Analysis of functional connectivity using machine learning and deep learning in different data modalities from individuals with schizophrenia.

Objective. Schizophrenia(SCZ) is a severe mental disorder associated with persistent or recurrent psychosis, hallucinations, delusions, and thought disorders that affect approximately 26 million people worldwide, according to the World Health Organization. Several studies encompass machine learning (ML) and deep learning algorithms to automate the diagnosis of this mental disorder. Others study SCZ brain networks to get new insights into the dynamics of information processing in individuals suffering from the condition. In this paper, we offer a rigorous approach with ML and deep learning techniques for evaluating connectivity matrices and measures of complex networks to establish an automated diagnosis and comprehend the topology and dynamics of brain networks in SCZ individuals.Approach.For this purpose, we employed an functional magnetic resonance imaging (fMRI) and electroencephalogram (EEG) dataset. In addition, we combined EEG measures, i.e. Hjorth mobility and complexity, with complex network measurements to be analyzed in our model for the first time in the literature.Main results.When comparing the SCZ group to the control group, we found a high positive correlation between the left superior parietal lobe and the left motor cortex and a positive correlation between the left dorsal posterior cingulate cortex and the left primary motor. Regarding complex network measures, the diameter, which corresponds to the longest shortest path length in a network, may be regarded as a biomarker because it is the most crucial measure in different data modalities. Furthermore, the SCZ brain networks exhibit less segregation and a lower distribution of information. As a result, EEG measures outperformed complex networks in capturing the brain alterations associated with SCZ.Significance. Our model achieved an area under receiver operating characteristic curve (AUC) of 100% and an accuracy of 98.5% for the fMRI, an AUC of 95%, and an accuracy of 95.4% for the EEG data set. These are excellent classification results. Furthermore, we investigated the impact of specific brain connections and network measures on these results, which helped us better describe changes in the diseased brain.

Biomarkers in Parkinson Disease: global gene expression analysis in peripheral blood from patients with and without mutations in PARK2 and PARK8 / Biomarcadores na doença de Parkinson: avaliação da expressão gênica no sangue periférico de pacientes com e sem mutações nos genes PARK2 e PARK8

Objective: To evaluate the performance of gene expression analysis in the peripheral blood of Parkinson disease patients with different genetic profiles using microarray as a tool to identify possible diseases related biomarkers which could contribute to the elucidation of the pathological process, as well as be useful in diagnosis. Methods: Global gene expression analysis by means of DNA microarrays was performed in peripheral blood of Parkinson disease patients with previously identified mutations in PARK2 or PARK8 genes, Parkinson disease patients without known mutations in these genes and normal controls. Each group consisted of five individuals. Results: Global gene expression profiles were heterogeneous among patients and controls, and it was not possible to detect a consistent pattern between groups. However, analyzing genes with differential expression of p < 0.005 and fold change greater than or equal to 1.2, we were able to identify a small group of well-annotated genes. Conclusions: Despite the small sample size, the identification of differentially expressed genes suggests that the microarray technique may be useful in identifying potential biomarkers in the peripheral blood of Parkinson disease patients or in people at risk of developing the disease. This will be important once neuroprotective therapies become available, and may contribute to the identification of new pathways involved in the disease physiopathology. Results presented here should be further validated in larger groups of patients.

Objetivo: Avaliar a viabilidade da análise da expressão gênica por microarray no sangue periférico de pacientes com doença de Parkinson com diferentes perfis genéticos, para a identificação de marcadores que possam estar relacionados ao desenvolvimento da doença ou que possam se tornar úteis para o seu o diagnóstico. Métodos: Foram selecionados pacientes portadores de mutações nos genes PARK2 ou PARK8, além de parkinsonianos não-portadores dessas mutações e controles sadios, sendo cinco pessoas em cada grupo. A expressão gênica global foi analisada por microarray com RNA extraído do sangue periférico desses pacientes. Resultados: O perfil de expressão global apresentou grande heterogeneidade entre os pacientes, não sendo possível identificar um padrão diferencial entre os grupos. No entanto, utilizando como critérios de seleção p < 0,005 e fold-change maior ou igual a 1,2, observamos expressão diferencial de alguns genes específicos entre os diferentes grupos estudados. Conclusões: A detecção de expressão diferencial de alguns genes sugere que a técnica pode vir a ser útil na identificação de marcadores em sangue periférico que possam caracterizar pessoas com risco de desenvolver doença de Parkinson, o que será importante, uma vez que terapias neutroprotetoras se tornem disponíveis, bem como auxiliará na elucidação da fisiopatologia da doença, identificando novas vias de sinalização que possam estar comprometidas. Esses achados deverão ainda ser confirmados por novos estudos com ampliação das amostras e testes para validação dos genes identificados.

Biomarkers in Parkinson Disease: global gene expression analysis in peripheral blood from patients with and without mutations in PARK2 and PARK8.

OBJECTIVE: To evaluate the performance of gene expression analysis in the peripheral blood of Parkinson disease patients with different genetic profiles using microarray as a tool to identify possible diseases related biomarkers which could contribute to the elucidation of the pathological process, as well as be useful in diagnosis. METHODS: Global gene expression analysis by means of DNA microarrays was performed in peripheral blood of Parkinson disease patients with previously identified mutations in PARK2 or PARK8 genes, Parkinson disease patients without known mutations in these genes and normal controls. Each group consisted of five individuals. RESULTS: Global gene expression profiles were heterogeneous among patients and controls, and it was not possible to detect a consistent pattern between groups. However, analyzing genes with differential expression of p < 0.005 and fold change ≥ 1.2, we were able to identify a small group of well-annotated genes. CONCLUSIONS: Despite the small sample size, the identification of differentially expressed genes suggests that the microarray technique may be useful in identifying potential biomarkers in the peripheral blood of Parkinson disease patients or in people at risk of developing the disease. This will be important once neuroprotective therapies become available, and may contribute to the identification of new pathways involved in the disease physiopathology. Results presented here should be further validated in larger groups of patients.

