EASYASPECT brought doctors' stroke CT scores closer to experts'

In the maker's reader trial that China's CMDE reviewed, doctors' stroke CT judgments agreed with an expert panel at a kappa of 0.80 with EASYASPECT, against 0.55 without it.

  • Not rated an organization

    Doctors scored past scans in the maker's pre-market trial, so no patient's care depended on the scores.

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

The same eight doctors scoring the same cases without the software, with an expert panel as the reference. Measured.

Without the system
Kappa 0.55 between doctors without the software and the expert panel
With it
Kappa 0.80 between doctors with the software and the expert panel (lower 95% confidence bound 0.79)
The system’s part
The same eight doctors scored every case with and without the software, so the gain in agreement is attributed to the software. The trial was the maker's own, and the reference was an expert panel's judgment.
Not yet checked
LimitsCosts and harmsLearns from dataLater outcome

Download data Cite Suggest a correction

Benefit type
Improved Task Accuracy
System
EASYASPECT (缺血性卒中CT图像辅助评估软件)
Made by
Yukun (Beijing) Network Technology Co., Ltd. (语坤（北京）网络科技有限公司)
Used by
Yukun (Beijing) Network Technology (retrospective reader trial at the Second Affiliated Hospital of Nanchang University and Hwa Mei Hospital of the University of Chinese Academy of Sciences in Ningbo)
Where
Ningbo, Zhejiang and Nanchang, Jiangxi, China
Stage
Tested in a laboratory
Date
, when the source was published
Kind
Aggregate result
Broad benefit
Identifying Objects, Actions, and Events, Analyzing Data or 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：缺血性卒中CT图像辅助评估软件 (technical review report for the registration of ischemic stroke CT image assessment-aid software), acceptance no. CQZ2201543, applicant 语坤（北京）网络科技有限公司. 11 July 2023. Section 三、临床评价概述 (clinical evaluation), pp. 7-8.

    医师使用AI与专家组间Kappa值（FAS和PPS：0.80）95%置信区间下限（FAS和 PPS：0.79）大于0.75，一致性较好，医师不使用AI与专家组间Kappa值（FAS和PPS：0.55）
    经对申请人提交的注册申报资料进行系统评价，基于当前认知水平，认为该产品临床使用受益大于风险，注册申报资料符合现行技术审评要求，建议予以注册。

Details

AI system

Reported configuration

Release 1.0 (full version 1.0.0.007)

Workflow

A deep learning algorithm segmented brain regions on non-contrast head CT, and the software judged whether each scoring region lost a point. Eight doctors at two hospitals read every case alone and with the software in randomized order, at least four weeks apart.

Follow-up

Conditions for replication

Patients are suspected of acute large-artery occlusion ischemic stroke within 6 hours. Trained doctors use the score and do not base clinical decisions on it alone. The software is not used in emergency care.

Entry details

Sector

Healthcare.

Purpose

Yukun (Beijing) Network Technology built EASYASPECT to compute the Alberta Stroke Program Early CT Score from non-contrast head CT of patients with suspected acute large-artery occlusion stroke within 6 hours.

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). EASYASPECT brought doctors' stroke CT scores closer to experts' (AIBD-1067). Artificial Intelligence Benefits Database, edition of 1 November 2026. https://petervartanian.xyz/aibd/records/AIBD-1067.html (archived at https://doi.org/10.7910/DVN/AADSII, version 7.0)

BibTeX Data Field definitions