Using non-mydriatic fundus photography to detect fundus pathology in Australian metropolitan emergency departments: A prospective prevalence and diagnostic accuracy study

Application of a Deep Learning System to Detect Papilledema on Nonmydriatic Ocular Fundus Photographs in an Emergency Department

PURPOSE

The Fundus photography vs Ophthalmoscopy Trial Outcomes in the Emergency Department (FOTO-ED) studies showed that ED providers poorly recognized funduscopic findings in patients in the ED. We tested a modified version of the Brain and Optic Nerve Study Artificial Intelligence (BONSAI) deep learning system on nonmydriatic fundus photographs from the FOTO-ED studies to determine if the deep learning system could have improved the detection of papilledema had it been available to ED providers as a real-time diagnostic aid.

DESIGN

Retrospective secondary analysis of a cohort of patients included in the FOTO-ED studies.

METHODS

The testing data set included 1608 photographs obtained from 828 patients in the FOTO-ED studies. Photographs were reclassified according to the optic disc classification system used by the deep learning system ("normal optic discs," "papilledema," and "other optic disc abnormalities"). The system's performance was evaluated by calculating the area under the receiver operating characteristic curve (AUC), sensitivity, and specificity using a 1-vs-rest strategy, with reference to expert neuro-ophthalmologists.

RESULTS

The BONSAI deep learning system successfully distinguished normal from abnormal optic discs (AUC 0.92 [95% confidence interval {CI} 0.90-0.93]; sensitivity 75.6% [73.7%-77.5%] and specificity 89.6% [86.3%-92.8%]), and papilledema from normal and others (AUC 0.97 [0.95-0.99]; sensitivity 84.0% [75.0%-92.6%] and specificity 98.9% [98.5%-99.4%]). Six patients with missed papilledema in 1 eye were correctly identified by the deep learning system as having papilledema in the other eye.

CONCLUSIONS

The BONSAI deep learning system was able to reliably identify papilledema and normal optic discs on nonmydriatic photographs obtained in the FOTO-ED studies. Our deep learning system has excellent potential as a diagnostic aid in EDs and non-ophthalmology clinics equipped with nonmydriatic fundus cameras. NOTE: Publication of this article is sponsored by the American Ophthalmological Society.

Application of non-mydriatic fundus photography-assisted telemedicine in diabetic retinopathy screening

BACKGROUND

Early screening and accurate staging of diabetic retinopathy (DR) can reduce blindness risk in type 2 diabetes patients. DR's complex pathogenesis involves many factors, making ophthalmologist screening alone insufficient for prevention and treatment. Often, endocrinologists are the first to see diabetic patients and thus should screen for retinopathy for early intervention.

AIM

To explore the efficacy of non-mydriatic fundus photography (NMFP)-enhanced telemedicine in assessing DR and its various stages.

METHODS

This retrospective study incorporated findings from an analysis of 93 diabetic patients, examining both NMFP-assisted telemedicine and fundus fluorescein angiography (FFA). It focused on assessing the concordance in DR detection between these two methodologies. Additionally, receiver operating characteristic (ROC) curves were generated to determine the optimal sensitivity and specificity of NMFP-assisted telemedicine, using FFA outcomes as the standard benchmark.

RESULTS

In the context of DR diagnosis and staging, the kappa coefficients for NMFP-assisted telemedicine and FFA were recorded at 0.775 and 0.689 respectively, indicating substantial intermethod agreement. Moreover, the NMFP-assisted telemedicine's predictive accuracy for positive FFA outcomes, as denoted by the area under the ROC curve, was remarkably high at 0.955, within a confidence interval of 0.914 to 0.995 and a statistically significant P-value of less than 0.001. This predictive model exhibited a specificity of 100%, a sensitivity of 90.9%, and a Youden index of 0.909.

CONCLUSION

NMFP-assisted telemedicine represents a pragmatic, objective, and precise modality for fundus examination, particularly applicable in the context of endocrinology inpatient care and primary healthcare settings for diabetic patients. Its implementation in these scenarios is of paramount significance, enhancing the clinical accuracy in the diagnosis and therapeutic management of DR. This methodology not only streamlines patient evaluation but also contributes substantially to the optimization of clinical outcomes in DR management.

