Predicting Parkinson's Disease Progression: A Non-Invasive Method Leveraging Voice Inputs

Abstract

Parkinson's Disease (PD) is a complex neurodegenerative condition with a global impact, demanding precise disease progression prediction to facilitate effective treatment strategies. To assess PD symptoms, the Unified Parkinson's Disease Rating Scale (UPDRS) is widely adopted, encompassing both motor and non-motor assessments. This research delves into voice inputs as a non-intrusive method to predict total UPDRS and motor UPDRS scores, offering new possibilities for Parkinson's assessment. Feature engineering and data augmentation techniques address challenges related to class imbalance and diverse demographics, including an original imbalanced dataset with more females than males. Additionally, three new datasets are created: oversampled balanced, only-female, and only-male datasets. Ensemble-based stacking model, including random forest and extreme gradient boosting as base models and the gradient boosting regressor as the meta-regressor, demonstrate promising performance and robustness in predicting UPDRS scores, showcasing the efficacy of voice inputs for PD assessment. Furthermore, the feature importance analysis provides insights into crucial contributors influencing predictions. Various performance metrics, such as accuracy, mean squared error (MSE), root mean squared error (RMSE), mean absolute error (MAE), and R-squared (R2), are used to evaluate the model’s performance. Additionally, by incorporating telemonitoring capabilities, the voice-based approach offers the possibility of remote and continuous PD assessment, allowing for real-time monitoring and early detection. This advancement could significantly improve the quality of life for PD patients and facilitate more personalized and effective treatment plans.

Keywords

• parkinsons
• parkinsons assessment
• UPDRS score estimation
• ensemble-based stacking
• extreme gradient boosting
• random forests
• gradient boosting regressor

Parkinson Hastalığının İlerlemesini Tahmin Etmek: Ses Girişlerinden Yararlanan İnvazif Olmayan Bir Yöntem

Abstract

Parkinson Disease (PD), etkili tedavi stratejilerini kolaylaştırmak için hastalığın ilerlemesinin kesin olarak tahmin edilmesini gerektiren, küresel etkiye sahip karmaşık bir nörodejeneratif durumdur. PD semptomlarını değerlendirmek için, hem motor hem de motor olmayan değerlendirmeleri kapsayan Universal Parkinson Disease Rating Scale (UPDRS) yaygın olarak benimsenmiştir. Bu araştırma, toplam UPDRS ve motor UPDRS puanlarını tahmin etmek için müdahaleci olmayan bir yöntem olarak ses girişlerini derinlemesine inceleyerek Parkinson değerlendirmesi için yeni olanaklar sunuyor. Feature engineering va data augmentation teknikleri, erkeklerden daha fazla kadın içeren orijinal dengesiz bir veri seti de dahil olmak üzere, sınıf dengesizliği ve çeşitli demografik özelliklerle ilgili zorlukları ele alır. Ek olarak üç yeni veri kümesi oluşturulur: aşırı örneklenmiş dengeli, yalnızca kadın ve yalnızca erkek veri kümeleri. Base model olarak random forest ve extreme gradient boosting ve meta-regressor olarak gradient boosting regressor'yi içeren ensemble-based stacking Modeli, UPDRS puanlarını tahmin etmede umut verici bir performans ve sağlamlık sergileyerek PD değerlendirmesi için ses girişlerinin etkinliğini ortaya koyuyor. Ayrıca, özellik önemi analizi, tahminleri etkileyen önemli katkıda bulunanlar hakkında bilgi sağlar. Modelin performansını değerlendirmek için doğruluk, mean squared error (MSE), root mean squared error (RMSE), mean absolute error (MAE), ve R-suared (R2) gibi çeşitli performans ölçümleri kullanılır. Ek olarak, uzaktan izleme yeteneklerini birleştirerek ses tabanlı yaklaşım, uzaktan ve sürekli PD değerlendirmesi olanağı sunarak gerçek zamanlı izleme ve erken tespite olanak tanır. Bu ilerleme, Parkinson hastalarının yaşam kalitesini önemli ölçüde artırabilir ve daha kişiselleştirilmiş ve etkili tedavi planlarını kolaylaştırabilir.

Keywords

• UPDRS puan tahmini
• ensemble-based stacking
• extreme gradient boosting
• random forests
• gradient boosting regressor
• parkinson değerlendirmesi
• parkinsons

