Development of a Berg Balance Scale Short-Form Using a Machine Learning Approach in Patients With Stroke.

IF 2.6 3区医学 Q2 CLINICAL NEUROLOGY

Journal of Neurologic Physical Therapy Pub Date : 2023-01-01 DOI:10.1097/NPT.0000000000000417

Inga Wang, Pei-Chi Li, Shih-Chieh Lee, Ya-Chen Lee, Chun-Hou Wang, Ching-Lin Hsieh

{"title":"Development of a Berg Balance Scale Short-Form Using a Machine Learning Approach in Patients With Stroke.","authors":"Inga Wang, Pei-Chi Li, Shih-Chieh Lee, Ya-Chen Lee, Chun-Hou Wang, Ching-Lin Hsieh","doi":"10.1097/NPT.0000000000000417","DOIUrl":null,"url":null,"abstract":"Background and purpose: The Berg Balance Scale (BBS) is frequently used in routine clinical care and research settings and has good psychometric properties. This study was conducted to develop a short form of the BBS using a machine learning approach (BBS-ML).Methods: Data of 408 individuals poststroke were extracted from a published database. The initial (ie, 4-, 5-, 6-, 7-, and 8-item) versions were constructed by selecting top-ranked items based on the feature selection algorithm in the artificial neural network model. The final version of the BBS-ML was chosen by selecting the short form that used a smaller number of items to achieve a higher predictive power R2 , a lower 95% limit of agreement (LoA), and an adequate possible scoring point (PSP). An independent sample of 226 persons with stroke was used for external validation.Results: The R2 values for the initial 4-, 5-, 6-, 7-, and 8-item short forms were 0.93, 0.95, 0.97, 0.97, and 0.97, respectively. The 95% LoAs were 14.2, 12.2, 9.7, 9.6, and 8.9, respectively. The PSPs were 25, 35, 34, 35, and 36, respectively. The 6-item version was selected as the final BBS-ML. Preliminary external validation supported its performance in an independent sample of persons with stroke ( R2 = 0.99, LoA = 10.6, PSP = 37).Discussion and conclusions: The BBS-ML seems to be a promising short-form alternative to improve administrative efficiency. Future research is needed to examine the psychometric properties and clinical usage of the 6-item BBS-ML in various settings and samples.Video Abstract available for more insights from the authors (see the Video, Supplemental Digital Content 1, available at: http://links.lww.com/JNPT/A402 ).","PeriodicalId":49030,"journal":{"name":"Journal of Neurologic Physical Therapy","volume":null,"pages":null},"PeriodicalIF":2.6000,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Neurologic Physical Therapy","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1097/NPT.0000000000000417","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"CLINICAL NEUROLOGY","Score":null,"Total":0}

引用次数: 1

Abstract

Background and purpose: The Berg Balance Scale (BBS) is frequently used in routine clinical care and research settings and has good psychometric properties. This study was conducted to develop a short form of the BBS using a machine learning approach (BBS-ML).

Methods: Data of 408 individuals poststroke were extracted from a published database. The initial (ie, 4-, 5-, 6-, 7-, and 8-item) versions were constructed by selecting top-ranked items based on the feature selection algorithm in the artificial neural network model. The final version of the BBS-ML was chosen by selecting the short form that used a smaller number of items to achieve a higher predictive power R2 , a lower 95% limit of agreement (LoA), and an adequate possible scoring point (PSP). An independent sample of 226 persons with stroke was used for external validation.

Results: The R2 values for the initial 4-, 5-, 6-, 7-, and 8-item short forms were 0.93, 0.95, 0.97, 0.97, and 0.97, respectively. The 95% LoAs were 14.2, 12.2, 9.7, 9.6, and 8.9, respectively. The PSPs were 25, 35, 34, 35, and 36, respectively. The 6-item version was selected as the final BBS-ML. Preliminary external validation supported its performance in an independent sample of persons with stroke ( R2 = 0.99, LoA = 10.6, PSP = 37).

Discussion and conclusions: The BBS-ML seems to be a promising short-form alternative to improve administrative efficiency. Future research is needed to examine the psychometric properties and clinical usage of the 6-item BBS-ML in various settings and samples.Video Abstract available for more insights from the authors (see the Video, Supplemental Digital Content 1, available at: http://links.lww.com/JNPT/A402 ).

查看原文本刊更多论文

利用机器学习方法在中风患者中开发Berg平衡量表简表。

背景与目的:伯格平衡量表(BBS)在常规临床护理和研究中经常使用，具有良好的心理测量特性。本研究旨在使用机器学习方法(BBS- ml)开发一种简短形式的BBS。方法:从已发表的数据库中提取408例脑卒中患者的资料。根据人工神经网络模型中的特征选择算法，选择排名靠前的项目，构建初始版本(即4-、5-、6-、7-和8-)。BBS-ML的最终版本是通过选择使用较少项目数量的简短形式来获得更高的预测能力R2，较低的95%一致性限制(LoA)和足够的可能评分点(PSP)来选择的。采用226例卒中患者的独立样本进行外部验证。结果:4项、5项、6项、7项和8项简短表格的初始R2值分别为0.93、0.95、0.97、0.97和0.97。95% loa分别为14.2、12.2、9.7、9.6和8.9。PSPs分别为25、35、34、35、36。6个项目的版本被选为最终的BBS-ML。初步的外部验证支持其在卒中患者独立样本中的表现(R2 = 0.99, LoA = 10.6, PSP = 37)。讨论和结论:BBS-ML似乎是提高管理效率的一种很有前途的短格式替代方案。未来的研究需要在不同的环境和样本中检验6项BBS-ML的心理测量特性和临床应用。视频摘要可获得作者的更多见解(参见视频，补充数字内容1，可在:http://links.lww.com/JNPT/A402)。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Journal of Neurologic Physical Therapy CLINICAL NEUROLOGY-REHABILITATION

CiteScore

5.70

自引率

2.60%

发文量

审稿时长

>12 weeks

期刊介绍： The Journal of Neurologic Physical Therapy (JNPT) is an indexed resource for dissemination of research-based evidence related to neurologic physical therapy intervention. High standards of quality are maintained through a rigorous, double-blinded, peer-review process and adherence to standards recommended by the International Committee of Medical Journal Editors. With an international editorial board made up of preeminent researchers and clinicians, JNPT publishes articles of global relevance for examination, evaluation, prognosis, intervention, and outcomes for individuals with movement deficits due to neurologic conditions. Through systematic reviews, research articles, case studies, and clinical perspectives, JNPT promotes the integration of evidence into theory, education, research, and practice of neurologic physical therapy, spanning the continuum from pathophysiology to societal participation.