Data Modeling
Mathematical and Computational Data Modeling
0
Citations
4.5k
Views
29
Articles
Volume 2 Number 1 2021
RESEARCH ARTICLE (Open Access)
A Multimodal Smartwatch Framework for Early Parkinson's Disease Detection: Preliminary Gait-Based Evidence Toward an Ensemble Approach
Md. Mahfujul Islam 1*, Khondaker Abdullah Al Mamun 2
Data Modeling 2 (1) 1-11 https://doi.org/10.25163/data.2110808
Submitted: 22 June 2021 Revised: 12 August 2021 Accepted: 23 August 2021 Published: 25 August 2021
Abstract
Parkinson's disease (PD) is typically diagnosed only after substantial dopaminergic neuron loss has already occurred, by which point motor symptoms — tremor, rigidity, bradykinesia — are well established. Earlier detection, even by a modest margin, could meaningfully change how the disease is managed, opening a window for interventions that work best before extensive neurodegeneration sets in. This work proposes a wearable framework that draws on three signal types from a single wrist-worn smartwatch — motor fluctuations, gait dynamics, and voice — with the intention of combining them through an ensemble, majority-voting classifier. Each component builds on previously validated approaches to PD-related sensing. The present analysis focuses largely on the gait component, comparing four conventional regression models (linear regression, Gaussian process regression, support vector regression, and regression trees) against two neural network architectures (CNN, LSTM) in estimating step length, swing time, and stance time from wrist-mounted sensor data. Gaussian process regression performed most consistently, achieving the lowest error across all three parameters, while the regression tree model lagged noticeably behind. Neural network models, working from raw rather than engineered features, underperformed relative to GPR — though this likely reflects dataset size as much as architectural limitations. Taken together, the results offer cautious support for wrist-worn gait sensing as a feasible, low-burden monitoring approach, while the motor fluctuation and voice components, and the ensemble that would unite all three, remain to be empirically validated in future work.
Keywords: Parkinson's disease; wearable sensors; smartwatch; gait analysis; ensemble machine learning
References
Arroyo-Gallego, T., Ledesma-Carbayo, M. J., Sanchez-Ferro, A., Butterworth, I., Mendoza, C. S., Matarazzo, M., Montero, P., Lopez-Blanco, R., Puertas-Martin, V., Trincado, R., & Giancardo, L. (2017). Detection of motor impairment in Parkinson’s disease via mobile touchscreen typing. IEEE Transactions on Biomedical Engineering, 64(9), 1994–2002. https://doi.org/10.1109/TBME.2016.2612662
Ashour, A. S., El-Attar, A., Dey, N., El-Kader, H. A., & Abd El-Naby, M. M. (2020). Long short-term memory based patient-dependent model for FOG detection in Parkinson’s disease. Pattern Recognition Letters, 131, 23–29. https://doi.org/10.1016/j.patrec.2019.11.005
Bilgin, S. (2017). The impact of feature extraction for the classification of amyotrophic lateral sclerosis among neurodegenerative diseases and healthy subjects. Biomedical Signal Processing and Control, 31, 288–294. https://doi.org/10.1016/j.bspc.2016.08.015
Braga, D., Madureira, A. M., Coelho, L., & Abraham, A. (2019). Automatic detection of Parkinson’s disease based on acoustic analysis of speech. Engineering Applications of Artificial Intelligence, 77, 148–158. https://doi.org/10.1016/j.engappai.2018.09.007
Das, R. (2010). A comparison of multiple classification methods for diagnosis of Parkinson disease. Expert Systems with Applications, 37(2), 1568–1572. https://doi.org/10.1016/j.eswa.2009.06.040