References

1. Ahmed, I., Aljahdali, S., Khan, M., & Kaddoura, S. (2021). Classification of Parkinson Disease Based on Patient’s Voice Signal Using Machine Learning. Intelligent Automation & Soft Computing, 32(2), 705–722. https://doi.org/10.32604/iasc.2022.022037
2. Alshammri, R., Alharbi, G., Alharbi, E., & Almubark, I. (2023). Machine learning approaches to identify Parkinson’s disease using voice signal features. Frontiers in Artificial Intelligence, 6. https://doi.org/10.3389/frai.2023.1084001
3. Arias-Londoño, J. D., & Gómez-García, J. (2020). Predicting UPDRS Scores in Parkinson’s Disease Using Voice Signals: A Deep Learning/Transfer-Learning-Based Approach (pp. 100–123). https://doi.org/10.1007/978-3-030-65654-6_6
4. Arias-Vergara, T., Vasquez, J., Orozco, J. R., Vargas-Bonilla, J., & Noeth, E. (2016). Parkinson’s Disease Progression Assessment from Speech Using GMM-UBM (p. 1937). https://doi.org/10.21437/Interspeech.2016-1122
5. Bradshaw, T. J., Huemann, Z., Hu, J., & Rahmim, A. (2023). A Guide to Cross-Validation for Artificial Intelligence in Medical Imaging. Radiology: Artificial Intelligence, 5(4), e220232. https://doi.org/10.1148/ryai.220232
6. Chawla, N. V., Bowyer, K. W., Hall, L. O., & Kegelmeyer, W. P. (2002). SMOTE: Synthetic Minority Over-sampling Technique. Journal of Artificial Intelligence Research, 16, 321–357. https://doi.org/10.1613/jair.953
7. Costantini, G., Cesarini, V., Di Leo, P., Amato, F., Suppa, A., Asci, F., Pisani, A., Calculli, A., & Saggio, G. (2023). Artificial Intelligence-Based Voice Assessment of Patients with Parkinson’s Disease Off and On Treatment: Machine vs. Deep-Learning Comparison. Sensors, 23(4), Article 4. https://doi.org/10.3390/s23042293
8. De Letter, M., Santens, P., De Bodt, M., Van Maele, G., Van Borsel, J., & Boon, P. (2007). The effect of levodopa on respiration and word intelligibility in people with advanced Parkinson’s disease. Clinical Neurology and Neurosurgery, 109(6), 495–500. https://doi.org/10.1016/j.clineuro.2007.04.003

