MACHINE LEARNING METHODS FOR EARLY-STAGE DIAGNOSIS OF PARKINSON'S DISEASE THROUGH HANDWRITING DATA
DOI:
https://doi.org/10.11113/aej.v13.18777Keywords:
feature selection and extraction, handwriting recognition, machine learning, Parkinson's disease diagnosis, vision-based classificationAbstract
Parkinson's disease (PD) deteriorates human cognitive and motor functions, causing slowness of movements and postural shakiness. PD is currently incurable, and managing symptoms in its late stages is difficult. PD diagnosis also has gaps in accuracy due to several clinical challenges. Thus, early-stage detection of PD through its symptoms, such as handwriting abnormality, has become a popular research area using machine learning. Since most related studies focus on advanced algorithms, this study aims to determine the classification accuracies of simpler classical models using the NewHandPD-NewMeander dataset. This study used the 9 features extracted from the meanders drawn by healthy participants and participants diagnosed with Parkinson’s disease and 3 features about the individual. The same features were reduced to the 8 best according to univariate selection and recursive feature elimination. The machine learning algorithms used for the models in this study are Logistic regression, Multilayer perceptron, and Naive Bayes. Additionally, hyperparameter optimization was done. Results have shown that feature selection improved the performances of the default model, while optimization had varying effects depending on the feature selection method used. Among 15 models built, Multilayer perceptron, which utilized top 8 features from univariate selection with default hyperparameters (MLPU8), performed best. It yielded an accuracy of 84.4% in cross-validation, 87.5% in holdout validation, and an F1-score of 87.5%. Remaining models had accuracies ranging from 81.4% - 84.4% in cross-validations and 82.5% - 85.0% in holdout validations. Other studies done on diagnosing PD using similar handwritten datasets resulted in lower accuracies of 87.14% and 77.38% despite utilizing complex algorithms for its models. This proved that the 15 models built using simple architecture can outperform complex classification methods. The 15 models built accurately classify meander data and can be used as an early assessment tool for detecting PD.
References
Tansey, M. G., Wallings, R. L., Houser, M. C., Herrick, M. K., Keating, C. E., & Joers, V. 2022. Inflammation and immune dysfunction in Parkinson disease. In Nature Reviews Immunology. 22(11): 657-673. DOI: 10.1038/s41577-022-00684-6
Deus, C. M., Teixeira, J., Raimundo, N., Tucci, P., Borges, F., Saso, L., & Oliveira, P. J. 2022. Modulation of cellular redox environment as a novel therapeutic strategy for Parkinson's disease. In European Journal of Clinical Investigation. 52(10). 13820 DOI: 10.1111/eci.13820
Fröhlich, F. 2016. Chapter 23 - Parkinson's Disease. In Network Neuroscience. 291-296. DOI: http://dx.doi.org/10.1016/B978-0-12-801560-5.00023-9
C Korczyn, A. D., Balash, Y., and Gurevich, T. 2017. Parkinson's disease. In International Encyclopedia of Public Health (Second Edition). 409-415. DOI: http://dx.doi.org/10.1016/B978-0-12-803678-5.00323-4
De Araújo, F. M., Cuenca-Bermejo, L., Fernández-Villalba, E., Costa, S. L., Silva, V. D. A., & Herrero, M. T. 2022. Role of Microgliosis and NLRP3 Inflammasome in Parkinson’s Disease Pathogenesis and Therapy. In Journal of Cellular and Molecular Neurobiology. 42(5): 1283-1300. DOI: 10.1007/s10571-020-01027-6
Rana, A., Dumka, A., Singh, R., Panda, M. K., Priyadarshi, N., & Twala, B. 2022. Imperative role of machine learning algorithm for detection of Parkinson’s disease: Review, challenges and recommendations. In Journal of Diagnostics. 12(8): 2003. DOI: 10.3390/diagnostics12082003
Babaei, Z. A., and Majumdar, P., “Genetic Variations Associated with Parkinson’s Disease,” In The Handbook of Neuromodulation, 1, Nova Science Publishers, Inc., 63-82, 2022.
