LungDiag: Empowering artificial intelligence for respiratory diseases diagnosis based on electronic health records, a multicenter study
Abstract 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 LungDiag, an artificial intelligence (AI)‐based dia...
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2025-01-01
|
| Series: | MedComm |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/mco2.70043 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832594254177763328 |
|---|---|
| author | Hengrui Liang Tao Yang Zihao Liu Wenhua Jian Yilong Chen Bingliang Li Zeping Yan Weiqiang Xu Luming Chen Yifan Qi Zhiwei Wang Yajing Liao Peixuan Lin Jiameng Li Wei Wang Li Li Meijia Wang YunHui Zhang Lizong Deng Taijiao Jiang Jianxing He |
| author_facet | Hengrui Liang Tao Yang Zihao Liu Wenhua Jian Yilong Chen Bingliang Li Zeping Yan Weiqiang Xu Luming Chen Yifan Qi Zhiwei Wang Yajing Liao Peixuan Lin Jiameng Li Wei Wang Li Li Meijia Wang YunHui Zhang Lizong Deng Taijiao Jiang Jianxing He |
| author_sort | Hengrui Liang |
| collection | DOAJ |
| description | Abstract 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 LungDiag, 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. LungDiag 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, LungDiag 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 LungDiag 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. |
| format | Article |
| id | doaj-art-f6123a366da94007a830c55ffc0d5a98 |
| institution | Kabale University |
| issn | 2688-2663 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | MedComm |
| spelling | doaj-art-f6123a366da94007a830c55ffc0d5a982025-01-20T01:45:44ZengWileyMedComm2688-26632025-01-0161n/an/a10.1002/mco2.70043LungDiag: Empowering artificial intelligence for respiratory diseases diagnosis based on electronic health records, a multicenter studyHengrui Liang0Tao Yang1Zihao Liu2Wenhua Jian3Yilong Chen4Bingliang Li5Zeping Yan6Weiqiang Xu7Luming Chen8Yifan Qi9Zhiwei Wang10Yajing Liao11Peixuan Lin12Jiameng Li13Wei Wang14Li Li15Meijia Wang16YunHui Zhang17Lizong Deng18Taijiao Jiang19Jianxing He20Department of Thoracic SurgeryChina State Key Laboratory of Respiratory Disease & National Clinical Research Center for Respiratory Diseasethe Key laboratory of Advanced Interdisciplinary Studies Centerthe First Affiliated Hospital of Guangzhou Medical UniversityGuangzhouChinaGuangzhou National LaboratoryGuangzhouChinaDepartment of Thoracic SurgeryChina State Key Laboratory of Respiratory Disease & National Clinical Research Center for Respiratory Diseasethe Key laboratory of Advanced Interdisciplinary Studies Centerthe First Affiliated Hospital of Guangzhou Medical UniversityGuangzhouChinaDepartment of Thoracic SurgeryChina State Key Laboratory of Respiratory Disease & National Clinical Research Center for Respiratory Diseasethe Key laboratory of Advanced Interdisciplinary Studies Centerthe First Affiliated Hospital of Guangzhou Medical UniversityGuangzhouChinaDepartment of Research and DevelopementTianpeng Technology Co. LtdGuangzhou ChinaDepartment of Thoracic SurgeryChina State Key Laboratory of Respiratory Disease & National Clinical Research Center for Respiratory Diseasethe Key laboratory of Advanced Interdisciplinary Studies Centerthe First Affiliated Hospital of Guangzhou Medical UniversityGuangzhouChinaDepartment of Thoracic SurgeryChina State Key Laboratory of Respiratory Disease & National Clinical Research Center for Respiratory Diseasethe Key laboratory of Advanced Interdisciplinary Studies Centerthe First Affiliated Hospital of Guangzhou Medical UniversityGuangzhouChinaDepartment of Thoracic SurgeryChina State Key Laboratory of Respiratory Disease & National Clinical