MIAS-3000 flagged macular degeneration on OCT scans in China's review

In the maker's trial that China's CMDE reviewed, MIAS-3000 flagged intermediate or later age-related macular degeneration on OCT with 95.5% sensitivity and 92.1% specificity per eye.

  • Not rated an organization

    The accuracy was measured in the maker's pre-market trial, and the report does not say that the software's suggestions changed any patient's care.

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

A target of 85% for the lower 95% confidence bounds of sensitivity and specificity. Measured.

Without the system
Target of 85% for the lower confidence bounds
With it
Sensitivity 95.5%, 95%CI（92.5%，97.5%） and specificity 92.1%, 95%CI（89.6%，94.2%） per eye
The system’s part
Not isolated. Doctors read the scans with and without the software, but the report gives only the difference in reading time between the groups. It does not say whether the primary accuracy figures describe the software or the doctors using it. The trial was the maker's own. The report says that the algorithm is a deep-learning model based on convolutional neural networks.
Not yet checked
LimitsCosts and harmsLearns from dataLater outcome

Download data Cite Suggest a correction

Benefit type
Improved Task Accuracy
System
MIAS-3000 (眼科OCT图像辅助诊断软件)
Made by
Suzhou Bigvision Medical Technology Co., Ltd. (苏州比格威医疗科技有限公司)
Used by
Suzhou Bigvision Medical Technology (prospective multicenter registration trial with 908 subjects)
Where
Trial sites in China that the report does not name
Stage
In a pilot
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：眼科OCT图像辅助诊断软件 (technical review report for the registration of ophthalmic OCT image diagnosis-aid software), acceptance no. CQZ2400999, applicant 苏州比格威医疗科技有限公司. 9 October 2025. Section 三、临床评价概述 (clinical evaluation).

    临床试验结果显示，主要有效性单人单眼层面 FAS 集灵敏度为 95.5%，95%CI（92.5%，97.5%）
    经对申请人提交的注册申报资料进行系统评价，申报产品符合安全性、有效性的要求，符合现有认知水平，建议准予注册。

Details

AI system

Reported configuration

Release V1

Workflow

The algorithm analyzed each OCT slice of an eye for lesions and features of age-related macular degeneration. The results for each eye were combined according to a Chinese clinical pathway of 2013 into a diagnostic suggestion.

Follow-up

Conditions for replication

Patients are aged 50 or over and are suspected of or followed up for age-related macular degeneration. Scans are taken with the BV1000 OCT device of Jiangxi Bigvision Medical Technology. A doctor judges whether the image quality allows analysis and does not decide on the software's suggestion alone.

Entry details

Sector

Healthcare.

Purpose

Suzhou Bigvision Medical Technology built MIAS-3000 to tell eye doctors whether patients aged 50 and over have intermediate or later age-related macular degeneration with large drusen on OCT scans.

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). MIAS-3000 flagged macular degeneration on OCT scans in China's review (AIBD-1091). Artificial Intelligence Benefits Database, edition of 1 November 2026. https://petervartanian.xyz/aibd/records/AIBD-1091.html (archived at https://doi.org/10.7910/DVN/AADSII, version 7.0)

BibTeX Data Field definitions