Assessing the Demand for Teleophthalmology in Florida Emergency Departments

Assessing the Impact of Image Quality on Deep Learning Classification of Infectious Keratitis

Objective

To investigate the impact of corneal photograph quality on convolutional neural network (CNN) predictions.

Design

A CNN trained to classify bacterial and fungal keratitis was evaluated using photographs of ulcers labeled according to 5 corneal image quality parameters: eccentric gaze direction, abnormal eyelid position, over/under-exposure, inadequate focus, and malpositioned light reflection.

Participants

All eligible subjects with culture and stain-proven bacterial and/or fungal ulcers presenting to Aravind Eye Hospital in Madurai, India, between January 1, 2021 and December 31, 2021.

Methods

Convolutional neural network classification performance was compared for each quality parameter, and gradient class activation heatmaps were generated to visualize regions of highest influence on CNN predictions.

Main Outcome Measures

Area under the receiver operating characteristic and precision recall curves were calculated to quantify model performance. Bootstrapped confidence intervals were used for statistical comparisons. Logistic loss was calculated to measure individual prediction accuracy.

Results

Individual presence of either light reflection or eyelids obscuring the corneal surface was associated with significantly higher CNN performance. No other quality parameter significantly influenced CNN performance. Qualitative review of gradient class activation heatmaps generally revealed the infiltrate as having the highest diagnostic relevance.

Conclusions

The CNN demonstrated expert-level performance regardless of image quality. Future studies may investigate use of smartphone cameras and image sets with greater variance in image quality to further explore the influence of these parameters on model performance.

Financial Disclosures

Proprietary or commercial disclosure may be found after the references.

Assessing the subjective quality of smartphone anterior segment photography: a non-inferiority study

PURPOSE

To assess the subjective quality of anterior segment photos taken from a smartphone camera adapted to the slit lamp compared to a commercial inbuilt slit-lamp camera.

METHODS

Non-inferiority study. Five paired images of the anterior segment of normal eyes were taken using an iPhone 11 (Apple, Inc., Calif., USA) camera attached to a universal slit-lamp adaptor and a commercial inbuilt slit-lamp camera (Haag-Streit Diagnostics, Bern, Switzerland). Images were collated into a survey in which ophthalmology students, residents, registrars, and consultants participated to select the image taken from the inbuilt slit-lamp camera. If the image quality was subjectively indistinguishable, we expected a 50:50 split for each photograph that was presented. We selected a 10% non-inferiority margin, with the hypothesis that no less than 40% of images believed to be from the conventional camera were in fact from the smartphone camera.

RESULTS

There were 27 respondents in the survey: ophthalmology consultants (n = 7), registrars (n = 10), residents (n = 7), intern (n = 1) and students (n = 2). The mean correct identification across the respondents was 11.3 out of 25 (45.2%) images. Overall, the smartphone camera was non-inferior to the inbuilt slit-lamp camera (p < 0.001). The non-inferiority of the smartphone camera was significant for consultants (47.4%, p < 0.01), registrars (47.6%, p < 0.001) and residents (37.7%, p < 0.0001).

CONCLUSIONS

Anterior segment images obtained with a smartphone camera were non-inferior to the commercial inbuilt slit-lamp camera. Smartphone cameras may be a non-inferior tool for communication of anterior segment images having implications for the ease of access to quality telehealth consultations.

Ophthalmic Trauma Malpractice in the Ophthalmic Mutual Insurance Company Database

PURPOSE

To review ophthalmic trauma malpractice claims in the Ophthalmic Mutual Insurance Company (OMIC) database to determine the frequency and causes of litigation.

METHODS

A retrospective case series analysis of ophthalmic trauma claims from 2009 to 2019 was completed. Cases were selected only if the injury was secondary to trauma (e.g., fall, gunshot wound, paintball injury, etc.); iatrogenic traumatic surgical injuries were excluded.

RESULTS

31 closed cases associated with 40 total claims related to ophthalmic trauma out of 2565 claims (1.56%) in the OMIC database were analysed. 13 of the 31 cases (41.9%) were decided for the plaintiff. In decisions for the plaintiff, the median settlement amount was $330,000 (range $125,000-$1,000,000). The most frequent initial diagnoses were corneal abrasion (n = 10), hyphema (n = 5) and open-globe injury (n = 5), and the most common final diagnoses were endophthalmitis (n = 8), intraocular foreign body (n = 7) and retinal detachment (n = 7). The most common causes of malpractice litigation were a delay in referral or follow-up (n = 11) and failure to get appropriate imaging (n = 8). In the 13 cases decided for the plaintiff, experts concluded nine did not meet standard of care.

CONCLUSIONS

Ophthalmic trauma malpractice claims are very uncommon in the United States, however, the payout is higher than non-trauma settlements, and approximately 40% of cases were decided for the plaintiff. Care could be improved with a careful history and complete ophthalmic examination (with dilated fundoscopy), imaging in appropriate patients, meticulous documentation, and early sub-specialist referral when the diagnosis or management plan was unclear.

A Systematic Analysis of the Impact of an Ambulatory Ophthalmology Urgent Care Clinic

Importance A same-day ophthalmic urgent care clinic can provide efficient eye care, a rich educational environment, and can improve patient experience.

Objective The aim of this study was to systematically evaluate volume, financial impact, care metrics, and the breadth of pathology of urgent new patient encounters based on their site of initial presentation.

