Heejun Kim, Jiwon Shin, Yunhwan Kim, Yongseok Lee, Joshua Sung H You
{"title":"利用临床机器学习模型识别 105 名中风后患者与跌倒相关的最佳平衡因素和机器人辅助步态训练属性。","authors":"Heejun Kim, Jiwon Shin, Yunhwan Kim, Yongseok Lee, Joshua Sung H You","doi":"10.3233/NRE-240116","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Despite the promising effects of robot-assisted gait training (RAGT) on balance and gait in post-stroke rehabilitation, the optimal predictors of fall-related balance and effective RAGT attributes remain unclear in post-stroke patients at a high risk of fall.</p><p><strong>Objective: </strong>We aimed to determine the most accurate clinical machine learning (ML) algorithm for predicting fall-related balance factors and identifying RAGT attributes.</p><p><strong>Methods: </strong>We applied five ML algorithms- logistic regression, random forest, decision tree, support vector machine (SVM), and extreme gradient boosting (XGboost)- to a dataset of 105 post-stroke patients undergoing RAGT. The variables included the Berg Balance Scale score, walking speed, steps, hip and knee active torques, functional ambulation categories, Fugl- Meyer assessment (FMA), the Korean version of the Modified Barthel Index, and fall history.</p><p><strong>Results: </strong>The random forest algorithm excelled (receiver operating characteristic area under the curve; AUC = 0.91) in predicting balance improvement, outperforming the SVM (AUC = 0.76) and XGboost (AUC = 0.71). Key determinants identified were knee active torque, age, step count, number of RAGT sessions, FMA, and hip torque.</p><p><strong>Conclusion: </strong>The random forest algorithm was the best prediction model for identifying fall-related balance and RAGT determinants, highlighting the importance of key factors for successful RAGT outcome performance in fall-related balance improvement.</p>","PeriodicalId":19717,"journal":{"name":"NeuroRehabilitation","volume":" ","pages":"1-10"},"PeriodicalIF":1.7000,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Identifying best fall-related balance factors and robotic-assisted gait training attributes in 105 post-stroke patients using clinical machine learning models.\",\"authors\":\"Heejun Kim, Jiwon Shin, Yunhwan Kim, Yongseok Lee, Joshua Sung H You\",\"doi\":\"10.3233/NRE-240116\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Background: </strong>Despite the promising effects of robot-assisted gait training (RAGT) on balance and gait in post-stroke rehabilitation, the optimal predictors of fall-related balance and effective RAGT attributes remain unclear in post-stroke patients at a high risk of fall.</p><p><strong>Objective: </strong>We aimed to determine the most accurate clinical machine learning (ML) algorithm for predicting fall-related balance factors and identifying RAGT attributes.</p><p><strong>Methods: </strong>We applied five ML algorithms- logistic regression, random forest, decision tree, support vector machine (SVM), and extreme gradient boosting (XGboost)- to a dataset of 105 post-stroke patients undergoing RAGT. The variables included the Berg Balance Scale score, walking speed, steps, hip and knee active torques, functional ambulation categories, Fugl- Meyer assessment (FMA), the Korean version of the Modified Barthel Index, and fall history.</p><p><strong>Results: </strong>The random forest algorithm excelled (receiver operating characteristic area under the curve; AUC = 0.91) in predicting balance improvement, outperforming the SVM (AUC = 0.76) and XGboost (AUC = 0.71). Key determinants identified were knee active torque, age, step count, number of RAGT sessions, FMA, and hip torque.</p><p><strong>Conclusion: </strong>The random forest algorithm was the best prediction model for identifying fall-related balance and RAGT determinants, highlighting the importance of key factors for successful RAGT outcome performance in fall-related balance improvement.</p>\",\"PeriodicalId\":19717,\"journal\":{\"name\":\"NeuroRehabilitation\",\"volume\":\" \",\"pages\":\"1-10\"},\"PeriodicalIF\":1.7000,\"publicationDate\":\"2024-01-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"NeuroRehabilitation\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.3233/NRE-240116\",\"RegionNum\":4,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"CLINICAL NEUROLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"NeuroRehabilitation","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.3233/NRE-240116","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"CLINICAL NEUROLOGY","Score":null,"Total":0}
Identifying best fall-related balance factors and robotic-assisted gait training attributes in 105 post-stroke patients using clinical machine learning models.
Background: Despite the promising effects of robot-assisted gait training (RAGT) on balance and gait in post-stroke rehabilitation, the optimal predictors of fall-related balance and effective RAGT attributes remain unclear in post-stroke patients at a high risk of fall.
Objective: We aimed to determine the most accurate clinical machine learning (ML) algorithm for predicting fall-related balance factors and identifying RAGT attributes.
Methods: We applied five ML algorithms- logistic regression, random forest, decision tree, support vector machine (SVM), and extreme gradient boosting (XGboost)- to a dataset of 105 post-stroke patients undergoing RAGT. The variables included the Berg Balance Scale score, walking speed, steps, hip and knee active torques, functional ambulation categories, Fugl- Meyer assessment (FMA), the Korean version of the Modified Barthel Index, and fall history.
Results: The random forest algorithm excelled (receiver operating characteristic area under the curve; AUC = 0.91) in predicting balance improvement, outperforming the SVM (AUC = 0.76) and XGboost (AUC = 0.71). Key determinants identified were knee active torque, age, step count, number of RAGT sessions, FMA, and hip torque.
Conclusion: The random forest algorithm was the best prediction model for identifying fall-related balance and RAGT determinants, highlighting the importance of key factors for successful RAGT outcome performance in fall-related balance improvement.
期刊介绍:
NeuroRehabilitation, an international, interdisciplinary, peer-reviewed journal, publishes manuscripts focused on scientifically based, practical information relevant to all aspects of neurologic rehabilitation. We publish unsolicited papers detailing original work/research that covers the full life span and range of neurological disabilities including stroke, spinal cord injury, traumatic brain injury, neuromuscular disease and other neurological disorders.
We also publish thematically organized issues that focus on specific clinical disorders, types of therapy and age groups. Proposals for thematic issues and suggestions for issue editors are welcomed.