<i>LungDiag</i>: Empowering artificial intelligence for respiratory diseases diagnosis based on electronic health records, a multicenter study
Respiratory diseases pose a significant global health burden, with challenges in early and accurate diagnosis due to overlapping clinical symptoms, which often leads to misdiagnosis or delayed treatment. To address this issue, we developed <i>LungDiag</i>, an artificial intelligence (AI)-based diagnostic system that utilizes natural language processing (NLP) to extract key clinical features from electronic health records (EHRs) for the accurate classification of respiratory diseases. This study employed a large cohort of 31,267 EHRs from multiple centers for model training and internal testing. Additionally, prospective real-world validation was conducted using 1142 EHRs from three external centers. <i>LungDiag</i> demonstrated superior diagnostic performance, achieving an F1 score of 0.711 for top 1 diagnosis and 0.927 for top 3 diagnoses. In real-world testing, <i>LungDiag</i> outperformed both human experts and ChatGPT 4.0, achieving an F1 score of 0.651 for top 1 diagnosis. The study emphasizes the potential of <i>LungDiag</i> as an effective tool to support physicians in diagnosing respiratory diseases more accurately and efficiently. Despite the promising results, further large-scale multicenter validation with larger sample sizes is still needed to confirm its clinical utility and generalizability.
Authors
- Zi-Hao Liu (ORCID: https://orcid.org/0000-0002-8809-1503)
- Peixuan Lin (ORCID: https://orcid.org/0000-0001-8825-1135)
- Hengrui Liang (ORCID: https://orcid.org/0000-0002-1155-5963)
- Luming Chen (ORCID: https://orcid.org/0000-0003-2468-8631)
- Tao Yang (ORCID: https://orcid.org/0000-0002-7521-4295)
- Bingliang Li
- Jiameng Li (ORCID: https://orcid.org/0000-0002-3486-3758)
- Zeping Yan
- Yifan Qi (ORCID: https://orcid.org/0000-0002-0665-2611)
- Taijiao Jiang (ORCID: https://orcid.org/0000-0002-6280-6347)
- Weiqiang Xu (ORCID: https://orcid.org/0000-0002-2929-6066)
- Meijia Wang
- Lizong Deng (ORCID: https://orcid.org/0000-0001-9314-262X)
- Li Li (ORCID: https://orcid.org/0000-0002-1522-6569)
- Wei Wang (ORCID: https://orcid.org/0000-0001-6853-7785)
- Zhiwei Wang (ORCID: https://orcid.org/0000-0001-6729-2237)
- Yilong Chen (ORCID: https://orcid.org/0000-0002-5127-2247)
- Yunhui Zhang (ORCID: https://orcid.org/0000-0001-9833-2908)
- Jianxing He (ORCID: https://orcid.org/0000-0003-1737-8192)
- Yajing Liao
- Wenhua Jian
Institutions
- First People's Hospital of Yunnan Province (CN)
- First Affiliated Hospital of Guangzhou Medical University (CN)
- Guangzhou Women and Children Medical Center (CN)
- Tiandi Science & Technology (China) (CN)
- Jiangsu Hengrui Medicine (China) (CN)
- State Key Laboratory of Respiratory Disease (CN)
- Tongji Hospital (CN)
- Huazhong University of Science and Technology (CN)
- Nanjing Medical University (CN)
- Guangzhou Medical University (CN)
Publication Details
- Journal
- MedComm
- Published
- 2025-01-01
- DOI
- https://doi.org/10.1002/mco2.70043
- Citations
- 7
- Primary Topic
- Machine Learning in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 17.37