Detection and forecasting of Parkinson disease progression from speech signal features using multilayer perceptron and LSTM

• Autorzy: Ali Majid , Shakir Hina , Samreen Asia , Ahmed Sohaib

Identyfikatory

DOI

10.7494/csci.2025.26.2.6691

• Języki publikacji: EN

Abstrakty

EN

Accurate diagnosis of Parkinson′s disease, especially in its early stages, can be a challenging task. The application of machine learning (ML) techniques has helped improve the diagnostic accuracy of Parkinson′s disease (PD) detection but integration of diagnostic features in ML models for the prediction of disease progression has remained an unexplored research avenue. In this research work, Long Short Term Memory (LSTM) was trained using diagnostic features on Parkinson patients speech signals, to predict the disease progression while a Multilayer Perceptron (MLP) was trained on the same diagnostic features to detect PD. Diagnostic features were selected using two well known feature selection methods named Relief F and Sequential Forward Selection method. The integration of feature selection methods in LSTM model has resulted in PD progression forecast with an accuracy of 88.7%. Further more, with the application of input diagnostic features on MLP, PD stage was accurately detected with an accuracy of 98.63%, precision of 97.64% and recall of 98.8% showing model robustness and efficiency for its potential application in health care.

Słowa kluczowe

EN

Parkinson disease; machine learning; MLP; diagnostic features; LSTM

• Wydawca: Wydawnictwa AGH
• Czasopismo: Computer Science
• Rocznik: 2025
• Tom: T. 26 (2)
• Strony: 31--48
• Opis fizyczny: Bibliogr. 27 poz., rys., tab., wykr.