Research Center for Respiratory Diseasethe Key laboratory of Advanced Interdisciplinary Studies Centerthe First Affiliated Hospital of Guangzhou Medical UniversityGuangzhouChinaGuangzhou National LaboratoryGuangzhouChinaSchool of Health Policy and ManagementNanjing Medical UniversityNanjing ChinaDepartment of Thoracic SurgeryChina State Key Laboratory of Respiratory Disease & National Clinical Research Center for Respiratory Diseasethe Key laboratory of Advanced Interdisciplinary Studies Centerthe First Affiliated Hospital of Guangzhou Medical UniversityGuangzhouChinaDepartment of Thoracic SurgeryChina State Key Laboratory of Respiratory Disease & National Clinical Research Center for Respiratory Diseasethe Key laboratory of Advanced Interdisciplinary Studies Centerthe First Affiliated Hospital of Guangzhou Medical UniversityGuangzhouChinaDepartment of Thoracic SurgeryChina State Key Laboratory of Respiratory Disease & National Clinical Research Center for Respiratory Diseasethe Key laboratory of Advanced Interdisciplinary Studies Centerthe First Affiliated Hospital of Guangzhou Medical UniversityGuangzhouChinaDepartment of Thoracic SurgeryChina State Key Laboratory of Respiratory Disease & National Clinical Research Center for Respiratory Diseasethe Key laboratory of Advanced Interdisciplinary Studies Centerthe First Affiliated Hospital of Guangzhou Medical UniversityGuangzhouChinaDepartment of Thoracic SurgeryChina State Key Laboratory of Respiratory Disease & National Clinical Research Center for Respiratory Diseasethe Key laboratory of Advanced Interdisciplinary Studies Centerthe First Affiliated Hospital of Guangzhou Medical UniversityGuangzhouChinaDepartment of Respiratory DiseaseThe First People's Hospital of Kashi PrefectureKashi ChinaDepartment of Respiratory and Critical Care MedicineNational Clinical Research Center of Respiratory DiseaseKey Laboratory of Pulmonary Diseases of Health MinistryTongji HospitalTongji Medical CollegeHuazhong University of Science and TechnologyWuhanHubeiChinaDepartment of Respiratory DiseaseThe First People's Hospital of Yunnan ProvinceKunming ChinaSchool of Health Policy and ManagementNanjing Medical UniversityNanjing ChinaGuangzhou National LaboratoryGuangzhouChinaDepartment of Thoracic SurgeryChina State Key Laboratory of Respiratory Disease & National Clinical Research Center for Respiratory Diseasethe Key laboratory of Advanced Interdisciplinary Studies Centerthe First Affiliated Hospital of Guangzhou Medical UniversityGuangzhouChinaAbstract 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 LungDiag, 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. LungDiag 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, LungDiag 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 LungDiag 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.https://doi.org/10.1002/mco2.70043artificial intelligence (AI)electronic medical records (EHRs)natural language processing (NLP)respiratory diseases |
| spellingShingle | Hengrui Liang Tao Yang Zihao Liu Wenhua Jian Yilong Chen Bingliang Li Zeping Yan Weiqiang Xu Luming Chen Yifan Qi Zhiwei Wang Yajing Liao Peixuan Lin Jiameng Li Wei Wang Li Li Meijia Wang YunHui Zhang Lizong Deng Taijiao Jiang Jianxing He LungDiag: Empowering artificial intelligence for respiratory diseases diagnosis based on electronic health records, a multicenter study MedComm artificial intelligence (AI) electronic medical records (EHRs) natural language processing (NLP) respiratory diseases |
| title | LungDiag: Empowering artificial intelligence for respiratory diseases diagnosis based on electronic health records, a multicenter study |
