Dissertations / Theses on the topic 'PARKINSON'S DISEASE DETECTION'

Le risque de chute provoqué par le phénomène épisodique de ‘Freeze of Gait’ (FoG) est un symptôme commun de la maladie de Parkinson. Cette étude concerne la détection et le diagnostic des épisodes de FoG à l'aide d'un prototype multi-capteurs. La première contribution est l'introduction de nouveaux capteurs (télémètres et goniomètres) dans le dispositif de mesure pour la détection des épisodes de FoG. Nous montrons que l'information supplémentaire obtenue avec ces capteurs améliore les performances de la détection. La seconde contribution met œuvre un algorithme de détection basé sur des réseaux de neurones gaussiens. Les performance de cet algorithme sont discutées et comparées à l'état de l'art. La troisième contribution est développement d'une approche de modélisation probabiliste basée sur les réseaux bayésiens pour diagnostiquer le changement du comportement de marche des patients avant, pendant et après un épisode de FoG. La dernière contribution est l'utilisation de réseaux bayésiens arborescents pour construire un modèle global qui lie plusieurs symptômes de la maladie de Parkinson : les épisodes de FoG, la déformation de l'écriture et de la parole. Pour tester et valider cette étude, des données cliniques ont été obtenues pour des patients atteints de Parkinson. Les performances en détection, classification et diagnostic sont soigneusement étudiées et évaluées<br>Freezing of Gait (FoG) is an episodic phenomenon that is a common symptom of Parkinson's disease (PD). This research is headed toward implementing a detection, diagnosis and correction system that prevents FoG episodes using a multi-sensor device. This particular study aims to detect/diagnose FoG using different machine learning approaches. In this study we validate the choice of integrating multiple sensors to detect FoG with better performance. Our first level of contribution is introducing new types of sensors for the detection of FoG (telemeter and goniometer). An advantage in our work is that due to the inconsistency of FoG events, the extracted features from all sensors are combined using the Principal Component Analysis technique. The second level of contribution is implementing a new detection algorithm in the field of FoG detection, which is the Gaussian Neural Network algorithm. The third level of contribution is developing a probabilistic modeling approach based on Bayesian Belief Networks that is able to diagnosis the behavioral walking change of patients before, during and after a freezing event. Our final level of contribution is utilizing tree-structured Bayesian Networks to build a global model that links and diagnoses multiple Parkinson's disease symptoms such as FoG, handwriting, and speech. To achieve our goals, clinical data are acquired from patients diagnosed with PD. The acquired data are subjected to effective time and frequency feature extraction then introduced to the different detection/diagnosis approaches. The used detection methods are able to detect 100% of the present appearances of FoG episodes. The classification performances of our approaches are studied thoroughly and the accuracy of all methodologies is considered carefully and evaluated

La maladie de Parkinson (MP) est un trouble neurologique causé par une diminution du niveau de dopamine dans le cerveau. Cette maladie est caractérisée par des symptômes moteurs et non moteurs qui s'aggravent avec le temps. Aux stades avancés de la maladie de Parkinson, le diagnostic clinique est clair. Cependant, dans les premiers stades, lorsque les symptômes sont souvent incomplets ou subtils, le diagnostic devient difficile et, parfois, le sujet peut rester non diagnostiqué. En outre, il n'existe pas de méthodes efficaces et fiables permettant d'établir avec certitude un diagnostic précoce du MP. La difficulté de la détection précoce est une forte motivation pour les outils d'évaluation informatisés/outils d'aide à la décision/instruments de test qui peuvent aider au diagnostic précoce et à la prédiction de la progression de la maladie de Parkinson. La détérioration de l'écriture et la déficience vocale peuvent être l'un des premiers indicateurs de l'apparition de la maladie. Selon la documentation examinée, un modèle indépendant du langage pour détecter la maladie de Parkinson à l'aide de signaux multimodaux n'a pas été suffisamment étudié. L'objectif principal de cette thèse est de construire un système multimodal indépendant du langage pour évaluer les troubles moteurs chez les patients atteints de la maladie de Parkinson à un stade précoce, basé sur des signaux combinés d'écriture et de parole, en utilisant des techniques d'apprentissage automatique. Dans ce but et en raison de l'absence d'un ensemble de données multimodales et multilingues, une telle base de données, également répartie entre les témoins et les patients atteints de la maladie de Parkinson, a d'abord été construite. La base de données comprend des enregistrements de l'écriture, de la parole et des mouvements oculaires recueillis auprès de patients témoins et de patients atteints de la maladie de Parkinson en deux phases (avec médication et sans médication). Dans cette thèse, nous nous sommes concentrés sur l'analyse de l'écriture et de la parole, où les patients atteints de la maladie de Parkinson ont été étudiés avec médication.Des modèles indépendants du langage pour la détection de la maladie de Parkinson basés sur les caractéristiques de l'écriture ont été construits ; deux approches ont été envisagées, étudiées et comparées : une approche classique d'extraction et de classification des caractéristiques et une approche d'apprentissage approfondi. Les deux approches ont permis d'atteindre une précision de classification d'environ 97 %. Un classificateur SVM multi-classes pour la détection des étapes basées sur les caractéristiques de l'écriture a été construit. Les performances obtenues n'étaient pas satisfaisantes par rapport aux résultats obtenus pour la détection de MD en raison des nombreux obstacles rencontrés.Un autre ensemble de caractéristiques acoustiques indépendantes de la langue et de la tâche a été construit pour évaluer les troubles moteurs chez les patients atteints de la maladie de Parkinson. Nous avons réussi à construire un modèle SVM indépendant du langage pour le diagnostic de la MP par analyse vocale avec une précision de 97,62%. Enfin, un système multimodal indépendant du langage pour la détection de la maladie de Parkinson en combinant l'écriture et les signaux vocaux a été mis au point, où le modèle SVM classique et les modèles d'apprentissage profond ont tous deux été analysés. Une précision de classification de 100 % est obtenue lorsque des caractéristiques artisanales des deux modalités sont combinées et appliquées au SVM. Malgré les résultats encourageants obtenus, il reste encore du travail à faire avant de mettre notre modèle multimodal de détection de la MP en usage clinique en raison de certaines limitations inhérentes à cette thèse<br>Parkinson’s disease (PD) is a neurological disorder caused by a decreased dopamine level on the brain. This disease is characterized by motor and non-motor symptoms that worsen over time. In advanced stages of PD, clinical diagnosis is clear-cut. However, in the early stages, when the symptoms are often incomplete or subtle, the diagnosis becomes difficult and at times, the subject may remain undiagnosed. Furthermore, there are no efficient and reliable methods capable of achieving PD early diagnosis with certainty. The difficulty in early detection is a strong motivation for computer-based assessment tools/decision support tools/test instruments that can aid in the early diagnosing and predicting the progression of PD.Handwriting’s deterioration and vocal impairment may be ones of the earliest indicators for the onset of the illness. According to the reviewed literature, a language independent model to detect PD using multimodal signals has not been enough addressed. The main goal of this thesis is to build a language independent multimodal system for assessment the motor disorders in PD patients at an early stage based on combined handwriting and speech signals, using machine learning techniques. For this purpose and due to the lack of a multimodal and multilingual dataset, such database that is equally distributed between controls and PD patients was first built. The database includes handwriting, speech, and eye movements’ recordings collected from control and PD patients in two phases (“on-state” and “off-state”). In this thesis we focused on handwriting and speech analysis, where PD patients were studied in their “on-state”.Language-independent models for PD detection based on handwriting features were built; where two approaches were considered, studied and compared: a classical feature extraction and classifier approach and a deep learning approach. Approximately 97% classification accuracy was reached with both approaches. A multi-class SVM classifier for stage detection based on handwriting features was built. The achieved performance was non-satisfactory compared to the results obtained for PD detection due to many obstacles faced.Another language and task-independent acoustic feature set for assessing the motor disorders in PD patients was built. We have succeeded to build a language independent SVM model for PD diagnosis through voice analysis with 97.62% accuracy. Finally, a language independent multimodal system for PD detection by combining handwriting and voice signals was built, where both classical SVM model and deep learning models were both analyzed. A classification accuracy of 100% is obtained when handcrafted features from both modalities are combined and applied to the SVM. Despite the encouraging results obtained, there is still some works to do before putting our PD detection multimodal model into clinical use due to some limitations inherent to this thesis

