Abstract
This paper presents federated Learning (FL), which is based on wearable devices, and applies the actual leg agility data that has been collected from people living with Parkinson’s disease (PD) to the model. Studies have shown that the implementation of FL can effectively protect the data privacy of PD patients. The classification accuracy of leg agility data is reduced by 2.72% when compared to the conventional method of summarizing all the data. However, it is higher than the model accuracy of each data owner, having increased by 22.68%. Secondly, during the communication process, the upload or download of the model parameters of each terminal node is interrupted for N times at the same time, and it is found that interrupting the upload of parameters reduces the accuracy of the central model. The impact of interrupting the download parameters on the central model is negligible. Then, the communication process of the terminal nodes with different data amounts was interrupted respectively, and it was found that the accuracy of the central model was basically not affected. Finally, noise is introduced to the various parameters in the communication process. The accuracy of the central model begins to gradually deteriorate as soon as the noise intensity reaches 0.012 or higher.
Similar content being viewed by others
Data availability
Our data was acquired from a hospital, and they have not given their permission for researchers to share their data. A small part of the data can be queried via this link: https://github.com/g8329/FL.
References
Aghanavesi S, Bergquist F, Nyholm D, Senek M, Memedi M (2019) Motion sensor-based assessment of Parkinson’s disease motor symptoms during leg agility tests: results from levodopa challenge. IEEE J Biomed Health Inform 24(1):111–119
Ammad-Ud-Din M, Ivannikova E, Khan SA, Oyomno W, Fu Q, Tan KE, Flanagan A (2019) Federated collaborative filtering for privacy-preserving personalized recommendation system. arXiv preprint arXiv:1901.09888
Antonini A, Reichmann H, Gentile G, Garon M, Tedesco C, Frank A, Falkenburger B, Konitsiotis S, Tsamis K, Rigas G et al (2023) Toward objective monitoring of Parkinson’s disease motor symptoms using a wearable device: wearability and performance evaluation of pdmonitor®. Front Neurol 14:1080752
Asci F, Vivacqua G, Zampogna A, D’Onofrio V, Mazzeo A, Suppa A (2022) Wearable electrochemical sensors in Parkinson’s disease. Sensors 22(3):951
Bonawitz K, Ivanov V, Kreuter B, Marcedone A, McMahan HB, Patel S, Ramage, D, Segal A, Seth K (2017) Practical secure aggregation for privacy-preserving machine learning. In: proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security, pp 1175–1191
Brauneck A, Schmalhorst L, Kazemi Majdabadi MM, Bakhtiari M, Völker U, Baumbach J, Baumbach L, Buchholtz G (2023) Federated machine learning, privacy-enhancing technologies, and data protection laws in medical research: scoping review. J Med Internet Res 25:e41588
Brisimi TS, Chen R, Mela T, Olshevsky A, Paschalidis IC, Shi W (2018) Federated learning of predictive models from federated electronic health records. Int J Med Inform 112:59–67
Carissimo C, Cerro G, Debelle H, Packer E, Yarnall A, Rochester L, Alcock L, Ferrigno L, Marino A, Di Libero T, et al (2023) Enhancing remote monitoring and classification of motor state in Parkinson’s disease using wearable technology and machine learning. In: 2023 IEEE International Symposium on Medical Measurements and Applications (MeMeA), pp 1–6. IEEE
Chen F, Luo M, Dong Z, Li Z, He X (2018) Federated meta-learning with fast convergence and efficient communication. arXiv preprint arXiv:1802.07876
Chen M, Mathews R, Ouyang T, Beaufays F (2019) Federated learning of out-of-vocabulary words. arXiv preprint arXiv:1903.10635
Chen Y, Qin X, Wang J, Yu C, Gao W (2020) Fedhealth: a federated transfer learning framework for wearable healthcare. IEEE Intell Syst 35(4):83–93
Chiew A, Mathew D, Kumar CM, Seet E, Imani F, Khademi SH (2023) Anesthetic considerations for cataract surgery in patients with Parkinson’s disease: A narrative review. Anesthesiol Pain Med 13(3)
Galna B, Barry G, Jackson D, Mhiripiri D, Olivier P, Rochester L (2014) Accuracy of the Microsoft Kinect sensor for measuring movement in people with Parkinson’s disease. Gait & Posture 39(4):1062–1068
Geyer RC, Klein T, Nabi M (2017) Differentially private federated learning: a client level perspective. arXiv preprint arXiv:1712.07557
Gudur GK, Perepu SK (2020) Federated learning with heterogeneous labels and models for mobile activity monitoring. arXiv preprint arXiv:2012.02539
