Logo PTI
Polish Information Processing Society
Logo FedCSIS

Annals of Computer Science and Information Systems, Volume 21

Proceedings of the 2020 Federated Conference on Computer Science and Information Systems

BiLSTM with Data Augmentation using Interpolation Methods to Improve Early Detection of Parkinson Disease

, , ,

DOI: http://dx.doi.org/10.15439/2020F188

Citation: Proceedings of the 2020 Federated Conference on Computer Science and Information Systems, M. Ganzha, L. Maciaszek, M. Paprzycki (eds). ACSIS, Vol. 21, pages 371–380 ()

Full text

Abstract. The lack of dopamine in the human brain is the cause of Parkinson disease (PD) which is a degenerative disorder common globally to older citizens. However, late detection of this disease before the first clinical diagnosis has led to increased mortality rate. Research effort towards the early detection of PD has encountered challenges such as: small dataset size, class imbalance, overfitting, high false detection rate, model complexity, etc. This paper aims to improve early detection of PD using machine learning through data augmentation for very small datasets. We propose using Spline interpolation and Piecewise Cubic Hermite Interpolating Polynomial (Pchip) interpolation methods to generate synthetic data instances. We further investigate on reducing dimensionality of features for effective and real-time classification while considering computational complexity of implementation on real-life mobile phones. For classification we use Bidirectional LSTM (BiLSTM) deep learning network and compare the results with traditional machine learning algorithms like Support Vector Machine (SVM), Decision Tree, Logistic regression, KNN and Ensemble bagged tree. For experimental validation we use the Oxford Parkinson disease dataset with 195 data samples, which we have augmented with 571 synthetic data samples. The results for BiLSTM shows that even with a holdout of 90\%, the model was still able to effectively recognize PD with an average accuracy for ten rounds experiment using 22 features as 82.86\%, 97.1\%, and 96.37\% for original, augmented (Spline) and augmented (Pchip) datasets, respectively. Our results show that proposed data augmentation schemes have significantly (p < 0.001) improved the accuracy of PD recognition on a small dataset using both classical machine learning models and BiLSTM.