Le travail présenté dans ce mémoire porte sur le développement d'un système de surveillance ambulatoire pour la détection de la dyskinésie induite par la Levodopa (LID) chez les patients de la maladie de Parkinson (PD). Le système est composé d’unités de mesure inertielle (IMUs) qui recueillent des signaux de mouvement chez des sujets sains et des patients parkinsoniens. Des méthodes différentes sont évaluées pour la détection de LID avec et sans classification des activités. Les données recueillies auprès des sujets sains sont utilisées pour concevoir un classificateur d'activité fiable. Par la suite, un algorithme qui effectue la classification des activités et la détection de la dyskinésie sur les données recueillies auprès de des patients parkinsoniens est proposé. Une nouvelle approche basée sur l'analyse de réseau complexe est également explorée et présente des résultats intéressants. Les méthodes de traitement développées ont été intégrées dans une plateforme complète d’analyse nommée PARADYSE<br>The work presented in this thesis is concerned with the development of an ambulatory monitoring system for the detection of Levodopa Induced Dyskinesia (LID) in Parkinson’s disease (PD) patients. The system is composed of Inertial Measurement Units (IMUs) that collect movement signals from healthy individuals and PD patients. Different methods are evaluated which consist of LID detection with and without activity classification. Data collected from healthy individuals is used to design a reliable activity classifier. Following that, an algorithm that performs activity classification and dyskinesia detection on data collected from PD patients is tested. A new approach based on complex network analysis is also explored and presents interesting results. The evaluated analysis methods are incorporated into a platform PARADYSE in order to further advance the system’s capabilities

Introduction: Parkinson’s Disease (PD) is the second most common neurodegenerative disorder, which affects more than 6 million people worldwide. PD is a progressive multiorgan proteinopathy, also called synucleinopathy, because of the abnormal neuronal accumulation of misfolded alpha-synuclein (αS), an intrinsically disorder protein (IDP) of 140 amino acids. αS is expressed ubiquitously in the cells and has been particularly found associated with membranes in the pre-synaptic terminal, suggesting a role in the regulation of vesicle trafficking, synaptic transmission and synaptic plasticity. Environmental toxins, genetic mutations, amplification of αS gene trigger αS misfolding and aggregation in Lewy Bodies (LBs) and Lewy Neurites (LNs), typical histopathological marker in PD. This event leads to a gradual loss of dopaminergic neurons in substantia nigra pars compacta (SNpc) and the spreading of LB pathology not only in neuronal networks of the central nervous system, but also in the autonomic and peripheral nervous systems. For these reasons, PD manifest with a broad range of motor (e.g. rigidity, tremor and bradykinesia) and non-motor symptoms (e.g. anosmia, constipation, cognitive dysfunction). However, the onset of motor symptoms occurs only when about the 50% of dopaminergic neurons are lost. Therefore, identifying the early step that trigger neuronal toxicity might help in halting neurodegeneration. Misfolding, oligomerization, and fibrillization of αS are thought to be central events in the onset and progression of PD. In fact, αS oligomers acts as seeds for the nucleation dependent process of αS intracellular aggregation, and as a template for the cell-to-cell transmission of αS pathology in a prion like manner. In light of this, we developed Alpha-synuclein FRET-based Biosensors (AFBs) capable to monitor any early αS conformational changes ubiquitously in the cell or in a specific subcellular compartment such as the ER, an early site of αS aggregation, under normal and stress conditions. Methods: AFBs were designed to detect different types of αS assembly such as: - relaxed vs globular αS conformation, where both CFP and YFP are cloned respectively at the C-terminal and N-terminal of the same molecule of WT human αS (intramolecular AFB); - parallel multimeric structures based on N-N and C-C termini interactions between molecules, where both fluorophores (CFP and YFP) are cloned separately at the C-terminal of WT human αS (intermolecular AFBs CC); - antiparallel multimers based on C-N termini interactions, where CFP and YFP are cloned separately and respectively at the C-terminal and N-terminal of WT human αS (intermolecular AFBs CN). AFBs were tested in two different cell lines: SH-SY5Y human neuroblastoma cell line and an inducible cell line stably expressing αS in the ER (iSH-SY5Y). Two different FRET methodologies were used to analyses AFBs behaviour: Sensitized Emission (SE) in SH-SY5Y living cells and Acceptor Photobleaching (AP) in iSH-SY5Y fixed cells. Results: interesting outcomes arose by the analysis of AFBs in iSH-SY5Y cells with AP. AFBs provided a radical different behaviour in the ability of detecting conformational differences in αS structure. Intramolecular AFB revealed a closed conformation of monomeric αS under normal conditions, whereas intermolecular AFBs highlighted a multimerization of αS in the ER, which occurred in an antiparallel orientation of αS monomers in normal condition and with a parallel orientation under the effect of leupeptin, an inhibitor of αS degradation pathway. Discussion and Conclusions: these findings suggested that AFBs represent a valuable strategy to detect conformational changes in αS structures in physiological condition and under the effect of stress stimuli. To the best of our knowledge they are the first fluorescent probes capable of detecting different type of αS multimers in the ER, an early site of pathological αS aggregation. Therefore, AFBs represent an interesting investigative approach on αS multimerization and, in the future, might be employed as a powerful tool for the screening of therapeutic agents which aim to halt αS pathological aggregation from the early phase and to prevent the irreversible progression of PD.

