Gradient boosting DD-MLP Net: An ensemble learning model using near-infrared spectroscopy to classify after-stroke dyskinesia degree during exercise
Jianbin Liang
School of Mechatronic Engineering and Automation, Foshan University, Foshan, China
Search for more papers by this authorMinjie Bian
Department of Rehabilitation Medicine, The Seventh Affiliated Hospital, Sun Yat-sen University, Shenzhen, China
Search for more papers by this authorHucheng Chen
School of Mechatronic Engineering and Automation, Foshan University, Foshan, China
Search for more papers by this authorKecheng Yan
School of Mechatronic Engineering and Automation, Foshan University, Foshan, China
Search for more papers by this authorYanmei Qin
School of Medicine, Foshan University, Foshan, China
Search for more papers by this authorDongyang Wang
School of Mechatronic Engineering and Automation, Foshan University, Foshan, China
Search for more papers by this authorChunjie Zhu
School of Mechatronic Engineering and Automation, Foshan University, Foshan, China
Search for more papers by this authorWenzhu Huang
The Fifth Affiliated Hospital of Foshan, Foshan University, Foshan, China
Search for more papers by this authorLi Yi
School of Mechatronic Engineering and Automation, Foshan University, Foshan, China
Search for more papers by this authorCorresponding Author
Jinyan Sun
School of Medicine, Foshan University, Foshan, China
Correspondence
Jinyan Sun, School of Medicine, Foshan University, Foshan, 33 Guangyun Load, Foshan 528225, China.
Email: [email protected]
Yurong Mao, Department of Rehabilitation Medicine, The Seventh Affiliated Hospital, Sun Yat-sen University, 628 Zhenyuan Road, Shenzhen 517108, China.
Email: [email protected]
Zhifeng Hao, College of Science, Shantou University, 243 Daxue Road, Shantou 515063, China.
Email: [email protected]
Search for more papers by this authorCorresponding Author
Yurong Mao
Department of Rehabilitation Medicine, The Seventh Affiliated Hospital, Sun Yat-sen University, Shenzhen, China
Correspondence
Jinyan Sun, School of Medicine, Foshan University, Foshan, 33 Guangyun Load, Foshan 528225, China.
Email: [email protected]
Yurong Mao, Department of Rehabilitation Medicine, The Seventh Affiliated Hospital, Sun Yat-sen University, 628 Zhenyuan Road, Shenzhen 517108, China.
Email: [email protected]
Zhifeng Hao, College of Science, Shantou University, 243 Daxue Road, Shantou 515063, China.
Email: [email protected]
Search for more papers by this authorCorresponding Author
Zhifeng Hao
College of Science, Shantou University, Shantou, China
Correspondence
Jinyan Sun, School of Medicine, Foshan University, Foshan, 33 Guangyun Load, Foshan 528225, China.
Email: [email protected]
Yurong Mao, Department of Rehabilitation Medicine, The Seventh Affiliated Hospital, Sun Yat-sen University, 628 Zhenyuan Road, Shenzhen 517108, China.
Email: [email protected]
Zhifeng Hao, College of Science, Shantou University, 243 Daxue Road, Shantou 515063, China.
Email: [email protected]
Search for more papers by this authorJianbin Liang
School of Mechatronic Engineering and Automation, Foshan University, Foshan, China
Search for more papers by this authorMinjie Bian
Department of Rehabilitation Medicine, The Seventh Affiliated Hospital, Sun Yat-sen University, Shenzhen, China
Search for more papers by this authorHucheng Chen
School of Mechatronic Engineering and Automation, Foshan University, Foshan, China
Search for more papers by this authorKecheng Yan
School of Mechatronic Engineering and Automation, Foshan University, Foshan, China
Search for more papers by this authorYanmei Qin
School of Medicine, Foshan University, Foshan, China
Search for more papers by this authorDongyang Wang
School of Mechatronic Engineering and Automation, Foshan University, Foshan, China
Search for more papers by this authorChunjie Zhu
School of Mechatronic Engineering and Automation, Foshan University, Foshan, China
Search for more papers by this authorWenzhu Huang
The Fifth Affiliated Hospital of Foshan, Foshan University, Foshan, China
Search for more papers by this authorLi Yi
School of Mechatronic Engineering and Automation, Foshan University, Foshan, China
Search for more papers by this authorCorresponding Author
Jinyan Sun
School of Medicine, Foshan University, Foshan, China
Correspondence
Jinyan Sun, School of Medicine, Foshan University, Foshan, 33 Guangyun Load, Foshan 528225, China.
Email: [email protected]
Yurong Mao, Department of Rehabilitation Medicine, The Seventh Affiliated Hospital, Sun Yat-sen University, 628 Zhenyuan Road, Shenzhen 517108, China.
Email: [email protected]
Zhifeng Hao, College of Science, Shantou University, 243 Daxue Road, Shantou 515063, China.
