Determinants of non-attendance at face-to-face and telemedicine ophthalmic consultations.

BACKGROUND/AIMS: Evaluation of telemedicine care models has highlighted its potential for exacerbating healthcare inequalities. This study seeks to identify and characterise factors associated with non-attendance across face-to-face and telemedicine outpatient appointments. METHODS: A retrospective cohort study at a tertiary-level ophthalmic institution in the UK, between 1 January 2019 and 31 October 2021. Logistic regression modelled non-attendance against sociodemographic, clinical and operational exposure variables for all new patient registrations across five delivery modes: asynchronous, synchronous telephone, synchronous audiovisual and face to face prior to the pandemic and face to face during the pandemic. RESULTS: A total of 85 924 patients (median age 55 years, 54.4% female) were newly registered. Non-attendance differed significantly by delivery mode: (9.0% face to face prepandemic, 10.5% face to face during the pandemic, 11.7% asynchronous and 7.8%, synchronous during pandemic). Male sex, greater levels of deprivation, a previously cancelled appointment and not self-reporting ethnicity were strongly associated with non-attendance across all delivery modes. Individuals identifying as black ethnicity had worse attendance in synchronous audiovisual clinics (adjusted OR 4.24, 95% CI 1.59 to 11.28) but not asynchronous. Those not self-reporting their ethnicity were from more deprived backgrounds, had worse broadband access and had significantly higher non-attendance across all modes (all p<0.001). CONCLUSION: Persistent non-attendance among underserved populations attending telemedicine appointments highlights the challenge digital transformation faces for reducing healthcare inequalities. Implementation of new programmes should be accompanied by investigation into the differential health outcomes of vulnerable populations.

Feasibility study of an automated Strabismus screening Test using Augmented Reality and Eye-tracking (STARE).

BACKGROUND: New digital technologies (augmented reality headsets, eye-tracking) may potentially allow for automated assessments of ocular misalignment. Here, we evaluate the feasibility of a novel, open-source strabismus test ("STARE") as an automated screening tool. METHODS: Work progressed in 2 phases. In phase 1 ("development"), we used Fresnel prisms to elicit horizontal misalignments of known magnitude (1-40 prism dioptres) in orthotropic controls. In phase 2 ("validation"), we applied the system to adults with an established diagnosis of strabismus, and quantified the ability of the test to distinguish between those with horizontal misalignment and those without. Agreement between the alternate prism cover test measurements and STARE measurements was computed using Bland-Altman plots and product-moment correlation coefficients. RESULTS: Seven orthotropic controls and nineteen patients with strabismus were recruited (mean age 58.7 ± 22.4 years). STARE was able to identify the presence of horizontal strabismus with an area under the curve of 1.00 (100% sensitivity and 100% specificity). The mean difference (bias) {95% CI} was 2.1 {-1.8, 9.9} prism dioptres, and the 95% coefficient of repeatability {95% CI} was ±27.9 {14.8, 50.8} prism dioptres. The Pearson correlation between APCT and STARE was r24 = 0.62, P < 0.001. CONCLUSIONS: STARE shows promise as a simple, automated tool for performing a screening assessment of strabismus. It is a rapid (60 s) test that can be performed using a consumer augmented reality headset with integrated eye-tracking, and might conceivably be used remotely by non-specialists in future as a means of highlighting individuals needing face-to-face specialist care.

Introducing the 'Benign Eyelid Lesion Pathway': 1 year experience of synchronous tele-oculoplastics in a tertiary hospital.

