Diagnostic decisions of specialist optometrists exposed to ambiguous deep-learning outputs.

Artificial intelligence (AI) has great potential in ophthalmology. We investigated how ambiguous outputs from an AI diagnostic support system (AI-DSS) affected diagnostic responses from optometrists when assessing cases of suspected retinal disease. Thirty optometrists (15 more experienced, 15 less) assessed 30 clinical cases. For ten, participants saw an optical coherence tomography (OCT) scan, basic clinical information and retinal photography ('no AI'). For another ten, they were also given AI-generated OCT-based probabilistic diagnoses ('AI diagnosis'); and for ten, both AI-diagnosis and AI-generated OCT segmentations ('AI diagnosis + segmentation') were provided. Cases were matched across the three types of presentation and were selected to include 40% ambiguous and 20% incorrect AI outputs. Optometrist diagnostic agreement with the predefined reference standard was lowest for 'AI diagnosis + segmentation' (204/300, 68%) compared to 'AI diagnosis' (224/300, 75% p = 0.010), and 'no Al' (242/300, 81%, p = < 0.001). Agreement with AI diagnosis consistent with the reference standard decreased (174/210 vs 199/210, p = 0.003), but participants trusted the AI more (p = 0.029) with segmentations. Practitioner experience did not affect diagnostic responses (p = 0.24). More experienced participants were more confident (p = 0.012) and trusted the AI less (p = 0.038). Our findings also highlight issues around reference standard definition.

The effectiveness of interventions for optometric referrals into the hospital eye service: A review.

PURPOSE: Ophthalmic services are currently under considerable stress; in the UK, ophthalmology departments have the highest number of outpatient appointments of any department within the National Health Service. Recognising the need for intervention, several approaches have been trialled to tackle the high numbers of false-positive referrals initiated in primary care and seen face to face within the hospital eye service (HES). In this mixed-methods narrative synthesis, we explored interventions based on their clinical impact, cost and acceptability to determine whether they are clinically effective, safe and sustainable. A systematic literature search of PubMed, MEDLINE and CINAHL, guided by the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA), was used to identify appropriate studies published between December 2001 and December 2022. RECENT FINDINGS: A total of 55 studies were reviewed. Four main interventions were assessed, where two studies covered more than one type: training and guidelines (n = 8), referral filtering schemes (n = 32), asynchronous teleophthalmology (n = 13) and synchronous teleophthalmology (n = 5). All four approaches demonstrated effectiveness for reducing false-positive referrals to the HES. There was sufficient evidence for stakeholder acceptance and cost-effectiveness of referral filtering schemes; however, cost comparisons involved assumptions. Referral filtering and asynchronous teleophthalmology reported moderate levels of false-negative cases (2%-20%), defined as discharged patients requiring HES monitoring. SUMMARY: The effectiveness of interventions varied depending on which outcome and stakeholder was considered. More studies are required to explore stakeholder opinions around all interventions. In order to maximise clinical safety, it may be appropriate to combine more than one approach, such as referral filtering schemes with virtual review of discharged patients to assess the rate of false-negative cases. The implementation of a successful intervention is more complex than a 'one-size-fits-all' approach and there is potential space for newer types of interventions, such as artificial intelligence clinical support systems within the referral pathway.

Assessment of optometrists' referral accuracy and contributing factors: A review.

