Deep learning (DL) represents a paradigm-shifting, burgeoning field of research with emerging clinical applications in optometry. Unlike traditional programming, which relies on human-set specific rules, DL works by exposing the algorithm to a large amount of annotated data and allowing the software to develop its own set of rules (i.e. learn) by adjusting the parameters inside the model (network) during a training process in order to complete the task on its own. One major limitation of traditional programming is that, with complex tasks, it may require an extensive set of rules to accurately complete the assignment. Additionally, traditional programming can be susceptible to human bias from programmer experience. With the dramatic increase in the amount and the complexity of clinical data, DL has been utilised to automate data analysis and thus to assist clinicians in patient management. This review will present the latest advances in DL, for managing posterior eye diseases as well as DL-based solutions for patients with vision loss.

Purpose: To review the optical principles of contact lens correction in keratoconus, with a focus on residual ocular wavefront error and its impact on vision performance. Findings: Corneal rigid gas permeable (RGP) contact lenses, commonly used in keratoconus management, often fail to improve vision quality to levels observed in non‐diseased eyes due to residual higher‐order aberrations (HOAs), primarily originating from posterior corneal irregularity. Dependent on the nature of the residual wavefront error, various lens parameter modifications, including optic zone asphericity, base‐down prism and scleral lens vault adjustments, can improve vision outcomes. Wavefront‐guided corrections have demonstrated potential to provide vision quality equivalent to that of healthy eyes, particularly when sufficient time is allowed for neural adaptation. Summary: This review examines the optical characteristics of the cornea in keratoconus, including the induction of elevated ocular wavefront errors. Challenges relating to optical correction with contact lenses are discussed, with an exploration of the origins of residual HOAs and their subsequent impacts on vision quality and quality‐of‐life. A range of contact lens modalities and parameter modifications are discussed, with evidence supporting their efficacy in reducing residual ocular wavefront error. Emerging data on wavefront‐guided corrections are presented, along with future directions for personalised optical corrections tailored to individual patient presentations.

Keratoconus is characterized by progressive thinning and increasing irregularity of the cornea, leading to substantial degradation in optical quality through the induction of both lower‐ and higher‐order aberrations (HOAs). In addition to inducing myopic and astigmatic refractive error, asymmetric corneal steepening generates complex optical distortions of the ocular wavefront, resulting in persistent reductions in image quality with conventional optical corrections including spectacles and soft contact lenses (CLs). In keratoconus, HOAs that comprise the ocular wavefront are significantly elevated, with marked variability in composition both across the population and between fellow eyes. Largely this is dominated by vertical coma, reflecting the asymmetric deformation of the cornea, with smaller contributions from trefoil and spherical aberrations. Rigid gas permeable CLs, including scleral lenses, can mask anterior corneal irregularity and partially reduce these aberrations, to improve vision quality. However, image quality in eyes with keratoconus remains reduced relative to nondiseased eyes due to residual HOAs, arising predominantly from the irregular posterior corneal surface and internal optics. This narrative review aims to translate the complex optics relating to the ocular wavefront in keratoconus into clinically relevant insights, examine current evidence on the origins of HOAs, describe related visual consequences, and outline implications for optical correction. An introduction to Zernike polynomials is presented, aiming to define the mathematical representation and facilitate a deeper understanding of wavefront data. These concepts provide a foundation for optimizing clinical care and guiding future approaches to customized optical correction in keratoconus.