Abstract

Parkinson Disease (PD) is one of the most common neurodegenerative disorders. It is a chronic disease that reduces dopamine fluid secretion in the brain causes the disorder of both motor and non-motor features. This paper intends to provide a comparative study on the performance measure of various popular machine learning algorithms on the PD dataset obtained from the University of California at Irvine (UCI) machine learning repository. It is observed that biasness prevails in the performance of the classifier towards the majority class due to the imbalanced class distribution of the PD dataset. Hence two most popular preprocessing techniques were employed to balance the dataset one being Synthetic Minority Oversampling TEchnique (SMOTE) and NEAR MISS (NM) an opposite to SMOTE. A SMOTE samples the minority class up to the level of majority class and NM downsamples and brings the majority class down to minority class. All the features in the dataset do not contain useful information about the dataset and also irrelevant data leads to false classification. So, feature reduction is done using information gain ratio and thus obtained reduced dataset is then subjected to classification. For classification five popular classifiers such as Random Forest (RF), Support Vector Machine (SVM), Naive Bayes (NB), K-Nearest Neighbor (KNN) and Decision Trees (DT) were used to compare the performance with the balanced and imbalanced dataset. The evaluation of the classifier’s performance is recorded in terms of accuracy, precision, recall, and F-Measure. The results of the conducted experiments show that balancing the majority and minority classes improve precision and recall and there is an increase in accuracy as well as precision. When compared with other classifiers, RF with SMOTE preprocessing was found to be prominent with the information gain greater than 0.18.

Keyword

Parkinsons disease, SMOTE, Near miss, NB, SVM, KNN, DT, RF.

Cite this article

Alice K, Natesan K, Dhanalakshmi B, Jaisharma K

Refference

[1][1]https://archive.ics.uci.edu/ml/datasets/Parkinsons. Accessed 20 December 2020.

[2][2]Ali L, Zhu C, Zhang Z, Liu Y. Automated detection of Parkinson’s disease based on multiple types of sustained phonations using linear discriminant analysis and genetically optimized neural network. IEEE Journal of Translational Engineering in Health and Medicine. 2019; 7:1-10.

[3][3]Senior AW, Evans R, Jumper J, Kirkpatrick J, Sifre L, Green T, et al. Improved protein structure prediction using potentials from deep learning. Nature. 2020; 577:706-10.

[4][4]Zhao R, Yan R, Chen Z, Mao K, Wang P, Gao RX. Deep learning and its applications to machine health monitoring. Mechanical Systems and Signal Processing. 2019; 115:213-37.

[5][5]Johri A, Tripathi A. Parkinson disease detection using deep neural networks. In international conference on contemporary computing 2019 (pp. 1-4). IEEE.

[6][6]Ramani RG, Sivagami G. Parkinson disease classification using data mining algorithms. International Journal of Computer Applications. 2011; 32(9):17-22.

[7][7]Khan SU. Classification of Parkinsons disease using data mining techniques. Parkinsons Dis Alzheimer Dis. 2015; 2(1):1-4.

[8][8]Ladha GG, Pippal RK. An efficient distance estimation and centroid selection based on k-means clustering for small and large dataset. International Journal of Advanced Technology and Engineering Exploration. 2020; 7(73):234-40.

[9][9]Sriram TV, Rao MV, Narayana GS, Kaladhar DS, Vital TP. Intelligent Parkinson disease prediction using machine learning algorithms. International Journal of Innovative Technology and Exploring Engineering. 2013; 3(3):212-5.

[10][10]Chahar R, Kaur D. A systematic review of the machine learning algorithms for the computational analysis in different domains. International Journal of Advanced Technology and Engineering Exploration. 2020; 7(71):147-64.

[11][11]Chahar R. Computational decision support system in healthcare: a review and analysis. International Journal of Advanced Technology and Engineering Exploration. 2021; 8(75):199-220.

[12][12]Srinivasan SM, Martin M, Tripathi A. ANN based data mining analysis of the Parkinson’s disease. International Journal of Computer Applications. 2017; 168(1):1-7.

[13][13]Mamat RC, Ramli A, Kasa A, Razali SF, Omar MB. Artificial neural networks in slope of road embankment stability applications: a review and future perspectives. International Journal of Advanced Technology and Engineering Exploration. 2021; 8(75):304-19.

