Prevalence of zonulopathy in primary angle closure disease.

BACKGROUND: To determine the prevalence of zonulopathy in a large cohort of eyes with primary angle closure disease (PACD) that underwent cataract surgery. METHODS: Retrospective consecutive case series of PACD eyes (including primary angle closure suspect, primary angle closure, and primary angle closure glaucoma) that underwent phacoemulsification cataract surgery or clear lens extraction between 2009 and 2020 at a single ophthalmology centre. Those with risk factors for zonulopathy such as history of trauma, pseudoexfoliation syndrome, intraocular surgery, retinitis pigmentosa or connective tissue disorders were excluded. The primary outcomes included the prevalence of zonulopathy assessed intraoperatively and secondary pigment dispersion syndrome. RESULTS: In our cohort of 806 consecutive PACD eyes, the prevalence of zonulopathy was 7.3% (59 of 806 eyes) - significantly greater than the 0.46%-2.6% range reported for the general population (p < 0.001). Intraoperative signs of zonular weakness included floppy capsular bag (29 eyes, 3.6%), zonular laxity (25 eyes, 3.1%) and zonular dehiscence (11 eyes, 1.4%). Among these eyes, capsular tension ring was used in 23 eyes (39.0%), six eyes (10.2%) experienced vitreous prolapse intraoperatively and underwent anterior vitrectomy, and two eyes (3.4%) experienced posterior capsular rupture, one of which required a scleral-fixated intraocular lens. Secondary pigment dispersion syndrome was observed in 141 eyes (17.5%). CONCLUSIONS: This study evidenced a high prevalence of zonulopathy among a large cohort of PACD eyes and suggests zonulopathy as a possible under-recognised cause of angle closure. Until more sophisticated imaging modalities become available, awareness about the prevalence of zonulopathy in angle closure disease coupled with careful preoperative examinations can help minimise or prevent the complications of zonulopathy.

Predictive modeling of proliferative vitreoretinopathy using automated machine learning by ophthalmologists without coding experience.

We aimed to assess the feasibility of machine learning (ML) algorithm design to predict proliferative vitreoretinopathy (PVR) by ophthalmologists without coding experience using automated ML (AutoML). The study was a retrospective cohort study of 506 eyes who underwent pars plana vitrectomy for rhegmatogenous retinal detachment (RRD) by a single surgeon at a tertiary-care hospital between 2012 and 2019. Two ophthalmologists without coding experience used an interactive application in MATLAB to build and evaluate ML algorithms for the prediction of postoperative PVR using clinical data from the electronic health records. The clinical features associated with postoperative PVR were determined by univariate feature selection. The area under the curve (AUC) for predicting postoperative PVR was better for models that included pre-existing PVR as an input. The quadratic support vector machine (SVM) model built using all selected clinical features had an AUC of 0.90, a sensitivity of 63.0%, and a specificity of 97.8%. An optimized Naïve Bayes algorithm that did not include pre-existing PVR as an input feature had an AUC of 0.81, a sensitivity of 54.3%, and a specificity of 92.4%. In conclusion, the development of ML models for the prediction of PVR by ophthalmologists without coding experience is feasible. Input from a data scientist might still be needed to tackle class imbalance-a common challenge in ML classification using real-world clinical data.