Michel Velázquez Mariño

This paper proposes a generic architecture for devising interactive neurological assessment tests, aimed at being implemented on a touchscreen device. The objective is both to provide a set of software primitives that allow the modular implementation of tests, and to contribute to the standardization of test protocols. Although our original goal was the application of machine learning methods to the analysis of test data, it turned out that the construction of such framework was a pre-requisite… Mostrar más

This paper proposes a generic architecture for devising interactive neurological assessment tests, aimed at being implemented on a touchscreen device. The objective is both to provide a set of software primitives that allow the modular implementation of tests, and to contribute to the standardization of test protocols. Although our original goal was the application of machine learning methods to the analysis of test data, it turned out that the construction of such framework was a pre-requisite to collect enough data with the required levels of accuracy and reproducibility. In the proposed architecture, tests are defined by a set of stimuli, responses, feedback information, and execution control procedures. The presented definition has allowed for the implementation of a particular test, the Finger-Nose-Finger, that will allow the exploitation of data with intelligent techniques. Mostrar menos

In this paper we evaluate the use of the machine learning algorithms Support Vector Machines (SVM), K-Nearest Neighbors (KNN) and Classification and Regression Trees (CART) to identify non-spontaneous saccades in clinical electrooculography tests. We propose a modification to an adaptive threshold estimation algorithm for detecting signal impulses without the need for any manually pre-established parameters. Data mining tasks such as feature selection and model tuning were performed, obtaining… Mostrar más

In this paper we evaluate the use of the machine learning algorithms Support Vector Machines (SVM), K-Nearest Neighbors (KNN) and Classification and Regression Trees (CART) to identify non-spontaneous saccades in clinical electrooculography tests. We propose a modification to an adaptive threshold estimation algorithm for detecting signal impulses without the need for any manually pre-established parameters. Data mining tasks such as feature selection and model tuning were performed, obtaining very efficient models using only 3 attributes: amplitude deviation, absolute response latency and relative latency. The models were evaluated with signals recorded from subjects affected by Spinocerebellar Ataxia type 2 (SCA2). Results obtained by the algorithm show accuracies over 98%, recalls over 98 % and precisions over 95 % for the three models evaluated. Mostrar menos

One of the most common clinical tests to assess dysmetria is the Finger-Nose-Finger test. Despite it common use in healthcare, we do not have any reference about of a contribution studies of extracted variables in this test to discriminate between incoordination stages of subjects. This paper presents a study of the contribution of the features extracted from Finger-Nose-Finger using a touch-screen device. For this purpose 10 patients with Spinocerebellar Ataxia Type 2 and 10 control subjects… Mostrar más

One of the most common clinical tests to assess dysmetria is the Finger-Nose-Finger test. Despite it common use in healthcare, we do not have any reference about of a contribution studies of extracted variables in this test to discriminate between incoordination stages of subjects. This paper presents a study of the contribution of the features extracted from Finger-Nose-Finger using a touch-screen device. For this purpose 10 patients with Spinocerebellar Ataxia Type 2 and 10 control subjects were evaluated. The importances of features were extracted using the Random Forests algorithm. Features with higher importances were features related to the times responses. These results concluded that the assessment protocol allows classifying patients in different coordination stages, but does not allow an objective assessment of dysmetria and its components. The features related with dysmetria do not present importances values to achieve differentiate between healthy subjects and patients. Mostrar menos

The Finger-to-nose test (FNT) is an accepted neurological evaluation to study the coordination conditions. In this work, a methodology for the analysis of data from FNT is proposed, aimed at assessing the evolution of the condition of Spinocerebellar Ataxia type 2 (SCA2) patients. First of all, test results obtained from both patients and healthy individuals are processed through principal component analysis in order to reduce data dimensionality. Next, data were grouped in order to determine… Mostrar más

The Finger-to-nose test (FNT) is an accepted neurological evaluation to study the coordination conditions. In this work, a methodology for the analysis of data from FNT is proposed, aimed at assessing the evolution of the condition of Spinocerebellar Ataxia type 2 (SCA2) patients. First of all, test results obtained from both patients and healthy individuals are processed through principal component analysis in order to reduce data dimensionality. Next, data were grouped in order to determine classes of typical responses. The Mean Shift algorithm was used to perform an unsupervised clustering with no previous assumption on the number of clusters, whereas the k-means method provided an independent validation on the optimal cluster number. Experimental results showed the highest internal evaluation for distribution into three clusters, which could be identified as the responses of healthy subjects, SCA2 patients with medium incoordination level, and patients with severe incoordination. A membership function is defined, which allows to establish the subjects’ condition based on the classification of their responses. The results support that these protocols and the implemented clustering procedure can be used to accurately evaluate the incoordination stages of healthy subjects and SCA2 patients, thus offering a method to assess the impact of therapies and the progression of incoordination. Mostrar menos

Objective: To present the current advances of cerebellar injures that give rise to cognitive functioning deficits, specifically in the type 2 spinocerebellar ataxia (SCA2). Development: The role of the cerebellum on the control, integration and learning of motor activities is well known. The projections coming from the prefrontal cortex, temporo–parietal y paralimbic, through the thalamus allow the cerebellum to access higher order information. The mechanisms the brain use are complex and are… Mostrar más

