Use of Machine Learning in Stroke Rehabilitation: A Narrative Review

다국어 초록 (Multilingual Abstract)

A narrative review was conducted of machine learning applications and research in the field of stroke rehabilitation. The machine learning models commonly used in medical research include random forest, logistic regression, and deep neural networks. Convolutional neural networks (CNNs), a type of deep neural network, are typically used for image analysis.
Machine learning has been used in stroke rehabilitation to predict recover y of motor function using a large amount of clinical data as input. Recent studies on predicting motor function have trained CNN models using magnetic resonance images as input data together with clinical data to increase the accuracy of motor function prediction models. Additionally, a model interpreting videofluoroscopic swallowing studies was developed and investigated. In the future, we anticipate that machine learning will be actively used to treat stroke patients, such as predicting the occurrence of depression and the recover y of language, cognitive, and sensor y function, as well as prescribing appropriate rehabilitation treatments

참고문헌 (Reference)

1 Giulia A, "extending association rule mining to microbiome pattern analysis : tools and guidelines to support real applications" 1 : 794547-, 2022

2 Chen T, "Xgboost: a scalable tree boosting system" Association for Computing Machinery 785-794, 2016

3 Sperandei S, "Understanding logistic regression analysis" 24 : 12-18, 2014

4 Roshanzamir A, "Transformer-based deep neural network language models for Alzheimer’s disease risk assessment from targeted speech" 21 : 92-, 2021

5 Mendez KM, "Toward collaborative open data science in metabolomics using Jupyter Notebooks and cloud computing" 15 : 125-, 2019

6 Feng MC, "The mortality and the risk of aspiration pneumonia related with dysphagia in stroke patients" 28 : 1381-1387, 2019

7 Wagner M, "The importance of machine learning in autonomous actions for surgical decision making" 2 : 64-79, 2022

8 Chicco D, "The advantages of the Matthews correlation coefficient(MCC)over F1 score and accuracy in binary classification evaluation" 21 : 6-, 2020

9 Chicco D, "The Matthews correlation coefficient(MCC)is more reliable than balanced accuracy, bookmaker informedness, and markedness in two-class confusion matrix evaluation" 14 : 13-, 2021

10 Exarchos I, "Supervised and unsupervised machine learning for automated scoring of sleep-wake and cataplexy in a mouse model of narcolepsy" 43 : zsz272-, 2020

11 Winters-Hilt S, "SVM clustering" 8 (8): S18-, 2007

12 Chen X, "Random forests for genomic data analysis" 99 : 323-329, 2012

13 Mazumdar D, "Random forest similarity maps: a scalable visual representation for global and local interpretation" 10 : 2862-, 2021

14 Pirneskoski J, "Random forest machine learning method outperforms prehospital National Early Warning Score for predicting one-day mortality : a retrospective study" 4 : 100046-, 2020

15 Svetnik V, "Random forest : a classification and regression tool for compound classification and QSAR modeling" 43 : 1947-1958, 2003

16 Gupta VP, "Prognosticating functional outcome after intracerebral hemorrhage : the ICHOP score" 101 : 577-583, 2017

17 Shin H, "Prediction of motor outcome of stroke patients using a deep learning algorithm with brain MRI as input data" 2022

18 Kim JK, "Prediction of ambulatory outcome in patients with corona radiata infarction using deep learning" 11 : 7989-, 2021

19 Meng Y, "Prediction model of hemorrhage transformation in patient with acute ischemic stroke based on multiparametric MRI radiomics and machine learning" 12 : 858-, 2022

20 Liang X, "Predicting post-stroke somatosensory function from resting-state functional connectivity : a feasibility study" 11 : 1388-, 2021

21 Lin WY, "Predicting post-stroke activities of daily living through a machine learning-based approach on initiating rehabilitation" 111 : 159-164, 2018

22 Kim JK, "Practical machine learning model to predict the recovery of motor function in patients with stroke" 85 : 273-279, 2022

