A deep learning approach for prediction of Parkinson’s disease progression

다국어 초록 (Multilingual Abstract)

This paper proposes a deep neural network (DNN) model using the reduced input feature space of Parkinson’s telemonitoringdataset to predict Parkinson’s disease (PD) progression. PD is a chronic and progressive nervous system disorder that aff ectsbody movement. PD is assessed by using the unifi ed Parkinson’s disease rating scale (UPDRS). In this paper, fi rstly, principalcomponent analysis (PCA) is employed to the featured dataset to address the multicollinearity problems in the dataset andto reduce the dimension of input feature space. Then, the reduced input feature space is fed into the proposed DNN modelwith a tuned parameter norm penalty (L2) and analyses the prediction performance of it in PD progression by predictingMotor and Total-UPDRS score. The model’s performance is evaluated by conducting several experiments and the result iscompared with the result of previously developed methods on the same dataset. The model’s prediction accuracy is measuredby fi tness parameters, mean absolute error (MAE), root mean squared error (RMSE), and coeffi cient of determination (R 2 ).
The MAE, RMSE, and R 2 values are 0.926, 1.422, and 0.970 respectively for motor-UPDRS. These values are 1.334, 2.221,and 0.956 respectively for Total-UPDRS. Both the Motor and Total-UPDRS score is better predicted by the proposed method.
This paper shows the usefulness and effi cacy of the proposed method for predicting the UPDRS score in PD progression.

참고문헌 (Reference)

1 Kallenberg M, "Unsupervised deep learning applied to breast density segmentation and mammographic risk scoring" 35 (35): 1322-1331, 2016

2 Rosenbaum RB, "Understanding Parkinson’s disease: a personal and professional view" Greenwood Publishing Group 2006

3 Rascol O, "Treatment interventions for Parkinson’s disease : an evidence based assessment" 359 (359): 1589-1598, 2002

4 Bottou L, "The tradeoffs of large scale learning" 20 : 161-168, 2008

5 Xiong HY, "The human splicing code reveals new insights into the genetic determinants of disease" 347 (347): 1254806-, 2015

6 Campbell N, "The geometry of canonical variate analysis" 30 (30): 268-280, 1981

7 Brooks DJ, "The early diagnosis of Parkinson’s disease" 44 (44): S10-S18, 1998

8 Shulman LM, "The clinically important difference on the unified Parkinson’s disease rating scale" 67 (67): 64-70, 2010

9 Hely MA, "The Sydney multicentre study of Parkinson’s disease : progression and mortality at 10 years" 67 (67): 300-307, 1999

10 Ramaker C, "Systematic evaluation of rating scales for impairment and disability in Parkinson’s disease" 17 (17): 867-876, 2002

11 Mikolov T, "Strategies for training large scale neural network language models" IEEE 2011

12 Bühlmann P, "Statistics for high-dimensional data:methods, theory and applications" Springer 2011

13 Xu K, "Show, attend and tell: neural image caption generation with visual attention" 2015

14 Ozcift A, "SVM feature selection based rotation forest ensemble classifiers to improve computer-aided diagnosis of Parkinson disease" 36 (36): 2141-2147, 2012

15 Bhattacharya I, "SVM classification to distinguish Parkinson disease patients" ACM 2010

16 Belagiannis V, "Robust optimization for deep regression" 2015

17 Hu T, "Rainfall–runoff modeling using principal component analysis and neural network" 38 (38): 235-248, 2007

18 Marras C, "Prevalence of Parkinson’s disease across North America" 4 (4): 21-, 2018

19 Peterek T, "Performance evaluation of Random Forest regression model in tracking Parkinson’s disease progress" IEEE 2013

20 National Institute of Neurological Disorders and Stroke, "Parkinson’s disease: hope through research" National Institute of Neurological Disorders and Stroke 1994

21 Babu GS, "Parkinson’s disease prediction using gene expression—a projection based learning meta-cognitive neural classifier approach" 40 (40): 1519-1529, 2013

22 Clinic M., "Parkinson’s disease"

23 Buza K, "ParkinsoNET: estimation of UPDRS score using hubness-aware feedforward neural networks" 30 (30): 541-555, 2016

24 Bigiarini MZ, "Package “hydroGOF”" R-package

25 Tieleman T, "Lecture 6.5-rmsprop: divide the gradient by a running average of its recent magnitude" 4 (4): 26-31, 2012

26 Farabet C, "Learning hierarchical features for scene labeling" 35 (35): 1915-1929, 2013

27 Liu M, "Landmark-based deep multiinstance learning for brain disease diagnosis" 43 : 157-168, 2018

28 Jolliffe I., "International encyclopedia of statistical science" Springer 1094-1096, 2011

29 Jain S, "Improving accuracy in noninvasive telemonitoring of progression of Parkinson’s disease using two-step predictive model" IEEE 2016

