Recurrent Neural Network Optimized by Grasshopper for Accurate Audio Data-Based Diagnosis of Parkinson's Disease

Saif Wali Ali  Alsudani; Ghassan Khudair Saud

doi:10.31185/wjps.766

Authors

Saif Wali Ali Alsudani Computerized Intelligence Systems Laboratory, Department of Computer Engineering, University of Tabriz, Tabriz, IRAN.
Ghassan Khudair Saud Imam Reza International University, Department of Computer Engineering, Mashhad, IRAN

DOI:

https://doi.org/10.31185/wjps.766

Keywords:

Parkinson’s disease, speech signal analysis, Long Short-Term Memory (LSTM), Grasshopper Optimization Algorithm (GOA), feature extraction, Linear Discriminant Analysis (LDA)

Abstract

Proposed here is a speech-based diagnostic framework for detecting Parkinson's disease that utilizes a Long Short-Term Memory neural network and the Grasshopper Optimization Algorithm. The framework aims to improve the detection of PD while ensuring accurate and efficient classification of speech-based signals. Incorporated within the system is a dimensionality reduction technique called Linear Discriminant Analysis. This approach allows the system to optimally utilize the features extracted from the given speech signal while ensuring that all the conditions necessary for successful classification are met.

The LSTM neural network serves as the core deep learning model for this framework. It is trained on the speech signals produced by both healthy individuals and those with PD, allowing it to detect the class of a given speech signal based on the conditions necessary for successful classification.

We assess the suggested technique on two speech datasets that are publicly available: NeuroVoz, a Castilian-Spanish body of work, and EWA-DB, a database in the Slovak language. The classification accuracy of our model on NeuroVoz is 99.45%, while on EWA-DB it is 99.71%. Moreover, these results exceed those from several contemporary approaches that were also tested on these two datasets. We interpret our results as strong evidence that uniting deep learning with nature-inspired optimization does yield an effective tool for providing, in a non-invasive way, a diagnosis of early-stage Parkinson's across diverse linguistic contexts.

References

[1] C. Pan, Y. Tian, L. Ma, T. Zhou, S. Ouyang, and J. Li, “CISL-PD: A deep learning framework of clinical intervention strategies for Parkinson’s disease based on directional counterfactual Dual GANs,” Expert Syst. Appl., vol. 261, p. 125506, Feb. 2025. http://doi.org/10.1016/j.eswa.2024.125506.

[2] J. M. Ison, J. D. Jackson, H. Hemley, A. Willis, B. Siddiqi, E. A. Macklin, C. Ulysse, M. S. Fitts, T. T.-H. Pham, M. Afshari, P. Agarwal, M. Aminoff, S. Bissonnette, M. Fullard, T. S. Khan, D. N. Larson, C. Wielinski, and A. V. Sanchez, "Fostering inclusivity in research engagement for underrepresented populations in Parkinson's disease: The FIRE-UP PD study," Contemp. Clin. Trials, vol. 144, p. 107619, Sep. 2024. http://doi.org/10.1016/j.cct.2024.107619.

[3] Z. Chen, W. Li, B. Meng, C. Xu, Y. Huang, G. Li, Z. Wen, J. Liu, and Z. Mao, “Neuronal-enriched small extracellular vesicles trigger a PD-L1-mediated broad suppression of T cells in Parkinson’s disease,” iScience, vol. 27, no. 7, p. 110243, Jul. 2024. http://doi.org/10.1016/j.isci.2024.110243.

[4] N. Madusanka and B.-i. Lee, "Vocal biomarkers for Parkinson’s disease classification using audio spectrogram transformers," J. Voice, In Press, Corrected Proof, Dec. 2024. [Online]. Available: http://doi.org/10.1016/j.jvoice.2024.11.008.

[5] J. Rusz, P. Krack, and E. Tripoliti, "From prodromal stages to clinical trials: The promise of digital speech biomarkers in Parkinson's disease," Neuroscience & Biobehavioral Reviews, vol. 167, p. 105922, Dec. 2024. [Online]. Available: http://doi.org/10.1016/j.neubiorev.2024.105922.

