Page 87 - Read Online

Page 75 Shu et al. Intell Robot 2024;4(1):74-86 I http://dx.doi.org/10.20517/ir.2024.05

weighted precision, and kappa coefficient by 8.89%-15.56%, 9.22%-16.37%, and 0.13-0.23, respectively, compared
with support vector machines, long short-term memory, and convolutional prototype network. For the lower limb
movement data, the proposed method improved the classification accuracy, weighted precision, and kappa coeffi-
cient by 8.16%-20.41%, 10.01%-23.73%, and 0.12-0.28, respectively. The experiments and results show that the
proposed method can objectively and accurately assess upper and lower limb bradykinesia in PD.

Keywords: Parkinson’s disease, bradykinesia, motion capture, dynamic time warping, attentional prototype network

1. INTRODUCTION
Parkinson’s disease (PD) is the second most prevalent neurodegenerative disease, which affects 1%–2% of indi-
[1]
viduals above 65 . The Global Burden of Disease Study 2016 reported that China has about 23% of the global
[2]
[3]
PD patients . By 2030, this proportion will reach 50% . This substantial number of affected individuals will
pose significant medical challenges and place a heavy economic burden on society.
PDtypicallypresentswithvaryingmotorsymptoms, includingbradykinesia, tremors, rigidity, gaitdisturbance,
and postural instability [4,5] . As the most characteristic clinical symptom, bradykinesia manifests as a general
slowness of movement, hesitations, and a reduction in movement amplitude or speed during continuous mo-
[6]
tion . According to the most recent clinical diagnostic criteria, the diagnosis of PD is based on the presence
of bradykinesia plus at least one among tremor, rigidity, and postural instability, which makes bradykinesia the
[7]
cornerstone of the disease . Therefore, accurate bradykinesia assessment can facilitate PD’s clinical diagnosis
and long-term monitoring. Currently, the clinical assessment of bradykinesia is mainly based on the Move-
ment Disorders Society United PD Rating Scale part III (MDS-UPDRS-part III), which primarily evaluates
the motor performance of the patient’s upper and lower limbs, such as finger and toe tapping. The severity of
[8]
bradykinesia is scored as 0-4 points, where 0 indicates normal, and 4 indicates severe condition . However,
the scale rating relies on the doctor’s judgment and clinical expertise, which may introduce a degree of subjec-
[9]
tivity and variation among individuals . Besides, the manual evaluation assessments are based on an overall
impression of movement, making it challenging to discern the minor differences [10] . Therefore, developing
an accurate and objective method for evaluating bradykinesia represents a significant challenge and a current
area of focus in PD diagnosis and therapy.

In recent years, a variety of intelligent instruments, such as inertial sensing units, gyroscopes, and accelerome-
ters, have been employed for the quantitative assessment of bradykinesia in PD [11–15] . These instruments can
collect movement data from patients with PD. However, their ability to directly capture movement features is
not always reliable, and they may generate errors due to fusion algorithms. Motion capture systems employ
markers on the patient’s limbs to monitor movement. These markers are tracked by a specialized capture sys-
tem that records their positions, enabling motion information collection. This technology outperforms other
instruments in capturing accurate and direct movement data, which is vital for improving the precision of
quantitative evaluations of bradykinesia in patients with PD.

Currently, researchers have utilized motion capture systems for quantitative assessments of bradykinesia in
PD. Given that clinical data often comprises small samples, analysis of motion capture data has predominantly
been manual feature extraction followed by traditional machine learning techniques. Das et al. have extracted
features such as movement amplitude and average speed from gait and toe tapping tasks. Using support vector
machine (SVM) methods, they differentiated between patients with mild and severe symptoms with an accu-
racy of about90% [10] . Wahid etal. used gait-based motion capture data to extract features such as stride length
and gait time, applying methods such as random forest and SVM to distinguish between patients with PD and
healthy controls, achieving an accuracy of 92.6% [16] . However, these methods have limitations in uncovering