ChatGPT and retinal disease: a cross-sectional study on AI comprehension of clinical guidelines.

OBJECTIVE: To evaluate the performance of an artificial intelligence (AI) large language model, ChatGPT (version 4.0), for common retinal diseases, in accordance with the American Academy of Ophthalmology (AAO) Preferred Practice Pattern (PPP) guidelines. DESIGN: A cross-sectional survey study design was employed to compare the responses made by ChatGPT to established clinical guidelines. PARTICIPANTS: Responses by the AI were reviewed by a panel of three vitreoretinal specialists for evaluation. METHODS: To investigate ChatGPT's comprehension of clinical guidelines, we designed 130 questions covering a broad spectrum of topics within 12 AAO PPP domains of retinal disease These questions were crafted to encompass diagnostic criteria, treatment guidelines, and management strategies, including both medical and surgical aspects of retinal care. A panel of 3 retinal specialists independently evaluated responses on a Likert scale from 1 to 5 based on their relevance, accuracy, and adherence to AAO PPP guidelines. Response readability was evaluated using Flesch Readability Ease and Flesch-Kincaid grade level scores. RESULTS: ChatGPT achieved an overall average score of 4.9/5.0, suggesting high alignment with the AAO PPP guidelines. Scores varied across domains, with the lowest in the surgical management of disease. The responses had a low reading ease score and required a college-to-graduate level of comprehension. Identified errors were related to diagnostic criteria, treatment options, and methodological procedures. CONCLUSION: ChatGPT 4.0 demonstrated significant potential in generating guideline-concordant responses, particularly for common medical retinal diseases. However, its performance slightly decreased in surgical retina, highlighting the ongoing need for clinician input, further model refinement, and improved comprehensibility.

Gender, Race, and Ethnicity of US Academic Ophthalmology Faculty and Department Chairs From 1966 to 2021.

Importance: Workforce diversity is integral to optimal function within health care teams. Objective: To analyze gender, race, and ethnicity trends in rank and leadership among US full-time academic ophthalmology faculty and department chairs between 1966 and 2021. Design, Setting, and Participants: This cohort study included full-time US academic ophthalmology faculty and department chairs registered in the Association of American Medical Colleges. Study data were analyzed in September 2023. Exposure: Identifying with an underrepresented in medicine (URiM) group. Main Outcomes and Measures: The main outcome measures were demographic (ie, gender, race, and ethnicity) changes among academic faculty and department chairs, assessed in 5-year intervals. The term minoritized race refers to any racial group other than White race. Results: There were 221 academic physicians in 1966 (27 women [12.2%]; 38 minoritized race [17.2%]; 8 Hispanic, Latino, or Spanish [3.6%]) and 3158 academic faculty by 2021 (1320 women [41.8%]; 1298 minoritized race [41.1%]; 147 Hispanic, Latino, or Spanish ethnicity [4.7%]). The annual proportional change for women, minoritized race, and Hispanic, Latino, or Spanish ethnicity was +0.63% per year (95% CI, 0.53%-0.72%), +0.54% per year (95% CI, 0.72%-0.36%), and -0.01% (95% CI, -0.03% to 0%), respectively. Women were underrepresented across academic ranks and increasingly so at higher echelons, ranging from nonprofessor/instructor roles (period-averaged mean difference [PA-MD], 19.88%; 95% CI, 16.82%-22.94%) to professor (PA-MD, 81.33%; 95% CI, 78.80%-83.86%). The corpus of department chairs grew from 77 in 1977 (0 women; 7 minoritized race [9.09%]; 2 Hispanic, Latino, or Spanish ethnicity [2.60%]) to 104 by 2021 (17 women [16.35%]; 22 minoritized race [21.15%]; 4 Hispanic, Latino, or Spanish ethnicity [3.85%]). For department chairs, the annual rate of change in the proportion of women, minoritized race, and Hispanic, Latino, or Spanish ethnicity was +0.32% per year (95% CI, 0.20%-0.44%), +0.34% per year (95% CI, 0.19%-0.49%), and +0.05% per year (95% CI, 0.02%-0.08%), respectively. In both faculty and department chairs, the proportion of URiM groups (American Indian or Alaska Native, Black or African American, Hispanic, and Native Hawaiian or Other Pacific Islander) grew the least. Intersectionality analysis suggested that men and non-URiM status were associated with greater representation across ophthalmology faculty and department chairs. However, among ophthalmology faculty, URiM women and men did not significantly differ across strata of academic ranks, whereas for department chairs, no difference was observed in representation between URiM men and non-URiM women. Conclusion & Relevance: Results of this cohort study revealed that since 1966, workforce diversity progressed slowly and was limited to lower academic ranks and leadership positions. Intersectionality of URiM status and gender persisted in representation trends. These findings suggest further advocacy and intervention are needed to increase workforce diversity.

