Evidence map›Paper›PMID 42098114›Full record

ArticleNature communications2026

A DeepSeek-powered AI system for automated chest radiograph interpretation in clinical practice.

Yaowei Bai, Ruiheng Zhang, Yu Lei, Xuhua Duan, Jingfeng Yao, Shuguang Ju, Chaoyang Wang, Wei Yao, Yiwan Guo, Guilin Zhang and 13 more

Registry-linked trialAbstract readMulticenter Study
PubMed Full text at PMC Publisher
In one paragraph

Article in Nature communications, 2026. The graph could read no effect estimate from its abstract, so it casts no vote on the map. It is linked to trial NCT07117266 (A DeepSeek-Powered AI System for Automated Chest Radiograph Interpretation in Clinical Practice), which is not on this map. Cited by 1 paper.

0numbers the graph read from it
0cells of the map it votes in
1citing papers in PubMed
–field-weighted citation impact
1 · What the graph read from it

What it found

Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.

The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.

2 · The registry

The trial behind it

Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.

NCT07117266 nacompletednot on this map

A DeepSeek-Powered AI System for Automated Chest Radiograph Interpretation in Clinical Practice

TypeinterventionalSponsorUnion Hospital, Tongji Medical College, Huazhong University of Science and TechnologyRan2025 to 2025Enrolled296ConditionsX-Ray, AI (Artificial Intelligence), RadiologyArmsradiologists reference AI reports
3 · Its place in the literature

Who cites it

1 citing paper in PubMed.

  1. Review
4 · The record

Corrections and comments

PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.

5 · Who and what money

Authors and funding

23 authors.

Yaowei Bai *School of Computer Science, Wuhan University, Wuhan, China.ORCID http://orcid.org/0000-0002-2360-1445
Ruiheng Zhang *School of Computer Science, Wuhan University, Wuhan, China.
Yu Lei *Department of Radiology, Union Hospital, Tongji Medical College, Huazhong, University of Science and Technology, Wuhan, China.ORCID http://orcid.org/0009-0005-4618-0822
Xuhua Duan *Department of Interventional Radiology, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, China.
Jingfeng YaoSchool of Electronic Information and Communications, Huazhong, University of Science and Technology, Wuhan, China.
Shuguang JuDepartment of Interventional Radiology, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, China.
Chaoyang WangDepartment of Interventional Radiology, The First Affiliated Hospital of Henan University of Science and Technology, Luoyang, China.
Wei YaoDepartment of Radiology, Union Hospital, Tongji Medical College, Huazhong, University of Science and Technology, Wuhan, China.
Yiwan GuoDepartment of Radiology, Union Hospital, Tongji Medical College, Huazhong, University of Science and Technology, Wuhan, China.
Guilin ZhangDepartment of Radiology, Union Hospital, Tongji Medical College, Huazhong, University of Science and Technology, Wuhan, China.
Chao WanCancer Center, Union Hospital, Tongji Medical College, Huazhong, University of Science and Technology, Wuhan, China.
Qian YuanDepartment of Nephrology, Union Hospital, Tongji Medical College, Huazhong, University of Science and Technology, Wuhan, China.
Lei ChenDepartment of Radiology, Union Hospital, Tongji Medical College, Huazhong, University of Science and Technology, Wuhan, China.
Wenjuan TangDepartment of Radiology, Union Hospital, Tongji Medical College, Huazhong, University of Science and Technology, Wuhan, China.
Biqiang ZhuDepartment of Urology, The Central Hospital of Wuhan, Tongji Medical College, Huazhong, University of Science and Technology, Wuhan, China.
Xinggang WangSchool of Electronic Information and Communications, Huazhong, University of Science and Technology, Wuhan, China.ORCID http://orcid.org/0000-0001-6732-7823
Tao SunDepartment of Interventional Radiology, The First Affiliated Hospital of University of Science and Technology of China, Hefei, China.
Wei ZhouWuhan Artificial Intelligence Computing Center, Wuhan Supercomputing Center, Wuhan, China.
Dacheng TaoSchool of Computer Science and Engineering, Nanyang Technological University, Singapore, Singapore. dacheng.tao@ntu.edu.sg.ORCID http://orcid.org/0000-0001-7225-5449
Yongchao XuSchool of Computer Science, Wuhan University, Wuhan, China. yongchao.xu@whu.edu.cn.ORCID http://orcid.org/0000-0002-7253-3151
Chuansheng ZhengDepartment of Radiology, Union Hospital, Tongji Medical College, Huazhong, University of Science and Technology, Wuhan, China. hqzcsxh@sina.com.ORCID http://orcid.org/0000-0002-2435-1417
Huangxuan ZhaoSchool of Computer Science, Wuhan University, Wuhan, China. zhao_huangxuan@sina.com.ORCID http://orcid.org/0000-0002-9995-7528
Bo DuSchool of Computer Science, Wuhan University, Wuhan, China. dubo@whu.edu.cn.ORCID http://orcid.org/0000-0002-0059-8458

Funding

No grant is acknowledged in the PubMed record.

6 · The paper itself

Abstract

A global shortage of radiologists has increased the burden of chest X-ray interpretation, particularly in primary and resource-limited settings. Although artificial intelligence systems can assist with report generation, most lack rigorous prospective validation in real clinical environments. Here we show that Janus-Pro-CXR, a lightweight artificial intelligence system optimized for chest radiograph interpretation, improves report quality and workflow efficiency in a multicenter prospective study (NCT07117266). Developed through domain-specific fine-tuning of a multimodal foundation model, Janus-Pro-CXR achieved strong diagnostic performance for key thoracic findings and generated clinically structured reports aligned with expert standards. In real-world deployment involving 296 patients, AI assistance significantly improved report quality scores and reduced interpretation time by 18.3% compared with standard practice. The system operates efficiently on standard hardware, supporting practical implementation in resource-constrained settings. These findings demonstrate the clinical value of lightweight, human-AI collaborative systems in radiology practice.

Indexed as

Artificial IntelligenceRadiographic Image Interpretation, Computer-AssistedRadiography, ThoracicHumansIntelligent SystemsProspective StudiesWorkflow

Identifiers

PMID42098114
PMCPMC13365505

What OpenQuestion holds

Textmetadata
LicenceCC BY
Read underepoch 390

Registered trials

Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.