Deep learning-based normative database of anterior chamber dimensions for angle closure assessment: the Singapore Chinese Eye Study.
Soh Zhi-Da, Tan Mingrui, Lee Zann, Yu Marco, Thakur Sahil, Lavanya Raghavan, Nongpiur Monisha Esther, Xu Xinxing, Koh Victor, Aung Tin
AI Summary
Deep learning established normative anterior chamber dimensions, finding age/gender variations. Specific ACD/LV percentiles accurately detect primary angle closure disease, offering a simpler diagnostic tool for clinicians.
Abstract
Background/ aims: The lack of context for anterior segment optical coherence tomography (ASOCT) measurements impedes its clinical utility. We established the normative distribution of anterior chamber depth (ACD), area (ACA) and width (ACW) and lens vault (LV), and applied percentile cut-offs to detect primary angle closure disease (PACD; ≥180° posterior trabecular meshwork occluded).
Methods
We included subjects from the Singapore Chinese Eye Study with ASOCT scans. Eyes with ocular surgery or laser procedures, and ocular trauma were excluded. A deep-learning algorithm was used to obtain Visante ASOCT (Carl Zeiss Meditec, USA) measurements. Normative distribution was established using 80% of eyes with open angles. Multivariable logistic regression was performed on 80% open and 80% angle closure eyes. Diagnostic performance was evaluated using 20% open and 20% angle closure eyes.
Results
We included 2157 eyes (1853 open angles; 304 angle closure) for analysis. ACD, ACA and ACW decreased with age and were smaller in females, and vice versa for LV (all p<0.022). ACD 20th percentile and LV 85th percentile had a balanced accuracy of 84.4% and 84.2% in detecting PACD, respectively. When combined, ACD 20th and LV 85th percentile had 88.68% sensitivity and 88.85% specificity in detecting PACD as compared with a multivariable regression model (ACA, angle opening distance, LV, iris area) with 88.33% sensitivity and 83.75% specificity.
Conclusion
Anterior chamber parameters varied with age and gender. The ACD 20th and LV 85th percentile values may be used in silos or in combination to detect PACD in the absence of more sophisticated classification algorithms.
MeSH Terms
Shields Classification
Key Concepts5
In the Singapore Chinese Eye Study, anterior chamber depth (ACD), area (ACA), and width (ACW) decreased with age and were smaller in females, while lens vault (LV) increased with age and was larger in females (all p<0.022) across 2157 eyes (1853 open angles; 304 angle closure).
In the Singapore Chinese Eye Study, the anterior chamber depth (ACD) 20th percentile had a balanced accuracy of 84.4% in detecting primary angle closure disease (PACD; defined as ≥180° posterior trabecular meshwork occluded) in a diagnostic performance evaluation using 20% open and 20% angle closure eyes.
In the Singapore Chinese Eye Study, the lens vault (LV) 85th percentile had a balanced accuracy of 84.2% in detecting primary angle closure disease (PACD; defined as ≥180° posterior trabecular meshwork occluded) in a diagnostic performance evaluation using 20% open and 20% angle closure eyes.
In the Singapore Chinese Eye Study, combining the anterior chamber depth (ACD) 20th percentile and lens vault (LV) 85th percentile achieved 88.68% sensitivity and 88.85% specificity in detecting primary angle closure disease (PACD; defined as ≥180° posterior trabecular meshwork occluded) in a diagnostic performance evaluation using 20% open and 20% angle closure eyes.
In the Singapore Chinese Eye Study, a multivariable regression model (including anterior chamber area, angle opening distance, lens vault, iris area) achieved 88.33% sensitivity and 83.75% specificity in detecting primary angle closure disease (PACD; defined as ≥180° posterior trabecular meshwork occluded) in a diagnostic performance evaluation using 20% open and 20% angle closure eyes.
Related Articles5
Acute Angle Closure Incidence in a Large Countywide Safety Net Teleretinal Screening Program.
Cohort StudyPrimary angle-closed diseases recognition through artificial intelligence-based anterior segment-optical coherence tomography imaging.
Cross-Sectional StudyInvestigating the determinants of iridolenticular contact area: a novel parameter for angle closure.
Cross-Sectional StudyRefractive Error and Anterior Chamber Depth as Risk Factors in Primary Angle Closure Disease: The Chinese American Eye Study.
Cohort StudyAnterior Segment Characteristics and Risk Factors for Primary Angle Closure Disease With Long Axial Lengths: The Handan Eye Study.
Cross-Sectional StudyIs this article assigned to the wrong chapter(s)? Let us know.