Dinov, I. D., Heavner, B., Tang, M., Glusman, G., Chard, K., Darcy, M., Madduri, R., Pa, J., Spino, C., Kesselman, C., Foster, I., Deutsch, E. W., Price, N. D., Van Horn, J. D., Ames, J., Clark, K., Hood, L., Hampstead, B. M., Dauer, W., & Toga, A. W. (2016). Predictive big data analytics: A study of Parkinson’s disease using large, complex, heterogeneous, incongruent, multi-source and incomplete observations. PLoS ONE, 11(8), e0157077. https://doi.org/10.1371/journal.pone.0157077
Drotár, P., Mekyska, J., Rektorová, I., Masarová, L., Smékal, Z., & Faundez-Zanuy, M. (2015). Decision support framework for Parkinson’s disease based on novel handwriting markers. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 23(3), 508–516. https://doi.org/10.1109/TNSRE.2014.2327298
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. Artificial Intelligence in Medicine, 67, 39–46. https://doi.org/10.1016/j.artmed.2016.01.004
El Maachi, I., Bilodeau, G.-A., & Bouachir, W. (2020). Deep 1D-ConvNet for accurate Parkinson disease detection and severity prediction from gait. Expert Systems with Applications, 143, Article 113075. https://doi.org/10.1016/j.eswa.2019.113075
Gao S, Wang Z, Huang Y, Yang G, Wang Y, Yi Y, Zhou Q, Jian X, Zhao G, Li B, Xu L, Xia K, Tang B, Li J. Early detection of Parkinson's disease through multiplex blood and urine biomarkers prior to clinical diagnosis. NPJ Parkinsons Dis. 2025 Feb 25;11(1):35. doi: 10.1038/s41531-025-00888-2
Gunduz, H. (2019). Deep learning-based Parkinson’s disease classification using vocal feature sets. IEEE Access, 7, 115540–115551. https://doi.org/10.1109/ACCESS.2019.2935131
Gupta, U., Bansal, H., & Joshi, D. (2020). An improved sex-specific and age-dependent classification model for Parkinson’s diagnosis using handwriting measurement. Computer Methods and Programs in Biomedicine, 189, Article 105305. https://doi.org/10.1016/j.cmpb.2020.105305
Harrou, F., Sun, Y., Hering, A. S., & Madakyaru, M. (2020). Statistical process monitoring using advanced data-driven and deep learning approaches: Theory and practical applications. Elsevier.
Iakovakis, D., Mastoras, R. E., Hadjidimitriou, S., Charisis, V., Bostanjopoulou, S., Katsarou, Z., ... & Hadjileontiadis, L. J. (2020, July). Smartwatch-based activity analysis during sleep for early Parkinson’s disease detection. In 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC) (pp. 4326-4329). IEEE.
Illner, V., Sovka, P., & Rusz, J. (2020). Validation of freely available pitch detection algorithms across various noise levels in assessing speech captured by smartphone in Parkinson’s disease. Biomedical Signal Processing and Control, 58, Article 101831. https://doi.org/10.1016/j.bspc.2019.101831
Lahmiri, S., & Shmuel, A. (2019). Detection of Parkinson’s disease based on voice patterns ranking and optimized support vector machine. Biomedical Signal Processing and Control, 49, 427–433. https://doi.org/10.1016/j.bspc.2018.11.019
Little, M. A., McSharry, P. E., Hunter, E. J., Spielman, J., & Ramig, L. O. (2009). Suitability of dysphonia measurements for telemonitoring of Parkinson’s disease. IEEE Transactions on Biomedical Engineering, 56(4), 1015–1022. https://doi.org/10.1109/TBME.2008.2005954
M. Young, “The Technical Writer's Handbook,” Mill Valley, CA: University Science, 1989.
Mamun, K. A., Alhussein, M., Sailunaz, K., & Islam, M. S. (2017). Cloud based framework for Parkinson’s disease diagnosis and monitoring system for remote healthcare applications. Future Generation Computer Systems, 66, 36-47.
