影像组学预测成人骨质疏松的诊断性能:系统综述与Meta分析
该系统综述与Meta分析纳入10项回顾性研究共5926名参与者,评估影像组学诊断骨质疏松或骨量异常的准确性。合并敏感度和特异度均为87%,AUC为0.94,合并诊断比值比为57.22(95%CI 27.62-118.52)。作者认为影像组学诊断准确性良好,但需更多前瞻性研究及多中心验证进一步确认。
要点
- 纳入10项回顾性研究共5926名参与者,影像组学诊断骨质疏松合并敏感度87%、特异度87%。
- 汇总受试者工作特征曲线下面积(AUC)为0.94(范围0.8至0.98),合并诊断比值比57.22(95%CI 27.62-118.52)。
- 平均METRICS评分为70.1%(范围49.6-83.2%),研究间存在中等异质性且异质性来源包括成像方式、特征选择方法和分类器。
核心结论
- 影像组学技术在诊断骨质疏松或骨量异常方面具有良好准确性,但该应用需更多前瞻性研究、严格遵循现有指南及多中心验证进一步确认。
研究设计与样本
- 系统综述与Meta分析,方案前瞻性注册于PROSPERO(CRD42023425058)。
- 检索PubMed、EMBASE、Web of Science和Cochrane Library数据库自建库至2023年6月1日的文献。
- 纳入10项回顾性研究,共5926名参与者。
- 采用影像组学质量评分(RQS)、影像组学方法学评分(METRICS)和诊断准确性研究质量评估-2(QUADAS-2)工具评价纳入研究的质量与偏倚风险。
- 数据分析使用R程序中的mada、metafor和meta包。
主要发现
- 各研究各领域的总体偏倚风险与适用性担忧均评为低,仅一项研究存在高流程与时间偏倚风险。
- 平均METRICS评分为70.1%(范围49.6-83.2%)。
- 研究间存在中等异质性,Meta回归识别的异质性来源包括成像方式、特征选择方法和分类器。
- 双变量随机效应模型合并诊断比值比(DOR)为57.22(95%CI 27.62-118.52)。
- 合并敏感度为87%(95%CI 81-92%),合并特异度为87%(95%CI 77-93%),汇总受试者工作特征曲线下面积(AUC)为0.94(范围0.8至0.98)。
局限性
- 纳入研究均为回顾性研究。
- 仅一项研究存在高流程与时间偏倚风险。
- 研究间存在中等异质性。
- 作者指出影像组学在骨质疏松诊断中的应用需更多前瞻性研究、严格遵循现有指南及多中心验证进一步确认。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
This study aimed to assess the diagnostic accuracy of radiomics for predicting osteoporosis and the quality of radiomic studies. The study protocol was prospectively registered on PROSPERO (CRD42023425058). We searched PubMed, EMBASE, Web of Science, and Cochrane Library databases from inception to June 1, 2023, for eligible articles that applied radiomic techniques to diagnosing osteoporosis or abnormal bone mass. Quality and risk of bias of the included studies were evaluated with radiomics quality score (RQS), METhodological RadiomICs Score (METRICS), and Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) tools. The data analysis utilized the R program with mada, metafor, and meta packages. Ten retrospective studies with 5926 participants were included in the systematic review and meta-analysis. The overall risk of bias and applicability concerns for each domain of the studies were rated as low, except for one study which was considered to have a high risk of flow and time bias. The mean METRICS score was 70.1% (range 49.6-83.2%). There was moderate heterogeneity across studies and meta-regression identified sources of heterogeneity in the data, including imaging modality, feature selection method, and classifier. The pooled diagnostic odds ratio (DOR) under the bivariate random effects model across the studies was 57.22 (95% CI 27.62-118.52). The pooled sensitivity and specificity were 87% (95% CI 81-92%) and 87% (95% CI 77-93%), respectively. The area under the summary receiver operating characteristic curve (AUC) of the radiomic models was 0.94 (range 0.8 to 0.98). The results supported that the radiomic techniques had good accuracy in diagnosing osteoporosis or abnormal bone mass. The application of radiomics in osteoporosis diagnosis needs to be further confirmed by more prospective studies with rigorous adherence to existing guidelines and multicenter validation.
引用
- Deng L, Shuai P, Liu Y, et al. Diagnostic performance of radiomics for predicting osteoporosis in adults: a systematic review and meta-analysis. Osteoporos Int. 2024. PMID: 38802557. doi:10.1007/s00198-024-07136-y
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。