30 Zhao Y-P, "Householder transformation based sparse least squares support vector regression" 161 : 243-253, 2015

31 Szegedy C, "Going deeper with convolutions" 2015

32 Haaxma CA, "Gender differences in Parkinson’s disease" 78 (78): 819-824, 2007

33 Al-Fatlawi AH, "Efficient diagnosis system for Parkinson’s disease using deep belief network" IEEE 2016

34 Diamond S, "Effect of age at onset on progression and mortality in Parkinson’s disease" 39 (39): 1187-1190, 1989

35 Gregor K, "Draw:a recurrent neural network for image generation"

36 Froelich W, "Diagnosis of Parkinson’s disease using speech samples and threshold-based classification" 5 (5): 1358-1363, 2015

37 Hinton G, "Deep neural networks for acoustic modeling in speech recognition : the shared views of four research groups" 29 (29): 82-97, 2012

38 Ma J, "Deep neural nets as a method for quantitative structure–activity relationships" 55 (55): 263-274, 2015

39 Leung MK, "Deep learning of the tissue-regulated splicing code" 30 (30): i121-i129, 2014

40 Ravı D, "Deep learning for health informatics" 21 (21): 4-21, 2017

41 Goodfellow I, "Deep learning" MIT Press 2016

42 LeCun Y, "Deep learning" 521 (521): 436-, 2015

43 Sainath TN, "Deep convolutional neural networks for LVCSR" IEEE 2013

44 Acharya UR, "Deep convolutional neural network for the automated detection and diagnosis of seizure using EEG signals" 100 : 270-278, 2018

45 Karpathy A, "Cs231n convolutional neural networks for visual recognition" 1 : 1-, 2016

46 Tajbakhsh N, "Convolutional neural networks for medical image analysis : full training or fine tuning" 35 (35): 1299-1312, 2016

47 Shahid AH, "Computational intelligence techniques for medical diagnosis and prognosis : problems and current developments" 10 (10): 345-, 2019

48 Leon S, "Comprehensive pharmacy review" West Camden Street 2004

49 Polat K, "Classification of Parkinson’s disease using feature weighting method on the basis of fuzzy C-means clustering" 43 (43): 597-609, 2012

50 Yu L, "Automated melanoma recognition in dermoscopy images via very deep residual networks" 36 (36): 994-1004, 2017

51 Acharya UR, "Automated identification of shockable and non-shockable life-threatening ventricular arrhythmias using convolutional neural network" 79 : 952-959, 2018

52 Acharya UR, "Automated detection of coronary artery disease using different durations of ECG segments with convolutional neural network" 132 : 62-71, 2017

53 Avci D, "An expert diagnosis system for parkinson disease based on genetic algorithm-wavelet kernel-extreme learning machine" 2016 : 5264743-, 2016

54 Chen H-L, "An efficient diagnosis system for detection of Parkinson’s disease using fuzzy k-nearest neighbor approach" 40 (40): 263-271, 2013

55 Krizhevsky A, "Advances in neural information processing systems" Curran Associates Inc 2012

56 Guo P-F, "Advances in detecting Parkinson’s disease" Springer 2010

57 Duchi J, "Adaptive subgradient methods for online learning and stochastic optimization" 12 : 2121-2159, 2011

58 Tsanas A, "Accurate telemonitoring of Parkinson’s disease progression by noninvasive speech tests" 57 (57): 884-893, 2010

59 Tsanas A, "Accurate telemonitoring of Parkinson’s disease progression by noninvasive speech tests" 57 (57): 884-893, 2009

60 Zeiler MD, "ADADELTA: an adaptive learning rate method"

61 Åström F, "A parallel neural network approach to prediction of Parkinson’s disease" 38 (38): 12470-12474, 2011

62 Hariharan M, "A new hybrid intelligent system for accurate detection of Parkinson’s disease" 113 (113): 904-913, 2014

63 Behroozi M, "A multiple-classifier framework for Parkinson’s disease detection based on various vocal tests" 2016

64 Kingma DP, "A method for stochastic optimization"

65 Nilashi M, "A hybrid intelligent system for the prediction of Parkinson’s disease progression using machine learning techniques" 38 (38): 1-15, 2018

66 Li D-C, "A fuzzy-based data transformation for feature extraction to increase classification performance with small medical data sets" 52 (52): 45-52, 2011

67 Eskidere Ö, "A comparison of regression methods for remote tracking of Parkinson’s disease progression" 39 (39): 5523-5528, 2012

68 Das R, "A comparison of multiple classification methods for diagnosis of Parkinson disease" 37 (37): 1568-1572, 2010