uAI-HematomaCare flagged brain bleeds on CT in China's review

In the maker's trial that China's CMDE reviewed, uAI-HematomaCare flagged acute brain bleeds on stored head CT of 600 subjects with a sensitivity of 97.32% and a specificity of 99.67%.

  • Not rated an organization

    Accuracy was measured on stored scans in the maker's pre-market trial, the screening time was not measured and the report gives no result from use after approval.

Depth runs from 1, a convenience or time saved, to 5, a life or a livelihood preserved.

Status
Intended benefit.
Evidence

foundstudiedreportedclaimed

An independent regulatory document supports the benefit.

Compared with

Target values of 90% for sensitivity and specificity, with senior doctors' readings as the reference. Measured.

Without the system
target value 90%
With it
sensitivity 97.32% (95%CI: 94.80%, 98.84%) and specificity 99.67% (95%CI:98.16%, 99.99%)
The system’s part
Not isolated. The trial compared the software's triage flags with senior doctors' readings against target values. It did not compare screening with and without the software, and it did not measure time. The report says that the product uses deep learning.
Not yet checked
LimitsCosts and harmsLearns from dataLater outcome

Download data Cite Suggest a correction

Benefit type
Reduced Task Time
System
uAI-HematomaCare (颅内出血CT影像辅助分诊软件)
Made by
Shanghai United Imaging Intelligence Co., Ltd. (上海联影智能医疗科技有限公司)
Used by
Shanghai United Imaging Intelligence (retrospective registration trial on head CT of 600 subjects from three centers)
Where
Three centers that the report does not name, for a registration in China
Stage
Tested in a laboratory
Date
, when the source was published
Kind
Aggregate result
Broad benefit
Identifying Objects, Actions, and Events, Organizing, Planning, and Prioritizing Work, Estimating the Quantifiable Characteristics of Products, Events, or Information
Collections
Scrutiny and findings
Last revised
1 November 2026

Sources

  1. Regulatory document, by authors with no tie to the system.

    Center for Medical Device Evaluation (CMDE), National Medical Products Administration, China. 医疗器械产品注册技术审评报告：颅内出血CT影像辅助分诊软件 (technical review report for the registration of intracranial hemorrhage CT image triage-aid software), acceptance no. CQZ2100676, applicant 上海联影智能医疗科技有限公司. 4 March 2022. Section 四、产品受益风险判定 (benefit-risk determination).

    该产品临床主要受益为：可对颅脑 CT平扫影像进行显示、处理和分析，用于对超急性期、急性期颅内出血患者的分诊提示，可提高颅内出血患者的筛选效率。

Details

AI system

Reported configuration

Release R002

Workflow

The software analyzed non-contrast head CT on a server with a deep learning image processing module. It gave triage prompts for hyperacute and acute intracranial hemorrhage and quantified the volume of suspected bleeding. Senior doctors' readings served as the reference standard.

Follow-up

Conditions for replication

Images are non-contrast head CT. Trained doctors use the prompts and do not base a clinical decision on the software alone.

Entry details

Sector

Healthcare.

Purpose

Shanghai United Imaging Intelligence built uAI-HematomaCare to give trained doctors triage prompts for hyperacute and acute intracranial hemorrhage on non-contrast head CT.

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-HematomaCare flagged brain bleeds on CT in China's review (AIBD-1076). Artificial Intelligence Benefits Database, edition of 1 November 2026. https://petervartanian.xyz/aibd/records/AIBD-1076.html (archived at https://doi.org/10.7910/DVN/AADSII, version 7.0)

BibTeX Data Field definitions