Gender inclusivity of ophthalmology journal submission guidelines and associated research metrics.

PURPOSE: This cross-sectional study evaluated the prevalence of inclusive author submission guidelines across ophthalmology journals. METHODS: Journals were identified from the 2021 Journal Citations Report (Clarivate Analytics). Independent reviewers rated each author submission guideline as "inclusive" for satisfying at-least one of six criteria: i) included examples of gender inclusive language; ii) recommended the use of gender-inclusive language; iii) distinguished between sex and gender; iv) provided educational resources on gender-inclusive language; v) provided a policy permitting name changes (e.g., in case of gender and name transition); and/or vi) provided a statement of commitment to inclusivity. The primary objective was to investigate the proportion of journals with "gender-inclusive" author submission guidelines and the elements of the gender-inclusive content within these guidelines. A secondary objective was to review the association between "gender-inclusivity" in author submission guidelines with publisher, origin country, and journal/source/influence metrics (Clarivate Analytics). RESULTS: Across 94 journals, 29.8% journals were rated as inclusive. Inclusive journals had significantly higher relative impact factor, citations, and article influence scores compared to non-inclusive journals. Of the 29.8% of inclusive journals, the three most common domains were inclusion of an inclusivity statement (71.4% of inclusive journals), distinguishing between sex and gender (67.9%), and provision of additional educational resources on gender reporting for authors (60.7%). CONCLUSION: A minority of ophthalmology journals have gender-inclusive author submission guidelines. Ophthalmology journals should update their submission guidelines to advance gender equity of both authors and study participants and promote the inclusion of gender-diverse communities.

Incidence of Sympathetic Ophthalmia after Intraocular Surgery: A Systematic Review and Meta-analysis.

TOPIC: Sympathetic ophthalmia (SO) is a rare bilateral granulomatous panuveitis that can present after trauma or intraocular surgery (IOS). The incidence of SO after IOS varies among studies. The purpose of this review was to determine the incidence proportion of SO after IOS. CLINICAL RELEVANCE: The incidence proportion of SO after IOS can provide physicians and patients with information on the risk of SO during the consent process before surgery. METHODS: In this systematic review and meta-analysis, MEDLINE, EMBASE, and Cochrane databases were searched from inception to January 1, 2023 for population-based studies of SO after IOS. Two reviewers independently screened the results. Random-effects meta-analyses calculated incidence proportion. Subgroup analysis assessed SO incidence based on IOS type and technological advancements. Study quality and bias were assessed using the Newcastle-Ottawa scale and the Grades of Recommendation, Assessment, Development, and Evaluation framework. RESULTS: The final meta-analyses included 19 studies, with 118 cases of SO occurring after 505 178 inciting events. The estimated overall incidence proportion of SO after IOS was 0.061% (95% confidence interval [CI], 0.033%-0.111%; I2 = 83%), and the estimated incidence rate was 9.24 cases per 100 000 person-years (95% CI, 4.03-21.19; I2 = 88%). The average study duration across these studies was 10.8 years. Within the reviewed literature, SO after glaucoma and vitreoretinal IOS was studied most, with 9 and 6 studies, respectively. Observed differences in incidence between glaucoma (0.098%; 95% CI, 0.042%-0.232%; I2 = 40%) and vitreoretinal (0.043%; 95% CI, 0.022%-0.085%; I2 = 88%) IOS were not statistically significant (P = 0.14). Also, no significant difference was found in the incidence proportion before and after 1975, when modern intraocular surgical techniques emerged (0.060% vs. 0.058%; P = 0.98). The outcome measures showed low-certainty Grades of Recommendation, Assessment, Development, and Evaluation evidence. DISCUSSION: Sympathetic ophthalmia after IOS is rare and might not have changed over the past 5 decades. The estimated incidence proportion of SO may be useful during the consent process before surgery. Also, no significant difference may exist in the incidence of SO between glaucoma and vitreoretinal IOS, based on low-certainty evidence. FINANCIAL DISCLOSURE(S): The author(s) have no proprietary or commercial interest in any materials discussed in this article.

Exploring the potential utility of AI large language models for medical ethics: an expert panel evaluation of GPT-4.

