EA PC-LGI helped endoscopists find more polyps in a Chinese trial

In EndoAngel's colonoscopy trial that China's CMDE reviewed, endoscopists using EA PC-LGI detected 84.97% of polyps, against 72.07% in colonoscopies without it.

  • Not rated an organization

    Endoscopists found more polyps with the software in the maker's pre-market trial, and the report gives no outcome of care.

  • Not rated a person

    Patients in the software group had more of their polyps detected, but the report gives no outcome for their health.

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

Status
Intended benefit.
Evidence

foundstudiedreportedclaimed

Two independent regulatory documents support the benefit.

Compared with

Colonoscopy without the software in the same trial, with experts' review of the recorded videos as the reference. Measured.

Without the system
72.07% polyp-level sensitivity
With it
84.97% polyp-level sensitivity
The system’s part
Patients had colonoscopy with or without the software in parallel groups, so the gain in sensitivity is attributed to the software. The trial was the maker's own, and EndoAngel funded the published paper on it.
Not yet checked
LimitsCosts and harmsLearns from dataLater outcome

Download data Cite Suggest a correction

Benefit type
Improved Task Accuracy
System
EA PC-LGI (肠息肉电子下消化道内窥镜图像辅助检测软件)
Made by
Wuhan EndoAngel Medical Technology Co., Ltd. (武汉楚精灵医疗科技有限公司)
Used by
Wuhan EndoAngel Medical Technology (prospective trial at Ruijin Hospital, Beijing Cancer Hospital and the Central Hospital of Wuhan)
Where
Shanghai, Beijing and Wuhan, 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. Peer-reviewed study, by an evaluator that the makers or users commissioned.

    Zhang H, Wu Q, Sun J, Wang J, Zhou L, Cai W, Zou D. A computer-aided system improves the performance of endoscopists in detecting colorectal polyps: a multi-center, randomized controlled trial. Frontiers in Medicine 10:1341259, 24 January 2024. doi:10.3389/fmed.2023.1341259. A sponsor-initiated study funded by Wuhan ENDOANGEL Medical Technology.

    The sensitivity of the endoscopists in the two groups was 84.97% (95% Confidence Interval [CI], 82.76-87.17%) and 72.07% (95% CI, 69.43-74.71%), the difference in sensitivity between the two groups was 12.89% (95% CI, 9.46-16.33%)

  2. 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 intestinal polyp lower gastrointestinal endoscope image detection-aid software), acceptance no. CQZ2200536, applicant 武汉楚精灵医疗科技有限公司. 20 April 2023. Section 三、临床评价概述 (clinical evaluation).

    医生在 AI 辅助下息肉检出敏感性（以息肉为单位）为 84.97%（95CI：82.76%，87.17%） ，优于医生独立检出敏感性 72.07%（95CI：69.43%，74.71%）
    临床试验结果显示，医生在本产品辅助下能够一定程度上提高息肉检出率。

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

    National Medical Products Administration (NMPA), China. Computer Aided Detection Software for Intestinal Polyps in Lower Gastrointestinal Endoscopy Approved for Marketing. NMPA English website, 12 May 2023.

    Compared with similar products already marketed at home and abroad, this product uses deep learning technology, perceptual hash algorithm, and other technologies to assist doctors in operation control while identifying polyps, further ensuring the quality of proctoscopy, reducing missed detections, and improving the standardization of examination operations.

Details

AI system

Reported configuration

Release V1.0

Workflow

The software took video from the endoscope's image processor and marked suspected polyps with boxes on a separate monitor. Endoscopists at three centers performed colonoscopy with or without the software, and experts reviewed the recorded videos as the reference.

Follow-up

Conditions for replication

Patients are adults having colonoscopy in a medical institution. The endoscope and image processor are specified models used in white light mode. Endoscopists judge polyps from the images and the patient's condition and do not decide on the marks alone.

Entry details

Sector

Healthcare.

Purpose

Wuhan EndoAngel Medical Technology built EA PC-LGI to mark suspected polyps in real time during adult colonoscopy and to monitor the cecum, withdrawal time and withdrawal speed.

References

Other identifiers

Chictr: ChiCTR2100041988.

28 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, category mappings.

Cite this record

Peter H. Vartanian. (2026). EA PC-LGI helped endoscopists find more polyps in a Chinese trial (AIBD-1069). Artificial Intelligence Benefits Database, edition of 1 November 2026. https://petervartanian.xyz/aibd/records/AIBD-1069.html (archived at https://doi.org/10.7910/DVN/AADSII, version 7.0)

BibTeX Data Field definitions