机器学习模型利用影像数据预测低级别胶质瘤BRAF改变的效能:系统评价与Meta分析
该系统评价与Meta分析纳入6项研究、951例患者,评估机器学习与深度学习模型利用影像数据预测低级别胶质瘤BRAF改变的效能。内部验证队列最佳模型的合并AUROC为84.44%,不同BRAF改变类型的合并灵敏度与特异度各有差异;作者认为模型预测表现相对较好,但需更大样本的未来研究以减少不精确性。
要点
- 纳入6项研究951例患者,最佳模型内部验证合并AUROC为84.44%。
- 从突变中区分BRAF融合的合并灵敏度80.3%、特异度88.57%。
- BRAF融合检测合并灵敏度87.51%、特异度70.41%,BRAF突变检测合并灵敏度74.14%、特异度83.98%。
核心结论
- AI模型利用影像数据预测低级别胶质瘤BRAF改变可能表现相对较好,并似乎能够达到较高的灵敏度和特异度。
- 作者指出,未来需要采用不同机器学习或深度学习算法、更大样本量的研究以减少不精确性。
研究设计与样本
- 系统评价与Meta分析,系统检索PubMed/MEDLINE、Embase和Cochrane Library截至2024年6月1日发表的研究。
- 纳入6项评估AI模型利用影像数据预测低级别胶质瘤BRAF改变效能的研究,共951例患者。
- 对合并灵敏度、特异度和受试者工作特征曲线下面积(AUROC)进行Meta分析。
主要发现
- 内部验证队列中最佳表现模型的合并AUROC为84.44%。
- 检测BRAF突变、BRAF融合、从突变中区分BRAF融合、BRAF野生型的模型AUROC分别为90.75%、84.59%、82.33%和82%。
- 从突变中区分BRAF融合的最佳表现模型合并灵敏度为80.3%、合并特异度为88.57%。
- 检测BRAF融合的最佳表现模型合并灵敏度为87.51%、合并特异度为70.41%。
- 检测BRAF突变的最佳表现模型合并灵敏度为74.14%、合并特异度为83.98%。
关键数值与推荐
- 内部验证队列最佳表现模型合并AUROC为84.44%。
- BRAF突变、BRAF融合、从突变中区分BRAF融合、BRAF野生型的AUROC分别为90.75%、84.59%、82.33%、82%。
- 从突变中区分BRAF融合:合并灵敏度80.3%,合并特异度88.57%。
- BRAF融合:合并灵敏度87.51%,合并特异度70.41%。
- BRAF突变:合并灵敏度74.14%,合并特异度83.98%。
临床怎么用
- 作者认为AI模型利用影像数据预测低级别胶质瘤BRAF改变可能表现相对较好,并可能辅助术前预测肿瘤行为。
- 作者指出未来需采用不同机器学习或深度学习算法、更大样本量的研究以减少不精确性。
局限性
- 作者指出未来需要采用不同机器学习或深度学习算法、更大样本量的研究以减少不精确性。
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
BACKGROUND: Understanding the BRAF alterations preoperatively could remarkably assist in predicting tumor behavior, which leads to a more precise prognostication and management strategy. Recent advances in artificial intelligence (AI) have resulted in effective predictive models. Therefore, for the first time, this study aimed to review the performance of machine learning and deep learning models in predicting the BRAF alterations in low-grade gliomas (LGGs)using imaging data. METHODS: PubMed/MEDLINE, Embase, and the Cochrane Library were systematically searched for studies published up to June 1, 2024, and evaluated the performance of AI models in predicting BRAF alterations in LGGs using imaging data. Pooled sensitivity, specificity, and area under the receiver operating curve (AUROC) were meta-analyzed. RESULTS: A total of 6 studies with 951 patients were included in this systematic review. The pooled AUROC of internal validation cohorts for their best-performing model was 84.44%, with models detecting BRAF mutation, BRAF fusion, BRAF fusion from mutation, and BRAF wild type producing similar AUROCs of 90.75%, 84.59%, 82.33%, and 82%, respectively. The best-performing models had pooled sensitivities of 80.3%, 87.51%, and 74.14% and pooled specificities of 88.57%, 70.41%, and 83.98% for detection of BRAF fusion from mutation, BRAF fusion, and BRAF mutation, respectively. CONCLUSIONS: AI models may perform relatively well in predicting BRAF alterations in LGG using imaging data and appear to be capable of high sensitivities and specificities. However, future studies with larger sample sizes implementing different machine learning or deep learning algorithms are required to reduce imprecision.
引用
- Firouzabadi SR, Tavanaei R, Mohammadi I, et al. Performance of Machine Learning Models in Predicting BRAF Alterations Using Imaging Data in Low-Grade Glioma: A Systematic Review and Meta-Analysis. World Neurosurg. 2025. PMID: 39914655. doi:10.1016/j.wneu.2025.123742
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。