9. De Miranda, B. R., & Greenamyre, J. T. (2017). Etiology and Pathogenesis of Parkinson’s Disease. https://doi.org/10.1039/9781782622888-00001
10. Disease, M. D. S. T. F. on R. S. for P. (2003). The Unified Parkinson’s Disease Rating Scale (UPDRS): Status and recommendations. Movement Disorders, 18(7), 738–750. https://doi.org/10.1002/mds.10473
11. Elreedy, D., Atiya, A. F., & Kamalov, F. (2023). A theoretical distribution analysis of synthetic minority oversampling technique (SMOTE) for imbalanced learning. Machine Learning. https://doi.org/10.1007/s10994-022-06296-4
12. Hamzehei, S., Akbarzadeh, O., Attar, H., Rezaee, K., Fasihihour, N., & Khosravi, M. R. (2023). Predicting the total Unified Parkinson’s Disease Rating Scale (UPDRS) based on ML techniques and cloud-based update. Journal of Cloud Computing, 12(1), 12. https://doi.org/10.1186/s13677-022-00388-1
13. Hassan, A., & Yousaf, N. (2022). Bankruptcy Prediction using Diverse Machine Learning Algorithms. 2022 International Conference on Frontiers of Information Technology (FIT), 106–111. https://doi.org/10.1109/FIT57066.2022.00029
14. Hemmerling, D., & Wojcik-Pedziwiatr, M. (2022). Prediction and Estimation of Parkinson’s Disease Severity Based on Voice Signal. Journal of Voice, 36(3), 439.e9-439.e20. https://doi.org/10.1016/j.jvoice.2020.06.004
15. Hendricks, R. M., & Khasawneh, M. T. (2021). An Investigation into the Use and Meaning of Parkinson’s Disease Clinical Scale Scores. Parkinson’s Disease, 2021, e1765220. https://doi.org/10.1155/2021/1765220
16. Holden, S. K., Finseth, T., Sillau, S. H., & Berman, B. D. (2018). Progression of MDS-UPDRS Scores Over Five Years in De Novo Parkinson Disease from the Parkinson’s Progression Markers Initiative Cohort. Movement Disorders Clinical Practice, 5(1), 47–53. https://doi.org/10.1002/mdc3.12553
17. Kaliappan, J., Bagepalli, A. R., Almal, S., Mishra, R., Hu, Y.-C., & Srinivasan, K. (2023). Impact of Cross-Validation on Machine Learning Models for Early Detection of Intrauterine Fetal Demise. Diagnostics, 13(10), Article 10. https://doi.org/10.3390/diagnostics13101692
18. McGregor, M. M., & Nelson, A. B. (2019). Circuit Mechanisms of Parkinson’s Disease. Neuron, 101(6), 1042–1056. https://doi.org/10.1016/j.neuron.2019.03.004
19. Nilashi, M., Abumalloh, R. A., Minaei-Bidgoli, B., Samad, S., Yousoof Ismail, M., Alhargan, A., & Abdu Zogaan, W. (2022). Predicting Parkinson’s Disease Progression: Evaluation of Ensemble Methods in Machine Learning. Journal of Healthcare Engineering, 2022, e2793361. https://doi.org/10.1155/2022/2793361
20. Nilashi, M., Ibrahim, O., & Ahani, A. (2016). Accuracy Improvement for Predicting Parkinson’s Disease Progression. Scientific Reports, 6(1), Article 1. https://doi.org/10.1038/srep34181
21. Nilashi, M., Ibrahim, O., Samad, S., Ahmadi, H., Shahmoradi, L., & Akbari, E. (2019). An analytical method for measuring the Parkinson’s disease progression: A case on a Parkinson’s telemonitoring dataset. Measurement, 136, 545–557. https://doi.org/10.1016/j.measurement.2019.01.014
22. Parkinson’s Disease Progression. (2023). https://www.kaggle.com/datasets/thedevastator/unlocking-clues-to-parkinson-s-disease-progressi
23. Pastor-Sanz, L., Pansera, M., Cancela, J., Pastorino, M., Waldmeyer, M. T. A., Pastor-Sanz, L., Pansera, M., Cancela, J., Pastorino, M., & Waldmeyer, M. T. A. (2011). Mobile Systems as a Challenge for Neurological Diseases Management – The Case of Parkinson’s Disease. In Diagnostics and Rehabilitation of Parkinson’s Disease. IntechOpen. https://doi.org/10.5772/16729
24. Polverino, P., Ajčević, M., Catalan, M., Bertolotti, C., Furlanis, G., Marsich, A., Buoite Stella, A., Accardo, A., & Manganotti, P. (2022). Comprehensive telemedicine solution for remote monitoring of Parkinson’s disease patients with orthostatic hypotension during COVID-19 pandemic. Neurological Sciences, 43(6), 3479–3487. https://doi.org/10.1007/s10072-022-05972-6
25. Rajeswari, S. S., & Nair, M. (2022). Prediction of Parkinson’s disease from Voice Signals Using Machine Learning. Journal of Pharmaceutical Negative Results, 2031–2035. https://doi.org/10.47750/pnr.2022.13.S07.294
26. Rizek, P., Kumar, N., & Jog, M. S. (2016). An update on the diagnosis and treatment of Parkinson disease. CMAJ, 188(16), 1157–1165. https://doi.org/10.1503/cmaj.151179
27. Sakar, B. E., Serbes, G., & Sakar, C. O. (2017). Analyzing the effectiveness of vocal features in early telediagnosis of Parkinson’s disease. PLOS ONE, 12(8), e0182428. https://doi.org/10.1371/journal.pone.0182428
28. Skodda, S., Grönheit, W., & Schlegel, U. (2011). Intonation and Speech Rate in Parkinson’s Disease: General and Dynamic Aspects and Responsiveness to Levodopa Admission. Journal of Voice, 25(4), e199–e205. https://doi.org/10.1016/j.jvoice.2010.04.007
29. Stamate, C., Magoulas, G. D., Kueppers, S., Nomikou, E., Daskalopoulos, I., Jha, A., Pons, J. S., Rothwell, J., Luchini, M. U., Moussouri, T., Iannone, M., & Roussos, G. (2018). The cloudUPDRS app: A medical device for the clinical assessment of Parkinson’s Disease. Pervasive and Mobile Computing, 43, 146–166. https://doi.org/10.1016/j.pmcj.2017.12.005
30. Suppa, A., Costantini, G., Asci, F., Di Leo, P., Al-Wardat, M. S., Di Lazzaro, G., Scalise, S., Pisani, A., & Saggio, G. (2022). Voice in Parkinson’s Disease: A Machine Learning Study. Frontiers in Neurology, 13. https://www.frontiersin.org/articles/10.3389/fneur.2022.831428
31. Trudelle, P. (2006). Instructions for the Unified Parkinson Disease Ratings Scale (UPDRS). Kinésithérapie, La Revue, 6. https://doi.org/10.1016/S1779-0123(06)74622-8
32. Tsanas, A., Little, M. A., McSharry, P. E., & Ramig, L. O. (2010). Nonlinear speech analysis algorithms mapped to a standard metric achieve clinically useful quantification of average Parkinson’s disease symptom severity. Journal of The Royal Society Interface, 8(59), 842–855. https://doi.org/10.1098/rsif.2010.0456
33. Tsanas, A., Little, M. A., & Ramig, L. O. (2021). Remote Assessment of Parkinson’s Disease Symptom Severity Using the Simulated Cellular Mobile Telephone Network. IEEE Access, 9, 11024–11036. https://doi.org/10.1109/ACCESS.2021.3050524
34. Van Den Bergh, R., Bloem, B. R., Meinders, M. J., & Evers, L. J. W. (2021). The state of telemedicine for persons with Parkinson’s disease. Current Opinion in Neurology, 34(4), 589. https://doi.org/10.1097/WCO.0000000000000953
35. White, J., & Power, S. D. (2023). k-Fold Cross-Validation Can Significantly Over-Estimate True Classification Accuracy in Common EEG-Based Passive BCI Experimental Designs: An Empirical Investigation. Sensors, 23(13), Article 13. https://doi.org/10.3390/s23136077
36. Zimmerman, M., Morgan, T. A., & Stanton, K. (2018). The severity of psychiatric disorders. World Psychiatry, 17(3), 258–275. https://doi.org/10.1002/wps.20569