Semi-global parametization of online handwriting features for characterizing early-stage alzheimer and mild cognitive impairment
| Autor: | Sonia Garcia-Salicetti, Anne-Sophie Rigaud, Hélène Kerhervé, Mounim A. El-Yacoubi, Christian Kahindo, Victoria Cristancho-Lacroix |
|---|---|
| Přispěvatelé: | Services répartis, Architectures, MOdélisation, Validation, Administration des Réseaux (SAMOVAR), Institut Mines-Télécom [Paris] (IMT)-Télécom SudParis (TSP), Centre National de la Recherche Scientifique (CNRS), ARMEDIA (ARMEDIA-SAMOVAR), Institut Mines-Télécom [Paris] (IMT)-Télécom SudParis (TSP)-Institut Mines-Télécom [Paris] (IMT)-Télécom SudParis (TSP), Département Electronique et Physique (EPH), AP-HP - Hôpital Cochin Broca Hôtel Dieu [Paris], Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP), Maladie d'Alzheimer : marqueurs génétiques et vasculaires, neuropsychologies (EA 4468), Université Paris Descartes - Paris 5 (UPD5)-Groupe hospitalier Broca, Institut Mines-Télécom [Paris] (IMT)-Télécom SudParis (TSP)-Centre National de la Recherche Scientifique (CNRS), Institut Mines-Télécom [Paris] (IMT)-Télécom SudParis (TSP)-Centre National de la Recherche Scientifique (CNRS)-Institut Mines-Télécom [Paris] (IMT)-Télécom SudParis (TSP)-Centre National de la Recherche Scientifique (CNRS) |
| Jazyk: | angličtina |
| Rok vydání: | 2018 |
| Předmět: |
Normalized mutual information
Computer science Population Biomedical Engineering Biophysics Kinematics Parameter space 050105 experimental psychology Clustering 03 medical and health sciences 0302 clinical medicine Discriminative model Handwriting 0501 psychology and cognitive sciences education Statistical hypothesis testing education.field_of_study business.industry 05 social sciences Semi-global features Mild cognitive impairment Pattern recognition Alzheimer's disease Hierarchical clustering Online handwriting Artificial intelligence business Parametrization [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing 030217 neurology & neurosurgery |
| Zdroj: | Innovation and Research in BioMedical engineering Innovation and Research in BioMedical engineering, Elsevier Masson, 2018, 39 (6), pp.421-429. ⟨10.1016/j.irbm.2018.10.001⟩ IRBM IRBM, Elsevier Masson, 2018, 39 (6), pp.421-429. ⟨10.1016/j.irbm.2018.10.001⟩ |
| ISSN: | 1959-0318 |
| DOI: | 10.1016/j.irbm.2018.10.001⟩ |
| Popis: | International audience; Background : because of the rich set of spatiotemporal features it allows to extract, online handwriting is being increasingly investigated for characterizing neurodegenerative diseases like Parkinson and Alzheimer. The state of the art on the latter is dominated by methods that extract global (average) kinematic parameters, and then apply basic classification techniques or standard statistical tests to assess the statistical significance of each parameter in discriminating a pathological population from a healthy control one. Methods : we propose a new approach for characterizing Early-Stage Alzheimer disease (ES-AD), and Mild Cognitive Impairment (MCI) w.r.t Healthy Controls (HC) that, instead of considering average kinematic HW parameters, which discards the dynamics related to each subject, is based on a semi-global parameterization scheme encoding the distribution of each kinematic parameter over a mixed number of bins. Such a distribution characterizes the gross dynamic associated which each parameter. A semi-supervised learning is proposed, in which a Normalized Mutual Information (NMI) selection scheme guides a hierarchical clustering algorithm to choose the best tradeoff between the number of clusters and the discriminative power of each w.r.t to the three cognitive profiles. Results : for both global and semi-global parameters, the semi-supervised learning scheme uncovers clusters with two trends, one cluster that consist essentially of HC and MCI, and one cluster essentially composed of MCI and ES-AD. The clusters obtained with semi-global parameters are more informative than those with global parameters as reflected by a better NMI value. Conclusion : A semi-global parametrization of handwriting spatiotemporal parameters allows for a better discrimination between the HC, MCI and ES-AD profiles, than a global one does. Unlike the latter, the former encodes the distribution of the dynamics of each parameter, which offers a larger parameter space in which discrimination is easier |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect