Understanding the role of machine learning in predicting progression of osteoarthritis.

IF 4.9 1区 医学 Q1 ORTHOPEDICS Bone & Joint Journal Pub Date : 2024-11-01 DOI:10.1302/0301-620X.106B11.BJJ-2024-0453.R1
Simone Castagno, Benjamin Gompels, Estelle Strangmark, Eve Robertson-Waters, Mark Birch, Mihaela van der Schaar, Andrew W McCaskie
{"title":"Understanding the role of machine learning in predicting progression of osteoarthritis.","authors":"Simone Castagno, Benjamin Gompels, Estelle Strangmark, Eve Robertson-Waters, Mark Birch, Mihaela van der Schaar, Andrew W McCaskie","doi":"10.1302/0301-620X.106B11.BJJ-2024-0453.R1","DOIUrl":null,"url":null,"abstract":"<p><strong>Aims: </strong>Machine learning (ML), a branch of artificial intelligence that uses algorithms to learn from data and make predictions, offers a pathway towards more personalized and tailored surgical treatments. This approach is particularly relevant to prevalent joint diseases such as osteoarthritis (OA). In contrast to end-stage disease, where joint arthroplasty provides excellent results, early stages of OA currently lack effective therapies to halt or reverse progression. Accurate prediction of OA progression is crucial if timely interventions are to be developed, to enhance patient care and optimize the design of clinical trials.</p><p><strong>Methods: </strong>A systematic review was conducted in accordance with PRISMA guidelines. We searched MEDLINE and Embase on 5 May 2024 for studies utilizing ML to predict OA progression. Titles and abstracts were independently screened, followed by full-text reviews for studies that met the eligibility criteria. Key information was extracted and synthesized for analysis, including types of data (such as clinical, radiological, or biochemical), definitions of OA progression, ML algorithms, validation methods, and outcome measures.</p><p><strong>Results: </strong>Out of 1,160 studies initially identified, 39 were included. Most studies (85%) were published between 2020 and 2024, with 82% using publicly available datasets, primarily the Osteoarthritis Initiative. ML methods were predominantly supervised, with significant variability in the definitions of OA progression: most studies focused on structural changes (59%), while fewer addressed pain progression or both. Deep learning was used in 44% of studies, while automated ML was used in 5%. There was a lack of standardization in evaluation metrics and limited external validation. Interpretability was explored in 54% of studies, primarily using SHapley Additive exPlanations.</p><p><strong>Conclusion: </strong>Our systematic review demonstrates the feasibility of ML models in predicting OA progression, but also uncovers critical limitations that currently restrict their clinical applicability. Future priorities should include diversifying data sources, standardizing outcome measures, enforcing rigorous validation, and integrating more sophisticated algorithms. This paradigm shift from predictive modelling to actionable clinical tools has the potential to transform patient care and disease management in orthopaedic practice.</p>","PeriodicalId":48944,"journal":{"name":"Bone & Joint Journal","volume":null,"pages":null},"PeriodicalIF":4.9000,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Bone & Joint Journal","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1302/0301-620X.106B11.BJJ-2024-0453.R1","RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ORTHOPEDICS","Score":null,"Total":0}
引用次数: 0

Abstract

Aims: Machine learning (ML), a branch of artificial intelligence that uses algorithms to learn from data and make predictions, offers a pathway towards more personalized and tailored surgical treatments. This approach is particularly relevant to prevalent joint diseases such as osteoarthritis (OA). In contrast to end-stage disease, where joint arthroplasty provides excellent results, early stages of OA currently lack effective therapies to halt or reverse progression. Accurate prediction of OA progression is crucial if timely interventions are to be developed, to enhance patient care and optimize the design of clinical trials.

Methods: A systematic review was conducted in accordance with PRISMA guidelines. We searched MEDLINE and Embase on 5 May 2024 for studies utilizing ML to predict OA progression. Titles and abstracts were independently screened, followed by full-text reviews for studies that met the eligibility criteria. Key information was extracted and synthesized for analysis, including types of data (such as clinical, radiological, or biochemical), definitions of OA progression, ML algorithms, validation methods, and outcome measures.