Integrating large language models (LLMs) like GPT-4 into medical ethics is a novel concept, and understanding the effectiveness of these models in aiding ethicists with decision-making can have significant implications for the healthcare sector. Thus, the objective of this study was to evaluate the performance of GPT-4 in responding to complex medical ethical vignettes and to gauge its utility and limitations for aiding medical ethicists. Using a mixed-methods, cross-sectional survey approach, a panel of six ethicists assessed LLM-generated responses to eight ethical vignettes.The main outcomes measured were relevance, reasoning, depth, technical and non-technical clarity, as well as acceptability of GPT-4's responses. The readability of the responses was also assessed. Of the six metrics evaluating the effectiveness of GPT-4's responses, the overall mean score was 4.1/5. GPT-4 was rated highest in providing technical (4.7/5) and non-technical clarity (4.4/5), whereas the lowest rated metrics were depth (3.8/5) and acceptability (3.8/5). There was poor-to-moderate inter-rater reliability characterised by an intraclass coefficient of 0.54 (95% CI: 0.30 to 0.71). Based on panellist feedback, GPT-4 was able to identify and articulate key ethical issues but struggled to appreciate the nuanced aspects of ethical dilemmas and misapplied certain moral principles.This study reveals limitations in the ability of GPT-4 to appreciate the depth and nuanced acceptability of real-world ethical dilemmas, particularly those that require a thorough understanding of relational complexities and context-specific values. Ongoing evaluation of LLM capabilities within medical ethics remains paramount, and further refinement is needed before it can be used effectively in clinical settings.

Evaluating ChatGPT on Orbital and Oculofacial Disorders: Accuracy and Readability Insights.

PURPOSE: To assess the accuracy and readability of responses generated by the artificial intelligence model, ChatGPT (version 4.0), to questions related to 10 essential domains of orbital and oculofacial disease. METHODS: A set of 100 questions related to the diagnosis, treatment, and interpretation of orbital and oculofacial diseases was posed to ChatGPT 4.0. Responses were evaluated by a panel of 7 experts based on appropriateness and accuracy, with performance scores measured on a 7-item Likert scale. Inter-rater reliability was determined via the intraclass correlation coefficient. RESULTS: The artificial intelligence model demonstrated accurate and consistent performance across all 10 domains of orbital and oculofacial disease, with an average appropriateness score of 5.3/6.0 ("mostly appropriate" to "completely appropriate"). Domains of cavernous sinus fistula, retrobulbar hemorrhage, and blepharospasm had the highest domain scores (average scores of 5.5 to 5.6), while the proptosis domain had the lowest (average score of 5.0/6.0). The intraclass correlation coefficient was 0.64 (95% CI: 0.52 to 0.74), reflecting moderate inter-rater reliability. The responses exhibited a high reading-level complexity, representing the comprehension levels of a college or graduate education. CONCLUSIONS: This study demonstrates the potential of ChatGPT 4.0 to provide accurate information in the field of ophthalmology, specifically orbital and oculofacial disease. However, challenges remain in ensuring accurate and comprehensive responses across all disease domains. Future improvements should focus on refining the model's correctness and eventually expanding the scope to visual data interpretation. Our results highlight the vast potential for artificial intelligence in educational and clinical ophthalmology contexts.

Gender Representation on North American Ophthalmology Societies' Governance Boards.

Purpose We examined the gender distribution and academic productivity of North American ophthalmology societies' board members. Methods Cross-sectional and retrospective study of board members on American and Canadian ophthalmology societies. In December 2022, data was gathered from society webpages, online archives, and the Scopus database for publication information. Results Of the identified 73 board presidents and 876 other board members, 49 (67.1%) board presidents were men and 24 (32.9%) were women, while 554 (63.2%) other board members were men and 322 (36.8%) were women ( p = 0.53). Overall, board members who were men had significantly higher median h-indexes (men vs. women: 10 [interquartile range [IQR] = 22] vs. 7 [IQR = 12], p = 0.03) and median publication numbers (men vs. women: 23 [IQR = 84] vs. 14 [IQR = 52.3], p = 0.01). However, m-quotients (h-index divided by length of academic career) were not significantly different (men vs. women: 0.46 [IQR = 0.74] vs. 0.50 [IQR = 0.55], p = 0.67). Overall, a significant increase in the proportion of women board presidents comparing periods 1942 to 1961 and 2002 to 2021 was observed for all societies combined (3.1% [2/65] to 23.6% [210/888], p < 0.001). Conclusion The fraction of women on the academic boards in North American ophthalmology societies has increased sevenfold over the past 83 years. The gender composition of ophthalmology society boards is consistent with the gender composition of practicing ophthalmologists in the United States. Women in board or society positions have comparable academic output to men. Existing and new efforts to sustain progress in promoting women's representation and leadership opportunities must continue.

Chatbots, generative AI, and scholarly manuscripts: WAME recommendations on chatbots and generative artificial intelligence in relation to scholarly publications.

This statement revises our earlier "WAME Recommendations on ChatGPT and Chatbots in Relation to Scholarly Publications" (January 20, 2023). The revision reflects the proliferation of chatbots and their expanding use in scholarly publishing over the last few months, as well as emerging concerns regarding lack of authenticity of content when using chatbots. These recommendations are intended to inform editors and help them develop policies for the use of chatbots in papers published in their journals. They aim to help authors and reviewers understand how best to attribute the use of chatbots in their work and to address the need for all journal editors to have access to manuscript screening tools. In this rapidly evolving field, we will continue to modify these recommendations as the software and its applications develop.

