Yum Kyu Sun, Chung Jong-Won, Ha Sue Young, Park Kwang-Yeol, Shin Dong-Ick, Park Hong-Kyun, Cho Yong-Jin, Hong Keun-Sik, Kim Jae Guk, Lee Soo Joo, Kim Joon-Tae, Seo Woo-Keun, Bang Oh Young, Kim Gyeong-Moon, Lee Myungjae, Kim Dongmin, Sunwoo Leonard, Bae Hee-Joon, Ryu Wi-Sun, Kim Beom Joon
Department of Neurology, College of Medicine, Chungbuk National University Hospital, Chungbuk National University, Cheongju, Republic of Korea.
Department of Neurology, Samsung Medical Center, Sungkyunkwan University College of Medicine, Seoul, Republic of Korea.
BMC Neurol. 2025 Mar 10;25(1):100. doi: 10.1186/s12883-025-04107-6.
To validate JLK-LVO, a software detecting large vessel occlusion (LVO) on computed tomography angiography (CTA), within a multicenter dataset.
From 2021 to 2023, we enrolled patients with ischemic stroke who underwent CTA within 24-hour of onset at six university hospitals for validation and calibration datasets and at another university hospital for an independent dataset for testing model calibration. The diagnostic performance was evaluated using area under the curve (AUC), sensitivity, and specificity across the entire study population and specifically in patients with isolated middle cerebral artery (MCA)-M2 occlusion. We calibrated LVO probabilities using logistic regression and by grouping LVO probabilities based on observed frequency.
After excluding 168 patients, 796 remained; the mean (SD) age was 68.9 (13.7) years, and 57.7% were men. LVO was present in 193 (24.3%) of patients, and the median interval from last-known-well to CTA was 5.7 h (IQR 2.5-12.1 h). The software achieved an AUC of 0.944 (95% CI 0.926-0.960), with a sensitivity of 89.6% (84.5-93.6%) and a specificity of 90.4% (87.7-92.6%). In isolated MCA-M2 occlusion, the AUROC was 0.880 (95% CI 0.824-0.921). Due to sparse data between 20 and 60% of LVO probabilities, recategorization into unlikely (0-20% LVO scores), less likely (20-60%), possible (60-90%), and suggestive (90-100%) provided a reliable estimation of LVO compared with mathematical calibration. The category of LVO probabilities was associated with follow-up infarct volumes and functional outcome.
In this multicenter study, we proved the clinical efficacy of the software in detecting LVO on CTA.
在多中心数据集中验证JLK-LVO，一种在计算机断层血管造影（CTA）上检测大血管闭塞（LVO）的软件。
从2021年到2023年，我们纳入了在六所大学医院发病24小时内接受CTA检查的缺血性中风患者，用于验证和校准数据集，并在另一所大学医院纳入用于测试模型校准的独立数据集。使用曲线下面积（AUC）、敏感性和特异性对整个研究人群进行诊断性能评估，特别是对孤立的大脑中动脉（MCA）-M2段闭塞患者。我们使用逻辑回归并根据观察频率对LVO概率进行分组来校准LVO概率。
排除168例患者后，剩余796例；平均（标准差）年龄为68.9（13.7）岁，57.7%为男性。193例（24.3%）患者存在LVO，从最后一次情况良好到CTA的中位间隔时间为5.7小时（四分位间距2.5 - 12.1小时）。该软件的AUC为0.944（95%可信区间0.926 - 0.960），敏感性为89.6%（84.5 - 93.6%），特异性为90.4%（87.7 - 92.6%）。在孤立的MCA-M2段闭塞中，AUROC为0.880（95%可信区间0.824 - 0.921）。由于20%至60%的LVO概率之间数据稀疏，与数学校准相比，重新分类为不太可能（LVO评分0 - 20%）、较不可能（20 - 60%）、可能（60 - 90%）和提示性（90 - 100%）可提供对LVO的可靠估计。LVO概率类别与随访梗死体积和功能结局相关。
在这项多中心研究中，我们证明了该软件在CTA上检测LVO的临床有效性。
