Zakariaee Seyed Salman, Kadir Dler Hussein, Molazadeh Mikaeil, Abdi Shahab
Ilam University of Medical Sciences, Ilam, Islamic Republic of Iran.
Salahaddin University-Erbil, Erbil, Iraq.
Neuroradiology. 2025 Sep 12. doi: 10.1007/s00234-025-03745-4.
The success of intravenous thrombolysis with tPA (IV-tPA) as the fastest and easiest treatment for stroke patients is closely related to time since stroke onset (TSS). Administering IV-tPA after the recommended time interval (< 4.5 h) increases the risk of cerebral hemorrhage. Despite advances in diagnostic approaches have been made, the determination of TSS remains a clinical challenge. In this study, the performances of different diagnostic approaches were investigated to classify TSS.
A systematic literature search was conducted in Web of Science, Pubmed, Scopus, Embase, and Cochrane databases until July 2025. The overall AUC, sensitivity, and specificity magnitudes with their 95%CIs were determined for each diagnostic approach to evaluate their classification performances.
This systematic review retrieved a total number of 9030 stroke patients until July 2025. The results showed that the human readings of DWI-FLAIR mismatch as the current gold standard method with AUC = 0.71 (95%CI: 0.66-0.76), sensitivity = 0.62 (95%CI: 0.54-0.71), and specificity = 0.78 (95%CI: 0.72-0.84) has a moderate performance to identify the TSS. ML model fed by radiomic features of CT data with AUC = 0.89 (95%CI: 0.80-0.98), sensitivity = 0.85 (95%CI: 0.75-0.96), and specificity = 0.86 (95%CI: 0.73-1.00) has the best performance in classifying TSS among the models reviewed.
ML models fed by radiomic features better classify TSS than the human reading of DWI-FLAIR mismatch. An efficient AI model fed by CT radiomic data could yield the best classification performance to determine patients' eligibility for IV-tPA treatment and improve treatment outcomes.
静脉注射组织型纤溶酶原激活剂（IV-tPA）作为中风患者最快且最简单的治疗方法，其成功与否与中风发作时间（TSS）密切相关。在推荐的时间间隔（<4.5小时）后给予IV-tPA会增加脑出血的风险。尽管诊断方法已有进展，但TSS的确定仍然是一项临床挑战。在本研究中，对不同诊断方法的性能进行了调查，以对TSS进行分类。
在Web of Science、Pubmed、Scopus、Embase和Cochrane数据库中进行了系统的文献检索，直至2025年7月。确定了每种诊断方法的总体AUC、敏感性和特异性大小及其95%置信区间，以评估其分类性能。
截至2025年7月，该系统评价共检索到9030例中风患者。结果表明，作为当前金标准方法的DWI-FLAIR不匹配的人工判读，其AUC = 0.71（95%CI：0.66-0.76），敏感性 = 0.62（95%CI：0.54-0.71），特异性 = 0.78（95%CI：0.72-0.84），在识别TSS方面具有中等性能。由CT数据的放射组学特征提供数据的机器学习（ML）模型，其AUC = 0.89（95%CI：0.80-0.98），敏感性 = 0.85（95%CI：0.75-0.96），特异性 = 0.86（95%CI：0.73-1.00），在所审查的模型中，在TSS分类方面表现最佳。
由放射组学特征提供数据的ML模型在TSS分类方面比DWI-FLAIR不匹配的人工判读更好。由CT放射组学数据提供数据的高效人工智能模型可以产生最佳的分类性能，以确定患者是否适合IV-tPA治疗并改善治疗结果。
