Forecasting the Walking Assistance Rehabilitation Level of Stroke Patients Using Artificial Intelligence

Kanghyeon Seo; Bokjin Chung; Hamsa Priya Panchaseelan; TaeWoo Kim; Hyejung Park; Byungmo Oh; Minho Chun; Sunjae Won; Donkyu Kim; Jaewon Beom; Doyoung Jeon; Jihoon Yang

doi:10.3390/diagnostics11061096

journal article Open Access Jun 15, 2021

Forecasting the Walking Assistance Rehabilitation Level of Stroke Patients Using Artificial Intelligence

Kanghyeon Seo

Bokjin Chung Hamsa Priya Panchaseelan TaeWoo Kim

Hyejung Park Byungmo Oh Minho Chun Sunjae Won Donkyu Kim Jaewon Beom

Doyoung Jeon Jihoon Yang

Diagnostics Vol. 11 No. 6 pp. 1096 · MDPI AG

View at Publisher Save 10.3390/diagnostics11061096

Abstract

Cerebrovascular accidents (CVA) cause a range of impairments in coordination, such as a spectrum of walking impairments ranging from mild gait imbalance to complete loss of mobility. Patients with CVA need personalized approaches tailored to their degree of walking impairment for effective rehabilitation. This paper aims to evaluate the validity of using various machine learning (ML) and deep learning (DL) classification models (support vector machine, Decision Tree, Perceptron, Light Gradient Boosting Machine, AutoGluon, SuperTML, and TabNet) for automated classification of walking assistant devices for CVA patients. We reviewed a total of 383 CVA patients’ (1623 observations) prescription data for eight different walking assistant devices from five hospitals. Among the classification models, the advanced tree-based classification models (LightGBM and tree models in AutoGluon) achieved classification results of over 90% accuracy, recall, precision, and F1-score. In particular, AutoGluon not only presented the highest predictive performance (almost 92% in accuracy, recall, precision, and F1-score, and 86.8% in balanced accuracy) but also demonstrated that the classification performances of the tree-based models were higher than that of the other models on its leaderboard. Therefore, we believe that tree-based classification models have potential as practical diagnosis tools for medical rehabilitation.

Topics

No keywords indexed for this article. Browse by subject →

References

54

[1]

Bornstein "Rationality in medical decision making: A review of the literature on doctors’ decision-making biases" J. Eval. Clin. Pract. (2001) 10.1046/j.1365-2753.2001.00284.x

[2]

Deep Residual Learning for Image Recognition

Kaiming He, Xiangyu Zhang, Shaoqing Ren et al.

2016 IEEE Conference on Computer Vision and Patter... 10.1109/cvpr.2016.90

[3]

Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv.

[4]

Mastering the game of Go without human knowledge

David Silver, Julian Schrittwieser, Karen Simonyan et al.

Nature 2017 10.1038/nature24270

[5]

Mnih, V., Kavukcuoglu, K., Silver, D., Graves, A., Antonoglou, I., Wierstra, D., and Riedmiller, M. (2013). Playing atari with deep reinforcement learning. arXiv.

[6]

Vinyals "Grandmaster level in StarCraft II using multi-agent reinforcement learning" Nature (2019) 10.1038/s41586-019-1724-z

[7]

Charan, S., Khan, M.J., and Khurshid, K. (2018, January 3–4). Breast cancer detection in mammograms using convolutional neural network. Proceedings of the 2018 International Conference on Computing, Mathematics and Engineering Technologies (iCoMET), Sukkur, Pakistan. 10.1109/icomet.2018.8346384

[8]

Mathe "Model-based design of clinical information systems" Methods Inf. Med. (2008) 10.3414/me9121

[9]

Abedi "Novel screening tool for stroke using artificial neural network" Stroke (2017) 10.1161/strokeaha.117.017033

[10]

Park, S.J., Hussain, I., Hong, S., Kim, D., Park, H., and Benjamin, H.C.M. (2020, January 4–6). Real-time Gait Monitoring System for Consumer Stroke Prediction Service. Proceedings of the 2020 IEEE International Conference on Consumer Electronics (ICCE), Las Vegas, NV, USA. 10.1109/icce46568.2020.9043098

[11]

Wei, X., Zhang, X., and Yi, P. (2012, January 5–8). Design of control system for elderly-assistant & walking-assistant robot based on fuzzy adaptive method. Proceedings of the 2012 IEEE International Conference on Mechatronics and Automation, Chengdu, China. 10.1109/icma.2012.6285664

[12]

Lozano-Quilis, J.A., Gil-Gomez, H., Gil-Gómez, J.A., Albiol-Perez, S., Palacios, G., Fardoum, H.M., and Mashat, A.S. (2013, January 5–8). Virtual reality system for multiple sclerosis rehabilitation using KINECT. Proceedings of the 2013 7th International Conference on Pervasive Computing Technologies for Healthcare and Workshops, Venice, Italy. 10.4108/icst.pervasivehealth.2013.252208

[13]