The BONSAI (Brain and Optic Nerve Study with Artificial Intelligence) deep learning system can accurately identify pediatric papilledema on standard ocular fundus photographs

BACKGROUND

Pediatric papilledema often reflects an underlying severe neurologic disorder and may be difficult to appreciate, especially in young children. Ocular fundus photographs are easy to obtain even in young children and in nonophthalmology settings. The aim of our study was to ascertain whether an improved deep-learning system (DLS), previously validated in adults, can accurately identify papilledema and other optic disk abnormalities in children.

METHODS

The DLS was tested on mydriatic fundus photographs obtained in a multiethnic pediatric population (<17 years) from three centers (Atlanta-USA; Bucharest-Romania; Singapore). The DLS's multiclass classification accuracy (ie, normal optic disk, papilledema, disks with other abnormality) was calculated, and the DLS's performance to specifically detect papilledema and normal disks was evaluated in a one-vs-rest strategy using the AUC, sensitivity and specificity, with reference to expert neuro-ophthalmologists.

RESULTS

External testing was performed on 898 fundus photographs: 447 patients; mean age, 10.33 (231 patients ≤10 years of age; 216, 11-16 years); 558 normal disks, 254 papilledema, 86 other disk abnormalities. Overall multiclass accuracy of the DLS was 89.6% (range, 87.8%-91.6%). The DLS successfully distinguished "normal" from "abnormal" optic disks (AUC 0.99 [0.98-0.99]; sensitivity, 87.3% [84.9%-89.8%]; specificity, 98.5% [97.6%-99.6%]), and "papilledema" from "normal and other" (AUC 0.99 [0.98-1.0]; sensitivity, 98.0% [96.8%-99.4%]; specificity, 94.1% (92.4%-95.9%)].

CONCLUSIONS

Our DLS reliably distinguished papilledema from normal optic disks and other disk abnormalities in children, suggesting it could be utilized as a diagnostic aid for the assessment of optic nerve head appearance in the pediatric age group.

Diabetic Retinopathy Screening at the Point of Care (DR SPOC): detecting undiagnosed and vision-threatening retinopathy by integrating portable technologies within existing services

INTRODUCTION

The aim of this study was to determine the prevalence of diabetic retinopathy (DR) in a low socioeconomic region of a high-income country, as well as determine the diagnostic utility of point-of-care screening for high-risk populations in tertiary care settings.

RESEARCH DESIGN AND METHODS

This was a cross-sectional study of patients with diabetes attending foot ulcer or integrated care diabetes clinics at two Western Sydney hospitals (n=273). DR was assessed using portable, two-field, non-mydriatic fundus photography and combined electroretinogram/ pupillometry (ERG). With mydriatic photographs used as the reference standard, sensitivity and specificity of the devices were determined. Prevalence of DR and vision-threatening diabetic retinopathy (VTDR) were reported, with multivariate logistic regression used to identify predictors of DR.

RESULTS

Among 273 patients, 39.6% had any DR, while 15.8% had VTDR, of whom 59.3% and 62.8% were previously undiagnosed, respectively. Non-mydriatic photography demonstrated 20.2% sensitivity and 99.5% specificity for any DR, with a 56.7% screening failure rate. Meanwhile, mydriatic photography produced high-quality images with a 7.6% failure rate. ERG demonstrated 72.5% sensitivity and 70.1% specificity, with a 15.0% failure rate. The RETeval ERG was noted to have an optimal DR cut-off score at 22. Multivariate logistic regression identified an eGFR of ≤29 mL/min/1.73 m2, HbA1c of ≥7.0%, pupil size of <4 mm diameter, diabetes duration of 5-24 years and RETeval score of ≥22 as strong predictors of DR.

CONCLUSION

There is a high prevalence of vision-threatening and undiagnosed DR among patients attending high-risk tertiary clinics in Western Sydney. Point-of-care DR screening using portable, mydriatic photography demonstrates potential as a model of care which is easily accessible, targeted for high-risk populations and substantially enhances DR detection.