[6] S. Alsudani and M. N. Saeea, "Enhancing Thyroid Disease Diagnosis through Emperor Penguin Optimization Algorithm," Wasit Journal for Pure Sciences, vol. 2, no. 4, 2023. https://doi.org/10.31185/wjps.230.

[7] W. Gamaleldin, O. Attayyib, L. Mohaisen, N. Omer, and R. Ming, "Developing a hybrid model based on Convolutional Neural Network (CNN) and Linear Discriminant Analysis (LDA) for investigating anti-selection risk in insurance," J. Radiat. Res. Appl. Sci., vol. 18, no. 2, p. 101368, Jun. 2025. http://doi.org/10.1016/j.jrras.2025.101368.

[8] P. H. G. D. Diniz, M. F. Pistonesi, M. B. Alvarez, B. S. F. Band, and M. C. U. de Araújo, "Simplified tea classification based on a reduced chemical composition profile via successive projections algorithm linear discriminant analysis (SPA-LDA)," J. Food Compos. Anal., vol. 39, pp. 103–110, May 2015. http://doi.org/10.1016/j.jfca.2014.11.012.

[9] W. Gao, "Application of improved particle swarm optimization algorithm combined with genetic algorithm in shear wall design," Syst. Soft Comput., vol. 7, Dec. 2025, Art. no. 200198. [Online]. Available: http://doi.org/10.1016/j.sasc.2025.200198.

[10] S. M. S. Bukhari, M. H. Zafar, S. K. R. Moosavi, M. Mansoor, and F. Sanfilippo, "An integrated stacked convolutional neural network and the levy flight-based grasshopper optimization algorithm for predicting heart disease," Healthcare Analytics, vol. 7, p. 100374, June 2025. [Online]. Available: http://doi.org/10.1016/j.health.2024.100374.

[11] M. Jiang, J. Zhao, L. Wang, Y. Wang, Y. Zhou, Y. Zhu, and X. Liu, "Diagnosis of Parkinson’s disease by eliciting trait-specific eye movements in multi-visual tasks," Journal of Translational Medicine, vol. 23, no. 65, Jan. 2025. [Online]. Available: https://doi.org/10.1186/s12967-024-06044-3.

[12] N. Khalid and M. S. Ehsan, "Critical analysis of Parkinson’s disease detection using EEG sub-bands and gated recurrent unit," Engineering Science and Technology, an International Journal, vol. 59, p. 101855, Nov. 2024. [Online]. Available: http://doi.org/10.1016/j.jestch.2024.101855.

[13] S. Narayanan, L. J. Anbarasi, J. J. Sharon, R. Neeraja, and J. J. Gabriel, "Benchmark image and clinical datasets for analysis in the medical system," in Revolutionizing Medical Systems Using Artificial Intelligence: A Breakthrough in Healthcare, 2025, pp. 47-74. http://doi.org/10.1016/B978-0-443-32862-6.00003-1.

[14] S. W. A. Alsudani and A. Ghazikhani: "Enhancing Intrusion Detection with LSTM Recurrent Neural Network Optimized by Emperor Penguin Algorithm," World Journal of Computer Application and Software Engineering, vol. 2, no. 3, 2023. https://doi.org/10.31185/wjcms.166.

[15] Y. Zhang, J. Liu, T.-W. Lo, Y. Kim, F. Lucien, H. Dong, and Y. Liu, "A digital microfluidic device integrated with electrochemical sensor and 3D matrix for detecting soluble PD-L1," Biosensors and Bioelectronics: X, vol. 19, p. 100490, Aug. 2024. http://doi.org/10.1016/j.biosx.2024.100490.

[16] S. Alsudani, H. Nasrawi, M. Shattawi, and A. Ghazikhani, "Enhancing Spam Detection: A Crow-Optimized FFNN with LSTM for Email Security," Wasit Journal of Computer and Mathematics Science, vol. 3, pp. 1–15, 2024. https://doi.org/10.31185/wjcms.199.

[17] Z. Wang, Q. Li, A. Hou, R. Fang, and L. Shi, "Bimetallic Pd-Au nanoparticles decorated MoS₂/GO nanoflowers for sensitive detection of doxorubicin," Biosensors and Bioelectronics: International Journal of Electrochemical Science, vol. 20, no. 1, p. 100914, Jan. 2025. [Online]. Available: http://doi.org/10.1016/j.ijoes.2024.100914.