Design, Setting, and Participants A retrospective analysis was performed on consecutive urgent new patient evaluations in our same-day triage clinic at the Henkind Eye Institute at Montefiore Medical Center between February 2019 and January 2020. The cohort of patients who presented directly to this urgent care clinic were referred to as the “TRIAGE” group. Patients who initially presented to an emergency department (ED), and were subsequently referred to our triage clinic, are referred to as the “ED + TRIAGE” group.

Main Outcomes and Measures Visits were evaluated on a variety of metrics, including diagnosis, duration, charge, cost, and revenue. Furthermore, return to the ED or inpatient admission was documented.

Results Of 3,482 visits analyzed, 2,538 (72.9%) were in the “TRIAGE” group. Common presenting diagnoses were ocular surface disease (n = 486, 19.1%), trauma (n = 342, 13.5%; most commonly surface abrasion n = 195, 7.7%), and infectious conjunctivitis (n = 304, 12.0%). Patients in the “TRIAGE” group, on average, were seen 184.6% faster (158.2 vs. 450.2 minutes) than patients in the “ED + TRIAGE” group (p < 0.001). The “ED + TRIAGE” group were furthermore found to generate 442.1% higher charges ($870.20 vs. 4717.70) and were associated with 175.1% higher cost ($908.80 vs. 330.40) per patient. The hospital was found to save money when noncommercially insured patients with ophthalmic complaints presented to the triage clinic instead of the ED. Patients seen in the triage clinic had a low rate of readmission to the ED (n = 42, 1.2%).

Conclusions and Relevance A same-day ophthalmology triage clinic provides efficient care, while providing a rich learning environment for residents. Less wait time with direct access to subspecialist care can help improve quality, outcome, and satisfaction metrics.

Parent-provided photographs as an outcome measure for childhood chalazia

PURPOSE

To determine whether smartphone photographs of children's eyelids are reliable for diagnosing the presence of chalazia.

METHODS

In this prospective cross-sectional study, 60 participants, 7 months to 16.5 years of age, at four sites were enrolled; all participants had a chalazion measuring at least 2 mm on at least one eyelid based on an in-person clinical examination by a pediatric eye care professional. Smartphone photographs taken by the parent during the office visit were uploaded to the study website. A masked reader assessed each photograph for the presence or absence of chalazia; results were compared with the gold standard clinical examination results. Sensitivity and specificity for the presence of chalazion by eyelid were calculated.

RESULTS

Photographs were available for 240 eyelids; 85 had at least one chalazion and 155 were without a chalazion based on clinical examination. The masked reader correctly classified 68 of 85 eyelids with at least one chalazion and 151 of 155 eyelids without chalazia for a sensitivity of 80% (95% CI, 72%-86%) and a specificity of 97% (95% CI, 94%-99%). Sensitivity improved to 89% for chalazia 5 mm or larger and 94% when superficially located within the eyelid.

CONCLUSIONS

Parental smartphone photographs appear to be useful in assessing chalazia in children as an alternative to in-office follow-up examinations. These photographs may be a valuable outcome measure in future clinical trials of chalazia treatment, especially when assessing larger lesions.

Teleophthalmology and Artificial Intelligence As Game Changers in Ophthalmic Care After the COVID-19 Pandemic

The current COVID-19 pandemic has boosted a sudden demand for telemedicine due to quarantine and travel restrictions. The exponential increase in the use of telemedicine is expected to affect ophthalmology drastically. The aim of this review is to discuss the utility, effectiveness and challenges of teleophthalmological new tools for eyecare delivery as well as its implementation and possible facilitation with artificial intelligence. We used the terms: “teleophthalmology,” “telemedicine and COVID-19,” “retinal diseases and telemedicine,” “virtual ophthalmology,” “cost effectiveness of teleophthalmology,” “pediatric teleophthalmology,” “Artificial intelligence and ophthalmology,” “Glaucoma and teleophthalmology” and “teleophthalmology limitations” in the database of PubMed and selected the articles being published in the course of 2015-2020. After the initial search, 321 articles returned as relevant. A meticulous screening followed and eventually 103 published manuscripts were included and used as our references. Emerging in the market, teleophthalmology is showing great potential for the future of ophthalmological care, benefiting both patients and ophthalmologists in times of pandemics. The spectrum of eye diseases that could benefit from teleophthalmology is wide, including mostly retinal diseases such as diabetic retinopathy, retinopathy of prematurity, age-related macular degeneration but also glaucoma and anterior segment conditions. Simultaneously, artificial intelligence provides ways of implementing teleophthalmology easier and with better outcomes, contributing as significant changing factors for ophthalmology practice after the COVID-19 pandemic.

A Review of Ophthalmic Telemedicine for Emergency Department Settings

BACKGROUND

Patients presenting to emergency departments for ophthalmic emergencies benefit from prompt evaluation. However, Few emergency departments (EDs) have ophthalmologists on call, and eye care provided in EDs without ophthalmic services can be inaccurate.

METHODS

We review the current state of ophthalmic telemedical care in EDs and highlight important considerations when implementing telemedicine in this setting.

RESULTS

Telemedicine allows ophthalmologists to work with on-site emergency care providers to interview and examine patients remotely in EDs, enabling proper assessment of patient history, visual acuity, pupils, intraocular pressure, as well as the anterior and posterior segment. To date, patients' perceptions of this new model of care have been largely positive.

DISCUSSION

The use of telemedical consultations for remote evaluation of patients with ophthalmic complaints stands to improve the quality of care provided to patients and extend the reach of remote ophthalmologists. The onset of the COVID-19 pandemic and the risk of in-person care further highlights the potential for telemedicine to augment existing models of emergency care.