Hao M, Li H, Xu G, Liu Z, Chen Z (2020) Privacy-aware and resource-saving collaborative learning for healthcare in cloud computing. In: ICC 2020-2020 IEEE International Conference on Communications (ICC), pp 1–6. IEEE
Hard A, Rao K, Mathews R, Ramaswamy S, Beaufays F, Augenstein S, Eichner H, Kiddon C, Ramage D (2018) Federated learning for mobile keyboard prediction. arXiv preprint arXiv:1811.03604
Hssayeni MD, Jimenez-Shahed J, Burack MA, Ghoraani B (2019) Wearable sensors for estimation of Parkinsonian tremor severity during free body movements. Sensors 19(19):4215
Huang J, Qian F, Guo Y, Zhou Y, Xu Q, Mao ZM, Sen S, Spatscheck O (2013) An in-depth study of lte: effect of network protocol and application behavior on performance. ACM SIGCOMM Comput Commun Rev 43(4):363–374
Johnson JM, Khoshgoftaar TM (2019) Survey on deep learning with class imbalance. J Big Data 6(1):1–54
Kaissis G, Ziller A, Passerat-Palmbach J, Ryffel T, Usynin D, Trask A, Lima I Jr, Mancuso J, Jungmann F, Steinborn MM et al (2021) End-to-end privacy preserving deep learning on multi-institutional medical imaging. Nat Mach Intell 3(6):473–484
Kaissis GA, Makowski MR, Rückert D, Braren RF (2020) Secure, privacy-preserving and federated machine learning in medical imaging. Nat Mach Intell 2(6):305–311
Konečnỳ J, McMahan HB, Ramage D, Richtárik P (2016) Federated optimization: distributed machine learning for on-device intelligence. arXiv preprint arXiv:1610.02527
Kumar R, Khan AA, Kumar J, Golilarz NA, Zhang S, Ting Y, Zheng C, Wang W et al (2021) Blockchain-federated-learning and deep learning models for COVID-19 detection using CT imaging. IEEE Sens J 21(14):16301–16314
Lang AE, Eberly S, Goetz CG, Stebbins G, Oakes D, Marek K, Ravina B, Tanner CM, Shoulson I (2013) Movement disorder society unified Parkinson disease rating scale experiences in daily living: longitudinal changes and correlation with other assessments. Move Disord 28(14):1980–1986
Li T, Sahu AK, Talwalkar A, Smith V (2020) Federated learning: challenges, methods, and future directions. IEEE Signal Process Mag 37(3):50–60
Li W, Milletarì F, Xu D, Rieke N, Hancox J, Zhu W, Baust M, Cheng Y, Ourselin S, Cardoso MJ, et al (2019) Privacy-preserving federated brain tumor segmentation. In: Machine Learning in Medical Imaging: 10th International Workshop, MLMI 2019, Held in Conjunction with MICCAI 2019, Shenzhen, China, October 13, 2019, Proceedings 10. Springer, pp 133–141
Lu M, Poston K, Pfefferbaum A, Sullivan EV, Fei-Fei L, Pohl KM, Niebles JC, Adeli E (2020) Vision-based estimation of mds-updrs gait scores for assessing Parkinson’s disease motor severity. In: Medical Image Computing and Computer Assisted Intervention–MICCAI 2020: 23rd International Conference, Lima, Peru, October 4–8, 2020, Proceedings, Part III 23. Springer, pp 637–647
Mothukuri V, Parizi RM, Pouriyeh S, Huang Y, Dehghantanha A, Srivastava G (2021) A survey on security and privacy of federated learning. Futur Gener Comput Syst 115:619–640
Nguyen DC, Pham QV, Pathirana PN, Ding M, Seneviratne A, Lin Z, Dobre O, Hwang WJ (2022) Federated learning for smart healthcare: a survey. ACM Comput Surv (CSUR) 55(3):1–37
Ramsperger R, Meckler S, Heger T, van Uem J, Hucker S, Braatz U, Graessner H, Berg D, Manoli Y, Serrano JA et al (2016) Continuous leg dyskinesia assessment in Parkinson’s disease-clinical validity and ecological effect. Parkinsonism Relat Disord 26:41–46
Roy AG, Siddiqui S, Pölsterl S, Navab N, Wachinger C (2019) Braintorrent: a peer-to-peer environment for decentralized federated learning. arXiv preprint arXiv:1905.06731
Sheller MJ, Edwards B, Reina GA, Martin J, Pati S, Kotrotsou A, Milchenko M, Xu W, Marcus D, Colen RR et al (2020) Federated learning in medicine: facilitating multi-institutional collaborations without sharing patient data. Sci Rep 10(1):12598
Shokri R, Shmatikov V (2015) Privacy-preserving deep learning. In: Proceedings of the 22nd ACM SIGSAC conference on computer and communications security, pp. 1310–1321
Sigcha L, Borzì L, Amato F, Rechichi I, Ramos-Romero C, Cárdenas A, Gascó L, Olmo G (2023) Deep learning and wearable sensors for the diagnosis and monitoring of Parkinson’s disease: a systematic review. Expert Syst Appl 229:120541
Smith V, Chiang CK, Sanjabi M, Talwalkar AS (2017) Federated multi-task learning. Advances in neural information processing systems 30
Van K (2023) Advances in pathogenesis and treatment of Parkinson’s disease based on abnormal accumulation of alpha-synuclein
Van Berkel C (2009) Multi-core for mobile phones. In: 2009 Design, Automation & Test in Europe Conference & Exhibition. IEEE, pp. 1260–1265