Nassan, M., and Videnovic, A. 2022. Circadian rhythms in neurodegenerative disorders. In Nature Reviews Neurology. 18(1): 7-24. DOI: 10.1038/s41582-021-00577-7
Ayap, N. F. M., Eugenio, B. A., Hinolan, J. I. V., Puno, J. C. V., Baldovino, R. G., & Billones, R. K. C. 2021. A biomedical voice measurement diagnosis of Parkinson’s disease through the utilization of artificial neural network. In Journal of Physics: Conference Series. 2071: 12038. DOI: http://dx.doi.org/10.1088/1742-6596/2071/1/012038
Rohit Surya, A. T., Yaswanthram, P., Nair, P. R., Rajendra Prasath, S. S., & Akella, S. V. V. S. 2022. Prediction of Parkinson’s Disease Using Machine Learning Models—A Classifier Analysis. In International Conference on Advanced Computing and Intelligent Technologies, 218: 453-460. DOI: 10.1007/978-981-16-2164-2_35
Drotár, P., Mekyska, J., Smékal, Z., Rektorová, I., Masarová, L., & Faundez-Zanuy, M. 2013. Prediction potential of different handwriting tasks for diagnosis of Parkinson's. In Proceedings of the 2013 E-Health and Bioengineering Conference. 1-4. DOI: http://dx.doi.org/10.1109/EHB.2013.6707378
Xu, S., Zhu, Z., and Pan, Z. 2020. A Cascade Ensemble Learning Model for Parkinson’s Disease Diagnosis Using Handwritten Sensor Signals. In Journal of Physics: Conference Series. 1631: 12168. DOI: http://dx.doi.org/10.1088/1742-6596/1631/1/012168
Xu, S., and Pan, Z. 2020. A novel ensemble of random forest for assisting diagnosis of Parkinson's disease on small handwritten dynamics dataset. In International Journal of Medical Informatics. 144: 104283. DOI: http://dx.doi.org/10.1016/j.ijmedinf.2020.104283
Valla, E., Nõmm, S., Medijainen, K., Taba, P., & Toomela, A. 2022. Tremor-related feature engineering for machine learning based Parkinson’s disease diagnostics. In Biomedical Signal Processing and Control, 75: 1746-8094. DOI: https://doi.org/10.1016/j.bspc.2022.103551
Drotár, P., Mekyska, J., Rektorová, I., Masarová, L., Smékal, Z., & Faundez-Zanuy, M. 2016. Evaluation of handwriting kinematics and pressure for differential diagnosis of Parkinson's disease. In Artificial Intelligence in Medicine. 67: 39-46. DOI: http://dx.doi.org/10.1016/j.artmed.2016.01.004
Ali, L., Zhu, C., Golilarz, N. A., Javeed, A., Zhou, M., & Liu, Y. 2019. Reliable Parkinson’s Disease Detection by Analyzing Handwritten Drawings: Construction of an Unbiased Cascaded Learning System Based on Feature Selection and Adaptive Boosting Model. In IEEE Access. 7: 116480-116489. DOI: http://dx.doi.org/10.1109/ACCESS.2019.2932037
Wolfsegger, T., Pichler, R., Assar, H., & Topakian, R. 2022. Quantitative trunk sway analysis under challenging gait conditions in early and untreated Parkinson’s disease. In Neurological Sciences. 43(2): 1411-1413. DOI: doi:10.1007/s10072-021-05699-w
Sadiq, M., Khan, M. T., and Masood, S. 2022. Attention-based deep learning model for early detection of Parkinson’s disease. In Computers, Materials and Continua. 71: 5183-5200. DOI: http://dx.doi.org/10.32604/cmc.2022.020531
Kamran, I., Naz, S., Razzak, I., and Imran, M. 2021. Handwriting dynamics assessment using deep neural network for early identification of Parkinson’s disease. In Future Generation Computer Systems. 117: 234-244. DOI: http://dx.doi.org/10.1016/j.future.2020.11.020
Pereira, C. R., Weber, S. A. T., Hook, C., Rosa G. H., & Papa, J. P. 2016. Deep Learning-Aided Parkinson's Disease Diagnosis from Handwritten Dynamics. In 29th SIBGRAPI Conference on Graphics, Patterns and Images. 340-346. DOI: http://dx.doi.org/10.1109/SIBGRAPI.2016.054
Gopal, A., Hsu, W., Allen, D. D., & Bove, R. 2022. Remote assessments of hand function in neurological disorders: Systematic review. In JMIR Rehabilitation and Assistive Technologies. 9(1): 33157 DOI: 10.2196/33157
Taleb, C., Khachab, M., Mokbel, C and Likforman-Sulem, L. 2017. Feature selection for an improved parkinson’s disease identification based on handwriting. In Proceedings of the 2017 International Workshop on Arabic Script Analysis and Recognition. 52-56. DOI: http://dx.doi.org/10.1109/ASAR.2017.8067759.