Parkinson’s disease (PD). It is characterized by brief episodes of inability to step, or by extremely short steps that typically occur on gait initiation or on turning while walking. The consequences of FOG are aggravated mobility and higher affinity to falls, which have a direct effect on the quality of life of the individual. There does not exist completely effective pharmacological treatment for the FOG phenomena. However, external stimuli, such as lines on the floor or rhythmic sounds, can focus the attention of a person who experiences a FOG episode and help her initiate gait. The optimal effectiveness in such approach, known as cueing, is achieved through timely activation of a cueing device upon the accurate detection of a FOG episode. Therefore, a robust and accurate FOG detection is the main problem that needs to be solved when developing a suitable assistive technology solution for this specific user group. This thesis proposes the use of activity and spatial context of a person as the means to improve the detection of FOG episodes during monitoring at home. The thesis describes design, algorithm implementation and evaluation of a distributed home system for FOG detection based on multiple cameras and a single inertial gait sensor worn at the waist of the patient. Through detailed observation of collected home data of 17 PD patients, we realized that a novel solution for FOG detection could be achieved by using contextual information of the patient’s position, orientation, basic posture and movement on a semantically annotated two-dimensional (2D) map of the indoor environment. We envisioned the future context-aware system as a network of Microsoft Kinect cameras placed in the patient’s home that interacts with a wearable inertial sensor on the patient (smartphone). Since the hardware platform of the system constitutes from the commercial of-the-shelf hardware, the majority of the system development efforts involved the production of software modules (for position tracking, orientation tracking, activity recognition) that run on top of the middle-ware operating system in the home gateway server. The main component of the system that had to be developed is the Kinect application for tracking the position and height of multiple people, based on the input in the form of 3D point cloud data. Besides position tracking, this software module also provides mapping and semantic annotation of FOG specific zones on the scene in front of the Kinect. One instance of vision tracking application is supposed to run for every Kinect sensor in the system, yielding potentially high number of simultaneous tracks. At any moment, the system has to track one specific person - the patient. To enable tracking of the patient between different non-overlapped cameras in the distributed system, a new re-identification approach based on appearance model learning with one-class Support Vector Machine (SVM) was developed. Evaluation of the re-identification method was conducted on a 16 people dataset in a laboratory environment. Since the patient orientation in the indoor space was recognized as an important part of the context, the system necessitated the ability to estimate the orientation of the person, expressed in the frame of the 2D scene on which the patient is tracked by the camera. We devised method to fuse position tracking information from the vision system and inertial data from the smartphone in order to obtain patient’s 2D pose estimation on the scene map. Additionally, a method for the estimation of the position of the smartphone on the waist of the patient was proposed. Position and orientation estimation accuracy were evaluated on a 12 people dataset. Finally, having available positional, orientation and height information, a new seven-class activity classification was realized using a hierarchical classifier that combines height-based posture classifier with translational and rotational SVM movement classifiers. Each of the SVM movement classifiers and the joint hierarchical classifier were evaluated in the laboratory experiment with 8 healthy persons. The final context-based FOG detection algorithm uses activity information and spatial context information in order to confirm or disprove FOG detected by the current state-of-the-art FOG detection algorithm (which uses only wearable sensor data). A dataset with home data of 3 PD patients was produced using two Kinect cameras and a smartphone in synchronized recording. The new context-based FOG detection algorithm and the wearable-only FOG detection algorithm were both evaluated with the home dataset and their results were compared. The context-based algorithm very positively influences the reduction of false positive detections, which is expressed through achieved higher specificity. In some cases, context-based algorithm also eliminates true positive detections, reducing sensitivity to the lesser extent. The final comparison of the two algorithms on the basis of their sensitivity and specificity, shows the improvement in the overall FOG detection achieved with the new context-aware home system.<br>Esta tesis propone el uso de la actividad y el contexto espacial de una persona como medio para mejorar la detección de episodios de FOG (Freezing of gait) durante el seguimiento en el domicilio. La tesis describe el diseño, implementación de algoritmos y evaluación de un sistema doméstico distribuido para detección de FOG basado en varias cámaras y un único sensor de marcha inercial en la cintura del paciente. Mediante de la observación detallada de los datos caseros recopilados de 17 pacientes con EP, nos dimos cuenta de que se puede lograr una solución novedosa para la detección de FOG mediante el uso de información contextual de la posición del paciente, orientación, postura básica y movimiento anotada semánticamente en un mapa bidimensional (2D) del entorno interior. Imaginamos el futuro sistema de consciencia del contexto como una red de cámaras Microsoft Kinect colocadas en el hogar del paciente, que interactúa con un sensor de inercia portátil en el paciente (teléfono inteligente). Al constituirse la plataforma del sistema a partir de hardware comercial disponible, los esfuerzos de desarrollo consistieron en la producción de módulos de software (para el seguimiento de la posición, orientación seguimiento, reconocimiento de actividad) que se ejecutan en la parte superior del sistema operativo del servidor de puerta de enlace de casa. El componente principal del sistema que tuvo que desarrollarse es la aplicación Kinect para seguimiento de la posición y la altura de varias personas, según la entrada en forma de punto 3D de datos en la nube. Además del seguimiento de posición, este módulo de software también proporciona mapeo y semántica. anotación de zonas específicas de FOG en la escena frente al Kinect. Se supone que una instancia de la aplicación de seguimiento de visión se ejecuta para cada sensor Kinect en el sistema, produciendo un número potencialmente alto de pistas simultáneas. En cualquier momento, el sistema tiene que rastrear a una persona específica - el paciente. Para habilitar el seguimiento del paciente entre diferentes cámaras no superpuestas en el sistema distribuido, se desarrolló un nuevo enfoque de re-identificación basado en el aprendizaje de modelos de apariencia con one-class Suport Vector Machine (SVM). La evaluación del método de re-identificación se realizó con un conjunto de datos de 16 personas en un entorno de laboratorio. Dado que la orientación del paciente en el espacio interior fue reconocida como una parte importante del contexto, el sistema necesitaba la capacidad de estimar la orientación de la persona, expresada en el marco de la escena 2D en la que la cámara sigue al paciente. Diseñamos un método para fusionar la información de seguimiento de posición del sistema de visión y los datos de inercia del smartphone para obtener la estimación de postura 2D del paciente en el mapa de la escena. Además, se propuso un método para la estimación de la posición del Smartphone en la cintura del paciente. La precisión de la estimación de la posición y la orientación se evaluó en un conjunto de datos de 12 personas. Finalmente, al tener disponible información de posición, orientación y altura, se realizó una nueva clasificación de actividad de seven-class utilizando un clasificador jerárquico que combina un clasificador de postura basado en la altura con clasificadores de movimiento SVM traslacional y rotacional. Cada uno de los clasificadores de movimiento SVM y el clasificador jerárquico conjunto se evaluaron en el experimento de laboratorio con 8 personas sanas. El último algoritmo de detección de FOG basado en el contexto utiliza información de actividad e información de texto espacial para confirmar o refutar el FOG detectado por el algoritmo de detección de FOG actual. El algoritmo basado en el contexto influye muy positivamente en la reducción de las detecciones de falsos positivos, que se expresa a través de una mayor especificidad

Gastrointestinal (GI) alpha-synuclein (ASN) detection may represent a clinically useful biomarker of Parkinson's disease (PD), but this has been challenged by conflicting results of recent studies employing different immunohistochemical (IHC) methods and reporting diverse morphological patterns with variable biological interpretation. To increase sensitivity and specificity, we applied three different techniques to detect different possible conformations of ASN in GI tissue derived from biopsies of the GI tract, which were obtained from a longitudinally followed, clinically well-characterized cohort of PD subjects and healthy controls (HC) (Oxford Discovery study). With IHC, we used antibodies reactive for total (T-ASN-Abs), phosphorylated (P-ASN-Abs) and oligomeric (O-ASN-Abs) ASN; with the ASN Proximity Ligation Assay (AS-PLA), we targeted oligomeric ASN species specifically; finally, with the Paraffin-Embedded Tissue Blot (PET-Blot) we aimed to detect fibrillary conformations of ASN specifically. Optimisation and validation of the PET-Blot and PLA techniques was carried out with studies on brain tissue from subjects with ASN pathology, and these experiments were used to gain insight into morphology and distribution of different conformational variants of ASN in the brain of subjects with Lewy pathology. We specified all the detected morphological staining patterns with each technique interpreting them as pathologic or non-specific. Correlation to clinical symptoms was assessed to investigate the potential predictive or diagnostic value of specific staining patterns as biomarkers. A total of 163 GI tissue blocks were collected from 51 PD patients (113 blocks) and 21 healthy controls (50 blocks). In 31 PD patients, GI biopsies had been taken before PD diagnosis (Prodromal PD group); while in 20 PD patients biopsies were obtained after PD diagnosis (Manifest PD group). The majority of these tissues blocks were from large intestine (62%), followed by small intestine (21%), stomach (10%) and oesophagus (7%). With IHC, four ASN staining patterns were detected in GI tissue (Neuritic, Ganglionic, Epithelial, and Cellular), while two distinct staining patterns were detected with AS-PLA (cellular and diffuse signal) and with AS-PET-Blot (ASN-localised and peri-crypt signal). The level of agreement between different techniques was generally low, and no single technique or staining pattern was able to reliably distinguish PD patients (Prodromal or Manifest) from HC. Overall, our study suggests that even specific detection of ASN conformational variants currently considered pathologic was not adequate for the prediction of PD. Future studies with these or other novel techniques focusing on the upper part of the GI tract could overcome current limitations in sensitivity and specificity.

