Resting tremor is an essential characteristic in patients suffering from Parkinson’s disease (PD).
OBJECTIVE:
Quantification and monitoring of tremor severity is clinically important to help achieve medication or rehabilitation guidance in daily monitoring.
METHODS:
Wrist-worn tri-axial accelerometers were utilized to record the long-term acceleration signals of PD patients with different tremor severities rated by Unified Parkinson’s Disease Rating Scale (UPDRS). Based on the extracted features, three kinds of classifiers were used to identify different tremor severities. Statistical tests were further designed for the feature analysis.
RESULTS:
The support vector machine (SVM) achieved the best performance with an overall accuracy of 94.84%. Additional feature analysis indicated the validity of the proposed feature combination and revealed the importance of different features in differentiating tremor severities.
CONCLUSION:
The present work obtains a high-accuracy classification in tremor severity, which is expected to play a crucial role in PD treatment and symptom monitoring in real life.
van de WardtJvan der StouweAMMDirkxM, et al. Systematic clinical approach for diagnosing upper limb tremor. J Neurol Neurosurg Psychiatry.2020; 91(8): 822-830. doi: 10.1136/jnnp-2019-322676.
2.
PringsheimTJetteNFrolkisASteevesTD. The prevalence of Parkinson’s disease: a systematic review and meta-analysis. Mov Disord.2014; 29(13): 1583-1590. doi: 10.1002/mds.25945.
National Collaborating Centre for Chronic Conditions (UK). Parkinson’s Disease: National Clinical Guideline for Diagnosis and Management in Primary and Secondary Care. London: Royal College of Physicians (UK); 2006.
5.
FahnS. Unified Parkinson’s Disease Rating Scale, In: FahnS.MarsdenC.D.CalneD.B. and GoldsteinM., Recent Developments in Parkinson’s Disease. Macmillan Health Care Information. 1987; 2: 153-163.
6.
ValmarskaAMiljkovicDKonitsiotisSGatsiosDLavračNRobnik-ŠikonjaM. Symptoms and medications change patterns for Parkinson’s disease patients stratification. Artif Intell Med.2018; 91: 82-95. doi: 10.1016/j.artmed.2018.04.010.
7.
BasuIGraupeDTuninettiD, et al. Pathological tremor prediction using surface electromyogram and acceleration: potential use in ‘ON-OFF’ demand driven deep brain stimulator design. J Neural Eng.2013; 10(3): 036019. doi: 10.1088/1741-2560/10/3/036019.
8.
MohammedAZamaniMBayfordRDemosthenousA. Patient specific Parkinson’s disease detection for adaptive deep brain stimulation. Annu Int Conf IEEE Eng Med Biol Soc.2015; 2015: 1528-1531. doi: 10.1109/EMBC.2015.7318662.
9.
AlperMAGoudreauJDanielM. Pose and Optical Flow Fusion (POFF) for accurate tremor detection and quantification. Biocybern Biomed Eng, 2020; 40(1): 468-481. doi: 10.1016/j.bbe.2020.01.009.
10.
Vivar-EstudilloGIbarra-ManzanoMAAlmanza-OjedaDL. Tremor Signal Analysis for Parkinson’s Disease Detection Using Leap Motion Device. Lect. Notes Comput. Sci.2018; 342-353. doi: 10.1007/978-3-030-04491-6_26.
11.
TuncerTDoganSAcharyaUR. Automated detection of Parkinson’s disease using minimum average maximum tree and singular value decomposition method with vowels. Biocybern Biomed Eng, 2020; 40(1): 211-220. doi: 10.1016/j.bbe.2019.05.006.
12.
RuszJBonnetCKlempířJ, et al. Speech disorders reflect differing pathophysiology in Parkinson’s disease, progressive supranuclear palsy and multiple system atrophy. J Neurol.2015; 262(4): 992-1001. doi: 10.1007/s00415-015-7671-1.
13.
TsanasALittleMAMcSharryPESpielmanJRamigLO. Novel speech signal processing algorithms for high-accuracy classification of Parkinson’s disease. IEEE Trans Biomed Eng.2012; 59(5): 1264-1271. doi: 10.1109/TBME.2012.2183367.
14.
KaranBSahuSSMahtoK. Parkinson disease prediction using intrinsic mode function based features from speech signal. Biocybern Biomed Eng, 2020; 40(1): 249-264. doi: 10.1016/j.bbe.2019.05.005.
15.
Pascoal-FariaPPatrícioMLealA, et al. Understanding tremor in rapid upper limb movements using 3d accelerometers data. Neurosci Med, 2014; 5(5): 205. doi: 10.4236/nm.2014.55024.
16.
DideriksenJLGallegoJAHolobarARoconEPonsJLFarinaD. One central oscillatory drive is compatible with experimental motor unit behaviour in essential and Parkinsonian tremor. J Neural Eng.2015; 12(4): 046019. doi: 10.1088/1741-2560/12/4/046019.
17.
van den NoortJCVerhagenRvan DijkKJ, et al. Quantification of Hand Motor Symptoms in Parkinson’s Disease: A Proof-of-Principle Study Using Inertial and Force Sensors. Ann Biomed Eng.2017; 45(10): 2423-2436. doi: 10.1007/s10439-017-1881-x.
18.