| title_full | LungDiag: Empowering artificial intelligence for respiratory diseases diagnosis based on electronic health records, a multicenter study |
| title_fullStr | LungDiag: Empowering artificial intelligence for respiratory diseases diagnosis based on electronic health records, a multicenter study |
| title_full_unstemmed | LungDiag: Empowering artificial intelligence for respiratory diseases diagnosis based on electronic health records, a multicenter study |
| title_short | LungDiag: Empowering artificial intelligence for respiratory diseases diagnosis based on electronic health records, a multicenter study |
| title_sort | lungdiag empowering artificial intelligence for respiratory diseases diagnosis based on electronic health records a multicenter study |
| topic | artificial intelligence (AI) electronic medical records (EHRs) natural language processing (NLP) respiratory diseases |
| url | https://doi.org/10.1002/mco2.70043 |
| work_keys_str_mv | AT hengruiliang lungdiagempoweringartificialintelligenceforrespiratorydiseasesdiagnosisbasedonelectronichealthrecordsamulticenterstudy AT taoyang lungdiagempoweringartificialintelligenceforrespiratorydiseasesdiagnosisbasedonelectronichealthrecordsamulticenterstudy AT zihaoliu lungdiagempoweringartificialintelligenceforrespiratorydiseasesdiagnosisbasedonelectronichealthrecordsamulticenterstudy AT wenhuajian lungdiagempoweringartificialintelligenceforrespiratorydiseasesdiagnosisbasedonelectronichealthrecordsamulticenterstudy AT yilongchen lungdiagempoweringartificialintelligenceforrespiratorydiseasesdiagnosisbasedonelectronichealthrecordsamulticenterstudy AT bingliangli lungdiagempoweringartificialintelligenceforrespiratorydiseasesdiagnosisbasedonelectronichealthrecordsamulticenterstudy AT zepingyan lungdiagempoweringartificialintelligenceforrespiratorydiseasesdiagnosisbasedonelectronichealthrecordsamulticenterstudy AT weiqiangxu lungdiagempoweringartificialintelligenceforrespiratorydiseasesdiagnosisbasedonelectronichealthrecordsamulticenterstudy AT lumingchen lungdiagempoweringartificialintelligenceforrespiratorydiseasesdiagnosisbasedonelectronichealthrecordsamulticenterstudy AT yifanqi lungdiagempoweringartificialintelligenceforrespiratorydiseasesdiagnosisbasedonelectronichealthrecordsamulticenterstudy AT zhiweiwang lungdiagempoweringartificialintelligenceforrespiratorydiseasesdiagnosisbasedonelectronichealthrecordsamulticenterstudy AT yajingliao lungdiagempoweringartificialintelligenceforrespiratorydiseasesdiagnosisbasedonelectronichealthrecordsamulticenterstudy AT peixuanlin lungdiagempoweringartificialintelligenceforrespiratorydiseasesdiagnosisbasedonelectronichealthrecordsamulticenterstudy AT jiamengli lungdiagempoweringartificialintelligenceforrespiratorydiseasesdiagnosisbasedonelectronichealthrecordsamulticenterstudy AT weiwang lungdiagempoweringartificialintelligenceforrespiratorydiseasesdiagnosisbasedonelectronichealthrecordsamulticenterstudy AT lili lungdiagempoweringartificialintelligenceforrespiratorydiseasesdiagnosisbasedonelectronichealthrecordsamulticenterstudy AT meijiawang lungdiagempoweringartificialintelligenceforrespiratorydiseasesdiagnosisbasedonelectronichealthrecordsamulticenterstudy AT yunhuizhang lungdiagempoweringartificialintelligenceforrespiratorydiseasesdiagnosisbasedonelectronichealthrecordsamulticenterstudy AT lizongdeng lungdiagempoweringartificialintelligenceforrespiratorydiseasesdiagnosisbasedonelectronichealthrecordsamulticenterstudy AT taijiaojiang lungdiagempoweringartificialintelligenceforrespiratorydiseasesdiagnosisbasedonelectronichealthrecordsamulticenterstudy AT jianxinghe lungdiagempoweringartificialintelligenceforrespiratorydiseasesdiagnosisbasedonelectronichealthrecordsamulticenterstudy |