Objective: To present the current advances of cerebellar injures that give rise to cognitive functioning deficits, specifically in the type 2 spinocerebellar ataxia (SCA2). Development: The role of the cerebellum on the control, integration and learning of motor activities is well known. The projections coming from the prefrontal cortex, temporo–parietal y paralimbic, through the thalamus allow the cerebellum to access higher order information. The mechanisms the brain use are complex and are not completely known. It is considered that different cognitive deficits that are manifested in the cerebellar pathology are not produced by injure itself, yet by the disruption of different afferent and efferent connections with cortical and paralimbic associations. Conclusions: Two positions have been assumed by the scientific community regarding the deficits which the cerebellar injures causes, those who argue the cerebellum role on cognitive and emotional functions, and those who, on the other hand, disagree with this argument, focusing the cerebellum role to, exclusively, the motor component associated to every single behavior. Mostrar menos

In this paper an analysis of Spinocerebellar Ataxia type 2 (SCA2) and cognitive processes is performed from the model of information processing. The SCA2 is an autosomal dominant hereditary ataxia and progressive. Within this disease one of the least discussed aspects in the scientific community are the cognitive aspects. Recent studies show the possible involvement of the cerebellum in high-level functions such as memory, language, attention and thought. Therefore SCA2 in cognitive deficits… Mostrar más

In this paper an analysis of Spinocerebellar Ataxia type 2 (SCA2) and cognitive processes is performed from the model of information processing. The SCA2 is an autosomal dominant hereditary ataxia and progressive. Within this disease one of the least discussed aspects in the scientific community are the cognitive aspects. Recent studies show the possible involvement of the cerebellum in high-level functions such as memory, language, attention and thought. Therefore SCA2 in cognitive deficits associated with cerebellar degeneration shown. Mostrar menos

A saccade is an ocular movement that is characterized by speed and precision. The velocity profile of this movement is used to extract the maximum speed value, that is one of the most important features of the saccade. A gamma function was used by other authors to describe the waveform shape of the velocity profile. However, this function does not present an optimal profile description in records of patients suffering from Spinocerebellar Ataxia type 2. In order to find a function that better… Mostrar más

A saccade is an ocular movement that is characterized by speed and precision. The velocity profile of this movement is used to extract the maximum speed value, that is one of the most important features of the saccade. A gamma function was used by other authors to describe the waveform shape of the velocity profile. However, this function does not present an optimal profile description in records of patients suffering from Spinocerebellar Ataxia type 2. In order to find a function that better describes the velocity profile, this contribution compares the fittings of several functions through visual and numerical analysis. Results showed a better performance of the partial sums of gaussian series and a gaussian fit function. Mostrar menos

In this paper we evaluate the use of the machine learning algorithms Support Vector Machines (SVM), K-Nearest Neighbors (KNN), Classification and Regression Trees (CART) and Naive Bayes (NB) to identify non spontaneous saccades in clinical electrooculography tests. Our approach tries to solve problems like the use of manually established thresholds present in classical methods like identification by velocity threshold (I-VT) or identification by dispersion threshold (I-DT). We propose a… Mostrar más

In this paper we evaluate the use of the machine learning algorithms Support Vector Machines (SVM), K-Nearest Neighbors (KNN), Classification and Regression Trees (CART) and Naive Bayes (NB) to identify non spontaneous saccades in clinical electrooculography tests. Our approach tries to solve problems like the use of manually established thresholds present in classical methods like identification by velocity threshold (I-VT) or identification by dispersion threshold (I-DT). We propose a modification to an adaptive threshold estimation algorithm for detecting signal impulses without the need of any user input. Also, a set of features were selected to take advantage of intrinsic characteristics of clinical electrooculography tests. The models were evaluated with signals recorded to subjects affected by Spinocerebellar Ataxia type 2 (SCA2). Results obtained by the algorithm show accuracies over 97%, recalls over 97% and precisions over 91% for the four models evaluated. Mostrar menos

An accepted model for the saccade signal of ocular motor neurons comprises two components in the form of a pulse and a step. In this contribution, an assessment of two fitting functions for the saccadic pulse component is made, in order to obtain a reduced set of descriptors that could be used for the early diagnosis of ataxia. Results show that both models have achieved to describe the waveform of the saccadic pulse signal, evealing higher performance of Gauss series over the gamma function.