Wang W, Liu F, Yu Lei GB, Li Y (2021) Machine learning assessment method of hand flexibility in patients with Parkinson’s disease. J Shanxi Univ (Nat Sci Edn) 44(01):42–50
Wang W, Pei Y, Wang SH, Manuel Gorrz J, Zhang YD (2023) Pstcnn: explainable COVID-19 diagnosis using PSO-guided self-tuning CNN. Biocell 47(2):373
Wang W, Zhang X, Wang SH, Zhang YD (2022) COVID-19 diagnosis by we-saj. Syst Sci Control Eng 10(1):325–335
Warnat-Herresthal S, Schultze H, Shastry KL, Manamohan S, Mukherjee S, Garg V, Sarveswara R, Händler K, Pickkers P, Aziz NA et al (2021) Swarm learning for decentralized and confidential clinical machine learning. Nature 594(7862):265–270
Wu Q, Chen X, Zhou Z, Zhang J (2020) Fedhome: cloud-edge based personalized federated learning for in-home health monitoring. IEEE Trans Mob Comput 21(8):2818–2832
Yang Q, Liu Y, Chen T, Tong Y (2019) Federated machine learning: concept and applications. ACM Trans Intell Syst Technol (TIST) 10(2):1–19
Yang Q, Liu Y, Cheng Y, Kang Y, Chen T, Yu H (2019) Federated learning, vol. 13. Synthesis Lectures on Artificial Intelligence and Machine Learning
Zhang Y, Deng L, Zhu H, Wang W, Ren Z, Zhou Q, Lu S, Sun S, Zhu Z, Gorriz JM et al (2023) Deep learning in food category recognition. Inform Fusion 98:101859
Zhang Z, Zhang L, Li Q, Wang K, He N, Gao T (2022) Privacy-enhanced momentum federated learning via differential privacy and chaotic system in industrial cyber-physical systems. ISA Trans 128:17–31
Acknowledgements
This research was supported by the National Natural Science Foundation of China (Nos. 61803242, 12231012, 61873154), Special Fund Project for Guiding Local Scientific and Technological Development by the Central Government (No. YDZX20191400002563), Key R & D Projects of Shanxi Province (No. 202003D31011/GZ, 201803D31032), Health Commission of Shanxi Province (No. 2020XM18), Shanxi Key Laboratory (No. 201705D111006), International Cooperation Projects of Shanxi Province, China (No. 201703D421012), Research of Technological Important Programs in the City of Lvliang, China (No. 2022GXYF18).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendix
Appendix
1.1 Feature extraction
The leg agility action uses two sensors, each of which generates triaxial signals in the X, Y, and Z directions, for a total of six signals. Regardless of the signal, it is handled in the same manner. As an illustration, the following section uses the z-axis signal data from the toe position sensor to show how it works. In the first step, the data is normalized, and then each movement cycle of the patient is determined by looking at the z-axis signal, which is the data signal of successfully completing a leg agility movement. The collected data is treated as a node in each cycle, and a time-series complex network model with LPVG is created for each point in each cycle. We can extract four characteristics from the complex network: the global aggregation coefficient, the local aggregation coefficient, the aggregation coefficient entropy, and the deviation value of the node degree value and the time, speed, and amplitude at each action cycle, among others.
The global aggregation coefficient C:
The local aggregation coefficient \(\overline{C}\):
Aggregation coefficient entropy \(E_c\):
the deviation value of the node degree value \(K_{std}\):
\(\tau _\triangle\) represents the number of closed triples in a viewable network. \(\tau\) represents the number of open triples in a viewable network. \(\tau _j\) represents the number of open triples centered on node j in a viewable network. \(\tau _{j,\triangle }\) represents the number of closed triples centered on node j in a viewable network. C(j) represents the aggregation coefficient of node j. M indicates the number of nodes in the network. \(K_j\) represents the degree value of the node j. That is, the number of sides of node j.
Each action cycle time T: the time it takes to do one action,
Speed per action cycle v: \(v=\int _{0}^{T}adt\), where a represents acceleration,
Amplitude per action cycle s: \(s=vT\).
This gives \(2\times 3\times 4=24\) complex network eigenvalues, 2 denotes two sensors, 3 denotes three signals for each sensor, and 4 denotes four characteristics of each signal. And the features of time, speed and amplitude. In this way, a 27-dimensional feature data processed by periodic signal data is obtained.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Guan, B., Yu, L., Li, Y. et al. Assessment of patients with Parkinson’s disease based on federated learning. Int. J. Mach. Learn. & Cyber. 15, 1621–1632 (2024). https://doi.org/10.1007/s13042-023-01986-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13042-023-01986-4