Email: [email protected]
Search for more papers by this authorCorresponding Author
Yurong Mao
Department of Rehabilitation Medicine, The Seventh Affiliated Hospital, Sun Yat-sen University, Shenzhen, China
Correspondence
Jinyan Sun, School of Medicine, Foshan University, Foshan, 33 Guangyun Load, Foshan 528225, China.
Email: [email protected]
Yurong Mao, Department of Rehabilitation Medicine, The Seventh Affiliated Hospital, Sun Yat-sen University, 628 Zhenyuan Road, Shenzhen 517108, China.
Email: [email protected]
Zhifeng Hao, College of Science, Shantou University, 243 Daxue Road, Shantou 515063, China.
Email: [email protected]
Search for more papers by this authorCorresponding Author
Zhifeng Hao
College of Science, Shantou University, Shantou, China
Correspondence
Jinyan Sun, School of Medicine, Foshan University, Foshan, 33 Guangyun Load, Foshan 528225, China.
Email: [email protected]
Yurong Mao, Department of Rehabilitation Medicine, The Seventh Affiliated Hospital, Sun Yat-sen University, 628 Zhenyuan Road, Shenzhen 517108, China.
Email: [email protected]
Zhifeng Hao, College of Science, Shantou University, 243 Daxue Road, Shantou 515063, China.
Email: [email protected]
Search for more papers by this authorJianbin Liang, Minjie Bian and Hucheng Chen have contributed equally to this work.
Abstract
This study aims to develop an automatic assessment of after-stroke dyskinesias degree by combining machine learning and near-infrared spectroscopy (NIRS). Thirty-five subjects were divided into five stages (healthy, patient: Brunnstrom stages 3, 4, 5, 6). NIRS was used to record the muscular hemodynamic responses from bilateral femoris (biceps brachii) muscles during passive and active upper (lower) limbs circular exercise. We used the D-S evidence theory to conduct feature information fusion and established a Gradient Boosting DD-MLP Net model, combining the dendrite network and multilayer perceptron, to realize automatic dyskinesias degree evaluation. Our model classified the upper limb dyskinesias with high accuracy: 98.91% under the passive mode and 98.69% under the active mode, and classified the lower limb dyskinesias with high accuracy: 99.45% and 99.63% under the passive and active modes, respectively. Our model combined with NIRS has great potential in monitoring the after-stroke dyskinesias degree and guiding rehabilitation training.
CONFLICT OF INTEREST STATEMENT
The authors declare no financial or commercial conflict of interest.
Open Research
DATA AVAILABILITY STATEMENT
Data available on request due to privacy/ethical restrictions.
REFERENCES
- 1Y.-J. Wang, Z. X. Li, H. Q. Gu, Y. Zhai, Y. Jiang, X. Q. Zhao, Y. L. Wang, X. Yang, C. J. Wang, X. Meng, H. Li, L. P. Liu, J. Jing, J. Wu, A. D. Xu, Q. Dong, D. Wang, J. Z. Zhao, Stroke Vasc. Neurol. 2020, 5, 211.
- 2A. G. Thompson-Butel, G. Lin, C. T. Shiner, P. A. McNulty, Neurorehabil. Neural Repair 2015, 29, 341.
- 3L. Liparulo, Z. Zhang, M. Panella, X. Gu, Q. Fang, Med. Biol. Eng. Comput. 2017, 55, 1367.
- 4S.-H. Lee, J. Cui, L. Liu, M.-C. Su, L. Zheng, S.-C. Yeh, IEEE Access 2021, 9, 65871.
- 5K. Ding, B. Zhang, Z. Ling, J. Chen, L. Guo, D. Xiong, J. Wang, Sensors 2022, 22, 3368.
10.3390/s22093368 Google Scholar
- 6S. Zian, S. A. Kareem, K. D. Varathan, IEEE Access 2021, 9, 87434.
- 7J. G. Carbonell, ACM SIGART Bull. 1981, 77, 29.
10.1145/1056743.1056744 Google Scholar
- 8S. Agarwal, C. R. Chowdary, Expert Syst. Appl. 2020, 146, 113160.
- 9S. Özöğür-Akyüz, B. Ç. Otar, P. K. Atas, Comput. Intell. 2020, 36, 297.
- 10Z. Chen, Q. Li, R. Li, H. Zhao, Z. Li, Y. Zhou, R. Bian, X. Jin, M. Lou, R. Bai, Quant. Imaging Med. Surg. 2021, 11, 3978.
- 11C. Zhu, Z. Xu, Y. Gu, S. Zheng, X. Sun, J. Cao, B. Song, J. Jin, Y. Liu, X. Wen, S. Cheng, J. Li, X. Wu, J. Hosp. Infect. 2022, 122, 96.
- 12S. Badirli, X. Liu, Z. Xing, A. Bhowmik, K. Doan, S. Keerthi. arXiv e-prints: abs/2002.07971, 2020.
- 13V. Vagné, E. le Bars, J. Deverdun, O. Rossel, S. Perrey, V. Costalat, D. Guiraud, Comput. Biol. Med. 2020, 118, 103638.
