What happened
Infervision Medical Technology built IR-CT-AO, software that uses deep learning to segment and name the aorta on CT angiography and flag suspected aortic dissection for triage. It is meant for adults with risk factors, pain or signs that suggest dissection. 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 prospective, multicenter, single-arm study of 485 subjects. Three senior physicians with more than 10 years of cardiothoracic imaging experience read each case independently, and the majority view was the reference. Sensitivity was 87.83% (95% CI 82.30% to 92.13%) and specificity 97.64% (95% CI 95.19% to 98.95%), both above targets of 80%. The report gives the software's triage time as 130 seconds, and no software failure or adverse event occurred. On 5 August 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 report names neither the trial sites nor their number. It does not say that the prompts guided care.
Sources
-
Regulatory document, by authors with no tie to the system.
主动脉夹层分诊的灵敏度为 87.83%, 95%置信区间为[82.30%, 92.13%], 下限高于目标值 80%
综上,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 (full version 1.0.3.0)
- Workflow
-
The software segmented and named the aorta on CT angiography with deep learning and flagged suspected aortic dissection. Three physicians with more than 10 years of cardiothoracic imaging experience read each case independently, and the majority view served as the reference.
Follow-up
- Conditions for replication
-
Patients are adults with risk factors, pain or signs that suggest aortic dissection. CT angiography slices are 2 mm or thinner, as in the trial. Trained physicians use the prompt and do not base a clinical decision on it alone.
Entry details
- Sector
-
Healthcare.
- Purpose
-
Infervision Medical Technology built IR-CT-AO to flag suspected aortic dissection on CT angiography of adults so that trained physicians can triage and assess 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). IR-CT-AO flagged aortic dissections in a prospective trial in China (AIBD-1087). Artificial Intelligence Benefits Database, edition of 1 November 2026. https://petervartanian.xyz/aibd/records/AIBD-1087.html (archived at https://doi.org/10.7910/DVN/AADSII, version 7.0)