Machine learning for predicting post-operative outcomes in meningiomas: a systematic review and meta-analysis

IF 1.9 3区 医学 Q3 CLINICAL NEUROLOGY Acta Neurochirurgica Pub Date : 2024-12-17 DOI:10.1007/s00701-024-06344-z
Siraj Y. Abualnaja, James S. Morris, Hamza Rashid, William H. Cook, Adel E. Helmy
{"title":"Machine learning for predicting post-operative outcomes in meningiomas: a systematic review and meta-analysis","authors":"Siraj Y. Abualnaja,&nbsp;James S. Morris,&nbsp;Hamza Rashid,&nbsp;William H. Cook,&nbsp;Adel E. Helmy","doi":"10.1007/s00701-024-06344-z","DOIUrl":null,"url":null,"abstract":"<div><h3>Purpose</h3><p>Meningiomas are the most common primary brain tumour and account for over one-third of cases. Traditionally, estimations of morbidity and mortality following surgical resection have depended on subjective assessments of various factors, including tumour volume, location, WHO grade, extent of resection (Simpson grade) and pre-existing co-morbidities, an approach fraught with subjective variability. This systematic review and meta-analysis seeks to evaluate the efficacy with which machine learning (ML) algorithms predict post-operative outcomes in meningioma patients.</p><h3>Methods</h3><p>A literature search was conducted in December 2023 by two independent reviewers through PubMed, DARE, Cochrane Library and SCOPUS electronic databases. Random-effects meta-analysis was conducted.</p><h3>Results</h3><p>Systematic searches yielded 32 studies, comprising 142,459 patients and 139,043 meningiomas. Random-effects meta-analysis sought to generate restricted maximum-likelihood estimates for the accuracy of alternate ML algorithms in predicting several postoperative outcomes. ML models incorporating both clinical and radiomic data significantly outperformed models utilizing either data type alone as well as traditional methods. Pooled estimates for the AUCs achieved by different ML algorithms ranged from 0.74–0.81 in the prediction of overall survival and progression-/recurrence-free survival, with ensemble classifiers demonstrating particular promise for future clinical application. Additionally, current ML models may exhibit a bias in predictive accuracy towards female patients, presumably due to the higher prevalence of meningiomas in females.</p><h3>Conclusion</h3><p>This review underscores the potential of ML to improve the accuracy of prognoses for meningioma patients and provides insight into which model classes offer the greatest potential for predicting survival outcomes. However, future research will have to directly compare standardized ML methodologies to traditional approaches in large-scale, prospective studies, before their clinical utility can be confidently validated.</p></div>","PeriodicalId":7370,"journal":{"name":"Acta Neurochirurgica","volume":"166 1","pages":""},"PeriodicalIF":1.9000,"publicationDate":"2024-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s00701-024-06344-z.pdf","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Acta Neurochirurgica","FirstCategoryId":"3","ListUrlMain":"https://link.springer.com/article/10.1007/s00701-024-06344-z","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"CLINICAL NEUROLOGY","Score":null,"Total":0}
引用次数: 0

Abstract

Purpose

Meningiomas are the most common primary brain tumour and account for over one-third of cases. Traditionally, estimations of morbidity and mortality following surgical resection have depended on subjective assessments of various factors, including tumour volume, location, WHO grade, extent of resection (Simpson grade) and pre-existing co-morbidities, an approach fraught with subjective variability. This systematic review and meta-analysis seeks to evaluate the efficacy with which machine learning (ML) algorithms predict post-operative outcomes in meningioma patients.

Methods

A literature search was conducted in December 2023 by two independent reviewers through PubMed, DARE, Cochrane Library and SCOPUS electronic databases. Random-effects meta-analysis was conducted.

Results

Systematic searches yielded 32 studies, comprising 142,459 patients and 139,043 meningiomas. Random-effects meta-analysis sought to generate restricted maximum-likelihood estimates for the accuracy of alternate ML algorithms in predicting several postoperative outcomes. ML models incorporating both clinical and radiomic data significantly outperformed models utilizing either data type alone as well as traditional methods. Pooled estimates for the AUCs achieved by different ML algorithms ranged from 0.74–0.81 in the prediction of overall survival and progression-/recurrence-free survival, with ensemble classifiers demonstrating particular promise for future clinical application. Additionally, current ML models may exhibit a bias in predictive accuracy towards female patients, presumably due to the higher prevalence of meningiomas in females.

Conclusion

This review underscores the potential of ML to improve the accuracy of prognoses for meningioma patients and provides insight into which model classes offer the greatest potential for predicting survival outcomes. However, future research will have to directly compare standardized ML methodologies to traditional approaches in large-scale, prospective studies, before their clinical utility can be confidently validated.

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
预测脑膜瘤术后疗效的机器学习:系统综述与荟萃分析
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
Acta Neurochirurgica
Acta Neurochirurgica 医学-临床神经学
CiteScore
4.40
自引率
4.20%
发文量
342
审稿时长
1 months
期刊介绍: The journal "Acta Neurochirurgica" publishes only original papers useful both to research and clinical work. Papers should deal with clinical neurosurgery - diagnosis and diagnostic techniques, operative surgery and results, postoperative treatment - or with research work in neuroscience if the underlying questions or the results are of neurosurgical interest. Reports on congresses are given in brief accounts. As official organ of the European Association of Neurosurgical Societies the journal publishes all announcements of the E.A.N.S. and reports on the activities of its member societies. Only contributions written in English will be accepted.
期刊最新文献
Clinical and radiologic distinctions between familial cavernous malformation syndrome and cerebral amyloid angiopathy Mini-strokes within Broca-caudate connections during left insular glioma awake surgery cause transient severe naming deficits Treatment of unruptured intracranial vertebral artery dissection aneurysms with Flow Diverter compared with conventional stent-assisted coiling—a single-center study Machine learning for predicting post-operative outcomes in meningiomas: a systematic review and meta-analysis Exploration of simultaneous transients between cerebral hemodynamics and the autonomic nervous system using windowed time-lagged cross-correlation matrices: a CENTER-TBI 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