BACKGROUND: Patients with benign eyelid lesions make up a large proportion of referrals to the oculoplastic service and lend themselves well to telemedicine with assessments heavily reliant on history, observation-based examination and photographs to enable management decision-making. Our tertiary unit set up tele-oculoplastics clinics for all new patients referred for benign eyelid lesions comprising tele-consultation with antecedent patient photograph: Benign Eyelid Lesion Pathway (BELP). One year on, we describe a retrospective analysis of 974 patients looking at distinct parameters of effectiveness. METHODS: We retrospectively collected data from electronic patient records (EPR) for BELP patients from July 2020 to August 2021 (n = 974). We analysed time efficiency (referral time to treatment plan, consultation duration in minutes, average waiting times, number of patients seen per clinician and DNA rate), accessibility, safety (via video surveillance clinic) and theatre utilisation. RESULTS: 57.3% (n = 558) were listed for a surgical procedure direct from tele-consultation with 94.9% (n = 513) of these proceeding to surgery; 22.8% (n = 222) were discharged, 10.7% (n = 104) had further video follow-up and 6.7% (n = 65) required face-to-face follow-up. Our results showed efficient referral-to-treatment times, waiting times, consultation times and non-attendance rate. There was only a 2.57% non-attendance rate. There was no missed diagnosis of a malignancy of a presumed benign lesion. CONCLUSION: Tele-oculoplastics provides a streamlined, safe, effective, and logistically convenient way to review benign eyelid lesions. With the increased waiting times for referral to biopsy of eyelid lesions, this clinic shows it is imperative to provide digital accessibility for patient assessment and booking to operating theatre.

Creating a secure clinical 'Bring Your Own Device' BYOD photography service to document and monitor suspicious lesions in the lid oncology clinic.

BACKGROUND: Ophthalmic examinations are mostly documented using sketches and written descriptions. Improvements in app security and IT infrastructure mean that high-quality anterior segment photographs can be routinely collected with smartphones alone. The lid oncology team relied on pre-operative formal slit-lamp imaging in the one-stop biopsy clinic, a lengthy process with capacity limitations, that risked delays to care. METHODS: A Bring Your Own Device (BYOD) photography service was developed through a series of iterations and collaborations. Healthcare Assistants took photographs on iPhone SE with Quikvue lens attachments in Pando app. Lesions requiring a slit lamp were photographed by the doctor. Images were uploaded to the patient record twice weekly. The service was evaluated using time-motion studies, imaging quality and utility grading, and patient feedback. RESULTS: BYOD photography saved lid oncology patients 41 min (one-third of total appointment time) and reduced delays to treatment to zero. A patient survey reflected the acceptability of the service, with 100% feeling photography was important at every visit. In terms of utility, 97.5% of smartphone images were suitable for monitoring lesions and making management decisions. The management plan based on the smartphone photographs was consistent with the management plan formulated face-to-face in clinic in 92.5% images. CONCLUSION: BYOD photography has replaced formal slit-lamp imaging in the lid oncology service. This sustainable, cost-effective BYOD solution requires little training and can be adapted, reproduced, and scaled globally. BYOD photography can offer detailed records to monitor progress, contribute to remote care models, improve patient experience, and reducing medical error.

Comparing Home- and Clinic-Based Visual Acuity Testing.

This study compares visual acuity testing at home with visual acuity testing in a clinical setting.

Telemedicine in oculoplastic and adnexal surgery: clinicians' perspectives in the UK.

BACKGROUND/AIMS: The COVID-19 has facilitated a paradigm shift in the sphere of ophthalmic telemedicine: its utility is no longer limited to providing care to remote regions, rather it is expeditiously being adopted as the new standard of care. The aim of our paper is to explore the current attitudes of oculoplastic surgeons towards telemedicine and its utility in the present landscape and its prospects in the future. METHODS: A 39-item questionnaire was distributed to consultant oculoplastic surgeons practising across the UK and anonymised responses were collected and analysed. RESULTS: The COVID-19 pandemic has allowed rapid implementation of telemedicine services in oculoplastic departments across the UK with 86.6% of the respondents incorporating telemedicine into the routine clinical practice. Clinicians reported a statistically significant increase in utility of telemedicine, confidence in using telemedicine and quality of infrastructure available to employ telemedicine following the COVID-19 outbreak. The greatest utility of telemedicine is in triaging, postoperative assessment and eyelid lesion assessment. Main barriers to implementation of telemedicine included difficulties in conducting clinical examinations, lack of administrative support and poor access to digital technologies for patients. Overall, most clinicians were satisfied with the impact of telemedicine services and almost all experts foresee themselves continuing to use telemedicine in the future. CONCLUSIONS: Telemedicine has become an integral part of the oculoplastic service delivery since the COVID-19 pandemic its use is likely to continue. Further development of digital infrastructure and improvement of clinical examination capabilities are required to enable its wider adoption.