References

  1. Agarwal, A., Chandrayan, S. and Sahu, S.S., 2016. Prediction of Parkinson's disease using speech signal with Extreme Learning Machine. In 2016 International Conference on Electrical, Electronics, and Optimization Techniques (ICEEOT) (pp. 3776-3779). IEEE. http://dx.doi.org/ 10.1109/ICEEOT.2016.7755419
  2. Fayyazifar, N. and Samadiani, N., 2017. Parkinson's disease detection using ensemble techniques and genetic algorithm. In 2017 Artificial Intelligence and Signal Processing Conference (AISP) (pp. 162-165). IEEE. http://dx.doi.org/10.1109/AISP.2017.8324074
  3. Dorsey, E.R., Elbaz, A., Nichols, E., Abd-Allah, F., Abdelalim, A., Adsuar, J.C., Ansha, M.G., Brayne, C., Choi, J.Y.J., Collado-Mateo, D. and Dahodwala, N., 2018. Global, regional, and national burden of Parkinson's disease, 1990–2016: a systematic analysis for the Global Burden of Disease Study 2016. The Lancet Neurology, 17(11), 939-953. http://dx.doi.org/10.1016/S1474-4422(18)30295-3
  4. Saikia, A., Majhi, V., Hussain, M. and Paul, S., 2019. A Systematic review on Application based Parkinson’s disease Detection Systems. International Journal on Emerging Technologies 10(3): 166-173.
  5. Aich, S., Younga, K., Hui, K.L., Al-Absi, A.A. and Sain, M., 2018, February. A nonlinear decision tree based classification approach to predict the Parkinson's disease using different feature sets of voice data. In 2018 20th International Conference on Advanced Communication Technology (ICACT) (pp. 638-642). IEEE. http://dx.doi.org/10.23919/ICACT.2018.8323864
  6. Chan, M.Y., Chu, S.Y., Ahmad, K. and Ibrahim, N.M., 2019. Voice therapy for Parkinson’s disease via smartphone videoconference in Malaysia: A preliminary study. Journal of telemedicine and telecare, http://dx.doi.org/10.1177/1357633X19870913
  7. Despotovic, V., Skovranek, T. and Schommer, C., 2020. Speech Based Estimation of Parkinson’s Disease Using Gaussian Processes and Automatic Relevance Determination. Neurocomputing, , 401, 173–181. http://dx.doi.org/10.1016/j.neucom.2020.03.058
  8. Gil-Martín, M., Montero, J.M. and San-Segundo, R., 2019. Parkinson’s disease detection from drawing movements using convolutional neural networks. Electronics, 8(8), p.907. http://dx.doi.org/10.3390/electronics8080907
  9. Lavner, Y., Khatib, S., Artoul, F. and Vaya, J., 2014, December. An algorithm for processing and analysis of Gas Chromatography-Mass Spectrometry (GC-MS) signals for early detection of Parkinson's disease. In 2014 IEEE 28th Convention of Electrical & Electronics Engineers in Israel (IEEEI) (pp. 1-5). IEEE. http://dx.doi.org/ 10.1109/EEEI.2014.7005772
  10. Liu, H.J., Li, X.Y., Chen, H., Yu, H.L., Tao, Q.Q. and Wu, Z.Y., 2020. Identification of susceptibility loci for cognitive impairment in a cohort of Han Chinese patients with Parkinson’s disease. Neuroscience Letters, 135034. http://dx.doi.org/doi:10.1016/j.neulet.2020.135034
  11. Saikia, A., Hussain, M., Barua, A.R. and Paul, S., 2019. EEG-EMG correlation for parkinson’s disease. International Journal of Engineering and Advanced Technology, 8(6), pp.1179-85. http://dx.doi.org/10.35940/ijeat.F8360.088619
  12. Rumman, M., Tasneem, A.N., Farzana, S., Pavel, M.I. and Alam, M.A., 2018. Early detection of Parkinson’s disease using image processing and artificial neural network. In 2018 Joint 7th International Conference on Informatics, Electronics & Vision (ICIEV) and 2018 2nd International Conference on Imaging, Vision & Pattern Recognition (icIVPR) (pp. 256-261). IEEE. http://dx.doi.org/10.1109/ICIEV.2018.8641081
  13. Almeida, J.S., Rebouças Filho, P.P., Carneiro, T., Wei, W., Damaševičius, R., Maskeliūnas, R. and de Albuquerque, V.H.C., 2019. Detecting Parkinson’s disease with sustained phonation and speech signals using machine learning techniques. Pattern Recognition Letters, 125, pp. 55-62. http://dx.doi.org/10.1016/j.patrec.2019.04.005
  14. Lauraitis, A., Maskeliūnas, R., Damaševičius, R., Połap, D. and Woźniak, M., 2019. A smartphone application for automated decision support in cognitive task based evaluation of central nervous system motor disorders. IEEE journal of biomedical and health informatics, 23(5), pp. 1865-1876. http://dx.doi.org/10.1109/JBHI.2019.2891729
  15. Gatsios, D., Antonini, A., Gentile, G., Marcante, A., Pellicano, C., Macchiusi, L., Assogna, F., Spalletta, G., Gage, H., Touray, M. and Timotijevic, L., 2020. Mhealth for remote monitoring and management of Parkinson’s disease: determinants of compliance and validation of a tremor evaluation method. JMIR mHealth and uHealth.
