Parkinson’s disease (PD) is a neurodegenerative disorder that remains incurable. The available treatments for the disorder include pharmacologic therapies and deep brain stimulation (DBS). These approaches may cause distinct side effects and motor responses. This work presents the application oft-distributed stochastic neighbor embedding (t-SNE), which is a machine learning algorithm for nonlinear dimensionality reduction and data visualization, for the problem of discriminating neurologically healthy individuals from those suffering from PD (treated with levodopa and DBS). Furthermore, the assessment of classification methods is presented. Inertial and electromyographic data were collected while the subjects executed a sequence of four motor tasks. The results were focused on the comparison of the classification performance of a support vector machine (SVM) while discriminating two-dimensional feature sets estimated from Principal Component Analysis (PCA), Sammon’s mapping, andt-SNE. The results showed visual and statistical differences for all three investigated groups. Classification accuracy for PCA, Sammon’s mapping, andt-SNE was, respectively, 73.5%, 78.6%, and 96.9% for the training set and 67.8%, 74.1%, and 76.6% for the test set. The possibility of discriminating healthy individuals from those with PD treated with levodopa and DBS highlights the fact that each treatment method produces distinct motor behavior. The scatter plots resulting fromt-SNE could be used in the clinical practice as an objective tool for measuring the discrepancy between normal and abnormal motor behaviors, being thus useful for the adjustment of treatments and the follow-up of the disorder.

Over the years, a number of distinct treatments have been adopted for the management of the motor symptoms of Parkinson’s disease (PD), including pharmacologic therapies and deep brain stimulation (DBS). Efficacy is most often evaluated by subjective assessments, which are prone to error and dependent on the experience of the examiner. Our goal was to identify an objective means of assessing response to therapy. In this study, we employed objective analyses in order to visualize and identify differences between three groups: healthy control (N = 10), subjects with PD treated with DBS (N = 12), and subjects with PD treated with levodopa (N = 16). Subjects were assessed during execution of three dynamic tasks (finger taps, finger to nose, supination and pronation) and a static task (extended arm with no active movement). Measurements were acquired with two pairs of inertial and electromyographic sensors. Feature extraction was applied to estimate the relevant information from the data after which the high-dimensional feature space was reduced to a two-dimensional space using the nonlinear Sammon’s map. Non-parametric analysis of variance was employed for the verification of relevant statistical differences among the groups (p < 0.05). In addition, K-fold cross-validation for discriminant analysis based on Gaussian Finite Mixture Modeling was employed for data classification. The results showed visual and statistical differences for all groups and conditions (i.e., static and dynamic tasks). The employed methods were successful for the discrimination of the groups. Classification accuracy was 81 ± 6% (mean ± standard deviation) and 71 ± 8%, for training and test groups respectively. This research showed the discrimination between healthy and diseased groups conditions. The methods were also able to discriminate individuals with PD treated with DBS and levodopa. These methods enable objective characterization and visualization of features extracted from inertial and electromyographic sensors for different groups.

JUSTIFICATIVA E OBJETIVOS: A dor é uma sensação subjetiva e individual que causa muitos desconfortos para quem a sente. Dessa forma, é necessário por em prática métodos que a quantifiquem objetivamente. Vários estudos indicam que os potenciais evocados (PE) produzem respostas que podem refletir os processos dolorosos. Este estudo utilizou características extraídas da onda M, sendo esta um tipo de PE relacionado à resposta neuromuscular, como possíveis marcadores da sensação de dor. MÉTODO: Treze voluntários, sendo 6 do sexo masculino e 7 do sexo feminino, foram incluídos no estudo. Foram realizadas cinco sessões de um protocolo experimental. Em cada sessão o voluntário recebeu estímulos elétricos no músculo abdutor do hálux. Inicialmente foi aplicada uma corrente de 1 mA com 20 pulsos de 2 Hz. Depois a corrente elétrica foi incrementada de 1 mA em 1 mA até que o voluntário relatasse a dor máxima. Nos voluntários do sexo feminino foi registrado também o dia do ciclo menstrual em cada sessão do experimento. Foram avaliadas várias características das ondas M. RESULTADOS: O mínimo global da onda M é correlacionado com o aumento da amplitude da corrente elétrica do estímulo, consequentemente com o aumento da dor sentida pelo sujeito. Os participantes do sexo feminino relataram limiar e tolerância à dor com intensidades de corrente elétrica menor quando comparados aos voluntários do sexo masculino. CONCLUSÃO: O mínimo global da onda M mostrou relação com o aumento da sensação dolorosa sendo que no sexo masculino o limiar e a tolerância à dor foram maiores que no sexo feminino, e as diferentes fases do ciclo menstrual não interferiram nas avaliações.