HW-ES helped endoscopists miss fewer colon polyps in a trial

In the maker's randomized trial that China's CMDE reviewed, endoscopists using HW-ES missed 12.41% of polyps, against 50.80% without it.

  • Not rated an organization

    The miss rates were measured in the maker's pre-market trial, and the report gives no outcome of care for any patient.

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

Endoscopists examining without the software in the same randomized trial. Measured.

Without the system
50.80% lesion-level polyp miss rate
With it
12.41% lesion-level polyp miss rate
The system’s part
The randomized trial compared endoscopists with and without the software, so the difference in miss rates is attributed to the software. The trial was the maker's own. The report says that the core algorithm uses deep learning.
Not yet checked
LimitsCosts and harmsLearns from dataLater outcome

Download data Cite Suggest a correction

Benefit type
Improved Task Accuracy
System
HW-ES (肠息肉电子下消化道内窥镜图像辅助检测软件)
Made by
Changsha Huiwei Intelligent Medical Technology Co., Ltd. (长沙慧维智能医疗科技有限公司)
Used by
Changsha Huiwei Intelligent Medical Technology (prospective randomized trial with 354 patients at three sites)
Where
Three trial sites that the report does not name, for a registration in China
Stage
In a pilot
Date
, when the source was published
Kind
Aggregate result
Broad benefit
Identifying Objects, Actions, and Events, Monitoring Processes, Materials, or Surroundings
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：肠息肉电子下消化道内窥镜图像辅助检测软件 (technical review report for the registration of colon polyp detection-aid software for electronic lower gastrointestinal endoscope images), acceptance no. CQZ2302046, applicant 长沙慧维智能医疗科技有限公司. 16 December 2024. Section 三、临床评价概述 (clinical evaluation).

    主要评价指标：息肉漏诊率，FAS 集病灶水平，试验组为 12.41%，对照组为 50.80%，组间差值为-38.39%
    根据申请人提供的申报资料，经综合评价，在目前认知水平上，认为该产品的上市为适用人群带来的受益大于风险。

Details

AI system

Reported configuration

Release V1

Workflow

A dual-stream deep convolutional neural network checked each video frame, and a sliding-window algorithm removed likely false alarms. The software showed suspected polyp areas in real time on a separate video output from the endoscope's image processor.

Follow-up

Conditions for replication

Patients are adults aged 18 to 85 with adequate bowel preparation. The specified endoscope models are used in white-light mode. Endoscopists judge each mark and do not base a clinical decision on the software alone.

Entry details

Sector

Healthcare.

Purpose

Changsha Huiwei Intelligent Medical Technology built HW-ES to show licensed endoscopists the areas of suspected polyps in real time during adult colonoscopy.

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). HW-ES helped endoscopists miss fewer colon polyps in a trial (AIBD-1060). Artificial Intelligence Benefits Database, edition of 1 November 2026. https://petervartanian.xyz/aibd/records/AIBD-1060.html (archived at https://doi.org/10.7910/DVN/AADSII, version 7.0)

BibTeX Data Field definitions