Prashanth, R., & Roy, S. D. (2018). Early detection of Parkinson’s disease through patient questionnaire and predictive modelling. International Journal of Medical Informatics, 119, 75–87. https://doi.org/10.1016/j.ijmedinf.2018.08.010
Prashanth, R., Roy, S. D., Mandal, P. K., & Ghosh, S. (2016). High-accuracy detection of early Parkinson’s disease through multimodal features and machine learning. International Journal of Medical Informatics, 90, 13–21. https://doi.org/10.1016/j.ijmedinf.2016.03.001
Sajal, M. S. R., Ehsan, M. T., Vaidyanathan, R., Wang, S., Aziz, T., & Mamun, K. A. (2020, September). UPDRS Label Assignment by Analyzing Accelerometer Sensor Data Collected from Conventional Smartphones. In International Conference on Brain Informatics (pp. 173-182). Cham: Springer International Publishing.
Sharma, S., Moon, C. S., Khogali, A., Haidous, A., Chabenne, A., Ojo, C., Jelebinkov, M., Kurdi, Y., & Ebadi, M. (2013). Biomarkers in Parkinson’s disease (recent update). Neurochemistry International, 63(3), 201–229. https://doi.org/10.1016/j.neuint.2013.06.005
Sigcha, L., Pavón, I., Costa, N., Costa, S., Gago, M., Arezes, P., ... & De Arcas, G. (2021). Automatic resting tremor assessment in Parkinson’s disease using smartwatches and multitask convolutional neural networks. Sensors, 21(1), 291.
Silveira-Moriyama, L., Petrie, A., Williams, D. R., Evans, A., Katzenschlager, R., Barbosa, E. R., & Lees, A. J. (2009). The use of a color coded probability scale to interpret smell tests in suspected parkinsonism. Movement Disorders, 24(8), 1144–1153. https://doi.org/10.1002/mds.22508
Singh, N., Pillay, V., & Choonara, Y. E. (2007). Advances in the treatment of Parkinson’s disease. Progress in Neurobiology, 81(1), 29–44. https://doi.org/10.1016/j.pneurobio.2006.11.009
Solana-Lavalle, G., Galán-Hernández, J.-C., & Rosas-Romero, R. (2020). Automatic Parkinson disease detection at early stages as a pre-diagnosis tool by using classifiers and a small set of vocal features. Biocybernetics and Biomedical Engineering, 40(1), 505–516. https://doi.org/10.1016/j.bbe.2020.01.005
Tsanas, A., Little, M. A., McSharry, P. E., & Ramig, L. O. (2010). Accurate telemonitoring of Parkinson’s disease progression by noninvasive speech tests. IEEE Transactions on Biomedical Engineering, 57(4), 884–893. https://doi.org/10.1109/TBME.2009.2036000
Valenza, G., Orsolini, S., Diciotti, S., Citi, L., Scilingo, E. P., Guerrisi, M., Danti, S., Lucetti, C., Tessa, C., Barbieri, R., & Toschi, N. (2016). Assessment of spontaneous cardiovascular oscillations in Parkinson’s disease. Biomedical Signal Processing and Control, 26, 80–89. https://doi.org/10.1016/j.bspc.2015.11.006
Wagner, A., Fixler, N., & Resheff, Y. S. (2017, March). A wavelet-based approach to monitoring Parkinson’s disease symptoms. In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 5980–5984). IEEE. https://doi.org/10.1109/ICASSP.2017.7953264
Wang, W., Lee, J., Harrou, F., & Sun, Y. (2020). Early detection of Parkinson’s disease using deep learning and machine learning. IEEE access, 8, 147635-147646.
Zhao, A., Qi, L., Li, J., Dong, J., & Yu, H. (2018). A hybrid spatio-temporal model for detection and severity rating of Parkinson’s disease from gait data. Neurocomputing, 315, 1–8. https://doi.org/10.1016/j.neucom.2018.06.074
Recommended articles
Impact of Internet of Things (IoT) on Healthcare in Transforming Patient Care and Overcoming Operational Challenges
2
Save
Save
0
Citation
Citation
21
View
View
0
Share
Share