Enablers and Barriers to Deployment of Smartphone-Based Home Vision Monitoring in Clinical Practice Settings.

IMPORTANCE: Telemedicine is accelerating the remote detection and monitoring of medical conditions, such as vision-threatening diseases. Meaningful deployment of smartphone apps for home vision monitoring should consider the barriers to patient uptake and engagement and address issues around digital exclusion in vulnerable patient populations. OBJECTIVE: To quantify the associations between patient characteristics and clinical measures with vision monitoring app uptake and engagement. DESIGN, SETTING, AND PARTICIPANTS: In this cohort and survey study, consecutive adult patients attending Moorfields Eye Hospital receiving intravitreal injections for retinal disease between May 2020 and February 2021 were included. EXPOSURES: Patients were offered the Home Vision Monitor (HVM) smartphone app to self-test their vision. A patient survey was conducted to capture their experience. App data, demographic characteristics, survey results, and clinical data from the electronic health record were analyzed via regression and machine learning. MAIN OUTCOMES AND MEASURES: Associations of patient uptake, compliance, and use rate measured in odds ratios (ORs). RESULTS: Of 417 included patients, 236 (56.6%) were female, and the mean (SD) age was 72.8 (12.8) years. A total of 258 patients (61.9%) were active users. Uptake was negatively associated with age (OR, 0.98; 95% CI, 0.97-0.998; P = .02) and positively associated with both visual acuity in the better-seeing eye (OR, 1.02; 95% CI, 1.00-1.03; P = .01) and baseline number of intravitreal injections (OR, 1.01; 95% CI, 1.00-1.02; P = .02). Of 258 active patients, 166 (64.3%) fulfilled the definition of compliance. Compliance was associated with patients diagnosed with neovascular age-related macular degeneration (OR, 1.94; 95% CI, 1.07-3.53; P = .002), White British ethnicity (OR, 1.69; 95% CI, 0.96-3.01; P = .02), and visual acuity in the better-seeing eye at baseline (OR, 1.02; 95% CI, 1.01-1.04; P = .04). Use rate was higher with increasing levels of comfort with use of modern technologies (ß = 0.031; 95% CI, 0.007-0.055; P = .02). A total of 119 patients (98.4%) found the app either easy or very easy to use, while 96 (82.1%) experienced increased reassurance from using the app. CONCLUSIONS AND RELEVANCE: This evaluation of home vision monitoring for patients with common vision-threatening disease within a clinical practice setting revealed demographic, clinical, and patient-related factors associated with patient uptake and engagement. These insights inform targeted interventions to address risks of digital exclusion with smartphone-based medical devices.

Impact and Challenges of Integrating Artificial Intelligence and Telemedicine into Clinical Ophthalmology.

ABSTRACT: Aging populations and worsening burden of chronic, treatable disease is increasingly creating a global shortfall in ophthalmic care provision. Remote and automated systems carry the promise to expand the scale and potential of health care interventions, and reduce strain on health care services through safe, personalized, efficient, and cost-effective services. However, significant challenges remain. Forward planning in service design is paramount to safeguard patient safety, trust in digital services, data privacy, medico-legal implications, and digital exclusion. We explore the impact and challenges facing patients and clinicians in integrating AI and telemedicine into ophthalmic care-and how these may influence its direction.