- 14M. Miles, A. Rodrigues, S. Tajali, Y. Xiong, A. Orchanian-Cheff, W. D. Reid, D. Rozenberg, Chron. Respir. Dis. 2021, 18, 147997312199349.
10.1177/1479973121993494 Google Scholar
- 15K. L. Zaleski, B. D. Kussman, J. Cardiothorac. Vasc. Anesth. 2020, 34, 489.
- 16J. Sun, D. Wang, S. Chen, R. Pang, H. Liu, J. Wang, Y. Zhang, C. Wang, A. Yang, Med. Nov. Technol. Devices 2021, 11, 100083.
10.1016/j.medntd.2021.100083 Google Scholar
- 17J. Sun, R. Pang, S. Chen, H. Chen, Y. Xie, D. Chen, K. Wu, J. Liang, K. Yan, Z. Hao, J. Innov. Opt. Health Sci. 2021, 14, 2130006.
- 18 H. Chen, J. Liang, W. Huang, A. Yang, R. Pang, C. Zhao, K. Wu, C. Wang, K. Yan, Y. Zhang, S. Lin, Y. Xie, Y. Wu, J. Sun, Biomed. Opt. Express. 2022, 13, 4737.
- 19 R. Pang, D. Wang, T. S. R. Chen, A. Yang, L. Yi, S. Chen, J. Wang, K. Wu, C. Zhao, H. Liu, Y. Ai, A. Yang, J. Sun, J Biophotonics. 2022, 15, e202200014.
- 20P. Kadamati, J. J. Sugar, B. J. Quirk, S. Mehrvar, G. G. Chelimsky, H. T. Whelan, T. C. Chelimsky, M. Ranji, J. Innov. Opt. Health Sci. 2018, 11, 1850026.
- 21A. Scano, I. Pirovano, M. E. Manunza, L. Spinelli, D. Contini, A. Torricelli, R. Re, Opt. Express 2020, 11, 7357.
- 22V. Verratti, D. Bondi, G. Mulliri, G. Ghiani, A. Crisafulli, T. Pietrangelo, M. E. Marinozzi, P. Cerretelli, Front. Physiol. 2020, 11, 607616.
- 23S. K. Rout, M. Sahani, P. K. Dash, P. K. Biswal, Comput. Biol. Med. 2021, 132, 104299.
- 24M. Radman, M. Moradi, A. Chaibakhsh, M. Kordestani, M. Saif, IEEE Sens. J. 2021, 21, 3533.
- 25G. Wu, N. Yan, K. Choi, H. Jung, K. Cao, Adv. Mech. Eng. 2021, 13, 168781402110671.
10.1177/16878140211067155 Google Scholar
- 26Y. Chen, Y. Tang, Entropy 2021, 23, 402.
- 27P. Manganotti, S. Patuzzo, F. Cortese, A. Palermo, N. Smania, A. Fiaschi, Clin. Neurophysiol. 2002, 113, 936.
- 28C. English, H. McLennan, K. Thoirs, A. Coates, J. Bernhardt, Int. J. Stroke 2010, 5, 395.
- 29G. Liu, J. Wang, IEEE T CYBERNETICS. 2020, 52, 13774.
- 30C. Xiang, S. Ding, T. H. Lee, IEEE Trans. Neural Netw. 2005, 16, 84.
- 31D. Hendrycks, K. Gimpel. arXiv preprint. arXiv:1606.08415, 2016.
- 32T. Chen, C. Guestrin, Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, ACM, San Francisco, California, USA, 2016, p. 785.
10.1145/2939672.2939785 Google Scholar
- 33M. Reggio, D. Godin, Int. J. Comput. Math. 2000, 75, 465.
- 34J. Yan, Y. Xu, Q. Cheng, S. Jiang, Q. Wang, Y. Xiao, C. Ma, J. Yan, X. Wang, Genome Biol. 2021, 22, 271.
- 35A. V. Dorogush, V. Ershov, A. Gulin, Dorogush. arXiv: abs/1810.11363, 2018.
- 36S. Ferrante, D. Contini, L. Spinelli, A. Pedrocchi, A. Torricelli, F. Molteni, G. Ferrigno, R. Cubeddu, J. Biomed. Opt. 2009, 14, 11.
10.1117/1.3183802 Google Scholar
- 37J. Purton, J. Sim, S. M. Hunter, Disabil. Rehabil. 2022, 1.
- 38H. Wen, Z. Dou, S. Cheng, W. Qiu, L. Xie, H. Yang, Top. Stroke Rehabil. 2014, 21, 163.
- 39S.-H. Ciou, Y.-S. Hwang, C.-C. Chen, S.-C. Chen, S.-W. Chou, Y.-L. Chen, J. Phys. Ther. Sci. 2015, 27, 3855.
- 40K. Y. Jonsdottir, L. Østergaard, K. Mouridsen, Stroke 2009, 40, 3006.