  16. Linares-Del Rey, M., Vela-Desojo, L. and Cano-de la Cuerda, R., 2019. Mobile phone applications in Parkinson's disease: a systematic review. Neurología (English Edition), 34(1), pp. 38-54. http://dx.doi.org/10.1016/j.nrleng.2018.12.002
  17. Zhang, H., Song, C., Rathore, A.S., Huang, M., Zhang, Y. and Xu, W., 2020. mHealth Technologies towards Parkinson's Disease Detection and Monitoring in Daily Life: A Comprehensive Review. IEEE Reviews in Biomedical Engineering. http://dx.doi.org/10.1109/RBME.2020.2991813
  18. Zhang, H., Deng, K., Li, H., Albin, R.L. and Guan, Y., 2020. Deep Learning Identifies Digital Biomarkers for Self-Reported Parkinson's Disease. Patterns, 100042. http://dx.doi.org/10.1016/j.patter.2020.100042
  19. Nilashi, M., Ahmadi, H., Sheikhtaheri, A., Naemi, R., Alotaibi, R., Alarood, A.A., Munshi, A., Rashid, T.A. and Zhao, J., 2020. Remote Tracking of Parkinson's Disease Progression Using Ensembles of Deep Belief Network and Self-Organizing Map. Expert Systems with Applications, 113562. http://dx.doi.org/10.1016/j.eswa.2020.113562
  20. Lauraitis, A., Maskeliūnas, R., Damaševičius, R. and Krilavičius, T., 2020. Detection of Speech Impairments Using Cepstrum, Auditory Spectrogram and Wavelet Time Scattering Domain Features. IEEE Access, 8, 96162 – 96172. http://dx.doi.org/10.1109/ACCESS.2020.2995737
  21. Lauraitis, A., Maskeliūnas, R., Damaševičius, R. and Krilavičius, T., 2020. A Mobile Application for Smart Computer-Aided Self-Administered Testing of Cognition, Speech, and Motor Impairment. Sensors, 20, 3236. http://dx.doi.org/10.3390/s20113236
  22. Taleb, C., Likforman-Sulem, L. and Mokbel, C., 2019. Improving Deep Learning Parkinson’s Disease Detection Through Data Augmentation Training. In Mediterranean Conference on Pattern Recognition and Artificial Intelligence (pp. 79-93). Springer, Cham. Doi:
  23. Połap, D., Woźniak, M., Damaševičius, R. and Maskeliūnas, R., 2019. Bio-inspired voice evaluation mechanism. Applied Soft Computing, 80, pp. 342-357. http://dx.doi.org/10.1016/j.asoc.2019.04.006
  24. Jeancolas, L., Benali, H., Benkelfat, B.E., Mangone, G., Corvol, J.C., Vidailhet, M., Lehericy, S. and Petrovska-Delacrétaz, D., 2017. Automatic detection of early stages of Parkinson's disease through acoustic voice analysis with mel-frequency cepstral coefficients. In 2017 International Conference on Advanced Technologies for Signal and Image Processing (ATSIP) (pp. 1-6). IEEE. http://dx.doi.org/10.1109/ATSIP.2017.8075567
  25. Rueda, A. and Krishnan, S., 2017. Feature analysis of dysphonia speech for monitoring Parkinson's disease. In 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) (pp. 2308-2311). IEEE. http://dx.doi.org/10.1109/EMBC.2017.8037317
  26. Vikas, and Sharma, R.K. 2014, May. Early detection of Parkinson's disease through Voice. In 2014 International Conference on Advances in Engineering and Technology (ICAET) (pp. 1-5). IEEE. http://dx.doi.org/10.1109/ICAET.2014.7105237
  27. Wroge, T.J., Özkanca, Y., Demiroglu, C., Si, D., Atkins, D.C. and Ghomi, R.H., 2018, December. Parkinson’s disease diagnosis using machine learning and voice. In 2018 IEEE Signal Processing in Medicine and Biology Symposium (SPMB) (pp. 1-7). IEEE. http://dx.doi.org/10.1109/SPMB.2018.8615607
  28. Eskıdere, Ö., Karatutlu, A. and Ünal, C., 2015, September. Detection of Parkinson's disease from vocal features using random subspace classifier ensemble. In 2015 Twelve International Conference on Electronics Computer and Computation (ICECCO) (pp. 1-4). IEEE. http://dx.doi.org/10.1109/ICECCO.2015.7416886
  29. Polat, K., 2019. A Hybrid Approach to Parkinson Disease Classification Using Speech Signal: The Combination of SMOTE and Random Forests. In 2019 Scientific Meeting on Electrical-Electronics & Biomedical Engineering and Computer Science (EBBT) (pp. 1-3). IEEE. http://dx.doi.org/10.1109/EBBT.2019.8741725
  30. Olanrewaju, R.F., Sahari, N.S., Musa, A.A. and Hakiem, N., 2014. Application of neural networks in early detection and diagnosis of Parkinson's disease. In 2014 International Conference on Cyber and IT Service Management (CITSM) (pp. 78-82). IEEE. http://dx.doi.org/ 10.1109/CITSM.2014.7042180
  31. Um, T.T., Pfister, F.M., Pichler, D., Endo, S., Lang, M., Hirche, S., Fietzek, U. and Kulić, D., 2017. Data augmentation of wearable sensor data for parkinson’s disease monitoring using convolutional neural networks. In Proceedings of the 19th ACM International Conference on Multimodal Interaction (pp. 216-220). http://dx.doi.org/10.1145/3136755.3136817
