Analysis of anterior segment in primary angle closure suspect with deep learning models.

Autor: Fu Z; The Second Affiliated Hospital of Xi'an Medical University, Xi'an, Shaanxi, 710038, China.; Xi'an Medical University, Xi'an, Shaanxi, 710021, China.; Xi'an Key Laboratory for the Prevention and Treatment of Eye and Brain Neurological Related Diseases, Xi'an, Shaanxi, 710038, China., Xi J; The Second Affiliated Hospital of Xi'an Medical University, Xi'an, Shaanxi, 710038, China., Ji Z; The Second Affiliated Hospital of Xi'an Medical University, Xi'an, Shaanxi, 710038, China.; Xi'an Medical University, Xi'an, Shaanxi, 710021, China., Zhang R; School of Mathematics, Northwest University, Xi'an, 710127, China., Wang J; Shaanxi Provincial People's Hospital, Xi'an, Shaanxi, 710068, China., Shi R; Shaanxi Provincial People's Hospital, Xi'an, Shaanxi, 710068, China., Pu X; Xianyang First People's Hospital, Xianyang, Shaanxi Province, 712000, China., Yu J; Xi'an People's Hospital, Xi'an, Shaanxi, 712099, China., Xue F; Xi'an Medical University, Xi'an, Shaanxi, 710021, China., Liu J; Xi'an People's Hospital, Xi'an, Shaanxi, 712099, China., Wang Y; Yan'an People's Hospital, Yan'an, Shaanxi, 716099, China., Zhong H; The First Affiliated Hospital of Kunming Medical University, Kunming, Yunnan Province, 650032, China., Feng J; School of Mathematics, Northwest University, Xi'an, 710127, China., Zhang M; School of Mathematics, Northwest University, Xi'an, 710127, China. dr.zhangmin@nwu.edu.cn., He Y; The Second Affiliated Hospital of Xi'an Medical University, Xi'an, Shaanxi, 710038, China. heyuan@xiyi.edu.cn.; Xi'an Medical University, Xi'an, Shaanxi, 710021, China. heyuan@xiyi.edu.cn.; Xi'an Key Laboratory for the Prevention and Treatment of Eye and Brain Neurological Related Diseases, Xi'an, Shaanxi, 710038, China. heyuan@xiyi.edu.cn.
Jazyk: angličtina
Zdroj: BMC medical informatics and decision making [BMC Med Inform Decis Mak] 2024 Sep 09; Vol. 24 (1), pp. 251. Date of Electronic Publication: 2024 Sep 09.
DOI: 10.1186/s12911-024-02658-1
Abstrakt: Objective: To analyze primary angle closure suspect (PACS) patients' anatomical characteristics of anterior chamber configuration, and to establish artificial intelligence (AI)-aided diagnostic system for PACS screening.
Methods: A total of 1668 scans of 839 patients were included in this cross-sectional study. The subjects were divided into two groups: PACS group and normal group. With anterior segment optical coherence tomography scans, the anatomical diversity between two groups was compared, and anterior segment structure features of PACS were extracted. Then, AI-aided diagnostic system was constructed, which based different algorithms such as classification and regression tree (CART), random forest (RF), logistic regression (LR), VGG-16 and Alexnet. Then the diagnostic efficiencies of different algorithms were evaluated, and compared with junior physicians and experienced ophthalmologists.
Results: RF [sensitivity (Se) = 0.84; specificity (Sp) = 0.92; positive predict value (PPV) = 0.82; negative predict value (NPV) = 0.95; area under the curve (AUC) = 0.90] and CART (Se = 0.76, Sp = 0.93, PPV = 0.85, NPV = 0.92, AUC = 0.90) showed better performance than LR (Se = 0.68, Sp = 0.91, PPV = 0.79, NPV = 0.90, AUC = 0.86). In convolutional neural networks (CNN), Alexnet (Se = 0.83, Sp = 0.95, PPV = 0.92, NPV = 0.87, AUC = 0.85) was better than VGG-16 (Se = 0.84, Sp = 0.90, PPV = 0.85, NPV = 0.90, AUC = 0.79). The performance of 2 CNN algorithms was better than 5 junior physicians, and the mean value of diagnostic indicators of 2 CNN algorithm was similar to experienced ophthalmologists.
Conclusion: PACS patients have distinct anatomical characteristics compared with health controls. AI models for PACS screening are reliable and powerful, equivalent to experienced ophthalmologists.
(© 2024. The Author(s).)
Databáze: MEDLINE
Externí odkaz:
Nepřihlášeným uživatelům se plný text nezobrazuje