Diagnosis of Optic Disc Oedema: Fundus Features, Ocular Imaging Findings, and Artificial Intelligence

Optic disc swelling is a manifestation of a broad range of processes affecting the optic nerve head and/or the anterior segment of the optic nerve. Accurately diagnosing optic disc oedema, grading its severity, and recognising its cause, is crucial in order to treat patients in a timely manner and limit vision loss. Some ocular fundus features, in light of a patient's history and visual symptoms, may suggest a specific mechanism or aetiology of the visible disc oedema, but current criteria can at most enable an educated guess as to the most likely cause. In many cases only the clinical evolution and ancillary testing can inform the exact diagnosis. The development of ocular fundus imaging, including colour fundus photography, fluorescein angiography, optical coherence tomography, and multimodal imaging, has provided assistance in quantifying swelling, distinguishing true optic disc oedema from pseudo-optic disc oedema, and differentiating among the numerous causes of acute optic disc oedema. However, the diagnosis of disc oedema is often delayed or not made in busy emergency departments and outpatient neurology clinics. Indeed, most non-eye care providers are not able to accurately perform ocular fundus examination, increasing the risk of diagnostic errors in acute neurological settings. The implementation of non-mydriatic fundus photography and artificial intelligence technology in the diagnostic process addresses these important gaps in clinical practice.

Fundoscopy Use in Neurology Departments and the Utility of Smartphone photography ( FUNDUS ): A prospective prevalence and crossover diagnostic accuracy study amongst neurology inpatients

Background and purpose

Although fundoscopy is a crucial part of the neurological examination, it is challenging, under‐utilized and unreliably performed. The aim was to determine the prevalence of fundus pathology amongst neurology inpatients and the diagnostic accuracy of current fundoscopy practice compared with systematic screening with smartphone fundoscopy (SF) and portable non‐mydriatic fundus photography (NMFP).

Methods

This was a prospective cross‐sectional surveillance and diagnostic accuracy study on adult patients admitted under neurology in an Australian hospital. Inpatients were randomized to initial NMFP (RetinaVue 100, Welch Allyn) or SF (D‐EYE) followed by a crossover to the alternative modality. Images were graded by neurology doctors, using telemedicine consensus neuro‐ophthalmology NMFP grading as the reference standard. Feasibility parameters included ease, comfort and speed.

Results

Of 79 enrolled patients, 14.1% had neurologically relevant pathology (seven, disc pallor; one, hypertensive retinopathy; three, disc swelling). The neurology team performed direct ophthalmoscopy in 6.6% of cases and missed all abnormalities. SF had a sensitivity of 30%–40% compared with NMFP (45.5%); however, it had a lower rate of screening failure (1% vs. 13%, p < 0.001), a shorter examination time (1.10 vs. 2.25 min, p < 0.001) and a slightly higher patient comfort rating (9.2 vs. 8/10, p < 0.001).

Conclusion

Our study demonstrates a clinically significant prevalence of fundus pathology amongst neurology inpatients which was missed by current fundoscopy practices. Portable NMFP screening appears more accurate than SF, whilst both are diagnostically superior to routine fundoscopic practice, feasible and well tolerated by patients.

Utility of video-fundoscopy and prospects of portable stereo-photography of the ocular fundus in neurological patients

Background

Proper evaluation of ocular fundi is an integral part of neurological examination. Unfortunately, neurology residents are increasingly uncomfortable performing fundoscopy and interpreting findings because of diminishing skills and lack of experience. This became more prominent during the COVID-19 pandemic as fundoscopy requires proximity to the patient.

With the recent dramatic improvement of smartphone cameras, fundus photography using the PanOptic Ophthalmoscope (Welch Allyn, Skaneateles Falls, NY) with a smartphone adapter offered an alternative to direct fundoscopic examination. We present the first experience with our own design of a universal smartphone adapter.

Methods

This is a single-center case series, consecutive for a single user and certain presenting neurological symptoms, which is aimed to evaluate the feasibility and practicality of a new, universal PanOptic smartphone adapter. Presenting symptoms included headache, ocular symptoms, seizure, or encephalopathy. We used 3D modeling and printing techniques to create the adapter.

We also developed a methodology of capturing stereoscopic images of the optic disc using a single smartphone camera, but the method was not systematically evaluated in this paper.

Results

Here we present our initial experience of fundus video/photography in patients, who presented with encephalopathy, headache, seizure, vision loss, and other ocular symptoms. Fundoscopic abnormalities were discovered in 11 out of 100 patients. Some were incidental findings and were unrelated to the presentation. In one case, fundoscopy played a critical role in establishing the correct diagnosis.

