What happened
Shanghai United Imaging Intelligence built uAI-AorticDissection, software that uses deep learning on aortic CT angiography of adults to flag suspected acute aortic dissection for triage. The Center for Medical Device Evaluation (CMDE) of China's National Medical Products Administration reviewed the company's application for Class III registration. The trial was the maker's own, a retrospective, multicenter, single-arm study of 380 subjects at three institutions. An expert panel's reading served as the reference. The trial excluded patients with aortic ulcer, intramural hematoma, aneurysm, rupture or earlier aortic surgery or endovascular treatment. Case-level sensitivity was 99.46% (95% CI 96.99% to 99.90%) and specificity 98.45% (95% CI 95.55% to 99.47%). Both lower bounds exceeded the protocol's targets, which the report does not state. The software took 33.27 seconds per case on average, and no device defect occurred. On 4 November 2024, CMDE concluded that “该产品上市带来的受益大于风险” (the benefits of putting the product on the market outweigh the risks) and recommended approval. The trial used stored images, so the prompts guided no care. It did not compare doctors' reading with and without the software.
Sources
-
Regulatory document, by authors with no tie to the system.
AI软件分诊主动脉夹层患者的灵敏度和特异度分别为99.46%(95%CI: 96.99%,99.90%)和98.45%(95%CI: 95.55%, 99.47%),95%置信区间下限均高于目标值
经综合评价,认为该产品上市带来的受益大于风险,综合剩余风险可接受。
Details
AI system
- Reported configuration
-
Release 1.0 (full version 1.0.0.0.18)
- Workflow
-
The software analyzed adult aortic CT angiography with deep learning and gave a triage prompt for suspected acute aortic dissection. An expert panel's reading served as the reference standard.
Follow-up
- Conditions for replication
-
Images are chest or chest-abdomen CT angiography with slices thinner than 1.3 mm, as in the trial. The evidence covers patients without aortic ulcer, intramural hematoma, aneurysm, rupture or earlier aortic treatment, whom the trial excluded. Trained physicians use the prompt and do not base a clinical decision on it alone.
Entry details
- Sector
-
Healthcare.
- Purpose
-
Shanghai United Imaging Intelligence built uAI-AorticDissection to flag adults with suspected acute aortic dissection on aortic CT angiography so that trained physicians can triage them.
30 more questions not yet checked
model, provider, role, configuration, inputs and outputs, autonomy, human oversight, AI contribution, beneficiaries, reach, distribution and access, duration, every measurement question, every money question, ownership and control, dependencies, cross-border connections, geopolitical implications, replication attempts, availability, institutional decision, grounds, action and result, success criterion, every evidence question, observed or intended, alternative assessments, related entries, other identifiers, category mappings.
Cite this record
Peter H. Vartanian. (2026). uAI-AorticDissection flagged aortic dissections in China's review (AIBD-1084). Artificial Intelligence Benefits Database, edition of 1 November 2026. https://petervartanian.xyz/aibd/records/AIBD-1084.html (archived at https://doi.org/10.7910/DVN/AADSII, version 7.0)