[18] L. Klein and D. Seidl, "Advanced preliminary screening for PD detection for overhead distribution lines with covered conductors," IFAC-PapersOnLine, vol. 58, no. 9, pp. 114-119, 2024. http://doi.org/10.1016/j.ifacol.2024.07.381.

[19] X. Wang, Y. Zhu, and W. Gao, "Design of hydrogen sensor relying on Pd-MWCNT/WO₃ sensing materials for selective and rapid hydrogen detection," Sensors and Actuators B: Chemical, vol. 422, p. 136648, Jan. 2025. [Online]. Available: http://doi.org/10.1016/j.snb.2024.136648.

[20] M. Zhang, H. Lyu, H. Bian, and N. Ghadimi, “Improved chaos grasshopper optimizer and its application to HRES techno-economic evaluation,” Heliyon, vol. 10, no. 2, p. e24315, Jan. 2024. http://doi.org/10.1016/j.heliyon.2024.e24315.

[21] C. Zhang, H. Hu, J. Ji, K. Liu, X. Xia, M. S. Nazir, and T. Peng, "An evolutionary stacked generalization model based on deep learning and improved grasshopper optimization algorithm for predicting the remaining useful life of PEMFC," Appl. Energy, vol. 330, no. A, p. 120333, Jan. 2023. http://doi.org/10.1016/j.apenergy.2022.120333.

[22] H. Wang, T. H. Nguyen, Z. Lu, F. Rhiana, D. Fong, W. He, S. Owyong, H. T. Chen, and A. Lin, "Acoustic insulation optimization of walls and panels with functional graded hollow sections using graph transformer evaluator and probability-informed genetic algorithm," Building and Environment, vol. 270, p. 112550, Feb. 2025. [Online]. Available: http://doi.org/10.1016/j.buildenv.2025.112550.

[23] L. Jie, C. Huiling, Z. Qian, X. Yueting, H. Hui, and Z. Xuehua, "An improved grasshopper optimization algorithm with application to financial stress prediction," Appl. Math. Model., vol. 64, pp. 654–668, Dec. 2018. [Online]. Available: http://doi.org/10.1016/j.apm.2018.07.044.

[24] S. R. Kamel and R. Yaghoubzadeh, "Feature selection using grasshopper optimization algorithm in diagnosis of diabetes disease," Informatics in Medicine Unlocked, vol. 26, p. 100707, 2021. http://doi.org/10.1016/j.imu.2021.100707.

[25] P. Singh and S. Prakash, “Optimizing multiple ONUs placement in Fiber-Wireless (FiWi) access network using Grasshopper and Harris Hawks Optimization Algorithms,” Optical Fiber Technology, vol. 60, Dec. 2020, Art. no. 102357. http://doi.org/10.1016/j.yofte.2020.102357.

[26] S. W. A. Alsudani, M.-R. Feizi-Derakhshi, W. G. Mutasher, H. A. M. Nasrawi, M. A. Aswad, A. S. K. Al-Shammari, M. Saleh, M. N. Saeea, K. A. F. Al Hilfi, and S. M. Albkhati, “Enhancing IoT intrusion detection through a hybrid deep learning model with Dragonfly-based feature and ensemble optimization,” Int. J. Commun. Netw. Inf. Secur., 2025. [Online]. Available: https://ijcnis.org.

[27] W. Guo, Z. Hou, F. Dai, J. Wang, and S. Li, "Global information enhanced adaptive bald eagle search algorithm for photovoltaic system optimization," Energy Reports, vol. 13, pp. 2129-2152, Jun. 2025. [Online]. Available: http://doi.org/10.1016/j.egyr.2025.01.040.

[28] G. C. Oliveira, N. D. Pah, Q. C. Ngo, A. Yoshida, N. B. Gomes, J. P. Papa, and D. Kumar, “A pilot study for speech assessment to detect the severity of Parkinson’s disease: An ensemble approach,” Computers in Biology and Medicine, vol. 185, p. 109565, Feb. 2025. [Online]. Available: http://doi.org/10.1016/j.compbiomed.2024.109565.