Freezing of gait (FoG) presents as a sudden and brief episode of movement cessation despite the intention to continue walking. As a common symptom of Parkinson's Disease, early detection and quantification of FoG are of great importance in clinical practice. Therefore, this thesis focuses on vision-based and pressure-based FoG detection methods, which were seldom investigated in the past. The task can be treated as a human action recognition problem. Although various deep architectures have achieved encouraging performance for general action recognition, FoG events contain fine-grained patterns, which requires novel deep architectures to learn the domain knowledge. Hence, fine-grained deep architectures are studied, and the major contributions of this thesis are as follows: 1. A graph-based neural network is proposed for vision-based FoG detection by representing a temporal video segment as a directed graph where FoG related candidate regions are the vertices. A weakly-supervised learning strategy is studied to eliminate the resource expensive annotations. 2. A graph sequence recurrent neural network is proposed to formulate long-term graph temporal patterns, which takes graph sequences of dynamic structures as inputs and characterizes FoG patterns by graph recurrent cells. 3. An adversarial spatio-temporal network is proposed to learn FoG patterns across multiple levels using footstep pressure sequences. The adversarial training scheme aims to obtain subject-independent representations to alleviate the issue of high inter-subject variance. 4. A graph fusion neural network is introduced for multimodal learning using footstep pressure maps, video recordings and their associated optical flows. Multimodal graphs are introduced by treating the encoded features of each modality as vertex-level inputs. Comprehensive experiments demonstrate the effectiveness of the proposed methods.

Inertial measurement sensing technology with the capability of capturing disease-relevant data has a great potential for improving the current clinical assessments and enhancing the quality of life in patients with neuro-developmental and neuro-degenerative diseases such as autism spectrum disorders (ASD) and Parkinson's disease (PD). The current clinical assessments can be improved by developing objective tools for the disease diagnosis and continuous monitoring of patients in out of clinical settings. To this end, it is necessary to develop automatic abnormal movement detection methods with the capability of adjusting on new patients' data in real-life settings. However, achieving this goal is challenging mainly because of the inter and intra-subject variability in acquired signals and the lack of labeled data. The research presented in this thesis investigates the application of deep neural networks to address these challenges of abnormal movement detection using inertial measurement unit (IMU) sensors with case studies on stereotypical motor movements in ASD and freezing of gait in PD patients. In this direction, this thesis provides four main contributions: i) A convolutional neural network (CNN) architecture is proposed to learn discriminative features which are sufficiently robust to inter and intra-subject variability. It is further shown how the proposed CNN architecture can be used for parameter transfer learning to enhance the adaptability of the abnormal movement detection system to new data in a longitudinal study. ii) An application of recurrent neural networks and more specifically long short-term memory (LSTM) in combination with CNN is proposed in order to incorporate more the temporal dynamics of IMU signals in the process of feature learning for abnormal movement detection. iii) An ensemble learning approach is proposed to improve the detection accuracy and at the same time to reduce the variance of models. iv) In the normative modeling framework, the problem of abnormal movement detection is redefined in the context of novelty detection and it is shown how a probabilistic denoising autoencoder can be used to learn the distribution of the normal human movements. The resulting deep normative model then is used in a novelty detection setting for unsupervised abnormal movement detection. The experimental results on three benchmark datasets collected from ASD and PD patients illustrate the high potentials of deep learning paradigm to address the crucial challenges toward real-time abnormal movement detection systems using wearable technologies.

Inertial measurement sensing technology with the capability of capturing disease-relevant data has a great potential for improving the current clinical assessments and enhancing the quality of life in patients with neuro-developmental and neuro-degenerative diseases such as autism spectrum disorders (ASD) and Parkinson's disease (PD). The current clinical assessments can be improved by developing objective tools for the disease diagnosis and continuous monitoring of patients in out of clinical settings. To this end, it is necessary to develop automatic abnormal movement detection methods with the capability of adjusting on new patients' data in real-life settings. However, achieving this goal is challenging mainly because of the inter and intra-subject variability in acquired signals and the lack of labeled data. The research presented in this thesis investigates the application of deep neural networks to address these challenges of abnormal movement detection using inertial measurement unit (IMU) sensors with case studies on stereotypical motor movements in ASD and freezing of gait in PD patients. In this direction, this thesis provides four main contributions: i) A convolutional neural network (CNN) architecture is proposed to learn discriminative features which are sufficiently robust to inter and intra-subject variability. It is further shown how the proposed CNN architecture can be used for parameter transfer learning to enhance the adaptability of the abnormal movement detection system to new data in a longitudinal study. ii) An application of recurrent neural networks and more specifically long short-term memory (LSTM) in combination with CNN is proposed in order to incorporate more the temporal dynamics of IMU signals in the process of feature learning for abnormal movement detection. iii) An ensemble learning approach is proposed to improve the detection accuracy and at the same time to reduce the variance of models. iv) In the normative modeling framework, the problem of abnormal movement detection is redefined in the context of novelty detection and it is shown how a probabilistic denoising autoencoder can be used to learn the distribution of the normal human movements. The resulting deep normative model then is used in a novelty detection setting for unsupervised abnormal movement detection. The experimental results on three benchmark datasets collected from ASD and PD patients illustrate the high potentials of deep learning paradigm to address the crucial challenges toward real-time abnormal movement detection systems using wearable technologies.

