首页 / 院系成果 / 成果详情页

Multimodal machine learning enables AI chatbot to diagnose ophthalmic diseases and provide high-quality medical responses 期刊论文

编号：

E924629ACD75C12BD2B4114629DCE6A6
作者：

Ma, Ruiqi^[1,2,3,4,5] Cheng, Qian^[6] Yao, Jing^[1,2,3,4,5] Peng, Zhiyu^{[1,2,3,4,5,7]} Yan, Mingxu^{[1,2,3,4,5,8]} Lu, Jie^{[1,2,3,4,5,8]} Liao, Jingjing^[6] Tian, Lejin^[9] Shu, Wenjun^{[1,2,3,4,5,8]} Zhang, Yunqiu^[10,11] Wang, Jinghan^[1,2,3,4,5] Jiang, Pengfei^[12] Xia, Weiyi^[1,2,3,4,5] Li, Xiaofeng^[1,2,3,4,5] Gan, Lu^[1,2,3,4,5] Zhao, Yue^[13] Zhu, Jiang^[14] Qin, Bing^[14] Jiang, Qin^[13,15] Wang, Xiawei^[7] Lin, Xintong^[1,2,3,4,5] Chen, Haifeng^[1,2,3,4,5] Zhu, Weifang^[6] Xiang, Dehui^[6] Nie, Baoqing^[6] Wang, Jingtao^[6] Guo, Jie^[1,2,3,4,5] Xue, Kang^[1,2,3,4,5] Cui, Hongguang^[7] Cheng, Jinwei^[1,2,3,4,5] Zhu, Xiangjia^[1,2,3,4,5] Hong, Jiaxu^[1,2,3,4,5] Shi, Fei^[6] Zhang, Rui^[1,2,3,4,5] Chen, Xinjian^[6,16] Zhao, Chen^[1,2,3,4,5]
语种：

英文
期刊：

NPJ DIGITAL MEDICINE ISSN：2398-6352 2025 年 8 卷 1 期 ; JAN 27
收录：
摘要：

Chatbot-based multimodal AI holds promise for collecting medical histories and diagnosing ophthalmic diseases using textual and imaging data. This study developed and evaluated the ChatGPT-powered Intelligent Ophthalmic Multimodal Interactive Diagnostic System (IOMIDS) to enable patient self-diagnosis and self-triage. IOMIDS included a text model and three multimodal models (text + slit-lamp, text + smartphone, text + slit-lamp + smartphone). The performance was evaluated through a two-stage cross-sectional study across three medical centers involving 10 subspecialties and 50 diseases. Using 15640 data entries, IOMIDS actively collected and analyzed medical history alongside slit-lamp and/or smartphone images. The text + smartphone model showed the highest diagnostic accuracy (internal: 79.6%, external: 81.1%), while other multimodal models underperformed or matched the text model (internal: 69.6%, external: 72.5%). Moreover, triage accuracy was consistent across models. Multimodal approaches enhanced response quality and reduced misinformation. This proof-of-concept study highlights the potential of chatbot-based multimodal AI for self-diagnosis and self-triage. (The clinical trial was registered on June 26, 2023, on ClinicalTrials.gov under the registration number NCT05930444.).
推荐引用方式
GB/T 7714：

Ma Ruiqi,Cheng Qian,Yao Jing, et al. Multimodal machine learning enables AI chatbot to diagnose ophthalmic diseases and provide high-quality medical responses [J].NPJ DIGITAL MEDICINE,2025,8(1).
APA：

Ma Ruiqi,Cheng Qian,Yao Jing,Peng Zhiyu,&Zhao Chen.(2025).Multimodal machine learning enables AI chatbot to diagnose ophthalmic diseases and provide high-quality medical responses .NPJ DIGITAL MEDICINE,8(1).
MLA：

Ma Ruiqi, et al. "Multimodal machine learning enables AI chatbot to diagnose ophthalmic diseases and provide high-quality medical responses" .NPJ DIGITAL MEDICINE 8,1(2025).
入库时间：

2025/2/28 18:37:55
更新时间：

2025/2/28 18:37:55

浏览次数：93  下载次数：0

分享到：

浏览次数：93

下载次数：0

打印次数：0