Development and multi-center validation of machine learning model for early detection of fungal keratitis

被引：11

作者：

Wei, Zhenyu ^{[1
]}

Wang, Shigeng ^{[2
]}

Wang, Zhiqun ^{[1
]}

Zhang, Yang ^{[1
]}

Chen, Kexin ^{[1
]}

Gong, Lan ^{[3
]}

Li, Guigang ^{[4
]}

Zheng, Qinxiang ^{[5
]}

Zhang, Qin ^{[6
]}

He, Yan ^{[7
]}

Zhang, Qi ^{[8
]}

Chen, Di ^{[9
]}

Cao, Kai ^{[1
]}

Pang, Jinding ^{[1
]}

Zhang, Zijun ^{[1
]}

Wang, Leying ^{[1
]}

Ou, Zhonghong ^{[2
]}

Liang, Qingfeng ^{[1
]}

机构：

[1] Capital Med Univ, Beijing Tongren Hosp, Beijing Inst Ophthalmol, Beijing Tongren Eye Ctr,Beijing Key Lab Ophthalmol, Beijing 100005, Peoples R China

[2] Beijing Univ Posts & Telecommun, Beijing 100876, Peoples R China

[3] Fudan Univ, Dept Ophthalmol, Eye & ENT Hosp, Shanghai 200031, Peoples R China

[4] Huazhong Univ Sci & Technol, Tongji Hosp, Dept Ophthalmol, Tongji Med Coll, Wuhan 430030, Peoples R China

[5] Eye Hosp, Wenzhou Med Coll, Wenzhou 325027, Peoples R China

[6] Peking Univ, Peoples Hosp, Dept Ophthalmol, Key Lab Vis Loss & Restorat,Minist Educ, Beijing 100044, Peoples R China

[7] Cent South Univ, Xiangya Hosp 2, Dept Ophthalmol, Changsha 410011, Hunan, Peoples R China

[8] Chongqing Med Univ, Dept Ophthalmol, Affiliated Hosp 1, Chongqing 400016, Peoples R China

[9] Chinese Acad Med Sci & Peking Union Med Coll, Peking Union Med Coll Hosp, Dept Ophthalmol, Beijing 100730, Peoples R China

来源：

EBIOMEDICINE | 2023年 / 88卷

关键词：

Fungal keratitis; Diagnostic model; Slit-lamp microscopy; Machine learning; RISK-FACTORS; SUPPURATIVE KERATITIS; BACTERIAL KERATITIS; MICROBIAL KERATITIS; CLINICAL-FEATURES; ACANTHAMOEBA;

D O I：

10.1016/j.ebiom.2023.104438

中图分类号：

R5 [内科学];

学科分类号：

1002 ; 100201 ;

摘要：

Background Fungal keratitis (FK) is a leading cause of corneal blindness in developing countries due to poor clinical recognition and laboratory identification. Here, we aimed to identify the distinct clinical signature of FK and develop a diagnostic model to differentiate FK from other types of infectious keratitis.Methods We reviewed the electronic health records (EHRs) of all patients with suspected infectious keratitis in Beijing Tongren Hospital from January 2011 to December 2021. Twelve clinical signs of slit-lamp images were assessed by Lasso regression analysis and collinear variables were excluded. Three models based on binary logistic regression, random forest classification, and decision tree classification were trained for FK diagnosis and employed for internal validation. Independent external validation of the models was performed in a cohort of 420 patients from seven different ophthalmic centers to evaluate the accuracy, specificity, and sensitivity in real world.Findings Three diagnostic models of FK based on binary logistic regression, random forest classification, and decision tree classification were established and internal validation were achieved with the mean AUC of 0.916, 0.920, and 0.859, respectively. The models were well-calibrated by external validation using a prospective cohort including 210 FK and 210 non-FK patients from seven eye centers across China. The diagnostic model with the binary logistic regression algorithm classified the external validation dataset with a sensitivity of 0.907 (0.774, 1.000), specificity 0.899 (0.750, 1.000), accuracy 0.905 (0.805, 1.000), and AUC 0.903 (0.808, 0.998).Interpretation Our model enables rapid identification of FK, which will help ophthalmologists to establish a preliminary diagnosis and to improve the diagnostic accuracy in clinic. Copyright (c) 2023 The Author(s). Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).

引用

页数：12

共 50 条

[1] Fungal keratitis associated with non-therapeutic soft contact lenses [J].