Analysis of in-air movement in handwriting: A novel marker for Parkinson's disease

• Published in: Computer methods and programs in biomedicine Vol. 117; no. 3; pp. 405 - 411
• Main Authors: Drotár, Peter, Mekyska, Jiří, Rektorová, Irena, Masarová, Lucia, Smékal, Zdenek, Faundez-Zanuy, Marcos
• Format: Journal Article
• Language: English
• Published: Kidlington Elsevier Ireland Ltd 01.12.2014; Elsevier
• Subjects: Accuracy; Aged; Algorithms; Applied sciences; Artificial Intelligence; Biological and medical sciences; Biomechanical Phenomena; Case-Control Studies; Classifications; Computer science; control theory; systems; Computerized, statistical medical data processing and models in biomedicine; Control equipment; Data processing. List processing. Character string processing; Decision support systems; Decision Support Systems, Clinical; Diagnosis; Diagnosis, Differential; Disease classification; Exact sciences and technology; Female; Hand - physiology; Handwriting; Headache. Facial pains. Syncopes. Epilepsia. Intracranial hypertension. Brain oedema. Cerebral palsy; Humans; In-air movement; Internal Medicine; Male; Markers; Medical sciences; Memory organisation. Data processing; Micrographia; Middle Aged; Models and simulation; Motor Skills; Movement; Nervous system (semeiology, syndromes); Neurology; Other; Parkinson Disease - diagnosis; Parkinson Disease - physiopathology; Parkinson's disease; Patients; Pattern recognition. Digital image processing. Computational geometry; Reproducibility of Results; Software; Support Vector Machine; Decision support systems; Handwriting; In-air movement; Parkinson's disease; Disease classification; Micrographia; Human; Computer vision; Cognitive disorder; Motion estimation; Decision support system; Parkinson disease; Text; Marker; Hand; Kinematics; Body movement; Vector support machine; Diagnosis; Manuscript character; Elderly; Sentence; Age; Micrography

•We exploit the fact that movement during handwriting of a text consists of on-surface and in-air movements and use it for differential diagnosis of PD.•By applying feature selection algorithms and support vector machine learning methods to separate PD from HC, we demonstrated 85% classification acc...