banner

Automated detection and classification of neurodegenerative diseases using time-frequency based methods and artificial neural network classifier

J. Prasanna, S. Thomas George, M. S. P. Subathra, C. Prajitha

Abstract


Background: Neurodegenerative diseases (NDDs) such as Huntington’s disease (HD), amyotrophic lateral sclerosis (ALS), and Parkinson’s disease (PD) are reflected in fluctuations in gait dynamics and affect motor activity. The classification of gait data using machine learning techniques can help physicians diagnose a neural disorder early when clinical symptoms are not yet visible. Problems identified: Because NDD can cause gait abnormalities, screening for NDD using a gait signal is a viable option. Proposed work: This study aimed to develop an automated system for differentiating NDDs from a healthy control (HC) group. This study used frequency and time-frequency-based techniques, namely Fast Walsh Hadamard Transform (FWHT) and Fourier synchrosqueezed transform (FSST), to analyze the gait time series. Statistical and entropy measures are computed to capture the non-linear characteristics in the gait fluctuating patterns while performing extended gait analysis. Furthermore, we investigated the impact of the proposed technique with different feature rankings to select optimum features from the time series gait dynamics data. Research findings: The efficient features have been computed for the classification where an artificial neural network (ANN) classifier is utilized to effectively classify gait abnormalities, which attains better performance in each classification task. The classification performance of the proposed study is compared with the traditional approach, where it outperforms with the highest classification accuracy.


Keywords


neurodegenerative disease; feature extraction; artificial neural network; classification

Full Text:

PDF

References


1. Ren P, Tang S, Fang F, et al. Gait Rhythm Fluctuation Analysis for Neurodegenerative Diseases by Empirical Mode Decomposition. IEEE Transactions on Biomedical Engineering. 2017; 64(1): 52-60. doi: 10.1109/tbme.2016.2536438

2. Tysnes OB, Storstein A. Epidemiology of Parkinson’s disease. Journal of Neural Transmission. 2017; 124(8): 901-905. doi: 10.1007/s00702-017-1686-y

3. Chiò A, Logroscino G, Traynor BJ, et al. Global Epidemiology of Amyotrophic Lateral Sclerosis: A Systematic Review of the Published Literature. Neuroepidemiology. 2013; 41(2): 118-130. doi: 10.1159/000351153

4. Suescun J, Chandra S, Schiess MC. The Role of Neuroinflammation in Neurodegenerative Disorders. In: Translational inflammation. Academic Press; 2019. pp. 241-267.

5. Dharmadasa T, Matamala JM, Huynh W, et al.Motor neurone disease. In: Handbook of clinical neurology. pp. 345-357.

6. Golbe LI, Mark MH, Sage J. Parkinson’s disease handbook. American Parkinson Disease Association; 2009.

7. Reilmann R. Parkinsonism in Huntington’s disease. International Review of Neurobiology. 2019; 149: 299-306. doi: 10.1016/bs.irn.2019.10.006

8. Joshi D, Khajuria A, Joshi P. An automatic non-invasive method for Parkinson’s disease classification. Computer Methods and Programs in Biomedicine. 2017; 145: 135-145. doi: 10.1016/j.cmpb.2017.04.007

9. El-Alfy H, Mitsugami I, Yagi Y. Gait Recognition Based on Normal Distance Maps. IEEE Transactions on Cybernetics. 2018; 48(5): 1526-1539. doi: 10.1109/tcyb.2017.2705799

10. Xia Y, Gao Q, Ye Q. Classification of gait rhythm signals between patients with neuro-degenerative diseases and normal subjects: Experiments with statistical features and different classification models. Biomedical Signal Processing and Control. 2015; 18: 254-262. doi: 10.1016/j.bspc.2015.02.002

11. Zeng W, Wang C. Classification of neurodegenerative diseases using gait dynamics via deterministic learning. Information Sciences. 2015; 317: 246-258. doi: 10.1016/j.ins.2015.04.047

12. Poria S, Hazarika D, Majumder N, et al. Meld: A multimodal multi-party dataset for emotion recognition in conversations. arXiv:1810.02508. 2018.

13. Rovini E, Maremmani C, Cavallo F. How Wearable Sensors Can Support Parkinson’s Disease Diagnosis and Treatment: A Systematic Review. Frontiers in Neuroscience. 2017; 11. doi: 10.3389/fnins.2017.00555

14. Beyrami SMG, Ghaderyan P. A robust, cost-effective and non-invasive computer-aided method for diagnosis three types of neurodegenerative diseases with gait signal analysis. Measurement. 2020; 156: 107579. doi: 10.1016/j.measurement.2020.107579

15. Soubra R, Diab MO, Moslem B. Identification of Parkinson’s disease by using multichannel Vertical Ground Reaction Force signals. In: Proceedings of the 2016 International Conference on Bio-engineering for Smart Technologies (BioSMART). IEEE. pp. 1-4.