[14][14]Khawaja AW, Kamari NA, Musirin I, Zulkifley MA, Sujod MZ. Design of optimal multi-objective-based facts component with proportional-integral-derivative controller using swarm optimization approach. International Journal of Advanced Technology and Engineering Exploration. 2021; 8(75):391-404.

[15][15]Salim NA, Jasni J, Mohamad H, Yasin ZM. Transformer health index prediction using feedforward neural network according to scoring and ranking method. International Journal of Advanced Technology and Engineering Exploration. 2021; 8(75):292-303.

[16][16]Rosdan RM, Awang WS, Bakar WA. Comparison of affinity degree classification with four different classifiers in several data sets. International Journal of Advanced Technology and Engineering Exploration. 2021; 8(75):247-57.

[17][17]Saikia D, Boruah PK, Sarma U. A computational model for optimum process parameters based on factory data and overall liquor rating of black tea. International Journal of Advanced Technology and Engineering Exploration. 2020; 7(73):220-33.

[18][18]Braga D, Madureira AM, Coelho L, Ajith R. Automatic detection of Parkinson’s disease based on acoustic analysis of speech. Engineering Applications of Artificial Intelligence. 2019; 77:148-58.

[19][19]Gil D, Manuel DJ. Diagnosing parkinson by using artificial neural networks and support vector machines. Global Journal of Computer Science and Technology. 2009; 9(4):63-71.

[20][20]Khemphila A, Boonjing V. Parkinsons disease classification using neural network and feature selection. International Journal of Mathematical and Computational Sciences. 2012; 6(4):377-80.

[21][21]Vásquez-Correa JC, Arias-Vergara T, Orozco-Arroyave JR, Eskofier B, Klucken J, Nöth E. Multimodal assessment of Parkinsons disease: a deep learning approach. IEEE Journal of Biomedical and Health Informatics. 2018; 23(4):1618-30.

[22][22]Ali L, Zhu C, Zhou M, Liu Y. Early diagnosis of Parkinson’s disease from multiple voice recordings by simultaneous sample and feature selection. Expert Systems with Applications. 2019; 137:22-8.

[23][23]Wang W, Lee J, Harrou F, Sun Y. Early detection of Parkinsons disease using deep learning and machine learning. IEEE Access. 2020; 8:147635-46.

[24][24]Lahmiri S, Dawson DA, Shmuel A. Performance of machine learning methods in diagnosing Parkinsons disease based on dysphonia measures. Biomedical Engineering Letters. 2018; 8(1):29-39.

[25][25]Illner V, Sovka P, Rusz J. Validation of freely-available pitch detection algorithms across various noise levels in assessing speech captured by smartphone in Parkinson’s disease. Biomedical Signal Processing and Control. 2020.

[26][26]Ali L, Zhu C, Golilarz NA, Javeed A, Zhou M, Liu Y. Reliable Parkinson’s disease detection by analyzing handwritten drawings: construction of an unbiased cascaded learning system based on feature selection and adaptive boosting model. IEEE Access. 2019; 7:116480-9.

[27][27]Lahmiri S, Shmuel A. Detection of Parkinsons disease based on voice patterns ranking and optimized support vector machine. Biomedical Signal Processing and Control. 2019; 49:427-33.

[28][28]Almeida JS, Rebouças FPP, Carneiro T, Wei W, Damaševičius R, Maskeliūnas R, et al. Detecting Parkinson’s disease with sustained phonation and speech signals using machine learning techniques. Pattern Recognition Letters. 2019; 125:55-62.

[29][29]Tracy JM, Özkanca Y, Atkins DC, Ghomi RH. Investigating voice as a biomarker: deep phenotyping methods for early detection of Parkinsons disease. Journal of Biomedical Informatics. 2020; 104:1-10.

[30][30]Jain D, Mishra AK, Das SK. Machine learning based automatic prediction of Parkinson’s disease using speech features. In proceedings of international conference on artificial intelligence and applications 2021 (pp. 351-62). Springer, Singapore.

[31][31]Gunduz H. Deep learning-based Parkinson s disease classification using vocal feature sets. IEEE Access. 2019; 7:115540-51.

[32][32]Aich S, Kim HC, Hui KL, Al-Absi AA, Sain M. A supervised machine learning approach using different feature selection techniques on voice datasets for prediction of Parkinson’s disease. In international conference on advanced communication technology 2019 (pp. 1116-21). IEEE.