Scrutinio "Machine learning to predict mortality after rehabilitation among patients with severe stroke" Sci. Rep. (2020) 10.1038/s41598-020-77243-3

[14]

Mannini, A., Trojaniello, D., Cereatti, A., and Sabatini, A.M. (2016). A machine learning framework for gait classification using inertial sensors: Application to elderly, post-stroke and huntington’s disease patients. Sensors, 16. 10.3390/s16010134

[15]

Harari "Inpatient stroke rehabilitation: Prediction of clinical outcomes using a machine-learning approach" J. Neuroeng. Rehabil. (2020) 10.1186/s12984-020-00704-3

[16]

Kao, M.Y. (2008). Support Vector Machines. Encyclopedia of Algorithms, Springer. 10.1007/978-3-642-27848-8

[17]

An introduction to hidden Markov models

L. Rabiner, B. Juang

IEEE ASSP Magazine 1986 10.1109/massp.1986.1165342

[18]

Regression Shrinkage and Selection Via the Lasso

Robert Tibshirani

Journal of the Royal Statistical Society Series B:... 1996 10.1111/j.2517-6161.1996.tb02080.x

[19]

SMOTE: Synthetic Minority Over-sampling Technique

N. V. Chawla, K. W. Bowyer, L. O. Hall et al.

Journal of Artificial Intelligence Research 2002 10.1613/jair.953

[20]

Two Modifications of CNN

IEEE Transactions on Systems, Man, and Cybernetics 1976 10.1109/tsmc.1976.4309452

[21]

A study of the behavior of several methods for balancing machine learning training data

Gustavo E. A. P. A. Batista, Ronaldo C. Prati, Maria Carolina Monard

ACM SIGKDD Explorations Newsletter 2004 10.1145/1007730.1007735

[22]

Nogueira "Imbalanced-learn: A Python Toolbox to Tackle the Curse of Imbalanced Datasets in Machine Learning" J. Mach. Learn. Res. (2017)

[23]

Pedregosa "Scikit-learn: Machine Learning in Python" J. Mach. Learn. Res. (2011)

[24]

Buitinck, L., Louppe, G., Blondel, M., Pedregosa, F., Mueller, A., Grisel, O., Niculae, V., Prettenhofer, P., Gramfort, A., and Grobler, J. (2013). API design for machine learning software: Experiences from the scikit-learn project. arXiv.

[25]

Gallant "Perceptron-based learning algorithms" IEEE Trans. Neural Netw. (1990) 10.1109/72.80230

[26]

Safavian "A survey of decision tree classifier methodology" IEEE Trans. Syst. Man Cybern. (1991) 10.1109/21.97458

[27]

Ke "Lightgbm: A highly efficient gradient boosting decision tree" Adv. Neural Inf. Process. Syst. (2017)

[28]

AutoML: A survey of the state-of-the-art

Xin He, Kaiyong Zhao, Xiaowen Chu

Knowledge-Based Systems 2019 10.1016/j.knosys.2020.106622

[29]

Erickson, N., Mueller, J., Shirkov, A., Zhang, H., Larroy, P., Li, M., and Smola, A. (2020). AutoGluon-Tabular: Robust and Accurate AutoML for Structured Data. arXiv.

[30]

Sun, B., Yang, L., Zhang, W., Lin, M., Dong, P., Young, C., and Dong, J. (2019, January 16–17). Supertml: Two-dimensional word embedding for the precognition on structured tabular data. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, Long Beach, CA, USA. 10.1109/cvprw.2019.00360

[31]

Arik, S.O., and Pfister, T. (2019). Tabnet: Attentive interpretable tabular learning. arXiv.

[32]

Murphy, K.P. (2012). Machine Learning: A Probabilistic Perspective, MIT Press.

[33]

Schmarje, L., Santarossa, M., Schröder, S.M., and Koch, R. (2020). A survey on semi-, self-and unsupervised techniques in image classification. arXiv. 10.1109/access.2021.3084358

[34]

Dorogush, A.V., Ershov, V., and Gulin, A. (2018). CatBoost: Gradient boosting with categorical features support. arXiv.

[35]

Ho, T.K. (1995, January 14–16). Random decision forests. Proceedings of the 3rd International Conference on Document Analysis and Recognition, Montreal, QC, Canada.

[36]

Extremely randomized trees

Pierre Geurts, Damien Ernst, Louis Wehenkel

Machine Learning 2006 10.1007/s10994-006-6226-1

[37]

Karthiga "Early prediction of heart disease using decision tree algorithm" Int. J. Adv. Res. Basic Eng. Sci. Technol. (2017)

[38]

Kassirer "Clinical problem solving: A behavioral analysis" Ann. Intern. Med. (1978) 10.7326/0003-4819-89-2-245

[39]

Gruppen "Medical student use of history and physical information in diagnostic reasoning" Arthritis Rheum. J. Am. Coll. Rheumatol. (1993) 10.1002/art.1790060204

[40]

Sherbino "How expert clinicians intuitively recognize a medical diagnosis" Am. J. Med. (2017) 10.1016/j.amjmed.2017.01.045

[41]

Middleton, K., Butt, M., Hammerla, N., Hamblin, S., Mehta, K., and Parsa, A. (2016). Sorting out symptoms: Design and evaluation of the’babylon check’automated triage system. arXiv.