Esta declaración revisa las anteriores "Recomendaciones de WAME sobre ChatGPT y Chatbots en Relation to Scholarly Publications" (20 de enero de 2023). La revisión refleja la proliferación de chatbots y su creciente uso en las publicaciones académicas en los últimos meses, así como la preocupación por la falta de autenticidad de los contenidos cuando se utilizan chatbots. Estas recomendaciones pretenden informar a los editores y ayudarles a desarrollar políticas para el uso de chatbots en los artículos sometidos en sus revistas. Su objetivo es ayudar a autores y revisores a entender cuál es la mejor manera de atribuir el uso de chatbots en su trabajo y a la necesidad de que todos los editores de revistas tengan acceso a herramientas de selección de manuscritos. En este campo en rápida evolución, seguiremos modificando estas recomendaciones a medida que se desarrollen el software y sus aplicaciones.

Chatbots, generative AI, and scholarly manuscripts: WAME recommendations on chatbots and generative artificial intelligence in relation to scholarly publications

This statement revises our earlier "WAME Recommendations on ChatGPT and Chatbots in Relation to Scholarly Publications" (January 20, 2023). The revision reflects the proliferation of chatbots and their expanding use in scholarly publishing over the last few months, as well as emerging concerns regarding lack of authenticity of content when using chatbots. These recommendations are intended to inform editors and help them develop policies for the use of chatbots in papers published in their journals. They aim to help authors and reviewers understand how best to attribute the use of chatbots in their work and to address the need for all journal editors to have access to manuscript screening tools. In this rapidly evolving field, we will continue to modify these recommendations as the software and its applications develop.

Esta declaración revisa las anteriores "Recomendaciones de WAME sobre ChatGPT y Chatbots en Relation to Scholarly Publications" (20 de enero de 2023). La revisión refleja la proliferación de chatbots y su creciente uso en las publicaciones académicas en los últimos meses, así como la preocupación por la falta de autenticidad de los contenidos cuando se utilizan chatbots. Estas recomendaciones pretenden informar a los editores y ayudarles a desarrollar políticas para el uso de chatbots en los artículos sometidos en sus revistas. Su objetivo es ayudar a autores y revisores a entender cuál es la mejor manera de atribuir el uso de chatbots en su trabajo y a la necesidad de que todos los editores de revistas tengan acceso a herramientas de selección de manuscritos. En este campo en rápida evolución, seguiremos modificando estas recomendaciones a medida que se desarrollen el software y sus aplicaciones.

The Isabel Differential Diagnosis Generator for Orbital Diagnosis.

PURPOSE: The Isabel differential diagnosis generator is one of the most widely known electronic diagnosis decision support tools. The authors prospectively evaluated the utility of Isabel for orbital disease differential diagnosis. METHODS: The terms "proptosis," "lid retraction," "orbit inflammation," "orbit tumour," "orbit tumor, infiltrative" and "orbital tumor, well-circumscribed" were separately input into Isabel and the results were tabulated. Then the clinical details (patient age, gender, signs, symptoms, and imaging findings) of 25 orbital cases from a textbook of orbital surgery were entered into Isabel. The top 10 differential diagnoses generated by Isabel were compared with the correct diagnosis. RESULTS: Isabel identified hyperthyroidism and Graves ophthalmopathy as the leading causes of lid retraction, but many common causes of proptosis and orbital tumors were not correctly elucidated. Of the textbook cases, Isabel correctly identified 4/25 (16%) of orbital cases as one of its top 10 differential diagnoses, and the median rank of the correct diagnosis was 6/10. Thirty-two percent of the output diagnoses were unlikely to cause orbital disease. CONCLUSION: Isabel is currently of limited value in the mainstream orbital differential diagnosis. The incorporation of anatomic localizations and imaging findings may help increase the accuracy of orbital diagnosis.

A technique for excisional optic nerve biopsy.

PURPOSE: To describe a transconjunctival technique for full-thickness (excisional) optic nerve biopsy. METHOD: A medial transconjunctival approach to the optic nerve with disinsertion of the medial rectus is used. A small right-angle Mixter forcep is used to clamp the optic nerve far posteriorly, and then a microscalpel is directed metal-on-metal to cut the posterior optic nerve. The cut nerve is then rotated anteriorly to complete the proximal nerve cut. RESULT: A full-thickness specimen of 11 mm of more can be obtained without undue traction on the globe. The globe remains viable. CONCLUSION: A long length, excisional optic nerve biopsy can be readily and safely performed without endoscopic techniques.