Machine Teaching Allows for Rapid Development of Automated Systems for Retinal Lesion Detection From Small Image Datasets.

Machine teaching, a machine learning subfield, may allow for rapid development of artificial intelligence systems able to automatically identify emerging ocular biomarkers from small imaging datasets. We sought to use machine teaching to automatically identify retinal ischemic perivascular lesions (RIPLs) and subretinal drusenoid deposits (SDDs), two emerging ocular biomarkers of cardiovascular disease. IRB approval was obtained. Four small datasets of SD-OCT B-scans were used to train and test two distinct automated systems, one identifying RIPLs and the other identifying SDDs. An open-source interactive machine-learning software program, RootPainter, was used to perform annotation and training simultaneously over a 6-hour period. For SDDs at the B-scan level, test-set accuracy = 92%, sensitivity = 100%, specificity = 88%, positive predictive value (PPV) = 82%, and negative predictive value (NPV) = 100%. For RIPLs at the B-scan level, test-set accuracy = 90%, sensitivity = 60%, specificity = 93%, PPV = 50%, and NPV = 95%. Machine teaching demonstrates promise within ophthalmic imaging to rapidly allow for automated identification of novel biomarkers from small image datasets. [Ophthalmic Surg Lasers Imaging Retina 2024;55:475-478.].

Exploring Diagnostic Precision and Triage Proficiency: A Comparative Study of GPT-4 and Bard in Addressing Common Ophthalmic Complaints.

In the modern era, patients often resort to the internet for answers to their health-related concerns, and clinics face challenges to providing timely response to patient concerns. This has led to a need to investigate the capabilities of AI chatbots for ophthalmic diagnosis and triage. In this in silico study, 80 simulated patient complaints in ophthalmology with varying urgency levels and clinical descriptors were entered into both ChatGPT and Bard in a systematic 3-step submission process asking chatbots to triage, diagnose, and evaluate urgency. Three ophthalmologists graded chatbot responses. Chatbots were significantly better at ophthalmic triage than diagnosis (90.0% appropriate triage vs. 48.8% correct leading diagnosis; p < 0.001), and GPT-4 performed better than Bard for appropriate triage recommendations (96.3% vs. 83.8%; p = 0.008), grader satisfaction for patient use (81.3% vs. 55.0%; p < 0.001), and lower potential harm rates (6.3% vs. 20.0%; p = 0.010). More descriptors improved the accuracy of diagnosis for both GPT-4 and Bard. These results indicate that chatbots may not need to recognize the correct diagnosis to provide appropriate ophthalmic triage, and there is a potential utility of these tools in aiding patients or triage staff; however, they are not a replacement for professional ophthalmic evaluation or advice.

Disease Awareness Among Patients With Age-Related Macular Degeneration: Patterns and Predictors.

Purpose: To examine the prevalence and predictors of patient awareness of their disease in adults with age-related macular degeneration (AMD). Methods: This study analyzed 5553 adults 40 years or older in the 2005-2008 National Health and Nutrition Examination Survey who underwent retinal imaging. AMD was determined based on retinal images. Patient awareness of their AMD was assessed by a self-reported AMD diagnosis. Multivariable logistic regression models were constructed to examine the association of patient awareness of their AMD with sociodemographic characteristics and specific AMD lesion types on retinal imaging. Results: AMD was identified in 425 of the adults surveyed (6.5%) (95% confidence interval [CI], 5.5%-7.5%), including 87.7% (95% CI, 82.9%-92.5%) with early AMD and 12.3% (95% CI, 7.5%-17.1%) with late AMD. Among adults with either type of AMD on retinal imaging, 17.5% (95% CI, 13.1%-22.0%) were aware of their disease, which included 11.6% (95% CI, 8.4%-14.9%) with early AMD and 59.2% (95% CI, 43.1%-75.3%) with late AMD (P < .0001). In the same group, those aged 60 years or older (odds ratio [OR], 33.46; 95% CI, 7.67-146.03) and with a best-corrected visual acuity of 20/40 or worse (OR, 4.63; 95% CI, 2.95-7.26) had higher awareness of their AMD diagnosis, whereas Hispanic (OR, 0.28; 95% CI, 0.09-0.88) vs White adults and those who did not speak English at home (OR, 0.05; 95% CI, 0.01-0.41) had lower awareness of their diagnosis. Conclusions: Fewer than 1 in 5 adults with AMD were aware of their personal diagnosis, including fewer than 3 in 5 adults with late AMD. Older adults and those with worse vision were more likely to know they have AMD, whereas Hispanic adults and those who did not speak English at home were less likely. Efforts to increase patients' awareness of their AMD may improve rates of follow-up and prevent vision loss.

Enhancing Mentorship Networks through the Experiences of Women Professors of Ophthalmology.

Purpose The aim of this study is to identify and characterize women professors in ophthalmology to enhance professional development and equity of women in academic ophthalmology. Design Cross-sectional descriptive survey study. Participants Participants in the survey were women in ophthalmology departments who have obtained full professor rank at their respective institutions. Methods A cross-sectional study was conducted using data from an electronic survey of women ophthalmologists and researchers who had obtained full professorship rank in ophthalmology. The survey included questions about degree obtained, training path, fellowship, length and trajectory of academic career, family or medical leave participation, previous positions, and mentorship involvement. Statistical comparisons were made based on response. Main Outcome Measures Survey responses to questions pertaining to three domains: education and training, academic career, and mentorship. Results Women that obtained the professor title within ophthalmology largely held Doctor of Medicine/Doctor of Osteopathic Medicine degrees, were more likely to have completed fellowship training, and on average took 11 to 15 years to obtain the full professor title. The participants held a variety of other positions and titles throughout their academic careers. The vast majority of women reported having between 1 and 3 mentors during their careers with the majority also noting they currently participate in mentoring programs. Surveys were completed by 62 (30% response rate) women full professors of ophthalmology. Conclusion The experiences women have along the academic path to professorship are described in this survey and can help to inform junior faculty. Literature review highlights the importance of mentorship for work productivity, retention, and promotion within academic medicine which is an element seen in the vast majority of our participants' career paths. Guided by the identification of women professors within departments of ophthalmology and characterization of their experiences, a new initiative called Women Professors of Ophthalmology was formed under the Association of University Professors of Ophthalmology's organizational structure in 2021. This group that is tailored for women professors of ophthalmology to foster peer mentorship and guidance is poised to increase the retention and promotion of women in academic ophthalmology.