[42]

Support-vector networks

Corinna Cortes, Vladimir Vapnik

Machine Learning 1995 10.1007/bf00994018

[43]

Induction of decision trees

J. R. Quinlan

Machine Learning 1986 10.1007/bf00116251

[44]

Quinlan, J.R. (2014). C4.5: Programs for Machine Learning, Elsevier.

[45]

Breiman, L., Friedman, J., Stone, C.J., and Olshen, R.A. (1984). Classification and Regression Trees, CRC Press.

[46]

The perceptron: A probabilistic model for information storage and organization in the brain.

F. Rosenblatt

Psychological Review 1958 10.1037/h0042519

[47]

Bishop, C.M. (2006). Pattern Recognition and Machine Learning, Springer.

[48]

Stochastic gradient boosting

Jerome H. Friedman

Computational Statistics & Data Analysis 2002 10.1016/s0167-9473(01)00065-2

[49]

The Elements of Statistical Learning

Trevor Hastie, Robert Tibshirani, Jerome Friedman

Springer Series in Statistics 10.1007/978-0-387-84858-7

[50]

Ridgeway "Generalized Boosted Models: A guide to the gbm package" Update (2007)

Showing 50 of 54 references

Metrics

19

Citations

54

References

Details

Published: Jun 15, 2021
Vol/Issue: 11(6)
Pages: 1096
License: View

Authors

K

Kanghyeon Seo

Machine Learning Research Laboratory, Department of Computer Science and Engineering, Sogang University, 35 Baekbeom-ro, Mapo-gu, Seoul 04107, Korea

B

Bokjin Chung

Machine Learning Research Laboratory, Department of Computer Science and Engineering, Sogang University, 35 Baekbeom-ro, Mapo-gu, Seoul 04107, Korea

H

Hamsa Priya Panchaseelan

Machine Learning Research Laboratory, Department of Computer Science and Engineering, Sogang University, 35 Baekbeom-ro, Mapo-gu, Seoul 04107, Korea

T

TaeWoo Kim

Department of Rehabilitation Medicine, National Traffic Injury Rehabilitation Hospital, 260 Jungang-ro, Yangpyeong-gun, Gyunggi-do 12564, Korea

H

Hyejung Park

Department of Rehabilitation Medicine, National Traffic Injury Rehabilitation Hospital, 260 Jungang-ro, Yangpyeong-gun, Gyunggi-do 12564, Korea

B

Byungmo Oh

Department of Rehabilitation Medicine, National Traffic Injury Rehabilitation Hospital, 260 Jungang-ro, Yangpyeong-gun, Gyunggi-do 12564, Korea; Department of Rehabilitation Medicine, Seoul National University Hospital, Seoul National University College of Medicine, 101 Daehak-ro, Jongno-gu, Seoul 03080, Korea

M

Minho Chun

Asan Medical Center, Department of Rehabilitation Medicine, University of Ulsan College of Medicine, 88 Olympic-ro 43-gil, Songpa-gu, Seoul 05505, Korea

S

Sunjae Won

Department of Rehabiliation Medicine, Yeouido St. Mary’s Hospital, College of Medicine, The Catholic University of Korea, 10 63-ro, Yeongdeungpo-gu, Seoul 07345, Korea

D

Donkyu Kim

Department of Physical Medicine and Rehabilitation, Chung-Ang University Hospital, Chung-Ang University College of Medicine, 102 Heukseok-ro, Dongjak-gu, Seoul 06973, Korea

J

Jaewon Beom

Department of Rehabilitation Medicine, Seoul National University College of Medicine, Seoul National University Bundang Hospital, 82 Gumi-ro, 173beon-gil, Bundang-gu, Seongnam-si 13620, Gyeonggi-do, Korea

D

Doyoung Jeon

Department of Mechanical Engineering, Sogang University, 35 Baekbeom-ro, Mapo-gu, Seoul 04107, Korea

J

Jihoon Yang

Machine Learning Research Laboratory, Department of Computer Science and Engineering, Sogang University, 35 Baekbeom-ro, Mapo-gu, Seoul 04107, Korea

Funding

The Ministry of Trade, Industry & Energy (MOTIE, Korea) Award: 10076752

Cite This Article

Kanghyeon Seo, Bokjin Chung, Hamsa Priya Panchaseelan, et al. (2021). Forecasting the Walking Assistance Rehabilitation Level of Stroke Patients Using Artificial Intelligence. Diagnostics, 11(6), 1096. https://doi.org/10.3390/diagnostics11061096

Forecasting the Walking Assistance Rehabilitation Level of Stroke Patients Using Artificial Intelligence

You May Also Like