Department of Convergence Medicine, University of Ulsan College of Medicine, Asan Medical Center, Seoul, Republic of Korea.
Department of Radiology and Research Institute of Radiology, University of Ulsan College of Medicine, Asan Medical Center, Seoul, Republic of Korea.
Nat Commun. 2022 Jul 22;13(1):4251. doi: 10.1038/s41467-022-31808-0.
Triage is essential for the early diagnosis and reporting of neurologic emergencies. Herein, we report the development of an anomaly detection algorithm (ADA) with a deep generative model trained on brain computed tomography (CT) images of healthy individuals that reprioritizes radiology worklists and provides lesion attention maps for brain CT images with critical findings. In the internal and external validation datasets, the ADA achieved area under the curve values (95% confidence interval) of 0.85 (0.81-0.89) and 0.87 (0.85-0.89), respectively, for detecting emergency cases. In a clinical simulation test of an emergency cohort, the median wait time was significantly shorter post-ADA triage than pre-ADA triage by 294 s (422.5 s [interquartile range, IQR 299] to 70.5 s [IQR 168]), and the median radiology report turnaround time was significantly faster post-ADA triage than pre-ADA triage by 297.5 s (445.0 s [IQR 298] to 88.5 s [IQR 179]) (all p < 0.001).
分诊对于神经急症的早期诊断和报告至关重要。在此，我们报告了一种异常检测算法（ADA）的开发，该算法使用经过健康个体脑部计算机断层扫描（CT）图像训练的深度生成模型，对放射科工作清单进行重新排序，并为具有关键发现的脑部 CT 图像提供病变注意力图。在内部和外部验证数据集，ADA 分别实现了 0.85（0.81-0.89）和 0.87（0.85-0.89）的曲线下面积值（95%置信区间），用于检测急症病例。在急症队列的临床模拟测试中，ADA 分诊后的中位等待时间比分诊前显著缩短 294 秒（422.5 秒 [四分位距，IQR 299] 至 70.5 秒 [IQR 168]），ADA 分诊后的中位放射科报告周转时间也显著快于分诊前，缩短 297.5 秒（445.0 秒 [IQR 298] 至 88.5 秒 [IQR 179]）（均 p < 0.001）。