PURPOSE: In the UK, ophthalmology has the highest number of outpatient appointments within the National Health Service. False-positive referrals from primary care are one of the main factors contributing to the oversubscription of hospital eye services (HESs). We reviewed the accuracy of referrals originating from primary care optometrists and contributing factors, such as condition type and years since registration. RECENT FINDINGS: Of the 31 studies included in the review, 22 were retrospective analyses of referrals and appointments at the HES. Eight were prospective studies, and one used online clinical vignettes. Seven assessed the accuracy of referrals for all ocular conditions. The remaining studies focused on glaucoma (n = 11), cataracts (n = 7), emergency conditions (n = 4), neovascular age-related macular degeneration (n = 1) and paediatric binocular vision (n = 1). The diagnostic agreement for suspected emergency ocular conditions was the lowest, with only 21.1% of referrals considered to require urgent attention in one study. For glaucoma, the first-visit discharge rate was high (16.7%-48%). Optometrist referral accuracy was overall 18.6% higher than General Medical Practitioners'; however, the two mainly referred different ocular conditions. Female optometrists made more false-positive referrals than males (p = 0.008). The proportion of false positives decreased by 6.2% per year since registration (p < 0.001). SUMMARY: There was significant variation in referral accuracy across different ocular conditions, partly due to differences when defining accurate referrals. Optometrists working in primary care are generally more limited in their resources than the HES. Thus, choosing the cautious option of referral when they are unsure could be in the patients' best interests. The possible effect of increased use of advanced imaging on referrals requires evaluation. Although interventions such as refinement schemes have been put in place, these vary across regions, and their approaches such as virtual referral triaging may reduce unnecessary HES face-to-face appointments and promote communication between primary and secondary care.

Neurodegeneration of the cornea and retina in patients with type 1 diabetes without clinical evidence of diabetic retinopathy.

Aim: Diabetic retinopathy (DR) is widely considered the earliest and most common microvascular complication of diabetes. However, recent studies have shown that retinal nerve fiber layer and corneal nerve abnormalities may be present in diabetic patients without retinopathy. This preliminary study aimed to establish if structural and functional changes in the nerve fiber layer of the retina and cornea occur in patients with type 1 diabetes (T1DM) without retinopathy. Methods: Twenty patients with T1DM, without clinical evidence of retinopathy (Age: 47.0 ± 2.5 years; Duration diabetes: 27.0 ± 3 years) and 15 age-matched healthy control subjects underwent detailed medical neurological examinations. Ophthalmic examinations using Spectral Domain Optical coherence tomography (SD-OCT), Standard Automated Perimetry (SAP), Flicker Defined Form High Edge Perimetry (FDF), Corneal Confocal Microscopy (CCM) and Non-contact corneal Aesthesiometry (NCCA) were performed to quantify the structure and function of the nerves in the retina and cornea, respectively. Results: At the structural level, retinal nerve fiber layer thickness (RNFL) was significantly reduced in the superior nasal (p=0.001) and inferior temporal (p=0.004) sectors, in diabetic patients. Retinal ganglion layer function was reduced in the patient group when assessed using Flicker Defined Form Perimetry (FDF), but this was not significant. The function of the cornea assessed by corneal sensitivity, using a non-contact corneal aesthesiometer (NCCA), was significantly reduced (p=0.001). Structural assessment of corneal nerves using corneal confocal microscopy (CCM) showed reduction at corneal nerve fiber density (CNFD) (p=0.01), branch density (CNBD) (p=0.006) and length (CNFL) (p=0.01) in patients with diabetes. Compared to control subjects, the percentage of abnormality in patients with T1DM for RNFL was 32% while the FDF was abnormal in 61% of patients. Corneal abnormality was observed in 47% for NCCA, 28% for CNFD, and 17% for CNFL. There was no correlation between neuronal damage in the retina and cornea. Conclusions: Neuronal abnormalities were observed in both the retina and cornea of diabetic patients without evidence of retinopathy. The prevalence of structural and functional changes was higher in the retina compared to the cornea. This preliminary study suggests that structural neuronal changes may occur in parallel and correlate with functional changes. The assessment of corneal and retinal nerve structure may be clinically useful for detecting and monitoring the earliest stages of diabetic microvascular abnormalities.

Implementation of corneal confocal microscopy for screening and early detection of diabetic neuropathy in primary care alongside retinopathy screening: Results from a feasibility study.

