A Multimodal Approach to the Quantification of Kinetic Tremor in Parkinson’s Disease

Abstract

Parkinson's disease results in motor impairment that deteriorates patients' quality of life. One of the symptoms negatively interfering with daily activities is kinetic tremor which should be measured to monitor the outcome of therapy. A new instrumented method of quantification of the kinetic tremor is proposed, based on the analysis of circles drawn on a digitizing tablet by a patient. The aim of this approach is to obtain a tremor scoring equivalent to that performed by trained clinicians. Models are trained with the least absolute shrinkage and selection operator (LASSO) method to predict the tremor scores on the basis of the parameters computed from the patients' drawings. Signal parametrization is derived from both expert knowledge and the response of an artificial neural network to the raw data, thus the approach was named multimodal. The fitted models are eventually combined into model ensembles that provide aggregated scores of the kinetic tremor captured in the drawings. The method was verified with a set of clinical data acquired from 64 Parkinson's disease patients. Automated and objective quantification of the kinetic tremor with the presented approach yielded promising results, as the Pearson's correlations between the visual ratings of tremor and the model predictions ranged from 0.839 to 0.890 in the best-performing models.

Automated Early Detection of Alzheimer’s Disease by Capturing Impairments in Multiple Cognitive Domains with Multiple Drawing Tasks

“…It is especially notable that the pressure variability consistently increased in the AD group for four of the five drawing tasks, with a medium-to-large effect size. Although the pressure variability during drawing tasks is known to increase for patients with Parkinson's disease [63] and Huntington's disease [64]-i.e., neurodegenerative diseases that typically involve motor symptoms-it has rarely been examined in the context of AD or MCI, except for a recent study on the CDT task by Davoudi et al [22]. On the other hand, recent studies on other types of behaviors in AD patients, such as the patient's gait [65][66][67] and finger tapping [68], have suggested that variability in motor control may be a useful marker for neuropathological changes.…”

“…The best combination of drawing tasks should be explored further in future studies. Furthermore, other neurodegenerative diseases such as Parkinson's disease [78] and Huntington's disease [79] also involve cognitive impairments in multiple domains, and the usefulness of drawing analysis has been reported for detecting those diseases, too [63,64]. Thus, our approach of capturing multifaceted cognitive impairments by analyzing drawing data also holds promise for improving the screening and diagnosis of those diseases.…”

Parkinson’s disease diagnosis using convolutional neural networks and figure-copying tasks

“…This dataset contains information about pen position (x and y components), pressure and grip angle. Szumilas et al [81] suggested also the use of an ESN-ensemble model to quantify kinetic tremor in PD by drawing circles on a digitising tablet, using, in this case, a dataset of 64 PD patients. Finally, in [75], the authors compared an ESN with a long short-term memory model using our dataset and reaching accuracies of 91% for the LSTM and 93.7% for the ESN.…”