Context: Most of the patients suffering from any neurological disorder pose ambulatory disturbance at any stage of disease which may result in falling without showing any warning sign and every patient is different from another. So there is a need to develop a mechanism to detect shaky motion. Objectives: The major objectives are: (i) To check different gait parameters in walking disorders using Shimmer platform (R). (ii) Wearing SHIMMER wireless sensors on hip, waist and chest, to check which one is the most suitable. (iii) To draw effective conclusion/results based on calibrated data in real time and offline processing in EyesWeb/Matlab.To develop an effective mechanism/algorithm for security warning and activating alarm systems. Methods: Our thesis project is related to analyze real-time gait of the patient suffering from Parkinson&apos;s disease for actively responding to the shaky movements. Based on real world data, we have developed a mechanism to monitor a real time gait analysis algorithm to detect any gait deviation. This algorithm is efficient, sensitive to detect miner deviation and not hard coded i.e. user can set Sampling Rate &amp; Threshold values to analyze motion. Researchers can directly use this algorithm in their study without need to implement themselves. It works on pre-calculated threshold values while initial sampling rate is set to 100MHz. Results: Accelerometers putting on the chest shows high unnecessary acceleration during fall, suggest putting on waist position. Also, if a patient initiates steps with energy, his/her gait may become more stable as shown in the conscious gait. Results show that after DBS surgical procedure, the patient still experiences postural instability with fall. So it is evident to show that such patients may have reduced cognition even after surgery. Another finding is that such patients may lean left or right during turning. Conclusions: We have presented a real time gait analysis algorithm, capable of detecting the motion of the patient with PD to actively respond to the shakier motion setting threshold values. Our proposed algorithm is easy to implement, reusable and can affectively generate healthcare alarms. Additionally, this system might be used by other researchers without the need to implement by themselves. The proposed method is sensitive to detect fall therefore objectively can be used for fall risk assessment as well .The same algorithm with minor modifications can be used for seizure detection in other disorders mainly epileptic seizers to alert health providers for emergency.<br>Any malfunctioning of neurons in the nervous system is called Neurological disorder. Over 100 neurological disorders have been discovered throughout the world. In our study, we have chosen one disorder: Falling in Parkinson’s disease. Experiments can be performed on different gait parameters like body velocity, time ratio, ground slope, stance/swing, body gestures and gait patterns. Sensors can be put on hips, knees, thighs, limbs, neck, head, chest or any other suitable body part to capture motion data for further pre-and post-processing. Pre-processing is real time gait analysis through time domain and frequency domain to trigger various security steps and messages for patient care. Post -processing is offline analysis of motion data in different tools such as EyesWeb, BioMOBIUS and Matlab for calculations, analysis and plotting of motion to take decisions to formulate a mechanism for patient activity detection and monitoring. The area which we choose is pretty interesting, pertaining to rehabilitation, wellness and healthcare for older people. Other related keywords may include keywords may be helpful using one or combination of more than one. WSN, BAN or WBAN, biosensors, neurological disorders, gait analysis, fall detection, fall avoidance, Parkinson’s disease, wireless accelerometer, ambulatory monitoring, freezing of gait and fall risk assessment. Most of the patients suffering from any neurological disorder in later stages of disease pose ambulatory disturbance especially falling. Such patients may fall without showing any warning sign and every patient is different from another. So there is a need to develop a mechanism to detect shaky motion to avoid such patients from falling. Therefore, a real time gait analysis algorithm is implemented to trigger security alarms. In order to assess &amp; evaluate gait analysis, accurate, reliable &amp; consistent measurement tools need to be utilized. Even slight deviation in the data monitoring through measurement tools is not encouraged to use [21]. Gait disturbance can be measured using 3 axis accelerometers like SHIMMER(R) for real time motion analysis. In the wireless sensor network, SHIMMER platform provides wireless Body Area Network (BAN) to capture motion data. This data can be saved in CSV (Comma Separated Version) file for post processing or a 2 GB MicroSD card can be used to capture data in the SHIMMER accelerometer itself. The use of accelerometer is more suitable due to the fact that we are 66 capturing data from postural instability. One two or combinations of accelerometers can be put on different body parts. SHIMMER Gyroscope is more suitable for jerky motion with disease such as epilepsy. Mostly accelerometers and gyroscopes are used for gait analysis [4]. Defining our research work, this study is carried out on the patient with Parkinson’s disease (PD), to study various gait parameters, test wireless accelerometers on different body parts, and implementing an algorithm to trigger a security alarm system by setting a threshold value. Criteria for setting threshold value are calculating standard deviation and employed by different researchers like [3]. The main motivation to perform this experimental research work is to avoid the patient with PD from falling during unstable shaky gait. Security alarms can be activated whenever a patient poses a shakier gait. Two types of alarms or sirens can be activated in the lgorithm. First, to activate Warning Alarms when the value from motion data exceeds maximum threshold value 1 and second to activate Emergency Alarms when the value from motion data exceeds maximum threshold value 2. Later on airbag can be put on the patient’s hip position to avoid him/her from injury and hip fracture. The results show the proposed system is fairly simple to implement in the real time environment, flexible to adjust to any necessary change in the future.The major advantage of this algorithm is its reusability. Algorithm is not hard coded because a user can set his own sampling rate or threshold value or both, and check results. This algorithm is further modifiable to trigger airbag, a security push button, SOS calls, messages, siren activation system, automatic email forwarding, health care alert, and many more. The same algorithm with minor modifications can be used for fall avoidance or health care assurance on other disorders mainly in epileptic seizers to alert health providers in case of emergency, can be used for other seizures and disorders such as epilepsy, etc. Overall, this report presents the analysis of an experiment to measure the usability of wireless accelerometer data to monitor the activity of the patient suffering from Parkinson disease. Our research and experimental work can be quoted toward fall risk assessment.<br>Inam-ul-Haq Lindblomsvagen 37233 Ronneby +46 760609660

The reach of technological innovation continues to grow, changing all industries as it evolves. In healthcare, technology is increasingly playing a role in almost all processes, from patient registration to data monitoring, from lab tests to self-care tools. The increase in the amount and diversity of generated clinical data requires development of new technologies and procedures capable of integrating and analyzing the BIG generated information as well as providing support in their interpretation. To that extent, this dissertation focuses on the analysis and processing of biomedical signals, specifically brain and heart signals, using advanced machine learning techniques. That is, the design and implementation of automatic biomedical signal pre-processing and monitoring algorithms, the design of novel feature extraction methods, and the design of classification techniques for specific decision making processes. In the first part of this dissertation Electroencephalogram (EEG) signals that are recorded in 14 different locations on the scalp are utilized to detect random eye state change in real-time. In summary, cross channel maximum and minimum is used to monitor real-time EEG signals in 14 channels. Upon detection of a possible change, Multivariate Empirical Mode Decomposes the last two seconds of the signal into narrow-band Intrinsic Mode Functions. Common Spatial Pattern is then employed to create discriminating features for classification purpose. Logistic Regression, Artificial Neural Network, and Support Vector Machine classifiers all could detect the eye state change with 83.4% accuracy in less than two seconds. We could increase the detection accuracy to 88.2% by extracting relevant features from Intrinsic Mode Functions and directly feeding it to the classification algorithms. Our approach takes less than 2 seconds to detect an eye state change which provides a significant improvement and promising real-life applications when compared to slow and computationally intensive instance based classification algorithms proposed in literatures. Increasing the training examples could even improve the accuracy of our analytic algorithms. We employ our proposed analytic method in detecting the three different dance moves that honey bees perform to communicate the location of a food source. The results are significantly better than other alternative methods in the literature in terms of both accuracy and run time. The last chapter of the dissertation brings out a collaborative research on Parkinson's disease. As a Parkinson’s Progression Markers Initiative (PPMI) investigator, I had access to the vast database of The Michael J. Fox Foundation for Parkinson's Research. We utilized available data to study the heredity factors leading to Parkinson's disease by using Maximum Likelihood and Bayesian approach. Through sophisticated modeling, we incorporated information from healthy individuals and those diagnosed with Parkinson's disease (PD) to available historical data on their grandparents' family to draw Bayesian estimations for the chances of developing PD in five types of families. That is, families with negative history of PD (type 1) and families with positive history in which estimations provided for the prevalence of developing PD when none of the parents (type 2), one of the parents (type 3 and 4), or both of the parents (type 5) carried the disease. The results in the provided data shows that for the families with negative history of PD the prevalence is estimated to be 20% meaning that a child in this family has 20% chance of developing Parkinson. If there is positive history of PD in the family the chance increases to 33% when none of the parents had PD and to 44% when both of the parents had the disease. The chance of developing PD in a family whose solely mother is diagnosed with the disease is estimated to be 26% in comparison to 31% when only father is diagnosed with Parkinson's.