  32. Bourdillon, A., Sawhney, K., Mehra, R., O’Grady, P. and Liu, T., Extracting kinetic features from wearable tech for clinical symptoms of Parkinsons Disease.
  33. Vaiciukynas, E., Gelzinis, A., Verikas, A. and Bacauskiene, M., 2017. Parkinson’s disease detection from speech using convolutional neural networks. In International Conference on Smart Objects and Technologies for Social Good (pp. 206-215). Springer, Cham.
  34. Bayestehtashk, A., Asgari, M., Shafran, I. and McNames, J., 2015. Fully automated assessment of the severity of Parkinson's disease from speech. Computer speech & language, 29(1), pp.172-185. http://dx.doi.org/10.1016/j.csl.2013.12.001
  35. Pan Q., Li, X., and Fang L. 2020. Data Augmentation of Deep learning-based on ECG Analysis. Feature Engineering and Computational Intelligence in ECG Monitoring, 91-111. Springer Nature Singapore Pte. http://dx.doi.org/10.1007/978-981-15-3824-7_6
  36. Kutlugün, M.A., Sirin, Y. and Karakaya, M., 2019. The Effects of Augmented Training Dataset on Performance of Convolutional Neural Networks in Face Recognition System. In 2019 Federated Conference on Computer Science and Information Systems (FedCSIS) (pp. 929-932). IEEE. http://dx.doi.org/10.15439/2019F181
  37. Lee, J.W., Nam, D.W., Yoo, W.Y., Kim, Y., Jeong, M. and Kim, C., 2018. Soccer object motion recognition based on 3D convolutional neural networks. In FedCSIS (Communication Papers) (pp. 129-134). http://dx.doi.org/10.15439/2018F48
  38. Li, Z., Yao, H., and Ma, F. (2020). Learning with Small Data. Proceedings of the 13th International Conference on Web Search and Data Mining, WSDM ’20. http://dx.doi.org/10.1145/3336191.3371874
  39. Little, M. A., McSharry, P. E., Hunter, E. J., Spielman, J., and Ramig, L. O. 2009. Suitability of dysphonia measurements for telemonitoring of Parkinson's disease. IEEE Transactions on bio-medical engineering, 56(4), 1015. http://dx.doi.org/10.1038/npre.2008.2298.1
  40. Levy, D., 2010. Introduction to numerical analysis. Department of Mathematics and Center for Scientific Computation and Mathematical Modeling (CSCAMM) University of Maryland, pp.2-2.
  41. Revett, Kenneth, Florin Gorunescu, and Abdel-Badeeh Mohamed Salem. "Feature selection in Parkinson's disease: A rough sets approach." In 2009 International Multiconference on Computer Science and Information Technology, pp. 425-428. IEEE, 2009. http://dx.doi.org/10.1109/IMCSIT.2009.5352688
  42. Cai, Z., Gu, J. and Chen, H.L., 2017. A new hybrid intelligent framework for predicting Parkinson’s disease. IEEE Access, 5, pp.17188-17200. http://dx.doi.org/10.1109/ACCESS.2017.2741521.
  43. Wang, X., 2014. Data Mining Analysis of the Parkinson's Disease. Masters thesis Submitted to the College of Arts and Sciences, Georgia State University.
  44. Bhattacharya, I. and Bhatia, M.P.S., 2010. SVM classification to distinguish Parkinson disease patients. In Proceedings of the 1st Amrita ACM-W Celebration on Women in Computing in India (pp. 1-6). http://dx.doi.org/10.1145/1858378.1858392
  45. Chen, H.L., Wang, G., Ma, C., Cai, Z.N., Liu, W.B. and Wang, S.J., 2016. An efficient hybrid kernel extreme learning machine approach for early diagnosis of Parkinson׳ s disease. Neurocomputing, 184, pp.131-144. http://dx.doi.org/10.1016/j.neucom.2015.07.138
  46. Kose, U., Deperlioglu, O., Alzubi, J. and Patrut, B., Diagnosing Parkinson by Using Deep Autoencoder Neural Network. In Deep Learning for Medical Decision Support Systems (pp. 73-93). Springer, Singapore. http://dx.doi.org/10.1007/978-981-15-6325-6_5
  47. Ozkan, H., 2016. A comparison of classification methods for telediagnosis of Parkinson’s disease. Entropy, 18(4), p.115. http://dx.doi.org/10.3390/e18040115
  48. Akyol, K., Bayir, Ş. and Baha, Ş.E.N., Importance of Attribute Selection for Parkinson Disease. Akademik Platform Mühendislik ve Fen Bilimleri Dergisi, 8(1), pp.175-180. http://dx.doi.org/10.21541/apjes.541637
  49. Peker, M., Sen, B. and Delen, D., 2015. Computer-aided diagnosis of Parkinson’s disease using complex-valued neural networks and mRMR feature selection algorithm. Journal of healthcare engineering, 6. http://dx.doi.org/10.1260/2040-2295.6.3.281
  50. Wu, K., Zhang, D., Lu, G., and Guo, Z. 2018. Influence of sampling rate on voice analysis for assessment of Parkinson’s disease. The Journal of the Acoustical Society of America, 144(3), 1416–1423. http://dx.doi.org/10.1121/1.5053681