Prediction of the Fundus Tessellation Severity With Machine Learning Methods

Lei Shao; Xiaomei Zhang; Teng Hu; Yang Chen; Chuan Zhang; Li Dong; Saiguang Ling; Zhou Dong; Wen Da Zhou; Rui Heng Zhang; Lei Qin; Wen Bin Wei

doi:10.3389/fmed.2022.817114

Prediction of the Fundus Tessellation Severity With Machine Learning Methods

Front Med (Lausanne). 2022 Mar 10:9:817114. doi: 10.3389/fmed.2022.817114. eCollection 2022.

Authors

Lei Shao¹, Xiaomei Zhang², Teng Hu³, Yang Chen², Chuan Zhang¹, Li Dong¹, Saiguang Ling⁴, Zhou Dong⁴, Wen Da Zhou¹, Rui Heng Zhang¹, Lei Qin², Wen Bin Wei¹

Affiliations

¹ Beijing Key Laboratory of Intraocular Tumor Diagnosis and Treatment, Beijing Ophthalmology & Visual Sciences Key Lab, Medical Artificial Intelligence Research and Verification Key Laboratory of the Ministry of Industry and Information Technology, Beijing Tongren Eye Center, Beijing Tongren Hospital, Capital Medical University, Beijing, China.
² School of Statistics, University of International Business and Economics, Beijing, China.
³ School of Banking and Finance, University of International Business and Economics, Beijing, China.
⁴ EVision Technology (Beijing) Co. LTD., Beijing, China.

Abstract

Purpose: To predict the fundus tessellation (FT) severity with machine learning methods.

Methods: A population-based cross-sectional study with 3,468 individuals (mean age of 64.6 ± 9.8 years) based on Beijing Eye Study 2011. Participants underwent detailed ophthalmic examinations including fundus images. Five machine learning methods including ordinal logistic regression, ordinal probit regression, ordinal log-gamma regression, ordinal forest and neural network were used.

Main outcome measure: FT precision, recall, F1-score, weighted-average F1-score and AUC value.

Results: Observed from the in-sample fitting performance, the optimal model was ordinal forest, which had correct classification rate (precision) of 81.28%, while 34.75, 93.73, 70.03, and 24.82% in each classified group by FT severity. The AUC value was 0.7249. And the F1-score was 65.05%, weighted-average F1-score was 79.64% on the whole dataset. For out-of-sample prediction performance, the optimal model was ordinal logistic regression, which had precision of 77.12% on the validation dataset, while 19.57, 92.68, 64.74, and 6.76% in each classified group by FT severity. The AUC value was 0.7187. The classification accuracy of light FT group was the highest, while that of severe FT group was the lowest. And the F1-score was 54.46%, weighted-average F1-score was 74.19% on the whole dataset.

Conclusions: The ordinal forest and ordinal logistic regression model had the strong prediction in-sample and out-sample performance, respectively. The threshold ranges of the ordinal forest model for no FT and light, moderate, severe FT were [0, 0.3078], [0.3078, 0.3347], [0.3347, 0.4048], [0.4048, 1], respectively. Likewise, the threshold ranges of ordinal logistic regression model were ≤ 3.7389, [3.7389, 10.5053], [10.5053, 13.9323], > 13.9323. These results can be applied to guide clinical fundus disease screening and FT severity assessment.

Keywords: fundus tessellated density; fundus tessellation; fundus tessellation severity; machine learning; the Beijing eye study.