AIDRscreening met its retinopathy accuracy targets in China's review

In the maker's prospective multicenter trial that China's CMDE reviewed, AIDRscreening detected stage II or worse diabetic retinopathy with accuracy that met its targets. No figures are given.

  • Not rated an organization

    The report gives no figures from the maker's pre-market trials and 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

Senior doctors' readings as the gold standard, with preset accuracy targets. Measured.

The system’s part
Not isolated. The trials compared the software's results with senior doctors' readings against preset targets. Secondary endpoints included gains in accuracy and time with the software, but the report gives no results for them. The report says that the product uses a convolutional neural network.
Not yet checked
LimitsCosts and harmsLearns from dataLater outcome

Download data Cite Suggest a correction

Benefit type
Improved Task Accuracy
System
AIDRscreening (糖尿病视网膜病变眼底图像辅助诊断软件)
Made by
Shenzhen SiBionics Intelligent Technology Co., Ltd. (深圳硅基智能科技有限公司)
Used by
Shenzhen SiBionics Intelligent Technology (prospective multicenter and retrospective registration trials)
Where
Trial 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
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：糖尿病视网膜病变眼底图像辅助诊断软件 (technical review report for the registration of diabetic retinopathy fundus image diagnosis-aid software), acceptance no. CQZ1900668, applicant 深圳硅基智能科技有限公司. 31 July 2020. Section 三、临床评价摘要 (clinical evaluation summary).

    该产品对需要获得糖尿病视网膜病变诊断的人员是否可见 II 期或 II 期以上的糖尿病视网膜病变进行辅助诊断的诊断准确度指标达到预期目标

Details

AI system

Reported configuration

Release V01 (full version V01.00.00.00)

Workflow

The software analyzed color fundus photos of both eyes with a convolutional neural network on a cloud server. Trained licensed doctors checked image quality before analysis. Senior doctors' readings served as the gold standard.

Follow-up

Conditions for replication

Patients are adults with diabetes. Photos come from the specified fundus camera models, and trained doctors approve their quality. Licensed doctors make the diagnosis and do not decide on the software's result alone.

Entry details

Sector

Healthcare.

Purpose

Shenzhen SiBionics Intelligent Technology built AIDRscreening to tell licensed doctors whether fundus photos of adults with diabetes show stage II or worse diabetic retinopathy and whether further examination is needed.

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). AIDRscreening met its retinopathy accuracy targets in China's review (AIBD-1080). Artificial Intelligence Benefits Database, edition of 1 November 2026. https://petervartanian.xyz/aibd/records/AIBD-1080.html (archived at https://doi.org/10.7910/DVN/AADSII, version 7.0)

BibTeX Data Field definitions