期刊
FRONTIERS IN ONCOLOGY
卷 12, 期 -, 页码 -出版社
FRONTIERS MEDIA SA
DOI: 10.3389/fonc.2022.799662
关键词
glioblastoma; machine learning; monitoring biomarkers; meta-analysis; artificial intelligence; treatment response; deep learning; glioma
类别
资金
- Wellcome/EPSRC Centre for Medical Engineering [WT 203148/Z/16/Z]
- Royal College of Radiologists
- King's College Hospital Research and Innovation
This study systematically reviewed the quality and performance accuracy of recently published studies on using machine learning to monitor biomarkers for determining glioblastoma treatment response. The results showed that ML models using MRI features to distinguish between progression and mimics demonstrated good diagnostic performance. However, the limited number of studies, high bias risk, and applicability concerns in these studies call for improvement in study quality and design.
Objective: Monitoring biomarkers using machine learning (ML) may determine glioblastoma treatment response. We systematically reviewed quality and performance accuracy of recently published studies.& nbsp;Methods: Following Preferred Reporting Items for Systematic Reviews and Meta-Analysis: Diagnostic Test Accuracy, we extracted articles from MEDLINE, EMBASE and Cochrane Register between 09/2018-01/2021. Included study participants were adults with glioblastoma having undergone standard treatment (maximal resection, radiotherapy with concomitant and adjuvant temozolomide), and follow-up imaging to determine treatment response status (specifically, distinguishing progression/recurrence from progression/recurrence mimics, the target condition). Using Quality Assessment of Diagnostic Accuracy Studies Two/Checklist for Artificial Intelligence in Medical Imaging, we assessed bias risk and applicability concerns. We determined test set performance accuracy (sensitivity, specificity, precision, F1-score, balanced accuracy). We used a bivariate random-effect model to determine pooled sensitivity, specificity, area-under the receiver operator characteristic curve (ROC-AUC). Pooled measures of balanced accuracy, positive/negative likelihood ratios (PLR/NLR) and diagnostic odds ratio (DOR) were calculated. PROSPERO registered(CRD42021261965).& nbsp;Results: Eighteen studies were included (1335/384 patients for training/testing respectively). Small patient numbers, high bias risk, applicability concerns (particularly confounding in reference standard and patient selection) and low level of evidence, allow limited conclusions from studies. Ten studies (10/18, 56%) included in meta-analysis gave 0.769 (0.649-0.858) sensitivity [pooled (95% CI)]; 0.648 (0.749-0.532) specificity; 0.706 (0.623-0.779) balanced accuracy; 2.220 (1.560-3.140) PLR; 0.366 (0.213-0.572) NLR; 6.670 (2.800-13.500) DOR; 0.765 ROC-AUC.& nbsp;Conclusion: ML models using MRI features to distinguish between progression and mimics appear to demonstrate good diagnostic performance. However, study quality and design require improvement.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据