Analysis and evaluation of handwriting in patients with Parkinson's disease using kinematic, geometrical, and non-linear features. (May 2019)

• Record Type: Journal Article
• Authors: Rios-Urrego, C.D.; Vásquez-Correa, J.C.; Vargas-Bonilla, J.F.; Nöth, E.; Lopera, F.; Orozco-Arroyave, J.R.
• Is Part Of: Computer methods and programs in biomedicine. Volume 173(2019)
• Page Start: 43
• Page End: 52
• Publication Date: 2019-05
• Subjects: Parkinson's disease -- Handwriting -- Kinematic features -- Geometrical features -- Non-linear dynamics; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2019.03.005
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: We explored and evaluated the suitability of three different feature sets (kinematics, geometrical and NLD) to model handwriting impairments exhibited by PD patients. Kinematics features seemed to be the most accurate to discriminate between PD patients and HC subjects. The combination of the three feature sets in the same space also exhibited good classification results. The results show that it is possible to discriminate between PD and HC subjects (in a separate test set) with accuracies of up to 83.3%. A relevance analysis of the features showed that the speed, pressure, and acceleration of the strokes are the most relevant aspects to classify PD patients and HC subjects. Abstract: Background and objectives: Parkinson's disease is a neurological disorder that affects the motor system producing lack of coordination, resting tremor, and rigidity. Impairments in handwriting are among the main symptoms of the disease. Handwriting analysis can help in supporting the diagnosis and in monitoring the progress of the disease. This paper aims to evaluate the importance of different groups of features to model handwriting deficits that appear due to Parkinson's disease; and how those features are able to discriminate between Parkinson's disease patients and healthy subjects. Methods: Features based on kinematic, geometrical and non-linear dynamics analyses were evaluated to classify Parkinson's disease and healthy subjects. Classifiers based on K-nearest neighbors, support vector machines, and random forest were considered. Results: Accuracies of up to 93.1% were obtained in the classification of patients and healthy control subjects. A relevance analysis of the features indicated that those related to speed, acceleration, and pressure are the most discriminant. The automatic classification of patients in different stages of the disease shows κ indexes between 0.36 and 0.44. Accuracies of up to 83.3% were obtained in a different dataset used only for validation purposes. Conclusions: The results confirmed the negative impact of aging in the classification process when we considered different groups of healthy subjects. In addition, the results reported with the separate validation set comprise a step towards the development of automated tools to support the diagnosis process in clinical practice.