Parkinson Hastalığı Seviyesi Tahmininde Vokal Kord Ölçümü Tabanlı Yapay Sinir Ağı Yaklaşımı

Amaç: Parkinson hastalığı kronik, ilerleyici ve nörolojik

Anahtar Kelimeler:

Parkinson Hastalığı, Yapay Sinir Ağları, Regresyon Analizi

Vocal Cord Measures Based Artificial Neural Network Approach for Prediction of Parkinson’ s Disease Status

Objective: Parkinson’s disease is a chronicneurodegenerative impairment which causes movementimpairment. Dopaminergic deficiency resulted from the lossof dopaminergic neurons in the substantia nigracauses thedisease. UPDRS (Unified Park-inson’s disease rating scale)is an important scale for evaluation of clinical severity ofParkinson’s disease. Recent computational studies using insilico prediction methods show promising results in termsof their potential diagnostic relevance. This study aims toevaluate the diagnostic potential of in silico methods usingvocal cord vibrations and the UPDR scale of Parkinson’sDisease for obtaining more precise diagnosis model.Material-Method: In this study an in silico prediction modelusing telemonitoring measures, clinical motor and totalUPDRS for diagnosis of Parkinson’s disease was developedby using regression analysis with neural network model. Inaddition, we investigated the importance of different attributesin our regression algorithm provided from telemonitoring andUPDRS for evaluation of their predictive relevance.Results: The correlation between predicted motor UPDRSscore and clinical motor UPDRS score was found as 97%.Exclusion of Jitter values did not directly affect the predictivepower of the model.Conclusions: Clinical UPDRS scoring proved its importanceto achieve to generate more predictive models.

Keywords:

Parkinson’s Disease, Artificial Neural Network, Regression Analysis,

PDF

___

1. Poirier J, Parkinson J. Geriatrie et Psychologie Neuropsychiatrie Du Vieillissement 2013; 11(1): 65–72. 2. Kalia LV, Lang AE. Parkinson’s disease. The Lancet 2015; 386(9996): 896–912. 3. Tsanas A, Little MA, McSharry PE, Ramig LO. Accurate telemonitoring of Parkinson’s disease progression by noninvasive speech tests. IEEE Transactions on Biomedical Engineering 2010; 57(4): 884–893. 4. Tsanas A, Little MA, McSharry PE, Ramig LO. Enhanced Classical Dysphonia measures and sparse Regression for Tele Monitoring of Parkinson’s disease Progression 2010; 594–597. 5. Goetz CG, Stebbins GT, Wolff D, DeLeeuw W, Bronte- Stewart H, Elble R, Hallett M, Nutt J, Ramig L, Sanger T, Wu AD, Kraus PH, Blasucci LM, Shamim EA, Sethi KD, Spielman J, Kubota K, Grove AS, Dishman E, Taylor CB. Testing objective measures of motor impairment in early Parkinson’s disease: Feasibility study of an at-home testing device Movement Disorder 2009; 24(4): 551-556. 6. Little MA, McSharry PE, Hunter EJ, Spielman J, Ramig LO. Suitability of dysphonia meas-urements for telemonitoring of Parkinson’s disease. IEEE Trans. Biomed. Eng. 2009; 56(4): 1015-1022. 7. Amato F, López A, Peña-Méndez EM, Vaňhara P, Hampl A, Havel J. Artificial neural networks in medical diagnosis. Journal of Applied Biomedicine 2013; 11(2): 47-58 8. Hofmann M, Klinkenberg R. RapidMiner: Data MiningUse Cases and Business Analytics Applications Chapman & Hall / CRC Data Mining and Knowledge Discovery Series, CRC Press, 2013 9. Jankovic, J. Parkinson’s disease: Clinical Features and Diagnosis. J Neurol Neurosurg Psychiatry 2008; 79(4): 368- 76.