AI Local AutoVision cut karyotype analysis time in China's review

In the maker's trial that China's CMDE reviewed, investigators using AI Local AutoVision took 11.19 minutes on average per karyotype, against 34.42 minutes by hand.

  • Not rated an organization

    The time saving was measured in the maker's pre-market trial, and the report gives no result from laboratories using the approved product.

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

Traditional manual karyotype analysis of the same cases, with an expert panel's analysis as the reference. Measured.

Without the system
34.42±11.48min on average by traditional manual analysis
With it
11.19±5.48min on average with the software
The system’s part
Every case was analyzed both with the software and by traditional manual analysis against the same expert panel, so the time saving is attributed to the software. The trial was the maker's own. The report says that three of the software's functions use deep learning.
Not yet checked
LimitsCosts and harmsLearns from dataLater outcome

Download data Cite Suggest a correction

Benefit type
Reduced Task Time
System
AI Local AutoVision (染色体核型图像辅助诊断软件)
Made by
Hangzhou Diagens Biotechnology Co., Ltd. (杭州德适生物科技股份有限公司)
Used by
Hangzhou Diagens Biotechnology (registration trial with 1,734 subjects at three hospitals)
Where
First People's Hospital of Yunnan Province, Third Affiliated Hospital of Zhengzhou University and Reproductive Hospital Affiliated to Shandong University, China
Stage
Tested in a laboratory
Date
, when the source was published
Kind
Aggregate result
Broad benefit
Identifying Objects, Actions, and Events, Processing 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：染色体核型图像辅助诊断软件 (technical review report for the registration of chromosome karyotype image diagnosis-aid software), acceptance no. CQZ2501137, applicant 杭州德适生物科技股份有限公司. 14 May 2026. Section 三、临床评价概述 (clinical evaluation).

    研究者联合应用试验器械组较传统人工组减少核型分析用时 23.23min（95%CI：-23.67min，-22.80min）
    经综合评价，在目前认知水平上，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。

  2. Press release, by the makers. Context or contrary evidence.

    Hangzhou Diagens Biotechnology Co., Ltd. (stock code 2526). Voluntary announcement: the Company's core product, AI AutoVision®, received Class III medical device registration certificate from National Medical Products Administration. HKEXnews, 22 May 2026.

    on May 20, 2026, AI AutoVision®, the Company’s Core Product, received the Class III Medical Device Registration Certificate from the National Medical Products Administration of China

Details

AI system

Reported configuration

Release 2 (full version 2.0.0.0)

Workflow

The software read metaphase images of G-banded chromosomes from amniotic fluid and peripheral blood samples. It cut, counted, identified and arranged the chromosomes and flagged suspected abnormalities for the investigators to check. An expert panel's karyotype analysis served as the reference standard.

Follow-up

Conditions for replication

Trained professionals still analyze every chromosome, including those that the software does not flag. Professionals decide whether a case is abnormal and write the karyotype and the report themselves. Patients with blood diseases fall outside the intended use.

Entry details

Sector

Healthcare.

Purpose

Hangzhou Diagens Biotechnology built AI Local AutoVision to cut, count, identify and arrange chromosomes in karyotype images and to flag suspected abnormalities for trained professionals.

29 more questions not yet checked

model, provider, role, configuration, inputs and outputs, autonomy, human oversight, 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). AI Local AutoVision cut karyotype analysis time in China's review (AIBD-0956). Artificial Intelligence Benefits Database, edition of 1 November 2026. https://petervartanian.xyz/aibd/records/AIBD-0956.html (archived at https://doi.org/10.7910/DVN/AADSII, version 7.0)

BibTeX Data Field definitions