Smartphone-based remote monitoring of vision in macular disease enables early detection of worsening pathology and need for intravitreal therapy.

BACKGROUND/AIMS: To assess the outcomes of home monitoring of distortion caused by macular diseases using a smartphone-based application (app), and to examine them with hospital-based assessments of visual acuity (VA), optical coherence tomography-derived central macular thickness (CMT) and the requirement of intravitreal injection therapy. DESIGN: Observational study with retrospective analysis of data. METHODS: Participants were trained in the correct use of the app (Alleye, Oculocare, Zurich, Switzerland) in person or by using video and telephone consultations. Automated threshold-based alerts were communicated based on a traffic light system. A 'threshold alarm' was defined as three consecutive 'red' scores, and turned into a 'persistent alarm' if present for greater than a 7-day period. Changes of VA and CMT, and the requirement for intravitreal therapy after an alarm were examined. RESULTS: 245 patients performing a total of 11 592 tests (mean 46.9 tests per user) were included and 85 eyes (164 alarms) examined. Mean drop in VA from baseline was -4.23 letters (95% CI: -6.24 to -2.22; p<0.001) and mean increase in CMT was 29.5 µm (95% CI: -0.08 to 59.13; p=0.051). Sixty-six eyes (78.5%) producing alarms either had a drop in VA, increase in CMT or both and 60.0% received an injection. Eyes with persistent alarms had a greater loss of VA, -4.79 letters (95% CI: -6.73 to -2.85; p<0.001) or greater increase in CMT, +87.8 µm (95% CI: 5.2 to 170.4; p=0.038). CONCLUSION: Smartphone-based self-tests for macular disease may serve as reliable indicators for the worsening of pathology and the need for treatment.

Safety of video-based telemedicine compared to in-person triage in emergency ophthalmology during COVID-19.

BACKGROUND: the need for social distancing midst the COVID-19 pandemic has forced ophthalmologists to innovate with telemedicine. The novel process of triaging emergency ophthalmology patients via videoconsultations should reduce hospital attendances. However, the safety profile of such services were unknown. METHODS: in this retrospective cohort study, we reviewed case notes of 404 adults who used our videoconsultation service from 20/04/2020 to 03/05/2020. We compared these to 451 patient who attended eye casualty in person at the same time who were deemed not to require same day ophthalmic examination. FINDINGS: patients seen by videoconsultations tended to be younger (Median = 43 years, Inter-quartile range = 27 vs Median= 49 years, Inter-quartile range = 28)'. More males used the face-to-face triage (55%) while more females used videoconsultation (54%)%. Fewer patients seen by videoconsultations required specialist review compared to face-face triage [X 2 (1, N = 854) = 128.02, p<0.001)]. 35.5% of the patients initially seen by videoconsultation had unplanned reattendance within 1 month, compared to 15.7% in the group initially seen in person. X 2 (1, N = 234) = 7.31, p = 0.007). The rate of actual harm was no different (at 0% for each method), with perfect inter-grader correlation when graded independently by two senior ophthalmologists. 97% of patients seen on the video platform surveyed were satisfied with their care. INTERPRETATION: we demonstrate comparable patient safety of videoconsultations at one-month follow-up to in person review. The service is acceptable to patients and reduces the risk of COVID-19 transmission. We propose that videoconsultations are effective and desirable as a tool for triage in ophthalmology. FUNDING: the research supported by the National Institute for Health Research (NIHR) Biomedical Research Centre based at Moorfields Eye Hospital NHS Foundation Trust and UCL Institute of Ophthalmology who fund PT and DS's time to conduct research. The views expressed are those of the author(s) and not necessarily those of the NHS, the NIHR or the Department of Health.

Visual Acuity Apps for Rapid Integration in Teleconsultation Services in all Resource Settings: A Review.

