Differentiating a pachychoroid and healthy choroid using an unsupervised machine learning approach

Abstract

The purpose of this study was to introduce a new machine learning approach for differentiation of a pachychoroid from a healthy choroid based on enhanced depth-optical coherence tomography (EDI-OCT) imaging. This study included EDI-OCT images of 103 eyes from 82 patients with central serous chorioretinopathy or pachychoroid pigment epitheliopathy, and 103 eyes from 103 age- and sex-matched healthy subjects. Choroidal features including choroidal thickness (CT), choroidal area (CA), Haller layer thickness (HT), Sattler-choriocapillaris thickness (SCT), and the choroidal vascular index (CVI) were extracted. The Haller ratio (HR) was obtained by dividing HT by CT. Multivariate TwoStep cluster analysis was performed with a preset number of two clusters based on a combination of different choroidal features. Clinical criteria were developed based on the results of the cluster analysis, and two independent skilled retina specialists graded a separate testing dataset based on the new clinical criteria. TwoStep cluster analysis achieved a sensitivity of 1.000 (95-CI: 0.938–1.000) and a specificity of 0.986 (95-CI: 0.919–1.000) in the differentiation of pachy- and healthy choroid. The best result for identification of pachychoroid was obtained for a combination of CT, HR, and CVI, with a correct classification rate of 0.993 (95-CI: 0.980–1.000). Based on the relative variable importance (RVI), the cluster analysis prioritized the choroidal features as follows: HR (RVI: 1.0), CVI (RVI: 0.87), CT (RVI: 0.70), CA (RVI: 0.59), and SCT (RVI: 0.27). After performing a receiver operating characteristic curve analysis on the cluster membership variable, a cutoff point of 389 µm and 0.79 was determined for CT and HR, respectively. Based on these clinical criteria, a sensitivity of 0.793 (95-CI: 0.611–0.904) and a specificity of 0.786 (95-CI: 0.600–0.900) and 0.821 (95-CI: 0.638–0.924) were achieved for each grader. Cohen's kappa of inter-rater reliability was 0.895. Based on an unsupervised machine learning approach, a combination of the Haller ratio and choroidal thickness is the most valuable factor in the differentiation of pachy- and healthy choroids in a clinical setting.

Artificial Intelligence in Choroid Through Optical Coherence Tomography: A Comprehensive Review

“…Research by Devarakonda et al [119] and Srivastava et al [121] demonstrates that incorporating choroidal features significantly enhances model performance in classification tasks. Studies by Jee et al [129] and Mirshahi et al [131] exemplify the importance of choroidal features in AI analysis, aligning with our current understanding of choroidal involvement in various diseases.…”

Pachychoroid Spectrum Disorders: An Updated Review

“…[ 121 , 122 ] Recently, cluster analysis was used to determine salient criteria for CSCR or PPE differentiation from healthy eyes. [ 123 ] Using an unsupervised machine learning technique, these researchers found that the Haller ratio (Haller layer thickness divided by choroidal thickness), choroidal thickness, and CVI were the most important factors for delineation. The Haller ratio was the most valuable single factor, and, along with total choroidal thickness, it was noted that these two values may be the most useful for clinical practice.…”

“…The Haller ratio was the most valuable single factor, and, along with total choroidal thickness, it was noted that these two values may be the most useful for clinical practice. [ 123 ]…”

Artificial Intelligence Analysis and Reverse Engineering of Molecular Subtypes of Diffuse Large B-Cell Lymphoma Using Gene Expression Data

“…This method can handle mixed types of variables as well as large datasets. However, it cannot handle missing data [70][71][72][73].…”