Retrocollis, anterocollis or head tremor may predict the spreading of dystonic movements in primary cervical dystonia.

BACKGROUND AND PURPOSE: Few studies have attempted to develop clinical predictors for cervical dystonia (CD) aiming at progression of the dystonic movement. METHOD: We retrospectively evaluated 73 patients with primary CD who underwent treatment with Botulinum toxin type-A (BTX-A). The patients were assembled in two groups according to the spread of dystonia during follow-up: spreading and non-spreading CD. We performed a binary logistic regression model using spreading of cervical dystonia as dependent variable aiming to find covariates which increase the risk of spreading. RESULTS: Our logistic regression model found the following covariates and their respective risk ratios: time of disease >18.5 months=2.4, retrocollis=1.9, anterocollis=1.8, head tremor=1.6. CONCLUSION: Time of disease >18.5 months, retrocollis, anterocollis and head tremor may predict spreading of dystonic movement to other regions of the body in CD patients.

Retrocollis, anterocollis or head tremor may predict the spreading of dystonic movements in primary cervical dystonia / Retrocolis, anterocolis ou tremor cefálico podem predizer a progressão dos movimentos distônicos em pacientes com distonia cervical primária

BACKGROUND AND PURPOSE: Few studies have attempted to develop clinical predictors for cervical dystonia (CD) aiming at progression of the dystonic movement. METHOD: We retrospectively evaluated 73 patients with primary CD who underwent treatment with Botulinum toxin type-A (BTX-A). The patients were assembled in two groups according to the spread of dystonia during follow-up: spreading and non-spreading CD. We performed a binary logistic regression model using spreading of cervical dystonia as dependent variable aiming to find covariates which increase the risk of spreading. RESULTS: Our logistic regression model found the following covariates and their respective risk ratios: time of disease >18.5 months=2.4, retrocollis=1.9, anterocollis=1.8, head tremor=1.6. CONCLUSION: Time of disease >18.5 months, retrocollis, anterocollis and head tremor may predict spreading of dystonic movement to other regions of the body in CD patients.

INTRODUÇÃO: Poucos estudos avaliam preditores clínicos de progressão dos movimentos distônicos, para além da região cervical, em pacientes com distonia cervical (DC) primária. MÉTODO: Avaliamos, retrospectivamente, 73 pacientes com DC primária, que tinham sido submetidos ao tratamento com a toxina botulínica tipo A (BTX-A). Estes pacientes foram divididos em dois grupos de acordo com a progressão ou não da DC para outras áreas do corpo. Aplicamos um modelo de regressão logística binária usando a progressão da distonia como variável dependente com o objetivo de identificar co-variáveis que aumentassem o risco de progressão. RESULTADOS: O modelo de regressão logístico identificou as seguintes co-variáveis como preditoras de progressão e seus respectivos índices de risco: tempo de doença >18,5 meses=2,4, retrocolis=1,9, anterocolis=1,8, tremor cefálico=1,6. CONCLUSÃO: Tempo de doença >18,5 meses, retrocolis, anterocolis, e tremor cefálico podem predizer a progressão do movimento distônico para outras regiões do corpo em pacientes com DC primária.

Acoustic voice assessment in Parkinson's disease patients submitted to posteroventral pallidotomy.

UNLABELLED: Long-term complications in levodopa treated Parkinson's disease (PD) patients caused a resurgence of interest in pallidotomy as an option of treatment. However, postoperative complications such as speech disorders can occur. PURPOSE: The aim of this study is to evaluate the acoustic voice in PD patients, before and after posteroventral pallidotomy. METHOD: Twelve patients with PD were submitted to neurological and voice assessments during the off and on phases, in the pre-operative, 1st and 3rd post-operative months. The patients were evaluated with the UPDRS and the vocal acoustic parameters -- f0, NHR, jitter, PPQ, Shimmer, APQ (using the software MultiSpeech-Kay Elemetrics-3700). RESULTS: The off phase UPDRS scores revealed a tendency to improvement at the 1st month and the off phase worsened. The shimmer and APQ improved. CONCLUSION: This study shows that pallidotomy has little improvement on functional use of communication of PD patients.

Acoustic voice assessment in Parkinson's disease patients submitted to posteroventral pallidotomy

O uso prolongado da levodopa na doença de Parkinson (DP) pode ocasionar alterações em seu rendimento e possibilitou o interesse no ressurgimento da palidotomia. Contudo, complicações pós-operatórias podem ocorrer. OBJETIVO: O presente estudo tem por objetivo avaliar alguns parâmetros acústicos da voz de pacientes com DP pré e pós a realização da palidotomia posteroventral METODO: foram avaliados 12 pacientes com PD submetidos a avaliação neurológica e da voz durante as fases off e on do uso da levodopa, nos momentos pré-operatório, no primeiro e no terceiro mês pós-operatório. Os pacientes foram avaliados com base na escala UPDRS - item motor - e por meio dos parâmetros acústicos da voz - f0, NHR, jitter, PPQ, Shimmer, APQ (usando o software MDVP - Kay Elemetrics - 3700). RESULTADOS: Na fase off o escore UPDRS revelou tendência de melhora no 1º pós-operatório e na fase on piora. Os parâmetros acústicos shimmer e APQ apresentaram melhora. CONCLUSÃO: Este estudo mostrou que a palidotomia resulta em discreta melhora no uso funcional da comunicação dos pacientes com DP.