PURPOSE: There is a need for a simple and accurate way to assess visual acuity in telemedicine consultations in ophthalmology and other related specialties. DESIGN: We surveyed visual acuity testing apps available that allow patients to measure their own acuity, focusing on freely accessible resources suitable for all resource settings. METHODS: A systematic search was performed for visual acuity testing apps on 2 major platforms: Google Play Store (Google, CA, USA) and Apple App Store (Apple, CA, USA). RESULTS: Sixteen apps (67%) tested near vision, 5 apps (21%) tested distance vision, and 3 apps (13%) offered options for both near and distance vision testing. Of the 24 apps, 5 (21%) offered a method of calibration of optotype size. Three apps (13%) demonstrated evidence of clinical validation. Only 3 apps fulfilled our criteria for suitability for clinical practice. CONCLUSIONS: We have recommended 3 apps that may be quickly integrated into clinical practice in both ophthalmic and non-ophthalmic all resource settings.

Accuracy of periocular lesion assessment using telemedicine.

OBJECTIVES: To assess the agreement in diagnosis and management plans reached between clinicians reviewing eyelid lesions remotely and in face-to-face clinics. METHODS: In this single-centre observational case series, data were prospectively collected on 50 consecutive adults referred with eyelid lesions suitable to be seen by a nurse. A proforma was completed to gather salient information. A nurse specialist saw patients in face-to-face clinics and collected information using the proforma, devising a diagnosis and management plan. Photographs of the eyelid lesions were taken by a medical photographer. A subsequent remote review was completed by an oculoplastic consultant using the proforma information and photographs in the absence of the patient. The diagnosis and management plan constructed by the nurse specialist were compared with those reached by the consultant. RESULTS: Complete data were available for 44 consecutive cases. There was an overall 91% agreement (40 cases out of 44) between the diagnoses reached by the nurse specialist, and the remote reviewer; kappa coefficient 0.88 (95% CI 0.76 to 0.99). There was an overall 82% agreement (36 out of 44 cases) in the management plans devised by the nurse-led clinic and remote reviewer; kappa coefficient 0.74 (95% CI 0.58 to 0.90). The average time taken for a remote reviewer to reach a diagnosis and management plan was 1 min and 20 s. CONCLUSIONS: This study evaluated the feasibility of assessing eyelid lesions using asynchronous telemedicine. There was overall a high rate of concordance in the diagnosis reached, and management devised between the clinic and remote review.

Evaluation of a Home-Printable Vision Screening Test for Telemedicine.

Importance: Many ophthalmology appointments have been converted to telemedicine assessments. The use of a printed vision chart for ophthalmology telemedicine appointments that can be used by people who are excluded from digital testing has yet to be validated. Objectives: To evaluate the repeatability of visual acuity measured using the Home Acuity Test (HAT) and the agreement between the HAT and the last in-clinic visual acuity. Design, Setting, and Participants: This diagnostic study was conducted from May 11 to 22, 2020, among 50 control participants and 100 adult ophthalmology outpatients who reported subjectively stable vision and were attending routine telemedicine clinics. Bland-Altman analysis of corrected visual acuity measured with the HAT was compared with the last measured in-clinic visual acuity on a conventional Early Treatment Diabetic Retinopathy Study logMAR chart. Main Outcomes and Measures: For control participants, repeatability of the HAT and agreement with standard logMAR visual acuity measurement. For ophthalmology outpatients, agreement with the last recorded in-clinic visual acuity and with the International Classification of Diseases and Related Health Problems, 11th Revision visual impairment category. Results: A total of 50 control participants (33 [66%] women; mean [SD] age, 36.0 [10.8] years) and 100 ophthalmology patients with a wide range of diseases (65 [65%] women; mean [SD] age, 55.3 [22.2] years) were recruited. For control participants, mean (SD) test-retest difference in the HAT line score was -0.012 (0.06) logMAR, with limits of agreement (LOA) between -0.13 and 0.10 logMAR. The mean (SD) difference in visual acuity compared with conventional vision charts was -0.14 (0.14) logMAR (range, -0.4 to 0.18 log MAR) (-7 letters) in controls, with LOA of -0.41 to 0.12 logMAR (-20 to 6 letters). For ophthalmology outpatients, the mean (SD) difference in visual acuity was -0.10 (0.17) logMAR (range, -0.5 to 0.3 logMAR) (1 line on a conventional logMAR sight chart), with the HAT indicating poorer visual acuity than the previous in-clinic test, and LOA of -0.44 to 0.23 logMAR (-22 to 12 letters). There was good agreement in the visual impairment category for ophthalmology outpatients (Cohen κ = 0.77 [95% CI, 0.74-0.81]) and control participants (Cohen κ = 0.88 [95% CI, 0.88-0.88]). Conclusions and Relevance: This study suggests that the HAT can be used to measure visual acuity by telephone for a wide range of ophthalmology outpatients with diverse conditions. Test-retest repeatability is relatively high, and agreement in the visual impairment category is good for this sample, supporting the use of printed charts in this context.

