ABSTRACT
Background Gap years following medical school graduation have become more common, but research into their tangible career benefit is lacking. Examining the impact of gap years on resident scholarly productivity in ophthalmology may provide insight generalizable to all specialties. Objective To evaluate whether a gap year following medical school graduation significantly predicts scholarly productivity during ophthalmology residency. Methods In December 2021, residents were recorded from 110 publicly available American ophthalmology residency program webpages. They were included if educational history was listed on publicly accessible academic and social media profiles. Residents were then stratified into gap year and nongap year cohorts. Publication data were recorded from Scopus and PubMed. Pearson's chi-square, independent sample t -tests, and multivariable regression were performed. Results A total of 1,206 residents were analyzed, with 1,036 (85.9%) residents taking no gap year and 170 (14.1%) residents with at least one gap year. Gap year residents were predicted to have increase in the likelihoods of publishing at least one, two, or five total articles during residency, in addition to at least one article in a high-impact journal. There was no significant relationship between gap years and publications with senior authors affiliated with either the resident's medical school or residency program. Conclusion Residents taking gap years following graduation may publish more during residency, but these publications are not associated with senior authors at their institutions. Future investigations should continue to evaluate the significance of gap years in medical education.
ABSTRACT
INTRODUCTION: Age-related macular degeneration, diabetic retinopathy, and glaucoma are vision-threatening diseases that are leading causes of vision loss. Many studies have validated deep learning artificial intelligence for image-based diagnosis of vision-threatening diseases. Our study prospectively investigated deep learning artificial intelligence applications in student-run non-mydriatic screenings for an underserved, primarily Hispanic community during COVID-19. METHODS: Five supervised student-run community screenings were held in West New York, New Jersey. Participants underwent non-mydriatic 45-degree retinal imaging by medical students. Images were uploaded to a cloud-based deep learning artificial intelligence for vision-threatening disease referral. An on-site tele-ophthalmology grader and remote clinical ophthalmologist graded images, with adjudication by a senior ophthalmologist to establish the gold standard diagnosis, which was used to assess the performance of deep learning artificial intelligence. RESULTS: A total of 385 eyes from 195 screening participants were included (mean age 52.43 ± 14.5 years, 40.0% female). A total of 48 participants were referred for at least one vision-threatening disease. Deep learning artificial intelligence marked 150/385 (38.9%) eyes as ungradable, compared to 10/385 (2.6%) ungradable as per the human gold standard (p < 0.001). Deep learning artificial intelligence had 63.2% sensitivity, 94.5% specificity, 32.0% positive predictive value, and 98.4% negative predictive value in vision-threatening disease referrals. Deep learning artificial intelligence successfully referred all 4 eyes with multiple vision-threatening diseases. Deep learning artificial intelligence graded images (35.6 ± 13.3â s) faster than the tele-ophthalmology grader (129 ± 41.0) and clinical ophthalmologist (68 ± 21.9, p < 0.001). DISCUSSION: Deep learning artificial intelligence can increase the efficiency and accessibility of vision-threatening disease screenings, particularly in underserved communities. Deep learning artificial intelligence should be adaptable to different environments. Consideration should be given to how deep learning artificial intelligence can best be utilized in a real-world application, whether in computer-aided or autonomous diagnosis.