Conclusions

Our custom-designed smartphone adapter allowed obtaining high-quality video and photo recordings using PanOptic Ophthalmoscope. The acquisition of high-quality photos enables a high-yield diagnostic tool and allows revisiting the image in the patient’s chart. Improvement of smartphone cameras opens vast horizons for stereo-fundoscopy and 3D reconstruction of the ocular fundus without using sophisticated and costly equipment. Microscopic eye movements allow taking snapshots of two side-by-side photos for 3D reconstruction and stereoscopic image viewing, which is the next level of optic disc assessment.

Epidemiology, investigation, management, and outcome of headache in emergency departments (HEAD study)-A multinational observational study

OBJECTIVE

To describe the epidemiology of nontraumatic headache in adults presenting to emergency departments (EDs).

BACKGROUND

Headache is a common reason for presentation to EDs. Little is known about the epidemiology, investigation, and treatment of nontraumatic headache in patients attending EDs internationally.

METHODS

An international, multicenter, observational, cross-sectional study was conducted over one calendar month in 2019. Participants were adults (≥18 years) with nontraumatic headache as the main presenting complaint. Exclusion criteria were recent head trauma, missing records, interhospital transfers, re-presentation with same headache as a recent visit, and headache as an associated symptom. Data collected included demographics, clinical assessment, investigation, treatment, and outcome.

RESULTS

We enrolled 4536 patients (67 hospitals, 10 countries). "Thunderclap" onset was noted in 14.2% of cases (644/4536). Headache was rated as severe in 27.2% (1235/4536). New neurological examination findings were uncommon (3.2%; 147/4536). Head computed tomography (CT) was performed in 36.6% of patients (1661/4536), of which 9.9% showed clinically important pathology (165/1661). There was substantial variation in CT scan utilization between countries (15.9%-75.0%). More than 30 different diagnoses were made. Presumed nonmigraine benign headache accounted for 45.4% of cases (2058/4536) with another 24.3% classified as migraine (1101/4536). A small subgroup of patients have a serious secondary cause for their headache (7.1%; 323/4536) with subarachnoid hemorrhage (SAH), stroke, neoplasm, non-SAH intracranial hemorrhage/hematoma, and meningitis accounting for about 1% each. Most patients were treated with simple analgesics (paracetamol, aspirin, or nonsteroidal anti-inflammatory agents). Most patients were discharged home (83.8%; 3792/4526). In-hospital mortality was 0.3% (11/4526).

CONCLUSION

Diagnosis and management of headache in the ED is challenging. A small group of patients have a serious secondary cause for their symptoms. There is wide variation in the use of neuroimaging and treatments. Further work is needed to understand the variation in practice and to better inform international guidelines regarding emergent neuroimaging and treatment.

Comparison of conventional and wide field direct ophthalmoscopy on medical students' self-confidence for fundus examination: a 1-year follow-up

BACKGROUND

Fundus examination is an easy, quick and effective way to diagnose sight- and life-threatening diseases. However, medical students and physicians report lack of proficiency and self-confidence in perform fundoscopy. The aim of this study was to compare students' self-confidence in fundus examination, using two different direct ophthalmoscopes, 1 month and 1 year after practical training.

METHODS

In this prospective cohort, medical students (MS) of the same class were divided in small groups for PanOptic (PO) or conventional (CO) direct ophthalmoscope training. The intervention group encompassed MS of the 4th -year (class of 2019), and the control group encompassed MS of year behind (class of 2020). A questionnaire to measure self-confidence in fundoscopy technique assessing optic nerve, cup-to-disc ratio and macula was translated and validated to Portuguese, and applied 1-month and 1-year after practical training.

RESULTS

One-hundred and sixty-seven MS were enrolled (35 PO group, 38 CO group, and 94 control group). PO group had a significantly higher overall self-confidence comparing either control or CO groups, respectively (3.57 ± 0.65 vs. 2.97 ± 1.03 vs. 2.46 ± 0.87, p < 0.01) as well as in evaluate cup-to-disc ratio (3.09 ± 0.75 vs. 2.32 ± 0.87 vs. 1.46 ± 0.81, p < 0.01), optic disc margins (3.26 ± 0.85 vs. 2.71 ± 0.96 vs. 2.01 ± 0.97, p < 0.01) and macula (3.43 ± 1.12 vs. 2.89 ± 1.08 vs. 2.02 ± 0.89, p < 0.01) 1-month after practical training. One-year after intervention, CO group showed a significantly higher score compared to PO group in overall self-confidence (3.31 ± 0.69 vs. 3.18 ± 0.73, p = 0.03) and in optic disc margins assessing (3.16 ± 0.85 vs. 2.95 ± 0.78, p = 0.03), but not significant in the evaluation of cup-to-disc ratio (2.78 ± 0.97 vs. 2.68 ± 0.94, p = 0.08), and macula (3.34 ± 0.79 vs. 3.27 ± 0.98, p = 0.07).