[29] J. Rusz, P. Krack, and E. Tripoliti, “From prodromal stages to clinical trials: The promise of digital speech biomarkers in Parkinson's disease,” Neurosci. Biobehav. Rev., vol. 167, p. 105922, Dec. 2024, http://doi.org/10.1016/j.neubiorev.2024.105922.

[30] P. Modé, C. Demartino, C. T. Georgakis, and N. D. Lagaros, “Short-term extreme wind speed forecasting using dual-output LSTM-based regression and classification model,” J. Wind Eng. Ind. Aerodyn., vol. 259, p. 106035, Apr. 2025, http://doi.org/10.1016/j.jweia.2025.106035.

[31] A. Govindu and S. Palwe, "Early detection of Parkinson's disease using machine learning," Procedia Computer Science, vol. 218, pp. 249–261, 2023. http://doi.org/10.1016/j.procs.2023.01.007.

[32] K. Golalipour, I. F. Davoudkhani, S. Nasri, A. Naderipour, S. Mirjalili, A. Y. Abdelaziz, and A. El-Shahat, "The corona virus search optimizer for solving global and engineering optimization problems," Alexandria Engineering Journal, vol. 78, pp. 614-642, Sep. 2023. [Online]. Available: http://doi.org/10.1016/j.aej.2023.07.066.

[33] Mendes-Laureano, J., Gómez-García, J.A., Guerrero-López, A. et al. NeuroVoz: a Castillian Spanish corpus of parkinsonian speech. Sci Data 11, 1367 (2024). https://doi.org/10.1038/s41597-024-04186-z.

[34] M. Rusko, R. Sabo, M. Trnka, A. Zimmermann, R. Malaschitz, E. Ružický, P. Brandoburová, V. Kevická, and M. Škorvánek, “EWA-DB, Slovak database of speech affected by neurodegenerative diseases,” medRxiv, preprint, Oct. 2023. doi: 10.1101/2023.10.13.23296810.

[35] A. R. Palakayala and P. Kuppusamy, “Differentiating Parkinson’s disease from other neuro diseases and diagnosis using deep learning with nature inspired algorithms and ensemble learning,” Procedia Computer Science, vol. 235, pp. 588–597, 2024, doi: 10.1016/j.procs.2024.04.058.

[36] S. Saleh, Z. Alouani, O. Daanouni, S. Hamida, B. Cherradi, and O. Bouattane, “AIoT-based embedded systems optimization using feature selection for Parkinson’s disease diagnosis through speech disorders,” Intell.-Based Med., vol. 10, p. 100184, 2024, doi: 10.1016/j.ibmed.2024.100184.

[37] F. A. Torghabeh, Y. Modaresnia, and S. A. Hosseini, "An efficient tool for Parkinson's disease detection and severity grading based on time-frequency and fuzzy features of cumulative gait signals through improved LSTM networks," Medicine in Novel Technology and Devices, vol. 22, p. 100297, Jun. 2024. [Online]. Available: http://doi.org/10.1016/j.medntd.2024.100297.

[38] V. Shelke and A. Jadhav, “Influencer ranking framework using TH-DCNN for influence maximization,” Procedia Comput. Sci., vol. 252, pp. 583–592, 2025, http://doi.org/10.1016/j.procs.2025.01.018.

[39] O. Peretz, M. Koren, and O. Koren, “Naive Bayes classifier – An ensemble procedure for recall and precision enrichment,” Eng. Appl. Artif. Intell., vol. 136, pt. B, p. 108972, Oct. 2024, http://doi.org/10.1016/j.engappai.2024.108972.

[40] R.-M. Martikainen, H.-M. Kuivila, M. Koskenranta, S. Kamau, A. Oikarainen, N. Matinlompolo, J. Juntunen, and K. Mikkonen, “Exploring the integration of culturally and linguistically diverse nurses and nursing students in healthcare: A cross-sectional study,” Nurse Educ. Pract., vol. 80, p. 104129, Oct. 2024, http://doi.org/10.1016/j.nepr.2024.104129.