Objective: We aimed to investigate useful vocal parameters in differentiating PD and ET, using a machine-learning algorithm.
Background: Correlation between Parkinson’s disease (PD) and essential tremor (ET) has long been suggested, as both clinical characteristics and epidemiological factors have been found to overlap. A subset of patients with long-standing ET are found to develop subsequent PD, further suggesting an association between the two disease entities.
Method: Patients (27 PD[ON], 20 PD[OFF], 26 ET[ON] and 13 ET[OFF]) seen in the Neurology Clinic at Dongguk University Ilsan Hospital were included. Study procedures included the following: Vocal recording (“Ah~” for at least 5 seconds x 3 trials, reading a standardized sentence, and singing the Korean anthem), Brief Smell Identification Test, Unified Parkinson’s Disease Rating Scale (UPDRS) Parts I, II & III and in ET patients, the Clinical Tremor Rating Scale (CTRS) was also performed. Videotaping was conducted and analysis was performed offline.
Results: We applied a machine-learning algorithm to our data. Spectography was performed and binary classification of deep-learning was attempted. Simple utterance vocal data of the two patient groups in the medication-OFF state were found to have a 68% accuracy. Simple utterance vocal data of the ET group in the medication-OFF and ON state were found to have 60% LOSO accuracy.
Conclusion: Vocal data obtained by simple utterance may be useful to differentiate patients with PD and ET in the medication-OFF state. Our machine-learning algorithm was capable of differentiating vocal data of patients with ET in the medication-OFF and ON state, suggesting that the vocal tremor in ET patients may be affected by medication, in contrast with findings of the PD group. We anticipate applying our algorithm to vocal data of a subset of ET patients found to have moderate UPDRS scores and/or olfactory dysfunction, which may help to shed light on the association between ET and PD.
References: 1. Thenganatt MA, et al. The relationship between essential tremor and Parkinson’s disease. Parkinsonism Relat Disord. 2016 Jan;22 Suppl 1:S162-5. 2. Tarakad A, et al. Essential Tremor and Parkinson’s Disease: Exploring the Relationship. Tremor Other Hyperkinet Mov (N Y). 2019 Jan 9;8:589. 3. Fekete R, et al. Revisiting the relationship between essential tremor and Parkinson’s disease. Mov Disord. 2011 Feb 15;26(3):391-8. 4. Minen MT, et al. Emergence of Parkinsons Disease in Essential Tremor: A Study of the Clinical Correlates in 53 Patients. Mov Disord. 2008 Aug 15; 23(11): 1602–1605. 5. Shahed J, et al. Exploring the relationship between essential tremor and Parkinson’s disease. Parkinsonism Relat Disord. 2007 Mar;13(2):67-76.
To cite this abstract in AMA style:J.E Park, S.W Oh, J.Y Shin, S.Y Lee, S.H Hong, N.H Ahn, H.J Kim, K.H Lee, J.E Bae, H.B Lee. Say “AH~”: Vocal Analysis in Parkinson’s Disease and Essential Tremor [abstract]. Mov Disord. 2020; 35 (suppl 1). https://www.mdsabstracts.org/abstract/say-ah-vocal-analysis-in-parkinsons-disease-and-essential-tremor/. Accessed December 2, 2023.
« Back to MDS Virtual Congress 2020
MDS Abstracts - https://www.mdsabstracts.org/abstract/say-ah-vocal-analysis-in-parkinsons-disease-and-essential-tremor/