Results: Out of 1,160 studies initially identified, 39 were included. Most studies (85%) were published between 2020 and 2024, with 82% using publicly available datasets, primarily the Osteoarthritis Initiative. ML methods were predominantly supervised, with significant variability in the definitions of OA progression: most studies focused on structural changes (59%), while fewer addressed pain progression or both. Deep learning was used in 44% of studies, while automated ML was used in 5%. There was a lack of standardization in evaluation metrics and limited external validation. Interpretability was explored in 54% of studies, primarily using SHapley Additive exPlanations.

Conclusion: Our systematic review demonstrates the feasibility of ML models in predicting OA progression, but also uncovers critical limitations that currently restrict their clinical applicability. Future priorities should include diversifying data sources, standardizing outcome measures, enforcing rigorous validation, and integrating more sophisticated algorithms. This paradigm shift from predictive modelling to actionable clinical tools has the potential to transform patient care and disease management in orthopaedic 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
了解机器学习在预测骨关节炎进展中的作用。
目的:机器学习(ML)是人工智能的一个分支,它利用算法从数据中学习并进行预测。这种方法尤其适用于骨关节炎(OA)等常见关节疾病。与关节置换术效果极佳的终末期疾病相比,OA 的早期阶段目前缺乏有效的疗法来阻止或逆转病情的发展。要想及时采取干预措施,加强对患者的护理并优化临床试验的设计,准确预测 OA 的进展至关重要:方法:根据 PRISMA 指南进行了系统性综述。我们于 2024 年 5 月 5 日在 MEDLINE 和 Embase 中检索了利用 ML 预测 OA 进展的研究。对标题和摘要进行独立筛选,然后对符合资格标准的研究进行全文综述。提取关键信息并进行综合分析,包括数据类型(如临床、放射学或生化)、OA进展的定义、ML算法、验证方法和结果测量:在最初确定的 1160 项研究中,有 39 项被纳入。大多数研究(85%)发表于 2020 年至 2024 年之间,82%的研究使用了公开数据集,主要是骨关节炎倡议(Osteoarthritis Initiative)。ML 方法主要是监督式的,在 OA 进展的定义上存在很大差异:大多数研究侧重于结构变化(59%),而较少研究涉及疼痛进展或两者兼而有之。44%的研究使用了深度学习,5%的研究使用了自动 ML。评估指标缺乏标准化,外部验证有限。54%的研究探讨了可解释性,主要使用了SHapley Additive exPlanations:我们的系统综述证明了 ML 模型在预测 OA 进展方面的可行性,但也发现了目前限制其临床适用性的关键局限性。未来的工作重点应包括数据来源的多样化、结果测量的标准化、严格的验证以及整合更复杂的算法。从预测建模到可操作的临床工具,这种模式的转变有可能改变骨科实践中的患者护理和疾病管理。
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
Bone & Joint Journal
Bone & Joint Journal ORTHOPEDICS-SURGERY
CiteScore
9.40
自引率
10.90%
发文量
318
期刊介绍: We welcome original articles from any part of the world. The papers are assessed by members of the Editorial Board and our international panel of expert reviewers, then either accepted for publication or rejected by the Editor. We receive over 2000 submissions each year and accept about 250 for publication, many after revisions recommended by the reviewers, editors or statistical advisers. A decision usually takes between six and eight weeks. Each paper is assessed by two reviewers with a special interest in the subject covered by the paper, and also by members of the editorial team. Controversial papers will be discussed at a full meeting of the Editorial Board. Publication is between four and six months after acceptance.
期刊最新文献
Contemporary insights into spinopelvic mechanics. Core Outcome Domains for Elbow Replacement (CODER). Defining multilevel developmental cervical spinal stenosis using MRI. Delayed fixation of distal radial fractures beyond three weeks after initial failed closed reduction increases the odds of reoperation. Detection, classification, and characterization of proximal humerus fractures on plain radiographs.
×
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