Color Vision Deficiency Among Doctors: Can We Make Useful Adaptations to the Color Codes Used in the Clinical Environment?

ABSTRACT: Color vision deficiency (formerly known as color blindness) is common as a congenital and as an acquired condition. Some professions, most famously commercial aviation, require their members to demonstrate normal color vision. In the United States and United Kingdom, no restriction is placed on the ability of the color-deficient doctor to practice medicine, although there is evidence that certain clinical discriminations are harder for such doctors. Generally ignored has been the difficulty and the potential for error that arises from the use of color codes in clinical equipment. In this review, we introduce the basic concepts of color deficiency, summarize evidence for the challenges it poses to the doctor, examine global variation in policy, show the potential for confusion among clinical color codes, and suggest how the current situation could be improved to enhance both patient safety and the well-being of the color-deficient doctor.

Digital technology, tele-medicine and artificial intelligence in ophthalmology: A global perspective.

The simultaneous maturation of multiple digital and telecommunications technologies in 2020 has created an unprecedented opportunity for ophthalmology to adapt to new models of care using tele-health supported by digital innovations. These digital innovations include artificial intelligence (AI), 5th generation (5G) telecommunication networks and the Internet of Things (IoT), creating an inter-dependent ecosystem offering opportunities to develop new models of eye care addressing the challenges of COVID-19 and beyond. Ophthalmology has thrived in some of these areas partly due to its many image-based investigations. Tele-health and AI provide synchronous solutions to challenges facing ophthalmologists and healthcare providers worldwide. This article reviews how countries across the world have utilised these digital innovations to tackle diabetic retinopathy, retinopathy of prematurity, age-related macular degeneration, glaucoma, refractive error correction, cataract and other anterior segment disorders. The review summarises the digital strategies that countries are developing and discusses technologies that may increasingly enter the clinical workflow and processes of ophthalmologists. Furthermore as countries around the world have initiated a series of escalating containment and mitigation measures during the COVID-19 pandemic, the delivery of eye care services globally has been significantly impacted. As ophthalmic services adapt and form a "new normal", the rapid adoption of some of telehealth and digital innovation during the pandemic is also discussed. Finally, challenges for validation and clinical implementation are considered, as well as recommendations on future directions.

An Artificial Intelligence Approach to the Assessment of Abnormal Lid Position.

New artificial intelligence (AI) approaches to facial analysis show promise in the clinical evaluation of abnormal lid position. This could allow more naturalistic, quantitative, and automated assessment of lid position. The aim of this article was to determine whether OpenFace, an AI approach to real-time facial landmarking and analysis, can extract clinically useful measurements from images of patients before and after ptosis correction. Manual and AI-automated approaches to vertical palpebral aperture measurement of 128 eyes in pre- and postoperative full-face images of ptosis patients were compared in this study. Agreement in interpupillary distance to vertical palpebral aperture ratio between clinicians and an AI-based system was assessed. Image quality varied highly with interpupillary distance defined by a mean of 143.4 pixels (min = 60, max = 328, SD = 80.3 pixels). A Bland-Altman analysis suggests a good agreement between manual and AI analysis of vertical palpebral aperture (94.4% of measurements falling within 2 SDs of the mean). Correlation between the 2 methods yielded a Pearson's r(126) = 0.87 (P < 0.01) and r2 = 0.76. This feasibility study suggests that existing, open-source approaches to facial analysis can be applied to the clinical assessment of patients with abnormal lid position. The approach could be extended to further quantify clinical assessment of oculoplastic conditions.

