Purpose of review:In this article, we introduce the concept of model interpretability, review its applications in deep learning models for clinical ophthalmology, and discuss its role in the integration of artificial intelligence in healthcare. Recent findings:The advent of deep learning in medicine has introduced models with remarkable accuracy. However, the inherent complexity of these models undermines its users' ability to understand, debug and ultimately trust them in clinical practice. Novel methods are being increasingly explored to improve models' "interpretability" and draw clearer associations between their outputs and features in the input dataset. In the field of ophthalmology, interpretability methods have enabled users to make informed adjustments, identify clinically relevant imaging patterns, and predict outcomes in deep learning models.Summary: Interpretability methods support the transparency necessary to implement, operate and modify complex deep learning models. These benefits are becoming increasingly demonstrated in models for clinical ophthalmology. As quality standards for deep learning models used in healthcare continue to evolve, interpretability methods may prove influential in their path to regulatory approval and acceptance in clinical practice.

Purpose Neovascular age-related macular degeneration (nAMD) is a major global cause of blindness. Whilst anti-vascular endothelial growth factor (anti-VEGF) treatment is effective, response varies considerably between individuals. Thus, patients face substantial uncertainty regarding their future ability to perform daily tasks. In this study, we evaluate the performance of an automated machine learning (AutoML) model which predicts visual acuity (VA) outcomes in patients receiving treatment for nAMD, in comparison to a manually coded model built using the same dataset. Furthermore, we evaluate model performance across ethnic groups and analyse how the models reach their predictions. Methods Binary classification models were trained to predict whether patients’ VA would be ‘Above’ or ‘Below’ a score of 70 one year after initiating treatment, measured using the Early Treatment Diabetic Retinopathy Study (ETDRS) chart. The AutoML model was built using the Google Cloud Platform, whilst the bespoke model was trained using an XGBoost framework. Models were compared and analysed using the What-if Tool (WIT), a novel model-agnostic interpretability tool. Results Our study included 1631 eyes from patients attending Moorfields Eye Hospital. The AutoML model (area under the curve [AUC], 0.849) achieved a highly similar performance to the XGBoost model (AUC, 0.847). Using the WIT, we found that the models over-predicted negative outcomes in Asian patients and performed worse in those with an ethnic category of Other. Baseline VA, age and ethnicity were the most important determinants of model predictions. Partial dependence plot analysis revealed a sigmoidal relationship between baseline VA and the probability of an outcome of ‘Above’. Conclusion We have described and validated an AutoML-WIT pipeline which enables clinicians with minimal coding skills to match the performance of a state-of-the-art algorithm and obtain explainable predictions.

Cell morphology is critical for all cell functions. This is particularly true for glial cells as they rely on complex shape to contact and support neurons. However, methods to quantify complex glial cell shape accurately and reproducibly are lacking. To address this, we developed the image analysis pipeline “GliaMorph”. GliaMorph is a modular analysis toolkit developed to perform (i) image pre-processing, (ii) semi-automatic region-of-interest (ROI) selection, (iii) apicobasal texture analysis, (iv) glia segmentation, and (v) cell feature quantification. Müller Glia (MG) have a stereotypic shape linked to their maturation and physiological status. We here characterized MG on three levels, including (a) global image-level, (b) apicobasal texture, and (c) regional apicobasal vertical-to-horizontal alignment. Using GliaMorph we quantified MG development on a global and single-cell level, showing increased feature elaboration and subcellular morphological rearrangement in the zebrafish retina. As proof-of-principle, we analysed expression changes in a mouse glaucoma model, identifying subcellular protein localization changes in MG. Together, GliaMorph enables an in-depth understanding of MG morphology in the developing and diseased retina.

BackgroundIncreasing access to General Practice (GP) work experience placements for school students is a strategy for improving GP recruitment despite limited evidence and concerns surrounding equity of access to GP experiences.AimsTo examine the association between undertaking GP experience and the perceptions of GP as an appealing future career among prospective medical applicants. To identify socioeconomic factors associated with obtaining GP experience.Design & settingCross-sectional questionnaire study in the United Kingdom.MethodParticipants were UK residents aged 16 or older and seriously considering applying to study medicine in 2019/2020. They were invited to take part via the University Clinical Aptitude Test. Questionnaire data were analysed using a linear regression of GP appeal on GP experience adjusting for career motivations and demographics, and a logistic regression of GP experience on measures of social capital and demographics.ResultsOf 6,391 respondents, 4,031 were in their last year of school. GP experience predicted GP appeal after adjusting for career motivation and demographics (b=0.365, SE =0.06 p<0.00001). GP experience was more common among students at private (OR =1.65, 95% CI=1.31–2.08; P<0.0001) or grammar schools (OR =1.33, 95% CI =1.02–1.72; P=0.03) and in the highest socioeconomic group (OR =1.62, 95% CI =1.28–2.05; P<0.0001) and less likely among students of ‘Other’ ethnicity (OR =0.37, 95% CI =0.20–0.67; P=0.0011).ConclusionHaving GP experience prior to medical school was associated with finding GP appealing, which supports its utility in recruitment. Applicants from more deprived backgrounds were less likely to have had a GP experience, possibly through lack of accessible opportunities.

Cell morphology is critical for all cell functions. This is particularly true for glial cells as they rely on their complex shape to contact and support neurons. However, methods to quantify complex glial cell shape accurately and reproducibly are lacking. To address this gap in quantification approaches, we developed an analysis pipeline called "GliaMorph". GliaMorph is a modular image analysis toolkit developed to perform (i) image pre-processing, (ii) semi-automatic region-of-interest (ROI) selection, (iii) apicobasal texture analysis, (iv) glia segmentation, and (v) cell feature quantification. Mueller Glia (MG) are the principal retinal glial cell type with a stereotypic shape linked to their maturation and physiological status. We here characterized MG on three levels, including (a) global image-level, (b) apicobasal texture, and (c) apicobasal vertical-to-horizontal alignment. Using GliaMorph, we show structural changes occurring in the developing retina. Additionally, we study the loss of cadherin2 in the zebrafish retina, as well as a glaucoma mouse disease model. The GliaMorph toolkit enables an in-depth understanding of MG morphology in the developing and diseased retina.