Les signaux neuromodulateurs induisent une adaptation des fonctions neuronales par le biais de mécanismes d’intégration dynamiques complexes. Parmi les voies de signalisation intracellulaires, celle de l’AMPc/PKA joue un rôle essentiel dans la réponse cellulaire à la dopamine. Pour analyser ces processus d’intégration, nous combinons l’imagerie de biosenseurs dans des préparations ​ex vivo de tranches de cerveau de souris avec de la modélisation de la signalisation intracellulaire dans les neurones D1 et D2 striataux. Dans une première partie de mon travail de thèse, nous analysons la dynamique de la signalisation striatale en réponse à des stimulations dopaminergiques transitoires telles celles associées aux récompenses. Nous montrons par imagerie que, contrairement à ce qui est communément admis, les récepteurs D​2 à la dopamine permettent la détection de dopamine phasique au niveau de l’AMPc. De plus, les simulations suggèrent que les neurones D2 pourraient détecter une diminution du niveau de dopamine tonique, indicateur d’une situation aversive chez l’animal. Ce travail a fait l’objet d’une publication (​Yapo et al., ​J. Physiol 2017​). Dans une deuxième partie, nous avons analysé l’effet dans le noyau de ces stimulations dopaminergiques rapides. En comparaison avec les neurones du cortex, nous montrons que les neurones du striatum disposent d’un mécanisme de contrôle en-avant (“​feed forward​”) qui renforce les réponses PKA nucléaires. Cette situation originale, à l’opposé des rétrocontrôles homéostatiques habituels en biologie, amène à une réponse du noyau tout ou rien, extrêmement sensible. Nous pensons que ce mécanisme est impliqué dans la détection des signaux dopaminergiques transitoires. Ce travail a été publié dans un article (​Yapo et al., ​J Cell Science​ 2018​). Enfin une troisième partie, sous forme de résultats préliminaires, consistait à analyser l’adaptation des neurones du striatum à la perte des afférences dopaminergiques, caractéristique de la maladie de Parkinson. Nous avons observé l’hypersensibilité à la dopamine affectant les neurones D1, largement décrite dans la littérature. De plus, nous montrons que les neurones du striatum présentent une activité phosphodiestérase accrue. Une meilleure compréhension de ces adaptations pathologiques pourrait mener à de nouvelles stratégies thérapeutiques<br>Neuromodulatory signals trigger adaptations in neuronal functions via complex integrative properties. Among the various existing intracellular signaling pathways, the cAMP/PKA cascade plays a critical role in the cellular response to dopamine. To analyze these integrative processes, we combine biosensor imaging in mouse brain slices with in silico modelisation of the intracellular signaling in D1 and D2 medium-sized spiny neurons. In a first part of my thesis work, we analyze the dynamics of cAMP/PKA signaling in striatal neurons stimulated by transient dopaminergic signals, such as those associated with reward. With imaging we show that the dopamine D​2 receptors can sense phasic dopamine signals at the level of cAMP, a thought that has been argued for long. Moreover ​in silico simulations suggest that D2 spiny neurons could sense the interruptions in tonic dopamine levels associated with aversion in the animal. This work was published in (​Yapo et al., ​J Physiol 2017​). In a second part, we analyzed the effect of such brief dopaminergic signals on the nuclear PKA-dependent signaling. In comparison to cortical neurons, we show that the striatal neurons display a positive feedforward mechanism which strengthens the nuclear responses. This peculiar situation, which contrasts with the usual homeostatic feedback mechanisms found in biology, leads to all-or-nothing and extremely sensitive responses. We believe that this mechanism allows for the detection of transient dopaminergic signals. This work was published in (​Yapo et al., ​J Cell Science​ 2018​). Lastly a third part, that will be introduced as preliminary data, consisted in analyzing the adaptations of the striatal neurons following a dopamine depletion, such as the one found in Parkinson’s disease. We observed in our mouse model an hypersensitivity of the D1 spiny neurons to dopamine, already described by other groups. Additionally we show that striatal neurons display an increased phosphodiesterase activity. A better understanding of these pathological adaptations could lead to the emergence of new therapeutic strategies

Background/Aims: The diagnostic value of olfactory testing for the discrimination of tremor-dominant Parkinson’s disease (PD) from other tremor disorders remains enigmatic. We evaluated whether olfactory testing can accurately detect PD in tremor patients. Methods: A retrospective analysis of 299 consecutive subjects referred for the differential diagnosis of a tremor disorder was done. Olfactory testing was performed using ‘Sniffin’ Sticks’, resulting in a composite TDI score of odor threshold (T), discrimination (D), and identification (I). Receiver operating curve (ROC) plots were used to calculate sensitivity/specificity for the detection of PD. Results: Of all subjects, 167 (55.9%) had PD and 85 (28.4%) had essential tremor (ET). The mean TDI score in PD was significantly reduced compared to those in ET and other tremor disorders with no differences between ET and other tremor disorders. ROC analysis revealed strong correlations of TDI scores with PD [area under the curve: 0.85 (95% CI: 0.80–0.89); p < 0.001]. The highest Youden index was observed for a TDI score <25 (Youden index: 0.58). Using this cutoff score and that generated from normative data of healthy controls, the TDI score provided high sensitivity (negative predictive value) and specificity (positive predictive value) of approximately 80% for detecting PD. Conclusion: Olfactory testing is a useful, easily applied and inexpensive diagnostic test which is helpful to detect PD among tremor patients.

Freezing of Gait (FOG) is a neuro-motor symptom associated with Parkinson's disease (PD), which is suitably managed by Rhythmic Auditory Stimulation (RAS) and music therapy, if applied upon or prior to symptom onset. This stipulates an objective measurement of gait to automatically detect FOG. This research has improved on existing methods for automatic detection of freeze states using vertical acceleration of the leg. Accordingly, a method was devised, implemented and evaluated with the DAPHNet Freezing of Gait dataset. The proposed method is based on Discrete Wavelet Transform (DWT) for feature extraction and Support Vector Machine (SVM) with a Radial Basis Function (RBF) kernel to distinguish freezing of gait from normal locomotion in a binary classification problem. The method was evaluated on the DAPHNet dataset containing over 8 hours of recorded data from PD patients with a history of FOG. The performance of the method was examined in user-dependent and user-independent experimental scenarios with respect to the analysis of feature combinations and sliding window size. The evaluated method exceeded the state-of-the-art performance results in user-independent settings giving an average sensitivity of 76.37% and an average specificity of 85.15% with a maximum detection latency of 2 seconds.

The aim of the current study was divided into two separate goals, (i) optimization of a number of PCR-based protocols employed for genotyping transgenic mouse lines and (ii) evaluating a protocol for co-detection of mRNA and its correlated protein in the mouse midbrain. The optimization was performed on PCR protocols for genotyping the following transgenic mouse lines; Dat-Cre, Vglut2-Lox, Vglut2-Cre and Vmat2-Lox. Also, two different polymerases were evaluated parallel to each other – KAPA and Maxima Hot Start. One of the main findings from the PCR optimizations were that for the Vglut2-Lox protocol. By decreasing the annealing temp and increasing the MgCl2 the bands appeared brighter.  For the second part of the project, in-situ hybridization (ISH) was used to detect the mRNA expression with a `non-radioactive in situ hybridization´ protocol, using digoxigenin or fluorescein labelled riboprobes (mRNA probes). To detect the correlated protein a basic immunohistochemistry (IHC) protocol with the use of primary and secondary antibodies was implemented. The combined protocol was tested with Nd6 and Grp markers. Before testing to combined the protocols the ISH protocol was performed alone with riboprobes for Girk2, Lpl and Fst. The combined protocol detected mRNA and protein for both the control marker Th and the Nd6 marker. In conclusions, the optimized PCR protocols were optimal when used with the Maxima Hot Start polymerase and the new combined ISH and IHC protocol worked for markers Th and Nd6.