23 Kriegeskorte N, "Neural network models and deep learning" 29 : R231-R236, 2019

24 Sulubacak U, "Multimodal machine translation through visuals and speech" 34 : 97-147, 2020

25 Heo J, "Machine learning-based model for prediction of outcomes in acute stroke" 50 : 1263-1265, 2019

26 Janiesch C, "Machine learning and deep learning" 31 : 685-695, 2021

27 Choo YJ, "Machine learning analysis to predict the need for ankle foot orthosis in patients with stroke" 11 : 8499-, 2021

28 Ke G, "Lightgbm : a highly efficient gradient boosting decision tree" 30 : 3146-3154, 2017

29 Choi RY, "Introduction to machine learning, neural networks, and deep learning" 9 : 14-, 2020

30 이하경 ; 송종우, "Introduction to convolutional neural network using Keras; an understanding from a statistician" 한국통계학회 26 (26): 591-610, 2019

31 Chang AC, "Intelligence-based medicine" Academic Press 67-140, 2020

32 Saeed SU, "Image quality assessment for machine learning tasks using meta-reinforcement learning" 78 : 102427-, 2022

33 Awad M, "Efficient learning machines" Apress 2015

34 Shin H, "Development of convolutional neural network model for diagnosing meniscus tear using magnetic resonance image" 23 : 510-, 2022

35 Kim JK, "Deep learning algorithm trained on brain magnetic resonance images and clinical data to predict motor outcomes of patients with corona radiata infarct" 15 : 795553-, 2022

36 Sarker IH, "Deep learning : a comprehensive overview on techniques, taxonomy, applications and research directions" 2 : 420-, 2021

37 Sarker IH, "Deep learning : a comprehensive overview on techniques, taxonomy, applications and research directions" 2 : 420-, 2021

38 LeCun Y, "Deep learning" 521 : 436-444, 2015

39 Kim Jeoung Kun ; Choo Yoo Jin ; Choi Gyu Sang ; Shin Hyunkwang ; Chang Min Cheol ; Park Donghwi, "Deep Learning Analysis to Automatically Detect the Presence of Penetration or Aspiration in Videofluoroscopic Swallowing Study" 대한의학회 37 (37): 1-8, 2022

40 Weis DC, "Data mining PubChem using a support vector machine with the Signature molecular descriptor : classification of factor XIa inhibitors" 27 : 466-475, 2008

41 Rajula HS, "Comparison of conventional statistical methods with machine learning in medicine: diagnosis, drug development, and treatment" 56 : 455-, 2020

42 Mutke MA, "Comparing poor and favorable outcome prediction with machine learning after mechanical thrombectomy in acute ischemic stroke" 13 : 737667-, 2022

43 Pan W, "Cluster analysis : unsupervised learning via supervised learning with a non-convex penalty" 14 : 1865-, 2013

44 Nadkarni P, "Clinical research computing" Academic Press 85-114, 2016

45 González RG, "Clinical MRI of acute ischemic stroke" 36 : 259-271, 2012

46 Denisko D, "Classification and interaction in random forests" 115 : 1690-1692, 2018

47 Hancock JT, "CatBoost for big data : an interdisciplinary review" 7 : 94-, 2020

48 Vaswani A, "Attention is all you need" 30 : 1-11, 2017

49 Keilwagen J, "Area under precision-recall curves for weighted and unweighted data" 9 : e92209-, 2014

50 Huang S, "Applications of support vector machine(SVM)learning in cancer genomics" 15 : 41-51, 2018

51 Jovel J, "An introduction to machine learning approaches for biomedical research" 8 : 771607-, 2021

52 Odegua R, "An empirical study of ensemble techniques (bagging, boosting and stacking)" University of Lagos 1-10, 2019

53 Gates ED, "An efficient magnetic resonance image data quality screening dashboard" 23 : e13557-, 2022