Li Ben, Enichen Elizabeth J, Heydari Kimia, Kvedar Joseph C
Division of Vascular Surgery, University of Toronto, Toronto, ON, Canada.
Temerty Centre for Artificial Intelligence Research and Education in Medicine, University of Toronto, Toronto, ON, Canada.
NPJ Digit Med. 2025 May 5;8(1):248. doi: 10.1038/s41746-025-01613-2.
Deep vein thrombosis (DVT) causes significant morbidity/mortality and timely diagnosis often via ultrasound is critical. However, the shortage of trained ultrasound providers has been an ongoing challenge. Recently, Speranza and colleagues (2025) demonstrated that an artificial intelligence (AI) guided ultrasound system used by non-ultrasound-trained nurses with remote clinician review can achieve sensitivities of 90–98% and specificities of 74–100% for diagnosing DVT. This study highlights the potential for AI guided imaging to address important gaps in health care delivery.
深静脉血栓形成（DVT）会导致严重的发病/死亡情况，通常通过超声进行及时诊断至关重要。然而，训练有素的超声检查人员短缺一直是个持续存在的挑战。最近，斯佩兰扎及其同事（2025年）证明，由未经超声培训的护士使用并经远程临床医生审核的人工智能（AI）引导超声系统，在诊断DVT时可达到90 - 98%的灵敏度和74 - 100%的特异性。这项研究凸显了AI引导成像在弥补医疗服务重要差距方面的潜力。
