Machine learning methods in physical therapy: A scoping review of applications in clinical context

IF 2.2 3区 医学 Q1 REHABILITATION Musculoskeletal Science and Practice Pub Date : 2024-09-13 DOI:10.1016/j.msksp.2024.103184
Felipe J.J. Reis , Matheus Bartholazzi Lugão de Carvalho , Gabriela de Assis Neves , Leandro Calazans Nogueira , Ney Meziat-Filho
{"title":"Machine learning methods in physical therapy: A scoping review of applications in clinical context","authors":"Felipe J.J. Reis ,&nbsp;Matheus Bartholazzi Lugão de Carvalho ,&nbsp;Gabriela de Assis Neves ,&nbsp;Leandro Calazans Nogueira ,&nbsp;Ney Meziat-Filho","doi":"10.1016/j.msksp.2024.103184","DOIUrl":null,"url":null,"abstract":"<div><h3>Background</h3><p>Machine learning (ML) efficiently processes large datasets, showing promise in enhancing clinical practice within physical therapy.</p></div><div><h3>Objective</h3><p>The aim of this scoping review is to provide an overview of studies using ML approaches in clinical settings of physical therapy.</p></div><div><h3>Data sources</h3><p>A scoping review was performed in PubMed, EMBASE, PEDro, Cochrane, Web of Science, and Scopus.</p></div><div><h3>Selection criteria</h3><p>We included studies utilizing ML methods. ML was defined as the utilization of computational systems to encode patterns and relationships, enabling predictions or classifications with minimal human interference.</p></div><div><h3>Data extraction and data synthesis</h3><p>Data were extracted regarding methods, data types, performance metrics, and model availability.</p></div><div><h3>Results</h3><p>Forty-two studies were included. The majority were published after 2020 (n = 25). Fourteen studies (33.3%) were in the musculoskeletal physical therapy field, nine (21.4%) in neurological, and eight (19%) in sports physical therapy. We identified 44 different ML models, with random forest being the most used. Three studies reported on model availability. We identified several clinical applications for ML-based tools, including diagnosis (n = 14), prognosis (n = 7), treatment outcomes prediction (n = 7), clinical decision support (n = 5), movement analysis (n = 4), patient monitoring (n = 3), and personalized care plan (n = 2).</p></div><div><h3>Limitation</h3><p>Model performance metrics, costs, model interpretability, and explainability were not reported.</p></div><div><h3>Conclusion</h3><p>This scope review mapped the emerging landscape of machine learning applications in physical therapy. Despite the growing interest, the field still lacks high-quality studies on validation, model availability, and acceptability to advance from research to clinical practice.</p></div>","PeriodicalId":56036,"journal":{"name":"Musculoskeletal Science and Practice","volume":"74 ","pages":"Article 103184"},"PeriodicalIF":2.2000,"publicationDate":"2024-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Musculoskeletal Science and Practice","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2468781224002790","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"REHABILITATION","Score":null,"Total":0}
引用次数: 0

Abstract

Background

Machine learning (ML) efficiently processes large datasets, showing promise in enhancing clinical practice within physical therapy.

Objective

The aim of this scoping review is to provide an overview of studies using ML approaches in clinical settings of physical therapy.

Data sources

A scoping review was performed in PubMed, EMBASE, PEDro, Cochrane, Web of Science, and Scopus.

Selection criteria

We included studies utilizing ML methods. ML was defined as the utilization of computational systems to encode patterns and relationships, enabling predictions or classifications with minimal human interference.

Data extraction and data synthesis

Data were extracted regarding methods, data types, performance metrics, and model availability.

Results

Forty-two studies were included. The majority were published after 2020 (n = 25). Fourteen studies (33.3%) were in the musculoskeletal physical therapy field, nine (21.4%) in neurological, and eight (19%) in sports physical therapy. We identified 44 different ML models, with random forest being the most used. Three studies reported on model availability. We identified several clinical applications for ML-based tools, including diagnosis (n = 14), prognosis (n = 7), treatment outcomes prediction (n = 7), clinical decision support (n = 5), movement analysis (n = 4), patient monitoring (n = 3), and personalized care plan (n = 2).

Limitation

Model performance metrics, costs, model interpretability, and explainability were not reported.

Conclusion

This scope review mapped the emerging landscape of machine learning applications in physical therapy. Despite the growing interest, the field still lacks high-quality studies on validation, model availability, and acceptability to advance from research to clinical practice.

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
物理治疗中的机器学习方法:临床应用范围综述
背景机器学习(ML)可高效处理大型数据集,在提高物理治疗的临床实践方面大有可为。目的本范围综述旨在概述在物理治疗的临床环境中使用 ML 方法的研究。ML 被定义为利用计算系统对模式和关系进行编码,从而在最少人为干预的情况下进行预测或分类。数据提取和数据综合提取了有关方法、数据类型、性能指标和模型可用性的数据。大多数研究发表于 2020 年之后(n = 25)。14项研究(33.3%)涉及肌肉骨骼理疗领域,9项(21.4%)涉及神经理疗领域,8项(19%)涉及运动理疗领域。我们发现了 44 种不同的 ML 模型,其中使用最多的是随机森林模型。三项研究报告了模型的可用性。我们确定了基于 ML 工具的几种临床应用,包括诊断(14 例)、预后(7 例)、治疗结果预测(7 例)、临床决策支持(5 例)、运动分析(4 例)、患者监控(3 例)和个性化护理计划(2 例)。尽管人们对机器学习的兴趣与日俱增,但该领域仍然缺乏关于验证、模型可用性和可接受性的高质量研究,因此无法从研究推进到临床实践。
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 去求助
来源期刊
Musculoskeletal Science and Practice
Musculoskeletal Science and Practice Health Professions-Physical Therapy, Sports Therapy and Rehabilitation
CiteScore
4.10
自引率
8.70%
发文量
152
审稿时长
48 days
期刊介绍: Musculoskeletal Science & Practice, international journal of musculoskeletal physiotherapy, is a peer-reviewed international journal (previously Manual Therapy), publishing high quality original research, review and Masterclass articles that contribute to improving the clinical understanding of appropriate care processes for musculoskeletal disorders. The journal publishes articles that influence or add to the body of evidence on diagnostic and therapeutic processes, patient centered care, guidelines for musculoskeletal therapeutics and theoretical models that support developments in assessment, diagnosis, clinical reasoning and interventions.
期刊最新文献
The effectiveness of education for people with shoulder pain: A systematic review. Defining core competencies for telehealth in healthcare higher education: A Delphi study. Effects of a smartphone game to facilitate active neck movements on the incidence of neck pain among office workers: A 6-month cluster-randomized controlled trial. Validity and reliability of the Danish version of the Short Form Brief Pain Inventory. The prognostic reasoning by physiotherapists of musculoskeletal disorders: A phenomenological exploratory study.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1