[33][33]Ali L, Wajahat I, Golilarz NA, Keshtkar F, Bukhari SA. LDA–GA–SVM: improved hepatocellular carcinoma prediction through dimensionality reduction and genetically optimized support vector machine. Neural Computing and Applications. 2021; 33(7):2783-92.

[34][34]Bernardo LS, Quezada A, Munoz R, Maia FM, Pereira CR, Wu W, et al. Handwritten pattern recognition for early Parkinson’s disease diagnosis. Pattern Recognition Letters. 2019; 125:78-84.

[35][35]Peng J, Guan J, Shang X. Predicting Parkinsons disease genes based on node2vec and autoencoder. Frontiers in Genetics. 2019; 10:1-6.

[36][36]Wan KR, Maszczyk T, See AA, Dauwels J, King NK. A review on microelectrode recording selection of features for machine learning in deep brain stimulation surgery for Parkinson’s disease. Clinical Neurophysiology. 2019; 130(1):145-54.

[37][37]Rastegari E, Azizian S, Ali H. Machine learning and similarity network approaches to support automatic classification of Parkinson’s diseases using accelerometer-based gait analysis. In proceedings of the Hawaii international conference on system sciences 2019(pp.4231-42).

[38][38]Veeraragavan S, Gopalai AA, Gouwanda D, Ahmad SA. Parkinson’s disease diagnosis and severity assessment using ground reaction forces and neural networks. Frontiers in Physiology. 2020; 11:1-11.

[39][39]Moon S, Song HJ, Sharma VD, Lyons KE, Pahwa R, Akinwuntan AE, et al. Classification of Parkinson’s disease and essential tremor based on balance and gait characteristics from wearable motion sensors via machine learning techniques: a data-driven approach. Journal of NeuroEngineering and Rehabilitation. 2020; 17:1-8.

[40][40]Olivares R, Munoz R, Soto R, Crawford B, Cárdenas D, Ponce A, et al. An optimized brain-based algorithm for classifying Parkinson’s disease. Applied Sciences. 2020; 10(5):1-16.

[41][41]Ricciardi C, Amboni M, De Santis C, Ricciardelli G, Improta G, Iuppariello L, et al. Classifying different stages of Parkinson’s disease through random forests. In mediterranean conference on medical and biological engineering and computing 2019 (pp. 1155-62). Springer, Cham.

[42][42]Rehman RZ, Del Din S, Guan Y, Yarnall AJ, Shi JQ, Rochester L. Selecting clinically relevant gait characteristics for classification of early Parkinson’s disease: a comprehensive machine learning approach. Scientific Reports. 2019; 9:1-12.

[43][43]Ansari HF, Namdeo V. An efficient SKNN based approach for heart disease classification. International Journal of Advanced Technology and Engineering Exploration. 2019; 6(53):101-6.

[44][44]Granik M, Mesyura V. Fake news detection using naive bayes classifier. In first Ukraine conference on electrical and computer engineering 2017 (pp. 900-3). IEEE.

[45][45]Bužić D, Dobša J. Lyrics classification using naive bayes. In international convention on information and communication technology, electronics and microelectronics 2018 (pp. 1011-5). IEEE.

[46][46]Copur M, Ozyildirim BM, Ibrikci T. Image classification of aerial images using CNN-SVM. In innovations in intelligent systems and applications conference 2018 (pp. 1-6). IEEE.

[47][47]Vera JE, Martinez SM, Pérez AT, Avendano J. Classification of gerbera type flowers based in decision tree rules. In symposium on image, signal processing and artificial vision 2019 (pp. 1-4). IEEE.

[48][48]Paul A, Mukherjee DP, Das P, Gangopadhyay A, Chintha AR, Kundu S. Improved random forest for classification. IEEE Transactions on Image Processing. 2018; 27(8):4012-24.

[49][49]ONeill E, Yssel JD, McNamara C, Harkin A. Pharmacological targeting of β2‐adrenoceptors is neuroprotective in the LPS inflammatory rat model of Parkinsons disease. British Journal of Pharmacology. 2020; 177(2):282-97.

[50][50]Carrilho PE, Rodrigues MA, Oliveira BC, Silva EB, Silva TA, Schran LD, et al. Profile of caregivers of Parkinson’s disease patients and burden measured by zarit scale analysis of potential burden-generating factors and their correlation with disease severity. Dementia & Neuropsychologia. 2018; 12(3):299-305.