Superparamagnetic Clustering of Diabetes Patients Raman Spectra

Abstract

In this paper, we present a different way to the standard methods to classify Raman spectra whose grouping process is based on a phenomenon of clustering observed in nature at the atomic level and correctly described by the statistical physics model known as the Potts model, which represents the interacting spins on a crystalline lattice. This clustering method is known as the super paramagnetic clustering (SPC), which allows identifying hierarchical structures in data banks. In this novel method, we assigned a Potts spin to each data point (Raman spectrum) and introduced an interaction between neighboring points whose coupling strength is a decreasing function of the distance between the nearest neighboring sites. We found a hierarchical tree structure in our data bank of Raman spectra allowing us to discriminate between the spectra from control and diabetes patients. The sensitivity and specificity of the diabetes detection technique by Raman spectroscopy were calculated directly because the SPC method achieves an accurate determination of the members of each cluster. As a cross-check, SPC results were compared with published results of multivariate analysis, observing excellent agreements; however, the SPC method allows determining the members of all identified clusters explicitly.

Polisserosite associada à pericardite constritiva: relato de caso de doença de Concato

“…O sítio extrapulmonar mais acometido é o sistema linfático 9 . Estima-se que a tuberculose linfonodal represente aproximadamente 15% dos casos de tuberculose extrapulmonar 10 . Seus principais fatores de riscos são a coinfecção pelo HIV, sexo feminino, idade (crianças ou idosos) e diabéticos 10 .…”

“…Estima-se que a tuberculose linfonodal represente aproximadamente 15% dos casos de tuberculose extrapulmonar 10 . Seus principais fatores de riscos são a coinfecção pelo HIV, sexo feminino, idade (crianças ou idosos) e diabéticos 10 . É mais frequente em imunocomprometidos uma vez que frente a uma imunossupressão, os Bacilos de Koch presentes no pulmão ou em linfonodos, podem apresentar uma reativação pós primo-infecção e, eventualmente ingressar na circulação sistêmica, desencadeando uma reação de hipersensibilidade após ruptura de um foco caseoso e consequente contato com os antígenos da micobactéria 10 .…”

“…É mais frequente em imunocomprometidos uma vez que frente a uma imunossupressão, os Bacilos de Koch presentes no pulmão ou em linfonodos, podem apresentar uma reativação pós primo-infecção e, eventualmente ingressar na circulação sistêmica, desencadeando uma reação de hipersensibilidade após ruptura de um foco caseoso e consequente contato com os antígenos da micobactéria 10 . Podem ser acometidas, pleura, pericárdio, peritônio e meninges 10 . Esse quadro também pode ser denominado como tuberculose serosa 12 .…”

Vibrational Spectroscopy for Detection of Diabetes: A Review

“…Results showed 97.5% sensitivity and 91.2% specificity for correctly diagnosing the class of serum; however, no validation of the model was reported. 59 Blood plasma samples obtained from healthy (n ¼ 8) and type I diabetic individuals (n ¼ 12) were investigated not only using Raman spectroscopy, but also with Raman optical activity, electronic circular dichroism, and IR spectroscopy. LDA was used to evaluate each method individually, as well as combined.…”

Advances in Machine Learning Processing of Big Data from Disease Diagnosis Sensors

“…Unsupervised learning algorithms can learn from unlabeled data sets and visually represent them. Unsupervised learning is primarily employed in two domains: first, it enables the extraction of representative features from high-dimensional data to reduce data sparsity and complexity through dimensionality reduction techniques, such as principal component analysis (PCA) ,,,,, and t-distributed stochastic neighbor embedding (t-SNE); ,− second, it facilitates grouping of data points on the basis of pairwise similarity metrics using clustering methods, like K-Means clustering ,− and hierarchical clustering, − thereby revealing inherent relationships among the data.…”