DaiHZhangPLuethTC. Quantitative Assessment of Parkinsonian Tremor Based on an Inertial Measurement Unit. Sensors (Basel).2015; 15(10): 25055-25071. doi: 10.3390/s151025055.
19.
HossenADeuschlGGroppaSHeuteUMuthuramanM. Discrimination of physiological tremor from pathological tremor using accelerometer and surface EMG signals. Technol Health Care.2020; 28(5): 461-476. doi: 10.3233/THC-191947.
20.
MeigalAYRissanenSMTarvainenMP, et al. Linear and nonlinear tremor acceleration characteristics in patients with Parkinson’s disease. Physiol Meas.2012; 33(3): 395-412. doi: 10.1088/0967-3334/33/3/395.
21.
PereraTYohanandanSAThevathasanW, et al. Clinical validation of a precision electromagnetic tremor measurement system in participants receiving deep brain stimulation for essential tremor. Physiol Meas.2016; 37(9): 1516-1527. doi: 10.1088/0967-3334/37/9/1516.
22.
CamaraCIsasiPWarwickK, et al. Resting tremor classification and detection in Parkinson’s disease patients. Biomed Signal Proces.2015; 16: 88-97. doi: 10.1016/j.bspc.2014.09.006.
23.
Sanchez-PerezLASanchez-FernandezLPShaoutAMartinez-HernandezJMAlvarez-NoriegaMJ. Rest tremor quantification based on fuzzy inference systems and wearable sensors. Int J Med Inform.2018; 114: 6-17. doi: 10.1016/j.ijmedinf.2018.03.002.
24.
DaneaultJFCarignanBCodèreCÉSadikotAFDuvalC. Using a smart phone as a standalone platform for detection and monitoring of pathological tremors. Front Hum Neurosci.2013; 6: 357. doi: 10.3389/fnhum.2012.00357.
25.
RibeiroLCFAfonsoLCSPapaJP. Bag of Samplings for computer-assisted Parkinson’s disease diagnosis based on Recurrent Neural Networks. Comput Biol Med.2019; 115: 103477. doi: 10.1016/j.compbiomed.2019.103477.
26.
PereiraCRPereiraDRRosaGH, et al. Handwritten dynamics assessment through convolutional neural networks: An application to Parkinson’s disease identification. Artif Intell Med.2018; 87: 67-77. doi: 10.1016/j.artmed.2018.04.001.
27.
OktayABKocerA. Differential diagnosis of Parkinson and essential tremor with convolutional LSTM networks. Biomed Signal Proces.2020; 56: 101683. doi: 10.1016/j.bspc.2019.101683.
28.
MallingASBMorbergBMWermuthLGredalOBechPJensenBR. The influence of posture duration on hand tremor during tasks with attention-distraction in persons with Parkinson’s disease. J Neuroeng Rehabil.2019; 16(1): 61. doi: 10.1186/s12984-019-0534-8.
29.
JeonHLeeWParkH, et al. High-accuracy automatic classification of Parkinsonian tremor severity using machine learning method. Physiol Meas.2017; 38(11): 1980-1999. doi: 10.1088/1361-6579/aa8e1f.
30.
BudzianowskaAHonczarenkoK. Assessment of rest tremor in Parkinson’s disease. Neurol Neurochir Pol.2008; 42(1): 12-21.
31.
ElbleRJPullmanSLMatsumotoJY, et al. Tremor amplitude is logarithmically related to 4- and 5-point tremor rating scales. Brain.2006; 129(Pt 10): 2660-2666. doi: 10.1093/brain/awl190.
32.
MostileGGiuffridaJPAdamORDavidsonAJankovicJ. Correlation between Kinesia system assessments and clinical tremor scores in patients with essential tremor. Mov Disord.2010; 25(12): 1938-1943. doi: 10.1002/mds.23201.
33.
CaiGLinZDaiH, et al. Quantitative assessment of parkinsonian tremor based on a linear acceleration extraction algorithm. Biomed Signal Proces.2018; 42: 53-62. doi: 10.1016/j.bspc.2018.01.008.
34.
RigasGTzallasATTsipourasMG, et al. Assessment of tremor activity in the Parkinson’s disease using a set of wearable sensors. IEEE Trans Inf Technol Biomed.2012; 16(3): 478-487. doi: 10.1109/TITB.2011.2182616.
35.
RichmanJSMoormanJR. Physiological time-series analysis using approximate entropy and sample entropy. Am J Physiol Heart Circ Physiol.2000; 278(6): H2039-H2049. doi: 10.1152/ajpheart.2000.278.6.H2039.
36.
YohanandanSACJonesMPeppardR, et al. Evaluating machine learning algorithms estimating tremor severity ratings on the Bain-Findley scale. Meas Sci Technol.2016; 27(12): 125702. doi: 10.1088/0957-0233/27/12/125702.
37.
CramerJS. The origins of logistic regression. 2002.
38.
ChenTGuestrinC. Xgboost: A scalable tree boosting system. Proc. ACM SIGKDD Int. Conf. Knowl. Discov. Data Min.2016; 785-794. doi: 10.1145/2939672.2939785.
39.
YaoLBrownPShoaranM. Resting Tremor Detection in Parkinson’s Disease with Machine Learning and Kalman Filtering. IEEE Biomed Circuits Syst Conf.2019; 2018: BIOCAS.2018.8584721. doi: 10.1109/BIOCAS.2018.8584721.
