Karamian Armin, Seifi Ali
School of Medicine, University of Texas Health at San Antonio, San Antonio, TX 78229, USA.
Division of Neurocritical Care, Department of Neurosurgery, University of Texas Health at San Antonio, San Antonio, TX 78229, USA.
J Clin Med. 2025 Mar 30;14(7):2377. doi: 10.3390/jcm14072377.
: Intracranial hemorrhage (ICH) is a life-threatening medical condition that needs early detection and treatment. In this systematic review and meta-analysis, we aimed to update our knowledge of the performance of deep learning (DL) models in detecting ICH on non-contrast computed tomography (NCCT). : The study protocol was registered with PROSPERO (CRD420250654071). PubMed/MEDLINE and Google Scholar databases and the reference section of included studies were searched for eligible studies. The risk of bias in the included studies was assessed using the QUADAS-2 tool. Required data was collected to calculate pooled sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) with the corresponding 95% CI using the random effects model. : Seventy-three studies were included in our qualitative synthesis, and fifty-eight studies were selected for our meta-analysis. A pooled sensitivity of 0.92 (95% CI 0.90-0.94) and a pooled specificity of 0.94 (95% CI 0.92-0.95) were achieved. Pooled PPV was 0.84 (95% CI 0.78-0.89) and pooled NPV was 0.97 (95% CI 0.96-0.98). A bivariate model showed a pooled AUC of 0.96 (95% CI 0.95-0.97). : This meta-analysis demonstrates that DL performs well in detecting ICH from NCCTs, highlighting a promising potential for the use of AI tools in various practice settings. More prospective studies are needed to confirm the potential clinical benefit of implementing DL-based tools and reveal the limitations of such tools for automated ICH detection and their impact on clinical workflow and outcomes of patients.
颅内出血（ICH）是一种危及生命的疾病，需要早期检测和治疗。在这项系统评价和荟萃分析中，我们旨在更新我们对深度学习（DL）模型在非增强计算机断层扫描（NCCT）上检测ICH性能的认识。：该研究方案已在PROSPERO（CRD420250654071）注册。检索了PubMed/MEDLINE和谷歌学术数据库以及纳入研究的参考文献部分，以查找符合条件的研究。使用QUADAS-2工具评估纳入研究的偏倚风险。收集所需数据，使用随机效应模型计算合并敏感性、特异性、阳性预测值（PPV）和阴性预测值（NPV）以及相应的95%置信区间。：我们的定性综合分析纳入了73项研究，58项研究被选入我们的荟萃分析。合并敏感性为0.92（95%CI 0.90-0.94），合并特异性为0.94（95%CI 0.92-0.95）。合并PPV为0.84（95%CI 0.78-0.89），合并NPV为0.97（95%CI 0.96-0.98）。双变量模型显示合并AUC为0.96（95%CI 0.95-0.97）。：这项荟萃分析表明，DL在从NCCT中检测ICH方面表现良好，突出了在各种实践环境中使用人工智能工具的潜在前景。需要更多的前瞻性研究来证实实施基于DL的工具的潜在临床益处，并揭示此类工具在自动ICH检测方面的局限性及其对临床工作流程和患者结局的影响。
