Comparing code-free and bespoke deep learning approaches in ophthalmology.

AIM: Code-free deep learning (CFDL) allows clinicians without coding expertise to build high-quality artificial intelligence (AI) models without writing code. In this review, we comprehensively review the advantages that CFDL offers over bespoke expert-designed deep learning (DL). As exemplars, we use the following tasks: (1) diabetic retinopathy screening, (2) retinal multi-disease classification, (3) surgical video classification, (4) oculomics and (5) resource management. METHODS: We performed a search for studies reporting CFDL applications in ophthalmology in MEDLINE (through PubMed) from inception to June 25, 2023, using the keywords 'autoML' AND 'ophthalmology'. After identifying 5 CFDL studies looking at our target tasks, we performed a subsequent search to find corresponding bespoke DL studies focused on the same tasks. Only English-written articles with full text available were included. Reviews, editorials, protocols and case reports or case series were excluded. We identified ten relevant studies for this review. RESULTS: Overall, studies were optimistic towards CFDL's advantages over bespoke DL in the five ophthalmological tasks. However, much of such discussions were identified to be mono-dimensional and had wide applicability gaps. High-quality assessment of better CFDL applicability over bespoke DL warrants a context-specific, weighted assessment of clinician intent, patient acceptance and cost-effectiveness. We conclude that CFDL and bespoke DL are unique in their own assets and are irreplaceable with each other. Their benefits are differentially valued on a case-to-case basis. Future studies are warranted to perform a multidimensional analysis of both techniques and to improve limitations of suboptimal dataset quality, poor applicability implications and non-regulated study designs. CONCLUSION: For clinicians without DL expertise and easy access to AI experts, CFDL allows the prototyping of novel clinical AI systems. CFDL models concert with bespoke models, depending on the task at hand. A multidimensional, weighted evaluation of the factors involved in the implementation of those models for a designated task is warranted.

Omega-3 fatty acids in the management of dry eye disease-An updated systematic review and meta-analysis.

PURPOSE: The purpose of this study was to examine the effectiveness of omega-3 fatty acids in comparison to a placebo in the management of dry eye disease. METHODS: A systematic literature search was performed including randomised controlled trials (RCTs) comparing omega-3 versus placebo in the management of dry eye disease in human subjects. There were no language or time restrictions. Eligible trials were assessed for bias and assigned a risk-of-bias score. Data extraction was carried out using a standardised data extraction form, and meta-analysis was performed using a random effects model for continuous data. The outcome measures were Ocular Surface Disease Index (OSDI) scores, tear breakup time (TBUT) measurements, corneal staining and Schirmer's score. Statistical heterogeneity was defined as substantial if the I2 test achieved a value >60%. RESULTS: Eight parallel RCTs including 1107 subjects met eligibility criteria. None of the included studies achieved low risk of bias. Data synthesis demonstrated an improvement in the mean change in OSDI score from baseline to final assessment. Omega-3 supplementation conferred no evident improvement in corneal staining, TBUT or Schirmer's score. There was considerable statistical heterogeneity in all four outcome measures. CONCLUSIONS: This updated systematic review and meta-analysis indicates that omega-3 supplementation improves subjective symptoms in patients with dry eye disease.

Evaluating an automated machine learning model that predicts visual acuity outcomes in patients with neovascular age-related macular degeneration.

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.

Knowledge of face masks and attitudes to re-sterilisation among healthcare workers.

INTRODUCTION: COVID-19 was declared a pandemic in March 2020. With the sudden surge in demand for personal protective equipment (PPE), significant concerns regarding the ongoing availability emerged. One solution proposed is re-sterilisation of respirator masks and this has been commenced in some parts of the world. On review of the literature, very little is documented regarding the knowledge of masks and the attitudes of healthcare workers towards using re-sterilised masks. METHODS: A comprehensive questionnaire was used to assess general knowledge and attitudes around facemasks and respirators. RESULTS: There were 190 respondents. There were significant gaps in knowledge and understanding of when particular face masks should be worn. One-third had significant concerns about ongoing availability. One-third had concerns about the quality of the masks as the pandemic continued. Only 10% of respondents underwent formal face-fitting. Eighty percent of respondents stated they would wear a re-sterilised mask. A further 15% would use a re-sterilised mask but required certain reassurances. Five percent of our respondents would not use a re-sterilised mask under any circumstances. DISCUSSION: Ensuring an adequate understanding of face masks is crucial among healthcare workers (HCWs) and this study highlights a need for further education. It also demonstrates a general acceptability among HCWs towards the use of re-sterilised face masks.

Automated deep learning in ophthalmology: AI that can build AI.

PURPOSE OF REVIEW: The purpose of this review is to describe the current status of automated deep learning in healthcare and to explore and detail the development of these models using commercially available platforms. We highlight key studies demonstrating the effectiveness of this technique and discuss current challenges and future directions of automated deep learning. RECENT FINDINGS: There are several commercially available automated deep learning platforms. Although specific features differ between platforms, they utilise the common approach of supervised learning. Ophthalmology is an exemplar speciality in the area, with a number of recent proof-of-concept studies exploring classification of retinal fundus photographs, optical coherence tomography images and indocyanine green angiography images. Automated deep learning has also demonstrated impressive results in other specialities such as dermatology, radiology and histopathology. SUMMARY: Automated deep learning allows users without coding expertise to develop deep learning algorithms. It is rapidly establishing itself as a valuable tool for those with limited technical experience. Despite residual challenges, it offers considerable potential in the future of patient management, clinical research and medical education. VIDEO ABSTRACT: http://links.lww.com/COOP/A44.

Therapeutic Intervention in Musculoskeletal Radiology: Current Practice and Future Directions.

Over the last several decades, the volume and range of therapeutic musculoskeletal (MSK) interventions that radiologists can offer their patients has dramatically increased. With new materials and improving imaging modalities, as well as significant investment in research, the field of MSK interventional radiologic intervention will likely continue to expand. In this article, we summarize the range of interventions currently available to the MSK radiologist. We also seek to explore new and emerging techniques that may become commonplace in the near future while considering the challenges that may lie ahead in the field of MSK radiology.