Objective: Screening for diabetic peripheral neuropathy (DPN) is essential for early detection and timely intervention. Quantitative assessment of small nerve fiber damage is key to the early diagnosis and assessment of its progression. Corneal confocal microscopy (CCM) is a non-invasive, in-vivo diagnostic technique that provides an accurate surrogate biomarker for small-fiber neuropathy. In this novel study for the first time, we introduced CCM to primary care as a screening tool for DPN alongside retinopathy screening to assess the level of neuropathy in this novel cohort. Research design and methods: 450 consecutive subjects with type 1 or type 2 diabetes attending for annual eye screening in primary care optometry settings underwent assessment with CCM to establish the prevalence of sub-clinical diabetic peripheral neuropathy. Subjects underwent assessment for neurological and ocular symptoms of diabetes and a history of diabetic foot disease, neuropathy and diabetic retinopathy (DR). Results: CCM examination was completed successfully in 427 (94.9%) subjects, 22% of whom had neuropathy according to Diabetic Neuropathy Symptom (DNS) score. The prevalence of sub-clinical neuropathy as defined by abnormal corneal nerve fiber length (CNFL) was 12.9%. In the subjects with a short duration of type 2 diabetes, 9.2% had abnormal CNFL. CCM showed significant abnormalities in corneal nerve parameters in this cohort of subjects with reduction of corneal nerve fiber density (CNFD, p<0.001), CNFL (p<0.001) and corneal nerve branch density (CNBD, p<0.001) compared to healthy subjects. In subjects who had no evidence of DR (67% of all subjects), 12.0% had abnormal CNFL. Conclusions: CCM may be a sensitive biomarker for early detection and screening of DPN in primary care alongside retinopathy screening.

Protocol for a qualitative study to explore acceptability, barriers and facilitators of the implementation of new teleophthalmology technologies between community optometry practices and hospital eye services.

INTRODUCTION: Novel teleophthalmology technologies have the potential to reduce unnecessary and inaccurate referrals between community optometry practices and hospital eye services and as a result improve patients' access to appropriate and timely eye care. However, little is known about the acceptability and facilitators and barriers to the implementations of these technologies in real life. METHODS AND ANALYSIS: A theoretically informed, qualitative study will explore patients' and healthcare professionals' perspectives on teleophthalmology and Artificial Intelligence Decision Support System models of care. A combination of situated observations in community optometry practices and hospital eye services, semistructured qualitative interviews with patients and healthcare professionals and self-audiorecordings of healthcare professionals will be conducted. Participants will be purposively selected from 4 to 5 hospital eye services and 6-8 affiliated community optometry practices. The aim will be to recruit 30-36 patients and 30 healthcare professionals from hospital eye services and community optometry practices. All interviews will be audiorecorded, with participants' permission, and transcribed verbatim. Data from interviews, observations and self-audiorecordings will be analysed thematically and will be informed by normalisation process theory and an inductive approach. ETHICS AND DISSEMINATION: Ethical approval has been received from London-Bromley research ethics committee. Findings will be reported through academic journals and conferences in ophthalmology, health services research, management studies and human-computer interaction.

Advances in Screening, Early Diagnosis and Accurate Staging of Diabetic Neuropathy.

The incidence of both type 1 and type 2 diabetes is increasing worldwide. Diabetic peripheral neuropathy (DPN) is among the most distressing and costly of all the chronic complications of diabetes and is a cause of significant disability and poor quality of life. This incurs a significant burden on health care costs and society, especially as these young people enter their peak working and earning capacity at the time when diabetes-related complications most often first occur. DPN is often asymptomatic during the early stages; however, once symptoms and overt deficits have developed, it cannot be reversed. Therefore, early diagnosis and timely intervention are essential to prevent the development and progression of diabetic neuropathy. The diagnosis of DPN, the determination of the global prevalence, and incidence rates of DPN remain challenging. The opinions vary about the effectiveness of the expansion of screenings to enable early diagnosis and treatment initiation before disease onset and progression. Although research has evolved over the years, DPN still represents an enormous burden for clinicians and health systems worldwide due to its difficult diagnosis, high costs related to treatment, and the multidisciplinary approach required for effective management. Therefore, there is an unmet need for reliable surrogate biomarkers to monitor the onset and progression of early neuropathic changes in DPN and facilitate drug discovery. In this review paper, the aim was to assess the currently available tests for DPN's sensitivity and performance.