16. Wu Y, Chen P, Luo X, et al. Measuring signal fluctuations in gait rhythm time series of patients with Parkinson’s disease using entropy parameters. Biomedical Signal Processing and Control. 2017; 31: 265-271. doi: 10.1016/j.bspc.2016.08.022

17. Schalkamp AK, Peall KJ, Harrison NA, Sandor C. Wearable movement-tracking data identify Parkinson’s disease years before clinical diagnosis. Nature Medicine. 2023; 29(8): 2048-2056. doi.org/10.1038/s41591-023-02440-2

18. Liu AB, Lin CW. Multiscale Approximate Entropy for Gait Analysis in Patients with Neurodegenerative Diseases. Entropy. 2019; 21(10): 934. doi: 10.3390/e21100934

19. Yu J, Cao J, Liao WH, et al. Multivariate Multiscale Symbolic Entropy Analysis of Human Gait Signals. Entropy. 2017; 19(10): 557. doi: 10.3390/e19100557

20. Liao F, Wang J, He P. Multi-resolution entropy analysis of gait symmetry in neurological degenerative diseases and amyotrophic lateral sclerosis. Medical Engineering & Physics. 2008; 30(3): 299-310. doi: 10.1016/j.medengphy.2007.04.014

21. Mengarelli A, Tigrini A, Fioretti S, et al. Identification of Neurodegenerative Diseases from Gait Rhythm Through Time Domain and Time-Dependent Spectral Descriptors. IEEE Journal of Biomedical and Health Informatics. 2022; 26(12): 5974-5982. doi: 10.1109/jbhi.2022.3205058

22. Setiawan F, Lin CW. Identification of Neurodegenerative Diseases Based on Vertical Ground Reaction Force Classification Using Time–Frequency Spectrogram and Deep Learning Neural Network Features. Brain Sciences. 2021; 11(7): 902. doi: 10.3390/ brainsci11070902

23. Warule P, Mishra SP, Deb S. Time-frequency analysis of speech signal using Chirplet transform for automatic diagnosis of Parkinson’s disease. Biomedical Engineering Letters. 2023; 13(4): 613-623. doi: 10.1007/s13534-023-00283-x

24. Setiawan F, Liu AB, Lin CW. Development of Neuro-Degenerative Diseases’ Gait Classification Algorithm Using Convolutional Neural Network and Wavelet Coherence Spectrogram of Gait Synchronization. IEEE Access. 2022; 10: 38137-38153. doi: 10.1109/access.2022.3158961

25. Prasanna J, Subathra MSP, Mohammed MA, et al. Detection of Focal and Non-Focal Electroencephalogram Signals Using Fast Walsh-Hadamard Transform and Artificial Neural Network. Sensors. 2020; 20(17): 4952. doi: 10.3390/s20174952

26. Saka K, Aydemir O, Ozturk M. Classification of EEG Signals Recorded During Right/Left Hand Movement Imagery Using Fast Walsh Hadamard Transform Based Features. In: Proceedings of the 2016 39th International Conference on Telecommunications and Signal Processing (TSP); 27–29 June 2016; Vienna, Austria. pp. 413-416.

27. Sareen S, Sood SK, Gupta SK. A Cloud-Based Seizure Alert System for Epileptic Patients That Uses Higher-Order Statistics. Computing in Science & Engineering. 2016; 18(5): 56-67. doi: 10.1109/mcse.2016.82

28. Amira A, Bouridance A, Milligan P, et al. Novel FPGA implementations of Walsh-Hadamard transforms for signal processing. IEEE Proc. Image Signal Process. 2001; 148: 377-383.

29. Deveci TC, Cakir S. Cetin AE. Energy Efficient Hadamard Neural Networks. arXiv:1805.05421. 2018; 1-15.

30. Oberlin T, Meignen S, Perrier V. The Fourier-based synchrosqueezing transform. In: Proceedings of the 2014 IEEE international conference on acoustics, speech and signal processing (ICASSP). pp. 315-319.

31. Gundewar SK, Kane PV. Bearing fault diagnosis using time segmented Fourier synchrosqueezed transform images and convolution neural network. Measurement. 2022; 203: 111855. doi: 10.1016/j.measurement.2022.111855

32. Mamli S, Kalbkhani H. Gray-level co-occurrence matrix of Fourier synchro-squeezed transform for epileptic seizure detection. Biocybernetics and Biomedical Engineering. 2019; 39(1): 87-99. doi: 10.1016/j.bbe.2018.10.006

33. Li L, Cai H, Han H, et al. Adaptive short-time Fourier transform and synchrosqueezing transform for non-stationary signal separation. Signal Processing. 2020; 166: 107231. doi: 10.1016/j.sigpro.2019.07.024

34. Daliri MR. Automatic diagnosis of neuro-degenerative diseases using gait dynamics. Measurement. 2012; 45(7): 1729-1734. doi: 10.1016/j.measurement.2012.04.013

35. Acharya UR, Fujita H, Sudarshan VK, et al. Application of entropies for automated diagnosis of epilepsy using EEG signals: A review. Knowledge-Based Systems. 2015; 88: 85-96. doi: 10.1016/j.knosys.2015.08.004

36. Lemons DS, Lemons DS. A student’s guide to Entropy. Cambridge university press; 2013.

37. Renyi A. On measures of Entropy and information, Berkeley Symp. On Math. Statist. And Prob. 1961; 1: 547-561.

38. Cachin C. Smooth entropy and Renyi entropy, Advances in Cryptology Eurocrypt. Springer, Berlin Heidelberg; 2001. pp. 193-208.