CONCLUSIONS

Students were more confident in use PO as an instrument to perform direct ophthalmoscopy immediately after practical training, but confidence level of CO was higher compared to PO one year after practical training. These findings would help medical schools decide which ophthalmoscope to choose to teach fundus examination.

Impact on patient management of non-mydriatic fundus photography compared to direct ophthalmoscopy in a regional Australian emergency department

OBJECTIVE

To investigate the management impact of non-mydriatic fundus photography (NMFP) implementation for appropriate ED patients; compare the diagnostic accuracy of direct ophthalmoscopy (DO) and NMFP, and determine the prevalence of fundus pathology in a regional Australian ED.

METHODS

This before/after crossover study prospectively enrolled patients presenting with headache, neurological deficit, visual disturbance and/or hypertensive urgency. Patients received DO examination, then separate NMFP examination. Emergency clinicians (ECs) were surveyed on their patient management plans following both DO examination and NMFP imaging. Telemedicine review of NMFP images was performed by an ophthalmologist within 48 h, and any additional management changes were documented.

RESULTS

The use of NMFP influenced changes in management in 52 (39%) of 133 enrolled patients (95% confidence interval 31-48%). Of these, 65% were escalations of management due to acute fundus pathology, while 35% were de-escalating changes following normal fundus findings. ECs diagnostic accuracy for acute fundus pathology improved from 0% to 29% sensitivity, and 59% to 84% specificity using DO and NMFP respectively, and telemedicine registrar review increased this to 50% sensitivity and 86% specificity. The period prevalence of acute fundus pathology was 10.5% (95% confidence interval 6-17%).

CONCLUSION

The addition of NMFP images can significantly impact the management of ED patients requiring fundus examination, facilitating expedited and optimised patient care. NMFP improves ECs diagnostic acumen for fundus pathology over DO examination and telehealth specialist review is important for diagnostic accuracy. There is a clinically important prevalence of fundus pathology in this regional ED setting.

eFOCUS 2: A randomised crossover trial of smartphone fundoscopy and direct ophthalmoscopy aiming to improve optic disc interpretation by medical students with e-learning support

BACKGROUND

Ophthalmoscopy and its interpretation are complex. We aimed to compare the diagnostic accuracy of smartphone fundoscopy with traditional direct ophthalmoscopy for optic disc interpretation, with e-learning support.

METHODS

We conducted a randomised, crossover study of 102 medical students. Students were offered e-learning for optic disc interpretation. A fundoscopy objective structured clinical examination was conducted after an introductory lecture and 10-min practical training session on smartphone fundoscopy and traditional ophthalmoscopy. Participants examined patients and simulator slides with a randomised crossover between smartphone [D-eye (Padova, Italy) or iExaminer (Welch Allyn, Macquarie Park, Australia)] and traditional ophthalmoscopy (Welch Allyn). Optic discs were graded independently by three masked ophthalmologists. The primary outcome was the ability to interpret an optic disc as normal or abnormal. Secondary outcomes included other optic disc aspects; student preferences; and e-learning performance.

RESULTS

Students' agreement with the gold standard for an abnormal or normal disc was significantly greater using a smartphone (74.4%) than with direct ophthalmoscopy (68.1%, p = 0.032). More students preferred smartphone (74%) over direct ophthalmoscopy (26%, p < 0.001). E-learning led to an improvement in optic disc interpretation scores (mean improvement = 4.5%, 95% CI = 3.7-5.2, p < 0.001).

CONCLUSIONS

Medical students are more accurate at recognising an abnormal optic disc using smartphone fundoscopy than traditional direct ophthalmoscopy, and have a strong preference for smartphone fundoscopy. E-learning may improve the interpretation of optic disc abnormalities. Smartphone fundoscopy may mitigate some technical challenges of fundoscopy and reinvigorate use of this valuable clinical examination.