Can Psychophysics Be Fun? Exploring the Feasibility of a Gamified Contrast Sensitivity Function Measure in Amblyopic Children Aged 4-9 Years.

Routine assessments of the Contrast Sensitivity Function [CSF] could be useful for the diagnosis and monitoring of amblyopia. However, current CSF measures are not clinically practical, as they are too slow, too boring, and too uncomfortable to sustain a young child's interest. Here we assess the feasibility of a more gamified approach to CSF testing, in which a maximum likelihood psychophysical algorithm (QUEST+) is combined with a largely unconstrained user interface (no fixation target, head restraints, or discrete trials). Twenty-five amblyopes (strabismic, anisometropic, or mixed) aged 4.0-9.2 years performed the gamified CSF assessment monocularly (once per eye). The test required the child to "pop" (press) grating stimuli as they "bounced" around a tablet screen. Head tracking via the tablet's front-facing camera was used to adjust for variations in viewing distance post hoc. CSFs were fitted for each eye, and Area Under the CSF (AUCSF) computed as a summary measure of sensitivity. The results showed that AUCSF measurements were able to separate moderately and severely amblyopic eyes from fellow eyes (case-control effect), and to distinguish individuals with varying degrees of vision loss (dose effect). Even the youngest children exhibited no difficulties completing the test or comprehending what to do, and most children appeared to find the test genuinely enjoyable. Informal feedback from a focus group of older children was also positive, although potential shortcomings with the present design were identified. This feasibility study indicates that gamified, child-friendly vision assessments have promise as a future means of pediatric clinical assessment. Such measures could be particularly valuable for assessing children outside of conventional eye-care facilities (e.g., home-monitoring, school screening).

Feasibility of simple machine learning approaches to support detection of non-glaucomatous visual fields in future automated glaucoma clinics.

OBJECTIVES: To assess the performance of feed-forward back-propagation artificial neural networks (ANNs) in detecting field defects caused by pituitary disease from among a glaucomatous population. METHODS: 24-2 Humphrey Visual Field reports were gathered from 121 pituitary patients and 907 glaucomatous patients. Optical character recognition was used to extract the threshold values from PDF reports. Left and right eye visual fields were coupled for each patient in an array to create bilateral field representations. ANNs were created to detect chiasmal field defects. We also assessed the ability of ANNs to identify a single pituitary field among 907 glaucomatous distractors. RESULTS: Mean field thresholds across all locations were lower for pituitary patients (20.3 dB, SD = 5.2 dB) than for glaucoma patients (24.4 dB, SD = 5.0 dB) indicating a greater degree of field loss (p < 0.0001) in the pituitary group. However, substantial overlap between the groups meant that mean bilateral field loss was not a reliable indicator of aetiology. Representative ANNs showed good performance in the discrimination task with sensitivity and specificity routinely above 95%. Where a single pituitary field was hidden among 907 glaucomatous fields, it had one of the five highest indexes of suspicion on 91% of 2420 ANNs. CONCLUSIONS: Traditional artificial neural networks perform well at detecting chiasmal field defects among a glaucoma cohort by inspecting bilateral field representations. Increasing automation of care means we will need robust methods of automatically diagnosing and managing disease. This work shows that machine learning can perform a useful role in diagnostic oversight in highly automated glaucoma clinics, enhancing patient safety.