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

• Published in: BMC medical informatics and decision making Vol. 24; no. 1; pp. 251 - 12
• Main Authors: Fu, Ziwei, Xi, Jinwei, Ji, Zhi, Zhang, Ruxue, Wang, Jianping, Shi, Rui, Pu, Xiaoli, Yu, Jingni, Xue, Fang, Liu, Jianrong, Wang, Yanrong, Zhong, Hua, Feng, Jun, Zhang, Min, He, Yuan
• Format: Journal Article
• Language: English
• Published: London BioMed Central 09.09.2024; BioMed Central Ltd; Springer Nature B.V; BMC
• Subjects: Aged; Algorithms; Anatomical characteristics; Angle-closure glaucoma; Anterior chamber; Anterior chamber (Eye); Anterior Eye Segment - diagnostic imaging; Artificial intelligence; Artificial neural networks; Classification; Computer-aided medical diagnosis; Convolutional neural network; Cooperation; Cornea; Cross-Sectional Studies; Deep Learning; Diagnosis; Diagnostic systems; Female; Glaucoma; Glaucoma, Angle-Closure - diagnosis; Glaucoma, Angle-Closure - diagnostic imaging; Health Informatics; Humans; Information Systems and Communication Service; Iris; Lasers; Machine learning; Male; Management of Computing and Information Systems; Medical examination; Medicine; Medicine & Public Health; Methods; Middle Aged; Neural networks; Performance evaluation; Physicians; Primary angle closure suspect; Probability distribution; Random variables; Regression analysis; Screening; Segments; Sensitivity analysis; Tomography, Optical Coherence; China; Screening; Anatomical characteristics; Convolutional neural network; Primary angle closure suspect; Machine learning
• ISSN: 1472-6947; 1472-6947
• DOI: 10.1186/s12911-024-02658-1

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.