JF CXR-1 agreed with expert readers on TB chest X-rays in a trial

In the maker's six-center trial that China's CMDE reviewed, JF CXR-1 agreed with a central reading panel on 94.19% of positive and 91.17% of negative chest X-rays.

  • Not rated an organization

    Agreement was measured against a reading panel in the maker's pre-market trial, and the report does not say that the prompts guided 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

Preset targets for agreement with an independent central reading panel. Measured.

Without the system
Targets of 85% positive agreement and 70% negative agreement
With it
94.19% positive agreement and 91.17% negative agreement
The system’s part
Not isolated. The trial measured agreement between the software and an independent central reading panel against preset targets. It did not compare physicians' readings with and without the software. The trial was the maker's own. The report says that the tuberculosis image module uses deep learning.
Not yet checked
LimitsCosts and harmsLearns from dataLater outcome

Download data Cite Suggest a correction

Benefit type
Improved Task Accuracy
System
JF CXR-1 (肺结核X射线图像辅助评估软件)
Made by
Jiangxi Zhongke Jiufeng Smart Medical Technology Co., Ltd. (江西中科九峰智慧医疗科技有限公司)
Used by
Jiangxi Zhongke Jiufeng Smart Medical Technology (prospective trial with 1,165 cases at six centers)
Where
Six trial centers 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：肺结核X射线图像辅助评估软件 (technical review report for the registration of pulmonary tuberculosis X-ray image assessment-aid software), acceptance no. CQZ2100859, applicant 江西中科九峰智慧医疗科技有限公司. 18 October 2022. Section 三、临床评价概述 (clinical evaluation).

    Kappa 值为 0.854，表明试验产品结果与中心阅片结果一致
    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。

Details

AI system

Reported configuration

Release 2 (full version 2.0.0)

Workflow

The software read frontal chest DR images with a deep learning tuberculosis module on a server. An independent central reading panel served as the reference, and an arbitrating physician re-read 133 disputed cases.

Follow-up

Conditions for replication

The product does not apply to healed (old) pulmonary tuberculosis or to patients with immune deficiencies such as neutrophil disorders. Trained physicians use the prompt and do not base a diagnosis or treatment decision on it alone.

Entry details

Sector

Healthcare.

Purpose

Jiangxi Zhongke Jiufeng Smart Medical Technology built JF CXR-1 to prompt trained physicians when frontal chest DR images suggest active tuberculosis in patients without immune deficiency.

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). JF CXR-1 agreed with expert readers on TB chest X-rays in a trial (AIBD-1083). Artificial Intelligence Benefits Database, edition of 1 November 2026. https://petervartanian.xyz/aibd/records/AIBD-1083.html (archived at https://doi.org/10.7910/DVN/AADSII, version 7.0)

BibTeX Data Field definitions