynamic activity in the subject's prefrontal cortex were recorded during the experiment. From this data, the changes in blood volume were derived and represented as false color topograms. Finally, a human evaluator used these topograms as a guide to classify each answer into one of the three categories. His performance was compared with that of a support vector machine (SVM) classifier in terms of accuracy, specificity, and sensitivity. The human evaluator achieved an accuracy of 84.33 % in a tri-class problem and 92 % in a bi-class problem (induced vs. non-induced responses). In comparison, the SVM classifier correctly classified 95.63 % of the answers in a tri-class problem using cross-validation for the selection of the best features. These results suggest a tradeoff between accuracy and computational burden. In other words, it is possible for an interviewer to classify each response by only looking at the topogram of the hemodynamic activity, but at the cost of reduced prediction accuracy.