The scope of this thesis is to process and analyze statistically Magnetic Resonance Images (MR-T1) from Parkinson’s disease patients in order to detect brain areas that exhibit brain change which is caused by the disease. Parkinson’s disease is an idiopathic disease which means that its cause is yet unknown. It is a chronic neurodegenerative disorder of the central nervous system which causes the progressive death of specific brain neurons that leads to motor impairments (tremor, bradykinesia, muscle rigidity) and non motor ones (cognitive, sleep, sensation disturbances). Magnetic Resonance Images (T1-weighted) were acquired from both Parkinson’s patients and healthy subjects (Controls) at intervals of 0 and 5 years. The data have undergone longitudinal (two-time-point), cross sectional (single-time-point) and statistical analysis with the use of FSL software library. Evidence of atrophy among Parkinson’s patients aroused, in brain areas near the ventricles and the middle temporal gyrus, after statistical analysis<br>Ο σκοπός αυτής της εργασίας είναι η επεξεργασία και στατιστική ανάλυση μαγνητηκών τομογραφιών (MR-T1) από ασθενείς με Πάρκινσον για την ανίχνευση περιοχών του εγκεφάλου που παρουσιάζουν μεταβολές που οφείλονται στην ασθένεια. Η ασθένεια Πάρκινσον είναι ιδιοπαθής, δηλαδή ασθένεια της οποίας η αιτία παραμένει ακόμη άγνωστη. Είναι μια χρόνια δυσλειτουργία λόγω εκφυλισμού των νευρώνων του κεντρικού νευρικού συστήματος η οποία προκαλεί τη σταδιακή νεκρωση συγκεκριμένης ομάδας εγκεφαλικών νευρώνων. Αυτή η νέκρωση οδηγεί σε κινητικές δυσλειτουργίες (τρέμουλο, βραδυκινησία, και μυϊκή δυσκαμψία και σε μή κινητικές όπως γνωστικές, διαταραχής ύπνου,διαταραχές αφής κ.α. Μαγνητικές τομογραφίες (τύπου Τ1) ασθενών και υγιών ελήφθησαν σε διαστήματα 0 και 5 ετών. Τα δεδομένα αναλύθηκαν με δυο μεθόδους (longitudinal και cross-sectional) και εν συνεχεία έγινε στατιστική επεξεργασία των αποτελεσμάτων. Έγινε χρήση της βιβλιοθήκης FSL Μετά από στατιστική ανάλυση προέκυψαν ενδείξεις ατροφίας στους ασθενείς με Πάρκινσον σε περιοχές του εγεκφάλου κοντά στις εγκεφαλικές κοιλίες (ventricles) και στη μέσο-κροταφική έλικα (middle temporal gyrus).

In the list of most commonly occurring neurodegenerative disorders, Parkinson’s disease ranks second while Alzheimer’s disease tops the list. It has no definite examination for an exact diagnosis. It has been observed that the handwriting of an individual suffering from Parkinson's disease deteriorates considerably. Therefore, many computer vision and micrography-based methods have been used by researchers to explore handwriting as a detection parameter. Yet, these methods suffer from two major drawbacks, i.e., the prediction model's biasedness due to the imbalance in the data and low rate of classification accuracy. The proposed technique is designed to alleviate prediction bias and low classification accuracy by use of hybrid resampling (Synthetic Minority Oversampling Technique and Wilson's Edited Nearest Neighbours) techniques and Extreme Gradient Boosting (XGBoost). Additionally, there is proof of innate neurological dissimilarities between men and women and the aged and the young. There is also a significant link of the dominant hand of the person and the side of the body where initial manifestation begins. Further, the gender, age, and handedness information have not been utilized for Parkinson’s disease detection. In this research work, a prediction method is developed incorporating age, gender, and dominant hand as features to identify Parkinson’s disease. The proposed hybrid resampling and XGBoost method's experimental results yield an accuracy of 98.24% highest so far when age is taken as a parameter along with nine statistical parameters (root mean square, largest value of radius difference between ET and HT, smallest value of radius difference between ET and HT, standard deviation of ET and HT radius difference, mean relative tremor, maximum ET, minimum HT, standard deviation of exam template values, number of instances where the HT and ET radius difference undergoes a change from negative value to positive value or vice versa) achieved on the HandPD dataset. The conventional accuracy is 98.24% (meanders) and 95.37% (spirals) when age is used along with nine statistical parameters extracted from the dataset. It becomes 97.02% (meanders) and 97.12% (spirals) when age, gender and handedness information are utilised. The proposed method results were compared with existing methods, and it is evident that the method outperforms its predecessors.

博士<br>國立陽明大學<br>傳統醫藥研究所<br>101<br>Background/aim: The diagnosis and treatment of Parkison’s disease remains a challenging problem. The aim of this study was to investigate the role of retained acupuncture (RA) in neurotoxin-induced Parkinson’s disease (PD) mice and to correlate hand tremors analyzed by a non-invasive method with clinical manifestation among PD patients. Method: In animal study, male C57BL/6 mice were injected with 1-methyl-4-phenyl-1,2,3,6- tetrahydropyridine (MPTP) to induce the PD model. The mice were divided into four groups, namely, ( 1) normal; (2) MPTP + retained acupuncture (RA);( 3) MPTP + electroacupuncture (EA); (4) MPTP + sham acupuncture (SA). After mice being manipulated twice with/without acupuncture at acupoints (Daling, PC 7), groups 2-4 were injected with MPTP (15 mg/kg/d). The mice were evaluated for behavioral changes, in terms of time of landing, after another acupuncture treatment. The animals were sacrificed and their brains assayed for dopamine and its metabolites and tyrosine hydroxylase (TH) expression by using HPLC and immunohistochemistry /Western blotting, respectively. [123I] IBZM-SPECT imaging between SA and RA groups were compared. In human study, there were four modes in tremor detection during each testing session in PD patients, namely, Mode 1, single hand tremor detected during a single resting hand posture; Mode 2, single hand tremor detected during paired resting hands posture; Mode 3, single postural hand tremor detected during a single (lifting) hand posture; and Mode 4, single postural hand tremor detected during paired (lifting) hands posture. The hand tremor was detected using a laser line triangulation measurement method and the image was stored on a video system after acquisition from a computer and analyzed off-line. Results: The results of animal study showed that the time of landing of the three groups with treatment was significant longer than group 1(normal) (4.33 ± 0.15 sec). Nonetheless, group 2 (RA) (7.13 ±0.20 sec) had a shorter time of landing than group 4 (SA) (7.89 ± 0.46 sec). The number of TH (+) neurons and the expression of TH proteins were significantly higher in the RA group than in the SA/ EA groups. RA also increased the uptake of [123I] IBZM into the striatum compared to the SA group. The results of hand tremor detection showed a significant correlation between age at disease onset and tremor frequency obtained from the left hand, tremor frequency obtained from the non-dominant hand using Mode 1(single, resting) and tremor frequency obtained from the non-dominant hand using Mode 2(both, resting). Furthermore, there was a significant positive correlation between disease duration and tremor frequency obtained from the left hand, tremor frequency obtained from the non-dominant hand using Mode 1(single, resting), tremor frequency obtained from lifting the left hand using Mode 3(single, postural), tremor frequency obtained from lifting the right hand and tremor frequency obtained from lifting the dominant hand in Mode 4(both, postural). Conclusion: We conclude that RA possibly attenuates neuronal damage in MPTP-induced PD mice, which suggests RA may be useful as a complementary strategy when treating human PD. Moreover, the laser line triangulation measurement is a non-invasive method that can detect tremor early in the course of patients diagnosed with PD.