Pereira, C. R., Pereira, D. R., Da Silva, F. A., Hook, C., Weber, S. A. T., Pereira, L. A. M., & Papa, J. P. 2015. A Step Towards the Automated Diagnosis of Parkinson's Disease: Analyzing Handwriting Movements. In 2015 IEEE 28th International Symposium on Computer-Based Medical Systems. 171-176. DOI: http://dx.doi.org/10.1109/CBMS.2015.34
Alqahtani, A., Alsubai, S., Sha, M., Vilcekova, L., Javed, T. 2022. Cardiovascular Disease Detection using Ensemble Learning. In Computational Intelligence and Neuroscience. 2022: 5267498. DOI: 10.1155/2022/5267498
Jawa, T. M. 2022. Logistic regression analysis for studying the impact of home quarantine on psychological health during COVID-19 in Saudi Arabia. In Alexandria Engineering Journal. 61: 7995-8005. DOI: 10.1016/j.aej.2022.01.047
Bazrafashan, O., Ehteram, M., Latif, S. D., Huang, Y. F., Teo, F. Y., Ahmed, A. N., El-Shafie, A. 2022. Predicting crop yields using a new robust Bayesian averaging model based on multiple hybrid ANFIS and MLP models. In Ain Shams Engineering Journal. 13 (5): 101724. DOI: 10.1016/j.asej.2022.101724
Ma, T. M., Yamamori, K., and Thida, A. 2020. A Comparative Approach to Naïve Bayes Classifier and Support Vector Machine for Email Spam Classification. In Proceedings of the 2020 IEEE 9th Global Conference on Consumer Electronics. 324-326. DOI: http://dx.doi.org/10.1109/GCCE50665.2020.9291921
Ismail, S., Hassan, R. 2022. Evaluation of Naïve Bayesian Algorithms for Cyber-Attacks Detection in Wireless Sensor Networks. In 2022 IEEE World AI IoT Congress (AIIoT). 283-289. DOI: http://dx.doi.org/10.1109/AIIoT54504.2022.9817298.
Lauguico, S.C., Concepcion, R. S., Alejandrino, J. D., Tobias, R. R., and Dadios, E. P. 2020. Lettuce life stage classification from texture attributes using machine learning estimators and feature selection processes. In International Journal of Advances in Intelligent Informatics. 6: 173-184.nDOI: http://dx.doi.org/10.26555/ijain.v6i2.466
Lauguico, S.C., Concepcion, R. S., Alejandrino, J. D., Tobias, R. R., Macasaet, D. D., and Dadios, E. P. 2020. A Comparative Analysis of Machine Learning Algorithms Modeled from Machine Vision-Based Lettuce Growth Stage Classification in Smart Aquaponics. In International Journal of Environmental Science and Development 11(9): 442-449. DOI: http://dx.doi.org/10.18178/ijesd.2020.11.9.1288
Pereira, C. R., Pereira, D. R., Da Silva, F. A., Masieiro, J. P., Weber, S. A. T., Hook, C., & Papa, J. 2016. A new computer vision-based approach to aid the diagnosis of Parkinson’s disease. In Computer Methods and Programs in Biomedicine. 136: 79-88. DOI: http://dx.doi.org/10.1016/j.cmpb.2016.08.005