Twórcy

autor

Ali Majid

• Department of Software Engineering, Bahria University Karachi Pakistan

autor

Shakir Hina

• Department of Software Engineering, Bahria University Karachi Pakistan

autor

Samreen Asia

• Department of Software Engineering, Bahria University Karachi Pakistan

autor

Ahmed Sohaib

• Department of Software Engineering, Bahria University Karachi Pakistan

Bibliografia

• [1] Abd El Aal H.A., Taie S.A., El-Bendary N.: An optimized RNN-LSTM approachfor Parkinson’s disease early detection using speech features, Bulletin of Electrical Engineering and Informatics, vol. 10(5), pp. 2503–2512, 2021. doi: 10.11591/eei.v10i5.3128.
• [2] Abiodun O.I., Jantan A., Omolara A.E., Dada K.V., Mohamed N.A., Arshad H. :State-of-the-art in artificial neural network applications: A survey, Heliyon, vol. 4(11), 2018. doi: 10.1016/j.heliyon.2018.e00938.
• [3] Al-Fatlawi A.H., Jabardi M.H., Ling S.H.: Efficient diagnosis system for Parkinson’s disease using deep belief network. In: 2016 IEEE Congress on Evolutionary Computation (CEC), pp. 1324–1330, IEEE, 2016. doi: 10.1109/cec.2016.7743941.
• [4] Alshammri R., Alharbi G., Alharbi E., Almubark I.: Machine learning approachesto identify Parkinson’s disease using voice signal features, Frontiers in Artificial Intelligence, vol. 6, 1084001, 2023. doi: 10.3389/frai.2023.1084001.
• [5] Armananzas R., Bielza C., Chaudhuri K.R., Martinez-Martin P., Larranaga P.: Unveiling relevant non-motor Parkinson’s disease severity symptoms usinga machine learning approach, Artificial Intelligence in Medicine, vol. 58(3), pp. 195–202, 2013. doi: 10.1016/j.artmed.2013.04.002.
• [6] Bouchlaghem Y., Akhiat Y., Amjad S.: Feature selection: a review and comparative study. In: E3S web of conferences, vol. 351, EDP Sciences, 2022. doi: 10.1051/e3sconf/202235101046.
• [7] Braga D., Madureira A.M., Coelho L., Ajith R.: Automatic detection of Parkinson’s disease based on acoustic analysis of speech, Engineering Applications of Artificial Intelligence, vol. 77, pp. 148–158, 2019.doi: 10.1016/j.engappai.2018.09.018.
• [8] Chen Z., Fang R., Zhang Y., Ge P., Zhuang P., Chou A., Jiang J.: The Mandarinversion of the Consensus Auditory-Perceptual Evaluation of Voice (CAPE-V) andits reliability, Journal of Speech, Language, and Hearing Research, vol. 61(10), pp. 2451–2457, 2018. doi: 10.1044/2018jslhr-s-17-0386.
• [9] Chicco D., Warrens M.J., Jurman G.: The coefficient of determination R-squaredis more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation, Peerj Computer Science, vol. 7, e623, 2021. doi: 10.7717/peerj-cs.623.
• [10] Chitra Rajagopal P., Choudhury T., Sharma A., Kumar P.: Diagnosis of Parkinson’s diseases using classification based on voice recordings. In: Emerging Trendsin Expert Applications and Security: Proceedings of ICETEAS 2018, pp. 575–581,Springer, 2019.
• [11] Despotovic V., Skovranek T., Schommer C.: Speech based estimation of Parkinson’s disease using Gaussian processes and automatic relevance determination, Neurocomputing, vol. 401, pp. 173–181, 2020. doi: 10.1016/j.neucom.2020.03.058.
• [12] Haq A.U., Li J.P., Memon M.H., Khan J., Malik A., Ahmad T., Ali A., et al.: Feature selection based on L1-norm support vector machine and effective recognition system for Parkinson’s disease using voice recordings, IEEE Access, vol. 7, pp. 37718–37734, 2019. doi: 10.1109/access.2019.2906350.
• [13] Hardy J., Selkoe D.J.: The amyloid hypothesis of Alzheimer’s disease: progress and problems on the road to therapeutics, Science, vol. 297(5580), pp. 353–356, 2002. doi: 10.1126/science.1072994.
• [14] Lahmiri S., Shmuel A.: Detection of Parkinson’s disease based on voice patterns ranking and optimized support vector machine, Biomedical Signal Processing and Control, vol. 49, pp. 427–433, 2019. doi: 10.1016/j.bspc.2018.08.029.
• [15] Lamba R., Gulati T., Alharbi H.F., Jain A.: A hybrid system for Parkinson’s disease diagnosis using machine learning techniques, International Journal of SpeechTechnology, vol. 25, pp. 583–593, 2022. doi: 10.1007/s10772-021-09837-9.
• [16] Nutt J.G., Wooten G.F.: Diagnosis and initial management of Parkinson’s disease, New England Journal of Medicine, vol. 353(10), pp. 1021–1027, 2005.doi: 10.1056/nejmcp043908.
• [17] Pahuja G., Nagabhushan T.: A comparative study of existing machine learning approaches for Parkinson’s disease detection, IETE Journal of Research, vol. 67(1), pp. 4–14, 2021. doi: 10.1080/03772063.2018.1531730.
• [18] Postuma R., Montplaisir J.: Predicting Parkinson’s disease – why, when,and how?, Parkinsonism & Related Disorders, vol. 15, pp. S105–S109, 2009. doi: 10.1016/s1353-8020(09)70793-x.
• [19] Rasheed J., Hameed A.A., Ajlouni N., Jamil A., Ozyavas A., Orman Z.: Application of adaptive back-propagation neural networks for Parkinson’s disease prediction. In: 2020 International Conference on Data Analytics for Businessand Industry: Way Towards a Sustainable Economy (ICDABI), IEEE, 2020. doi: 10.1109/icdabi51230.2020.9325709.
• [20] Rizvi D.R., Nissar I., Masood S., Ahmed M., Ahmad F.: An LSTM based Deep learning model for voice-based detection of Parkinson’s disease, International Journal of Advanced Science and Technology, vol. 29(5s), pp. 337–343, 2020.
• [21] Shakir H., Aijaz B., Khan T.M.R., Hussain M.: A deep learning-based cancersurvival time classifier for small datasets,Computers in Biology and Medicine,vol. 160, 106896, 2023. doi: 10.1016/j.compbiomed.2023.106896.
• [22] Shakir H., Deng Y., Rasheed H., Khan T.M.R.: Radiomics based likelihood functions for cancer diagnosis, Scientific Reports, vol. 9(1), 9501, 2019. doi: 10.1038/s41598-019-45053-x.
• [23] Shakir H., Khan T., Rasheed H., Deng Y.: Radiomics based Bayesian inversion method for prediction of cancer and pathological stage, IEEE Journalof Translational Engineering in Health and Medicine, vol. 9, 4300208, 2021. doi: 10.1109/jtehm.2021.3108390.
• [24] Shakir H., Rasheed H., Rasool Khan T.M.: Radiomic feature selection forlung cancer classifiers, Journal of Intelligent & Fuzzy Systems, vol. 38(5), pp. 5847–5855, 2020. doi: 10.3233/jifs-179672.
• [25] Shulman L.M., Gruber-Baldini A.L., Anderson K.E., Fishman P.S., Reich S.G.,Weiner W.J.: The clinically important difference on the unified Parkinson’s disease rating scale, JAMA Neurology, vol. 67(1), pp. 64–70, 2010. doi: 10.1001/archneurol.2009.295.
• [26] Tsanas A., Little M.: Parkinsons Telemonitoring. UCI Machine Learning Repository.
• [27] Tuncer T., Dogan S., Acharya U.R.: Automated detection of Parkinson’s diseaseusing minimum average maximum tree and singular value decomposition method with vowels, Biocybernetics and Biomedical Engineering, vol. 40(1), pp. 211–220, 2020. doi: 10.1016/j.bbe.2019.05.006.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki (2025).