The study of eye movements is a vital tool for the diagnosis of an important number of neurological disorders. Among these movements, saccadic are an important target in a wide range of neurological diseases. These movements are generated by two independent neural centers, one in the form of pulse and a step-shaped. The pulse and step can be separated using a technique called Independent Component Analysis (ICA) for further study. This paper is about the practical application of this method in… Mostrar más

The study of eye movements is a vital tool for the diagnosis of an important number of neurological disorders. Among these movements, saccadic are an important target in a wide range of neurological diseases. These movements are generated by two independent neural centers, one in the form of pulse and a step-shaped. The pulse and step can be separated using a technique called Independent Component Analysis (ICA) for further study. This paper is about the practical application of this method in the processing of eye movements records using NSEog tool developed by the authors. Besides, a proposal for saccadic eye movement simulator is presented using the pulse-step model. Mostrar menos

The finger-finger test is used to diagnose coordination’s issues, and is performed by an evaluator who commands the patient to perform special movements with their fingers. According the data yielded by the test, the evaluator is capable to establish subject’s condition. This paper covers the development of a device which can be used to assess the finger-finger test. This device is able to detect which finger is in contact with the thumb allowing to an informatic system to capture those data… Mostrar más

The finger-finger test is used to diagnose coordination’s issues, and is performed by an evaluator who commands the patient to perform special movements with their fingers. According the data yielded by the test, the evaluator is capable to establish subject’s condition. This paper covers the development of a device which can be used to assess the finger-finger test. This device is able to detect which finger is in contact with the thumb allowing to an informatic system to capture those data and process it, decreasing in that way the subjectivity of the diagnose. Mostrar menos

This article describes the implementation of an experiment to determine the optimal capture zone of kinect sensor depth map. Addresses the issues related to gait disorders in Spinocerebellar Ataxia type 2. Describes the relevant aspects of the sensor. It also describes briefly how does it works and on what is used. The experimental results are discussed and statistical analysis thereof is performed. Finally gait tests are suggested taking into account the characteristics of the sensor and the… Mostrar más

This article describes the implementation of an experiment to determine the optimal capture zone of kinect sensor depth map. Addresses the issues related to gait disorders in Spinocerebellar Ataxia type 2. Describes the relevant aspects of the sensor. It also describes briefly how does it works and on what is used. The experimental results are discussed and statistical analysis thereof is performed. Finally gait tests are suggested taking into account the characteristics of the sensor and the study results. Mostrar menos

This paper describes a process to extract information from electrooculography records relevant to clinical diagnose. The process has five ordered stages: baseline wander correction, filtering, differentiation; segmentation and feature extraction; being each one output the input of the next. In each stage the best fit method founded in the literature for perform its task is presented. Finally, a software platform which make use of this process is briefly described.

The finger-nose test is one of the most used neurological test. Different variants has been developed provoking problems to homologate studies results, to follow disease progression and to establish accurate clinical scales. The aim of this work is to show the implementation of finger-nose test using an Android Tablet. Results can be used to study coordination movement in upper limbs and to evaluate rehabilitation therapies.

The Spinocerebellar Ataxia type 2 is character-ized by gait ataxia, diminished saccade velocity, cerebellar dysarthria and dysmetria of upper and lower limbs; and reach the highest world prevalence rate in Holguín province, Cuba. Quantify the upper limbs coordination in ataxic patients is part of their neurological exam and is a valuable tool to evaluate the impact of rehabilitation. Keep-the-path test as-sess the hand movement coordination and consists of drawing a superposed path to… Mostrar más

The Spinocerebellar Ataxia type 2 is character-ized by gait ataxia, diminished saccade velocity, cerebellar dysarthria and dysmetria of upper and lower limbs; and reach the highest world prevalence rate in Holguín province, Cuba. Quantify the upper limbs coordination in ataxic patients is part of their neurological exam and is a valuable tool to evaluate the impact of rehabilitation. Keep-the-path test as-sess the hand movement coordination and consists of drawing a superposed path to mathematical curve defined by the examiner, as quick and accu-racy as possible. The responses of the patients' test performance are characterized by rapid and little movements provoked by the own disease condition, this, joined to the variability of the scheduling algo-rithms for the process in different operating sys-tems, make difficult to select the appropriate sample frequency for the signal acquisition. For solve this Mostrar menos

The Spinocerebellar Ataxia type 2 is characterized by an ataxic gait, diminished saccade velocity, cerebellar dysarthria and dysmetria of the upper and lower limbs, and reach the highest world prevalence rate in Holguín, Cuba. Quantify the upper limbs coordination is a part of the neurological examination, the computer system NeuroScreening Coordination offers a set of test to this purpose. Keep-to-the-path test is one of them, it consist in draw a superposed path to mathematical curve as quick… Mostrar más

The Spinocerebellar Ataxia type 2 is characterized by an ataxic gait, diminished saccade velocity, cerebellar dysarthria and dysmetria of the upper and lower limbs, and reach the highest world prevalence rate in Holguín, Cuba. Quantify the upper limbs coordination is a part of the neurological examination, the computer system NeuroScreening Coordination offers a set of test to this purpose. Keep-to-the-path test is one of them, it consist in draw a superposed path to mathematical curve as quick and accuracy as possible. To support the design, performance and analysis of the Keep-to-the-path test were used different computational and mathematical methods. An Interpreter of Mathematical Functions based in part of the compiler theory is responsible of create, edit and evaluate mathematical functions used as stimulus in the mentioned test. Besides, a Processor of Movement Signals is used to process and obtain relevant data of patients responses, it implement spline cubic interpolation techniques, mean value algorithm, numerical integration and numerical differentiation. This implemented methods guaranty the correct test design and the reliability and accuracy capturing and processing data, making to Keep-to-the-path test a good tool for quantify hand movement coordination. Mostrar menos