Biomechanical parameters assessment for the classification of Parkinson Disease using Bidirectional Long Short-Term Memory.

Nowadays objective and efficient assessment of Parkinson Disease (PD) with machine learning techniques is a major focus for clinical management. This work presents a novel approach for classification of patients with PD (PwPD) and healthy controls (HC) using Bidirectional Long Short-Term Neural Network (BLSTM). In this paper, the SensHand and the SensFoot inertial wearable sensors for upper and lower limbs motion analysis were used to acquire motion data in thirteen tasks derived from the MDS-UPDRS III. Sixty-four PwPD and fifty HC were involved in this study. One hundred ninety extracted spatiotemporal and frequency parameters were applied as a single input against each subject to develop a recurrent BLSTM to discriminate the two groups. The maximum achieved accuracy was 82.4%, with the sensitivity of 92.3% and specificity of 76.2%. The obtained results suggest that the use of the extracted parameters for the development of the BLSTM contributed significantly to the classification of PwPD and HC.

Objective and automatic classification of Parkinson disease with Leap Motion controller.

BACKGROUND: The main objective of this paper is to develop and test the ability of the Leap Motion controller (LMC) to assess the motor dysfunction in patients with Parkinson disease (PwPD) based on the MDS-UPDRSIII exercises. Four exercises (thumb forefinger tapping, hand opening/closing, pronation/supination, postural tremor) were used to evaluate the characteristics described in MDS-UPDRSIII. Clinical ratings according to the MDS/UPDRS-section III items were used as target. For that purpose, 16 participants with PD and 12 healthy people were recruited in Ospedale Cisanello, Pisa, Italy. The participants performed standardized hand movements with camera-based marker. Time and frequency domain features related to velocity, angle, amplitude, and frequency were derived from the LMC data. RESULTS: Different machine learning techniques were used to classify the PD and healthy subjects by comparing the subjective scale given by neurologists against the predicted diagnosis from the machine learning classifiers. Feature selection methods were used to choose the most significant features. Logistic regression (LR), naive Bayes (NB), and support vector machine (SVM) were trained with tenfold cross validation with selected features. The maximum obtained classification accuracy with LR was 70.37%; the average area under the ROC curve (AUC) was 0.831. The obtained classification accuracy with NB was 81.4%, with AUC of 0.811. The obtained classification accuracy with SVM was 74.07%, with AUC of 0.675. CONCLUSIONS: Results revealed that the system did not return clinically meaningful data for measuring postural tremor in PwPD. In addition, it showed limited potential to measure the forearm pronation/supination. In contrast, for finger tapping and hand opening/closing, the derived parameters showed statistical and clinical significance. Future studies should continue to validate the LMC as updated versions of the software are developed. The obtained results support the fact that most of the set of selected features contributed significantly to classify the PwPD and healthy subjects.

Leap motion evaluation for assessment of upper limb motor skills in Parkinson's disease.

The main goal of this study is to investigate the potential of the Leap Motion Controller (LMC) for the objective assessment of motor dysfunctioning in patients with Parkinson's disease (PwPD). The most relevant clinical signs in Parkinson's Disease (PD), such as slowness of movements, frequency variation, amplitude variation, and speed, were extracted from the recorded LMC data. Data were clinically quantified using the LMC software development kit (SDK). In this study, 16 PwPD subjects and 12 control healthy subjects were involved. A neurologist assessed the subjects during the task execution, assigning them a score according to the MDS/UPDRS-Section III items. Features of motor performance from both subject groups (patients and healthy controls) were extracted with dedicated algorithms. Furthermore, to find out the significance of such features from the clinical point of view, machine learning based methods were used. Overall, our findings showed the moderate potential of LMC to extract the motor performance of PwPD.