39. Bezerianos A, Tong S, Thakor N. Time-Dependent Entropy Estimation of EEG Rhythm Changes Following Brain Ischemia. Annals of Biomedical Engineering. 2003; 31(2): 221-232. doi: 10.1114/1.1541013

40. Tong S, Bezerianos A, Malhotra A, et al. Parameterized entropy analysis of EEG following hypoxic-ischemic brain injury. Phys. Lett. A. 2003; 314(5-6): 354-361.

41. Geng X, Liu TY, Qin T, et al. Feature selection for ranking. In: Proceedings of the 30th annual international ACM SIGIR conference on research and development in information retrieval. pp. 407-414.

42. Shri TP, Sriraam N. Comparison of t-test ranking with PCA and SEPCOR feature selection for wake and stage 1 sleep pattern recognition in multichannel electroencephalograms. Biomedical Signal Processing and Control. 2017; 31: 499-512.

43. Ponti M, Kittler J, Riva M, et al. A decision cognizant Kullback–Leibler divergence. Pattern Recognition. 2017; 61: 470-478. doi: 10.1016/j.patcog.2016.08.018

44. Mookiah MRK, Chua CK, Min LC, et al. Computer Aided Diagnosis of Diabetic Retinopathy Using Multi-Resolution Analysis and Feature Ranking Frame Work. Journal of Medical Imaging and Health Informatics. 2013; 3(4): 598-606. doi: 10.1166/jmihi.2013.1210

45. Mookiah MRK, Acharya UR, Koh JEW, et al. Decision support system for age-related macular degeneration using discrete wavelet transform. Medical & Biological Engineering & Computing. 2014; 52(9): 781-796. doi: 10.1007/s11517-014-1180-8

46. Kumar R, Singh B, Shahani DT, et al. Recognition of Power-Quality Disturbances Using S-Transform-Based ANN Classifier and Rule-Based Decision Tree. IEEE Transactions on Industry Applications. 2015; 51(2): 1249-1258. doi: 10.1109/tia.2014.2356639

47. Rai HM, Trivedi A, Shukla S. ECG signal processing for abnormalities detection using multi-resolution wavelet transform and Artificial Neural Network classifier. Measurement. 2013; 46(9): 3238-3246. doi: 10.1016/j.measurement.2013.05.021

48. Ranganathan A. The levenberg-marquardt algorithm. Tutoral on LM algorithm. 2004; 11(1): 101-110.

49. Ghaderyan P, Beyrami SMG. Neurodegenerative diseases detection using distance metrics and sparse coding: A new perspective on gait symmetric features. Computers in Biology and Medicine. 2020; 120: 103736. doi: 10.1016/j.compbiomed.2020.103736

50. Yan Y, Omisore OM, Xue YC, et al. Classification of Neurodegenerative Diseases via Topological Motion Analysis—A Comparison Study for Multiple Gait Fluctuations. IEEE Access. 2020; 8: 96363-96377. doi: 10.1109/access.2020.2996667

51. Wu Y, Shi L. Analysis of altered gait cycle duration in amyotrophic lateral sclerosis based on nonparametric probability density function estimation. Medical Engineering & Physics. 2011; 33(3): 347-355. doi: 10.1016/j.medengphy.2010.10.023

52. Yan Y, Ivanov K, Mumini Omisore O, et al. Gait Rhythm Dynamics for Neuro-Degenerative Disease Classification via Persistence Landscape- Based Topological Representation. Sensors. 2020; 20(7): 2006. doi: 10.3390/s20072006

53. Tuncer T, Dogan S, Acharya UR. Automated detection of Parkinson’s disease using minimum average maximum tree and singular value decomposition method with vowels. Biocybernetics and Biomedical Engineering. 2020; 40(1): 211-220. doi: 10.1016/j.bbe.2019.05.006

54. Gupta K, Khajuria A, Chatterjee N, et al. Rule based classification of neurodegenerative diseases using data driven gait features. Health and Technology. 2018; 9(4): 547-560. doi: 10.1007/s12553-018-0274-y

55. Ren P, Zhao W, Zhao Z, et al. Analysis of Gait Rhythm Fluctuations for Neurodegenerative Diseases by Phase Synchronization and Conditional Entropy. IEEE Transactions on Neural Systems and Rehabilitation Engineering. 2016; 24(2): 291-299. doi: 10.1109/tnsre.2015.2477325

56. Marin-Lopez A, Martinez-Martinez F, Martínez-Cadena JA, et al. Multiscale SVD entropy for the analysis of gait dynamics. Biomedical Signal Processing and Control. 2024; 87: 105439. doi: 10.1016/j.bspc.2023.105439




DOI: https://doi.org/10.32629/jai.v7i5.1630

Refbacks

  • There are currently no refbacks.


Copyright (c) 2024 J. Prasanna, S. Thomas George, M. S. P. Subathra, C. Prajitha

License URL: https://creativecommons.org/licenses/by-nc/4.0/