碩士<br>長庚大學<br>電機工程學系<br>102<br>With aging society coming, there are more and more elderly people having the aging-related chronic diseases, such as Parkinson’s, and Alzheimer’s diseases. In this study, a time-less linear transformation method is proposed to obtain tilting angles from single axis accelerometer data. By wearing the previous designed posture monitor vest and with the proposed algorithm implemented, this wearable system can detect the forward-flexed posture which is frequently seen in the early symptom of Parkinson’s disease, the festination. Detection of this posture is the necessary function for the festination detection system which can work as an quantitative tool for early detection of Parkinson’s disease. The technology which is used in this paper are the calculating of angle and the detecting of walking pattern. The detecting of angle use the timeless angle detection but the inverse trigonometric function, using the data from the accelerometer at different situation to estimate the angle. With the different ranges selected, the corresponding accuracy can be choice. Another technology is the detecting of walking pattern by accelerometer, by using the affection of accelerometer from the walking to calculate the step frequency ratio or the time difference. Besides the step frequency ratio and time difference, there also is the step counts, including the prevention of surplus step or the compensation of the losing step. The device we using is the ADuC7024 of the AnalogDevice Inc. and the smart clothes. It can transform the data to handheld device, like cell phone or PDA, in real time, and also can transform to cloud and let the stuff of health care to observe the situation of patients. This would allow patients to have the health assessment not only in the hospital but only everywhere.

碩士<br>國立中興大學<br>資訊管理學系所<br>105<br>Parkinson&apos;&apos;s disease is second to Alzheimer disease, one of the slowest degenerative diseases known to affect us. Approximately 6.2 million people globally are battling this disease, and every 147.7 people in 100 thousand Taiwanese will be affected by it. Although people in their middle ages or elderly people are more likely to manifest this disease, it does seem that nowadays even young people can contract it. This is known medically as Early Onset Parkinsonism. It is caused by the deterioration of melanin generated by substantia nigra pars compacta, which in term effected the functions of Basal ganglia, causing the motion of an individual to slow down. In addition, the cognitive ability, such as visual and spacing ability, memory, depression, language ability, of the individual will be largely impeded as well. In the early stages of Parkinson&apos;&apos;s disease, individuals may seek professional medical help due to above symptoms but are usually turned away with no diagnosis. About 70%-90% of Parkinson&apos;&apos;s disease owners exhibit one of the common symptoms is language disability and voice abnormality. Their voice is lower. They mumble. Their pronunciation is slow and incoherent. This research uses voice characteristics data, using J48, MLP and KNN algorithm, to construct Parkinson&apos;&apos;s disease early detection model. All the three algorithm mentioned above have reached over 90% accuracy in detection and out of the three, KNN’s accuracy has reached as high as 95.4%, demonstrating that it is highly possible to detect Parkinson&apos;&apos;s through voice characteristics. This signifies the possibility to apply such data detection method in the medical field. As more and more data is collected and verified, these methods can be used in actual clinical scenarios and help Parkinson&apos;&apos;s disease developers to detect it early and start the treatment early.

碩士<br>國立臺灣大學<br>流行病學與預防醫學研究所<br>99<br>Background: Parkinson&apos;&apos;s disease (PD) is the second most common neurodegenerative disease in Taiwan. A total of 85,510 patients suffered from PD have been under treated in 2008 in Taiwan. It has been showed that screening for early PD can lead to 51% reduction for late stage of PD, and 25% mortality reduction. Thus, early detection could relieve medical burden from PD for patients themselves, the family members, and even for society. However, the cost-effectiveness of PD screening was never addressed. The aim of this thesis was to evaluate the cost-effectiveness of PD screening program. Materials and Methods: Parameters used in the Markov decision analytic model considering disease progress and the efficacy of PD screening were derived from Keelung Community–based survey for PD in 2001, which targeted at residents aged 40 years and above. Data on cost of PD treatment was derived from the national health insurance claimed data during the period of 2001 to 2008. Both deterministic and probabilistic cost-effectiveness analyses of PD screening program were conducted with computer simulation for a simulated hypothetical cohort of residents aged 40 years and above. The health policy maker’s view point was used for economic analysis. Results: Without considering discount rate, compared with no screen strategy, the incremental cost-effectiveness ratios (ICER) of PD screening with one-shot or with different interscreening intervals ranged from NTD 16,447 to 59,577 per life-year gained. The ICERs ranged from NTD 23,167 to 76,125 per life year gained considering 3% discount rate. The best strategy is one-shot screen for ceiling ratio ranged from NTD 21,000 to 80,000. The second and third strategies were triennial screen and biennial screen for which the ceiling ratios changed from NTD 80,000 to 110,000, and NTD 10,000 to 255,000, respectively. If the ceiling ratio is larger than NTD 255,000, then annual screen became the most cost-effective strategy. Conclusion: PD screening program is cost-effective.

碩士<br>國立臺北科技大學<br>機電整合研究所<br>101<br>The purpose of this study is to design a system and cueing function aiding devices equipment especially for the Parkinson’s disease patients. Symptoms of this disease are shaking and difficulty with walking which affects the sufferers’ daily living functions. When a senior PD patient falls down, it is very important to warn of his relatives quickly and efficiently. However, there are various types of mobility aids on the market that can be chosen for the senior PD patients to improve the mobility with their mobility impairment. For the convenience and portability, most elders will select cane as their moving aids.This study adds an accelerometer to the cane to implement falling detections, and further send out alarms automatically.The market has already canes with visual cueing designs, but mostly for straight walking purpose.The purpose of this study is to design a detachable walking aid which can be equipped on existing cane or any other walking aids, with visual cues especially when turning and walking straight with distance adjustability to help the senior PD patients.

no<br>There are a wide variety of ways to objectively detect neurological signs, but these either require special hard-ware (such as wearable technology) or patient behaviour change (such as engagement with smartphone tasks) [2]. Neither constraint applies to the technology of computer vision, which is the processing of single or multiple camera images by computer to automatically derive useful information. The only equipment involved is ubiquitous: camera and computer.We report a computer vision-enhanced video sequence from a 68-year-old man, diagnosed with idiopathic Parkinson’s disease 2 years previously.

碩士<br>國立臺北科技大學<br>電機工程系<br>107<br>As Taiwan has become an aging society, the number of patients suffering from Parkinson’s disease (PD) is about hundred thousand people. PD patients often have problems such as gait instability, which made walking more difficult than the normal persons. It is even more difficult when ascending and descending stairs. In order to help the patient’s reconstruction process effectively and enable clinicians and researchers to monitor and track patients, it is necessary to provide quantified patient rehabilitation data. This study proposes a system based on inertial measurement units, consisting of 5 sensors worn on specific areas recommended by the doctor, and calculate the human joint angles, which can effectively record, track, and assist patients in rehabilitation. This system is divided into three parts. First is the collection of gait information by the sensors, and the second is the information collected by the Unity 3D platform integrated sensing device and provides interactive functions to record and track patient posture information. For example, we can collect information about hip and knee flexion, extension, etc. Finally, gait information such as step sizes and number of steps are calculated for collecting gait information. According to the experimental results, when the subject was stair ascending and descending, compared with walking on the ground, the hip flexion and knee flexion angles were larger. In addition, the system can record the quantitative data of PD patients for stair ascending and descending, provide doctors to determine gait information, and allow doctors to obtain the best rehabilitation method for patients from their gait information. Then, physical therapists can recommend patients how to follow the instructions to achieve the correct rehabilitation posture.