Large language models such as ChatGPT have demonstrated significant potential in question-answering within ophthalmology, but there is a paucity of literature evaluating its ability to generate clinical assessments and discussions. The objectives of this study were to (1) assess the accuracy of assessment and plans generated by ChatGPT and (2) evaluate ophthalmologists’ abilities to distinguish between responses generated by clinicians versus ChatGPT. Cross-sectional mixed-methods study. Sixteen ophthalmologists from a single academic center, of which 10 were board-eligible and 6 were board-certified, were recruited to participate in this study. Prompt engineering was used to ensure ChatGPT output discussions in the style of the ophthalmologist author of the Medical College of Wisconsin Ophthalmic Case Studies. Cases where ChatGPT accurately identified the primary diagnoses were included and then paired. Masked human-generated and ChatGPT-generated discussions were sent to participating ophthalmologists to identify the author of the discussions. Response confidence was assessed using a 5-point Likert scale score, and subjective feedback was manually reviewed. Accuracy of ophthalmologist identification of discussion author, as well as subjective perceptions of human-generated versus ChatGPT-generated discussions. Overall, ChatGPT correctly identified the primary diagnosis in 15 of 17 (88.2%) cases. Two cases were excluded from the paired comparison due to hallucinations or fabrications of nonuser-provided data. Ophthalmologists correctly identified the author in 77.9% ± 26.6% of the 13 included cases, with a mean Likert scale confidence rating of 3.6 ± 1.0. No significant differences in performance or confidence were found between board-certified and board-eligible ophthalmologists. Subjectively, ophthalmologists found that discussions written by ChatGPT tended to have more generic responses, irrelevant information, hallucinated more frequently, and had distinct syntactic patterns (all P < 0.01). Large language models have the potential to synthesize clinical data and generate ophthalmic discussions. While these findings have exciting implications for artificial intelligence-assisted health care delivery, more rigorous real-world evaluation of these models is necessary before clinical deployment. The author(s) have no proprietary or commercial interest in any materials discussed in this article.
1 June 2015 in Journal of American Association for Pediatric Ophthalmology and Strabismus
Aim: To assess the impact of practice patterns amongst global ophthalmologists during severe acute respiratory syndrome Coronavirus 2 (SARS Cov2) causing Corona virus disease (COVID-19) and understand the various modifications made to address emergency surgeries and practice needs. Methods: An online survey was sent to practicing ophthalmologists around the world through email, Whatsapp™ ListServ17.0™ (for pediatric ophthalmologists), WeChat™ (China) and ophthalmology associations (Indonesia, Philippines, Ireland). All queries were collected and categorized. Responses to the queries were given according to the recommendations by the Ophthalmology association. Practices ability to deal with the COVID were also classified according to country and type of access to PPE. Statistical analyses of the association between these data and queries, where appropriate were carried out. Results: One thousand nine hundred sixteen ophthalmologists were invited to participate in a survey between April 10th and April 30th, 2020 of which 1207 responded, which is a response rate of approximately 63%. The majority of respondents were from India, Indonesia, China, Singapore and the USA. Our study indicates a precipitous drop in surgical procedures with 46% (n = 538) ophthalmologists ceased to operate on their patients and almost 40% (n = 486) were doing less than 25% of their original number of surgeries. The intent to resume elective surgeries was a consideration in 41% (n = 495) after an evaluation of the situation and in consultation with professional bodies. More than 2/3 of the respondents (n = 703) made it a priority to use and mandate their patients to practice physical distancing, wearing masks, and hand dis-infection for protection to limit the spread of infection. Conclusion: This global survey provides a real-world assessment of diverse practices that were in various forms of “shut down mode” and circumstances with varying capabilities to deal with COVID. It is unprecedented that the collective wisdom for a curtailment of practice has had an enormous immediate and far reaching implications on the livelihoods of ophthalmologists, their staff, and their families. Nevertheless, ophthalmologists and their staff remain resilient and have adapted to these changes pragmatically.
9 May 2024 in Journal of American Association for Pediatric Ophthalmology and Strabismus
To evaluate the effects of teprotumumab on individual extraocular muscle (EOM) volume and proptosis in thyroid eye disease (TED). A retrospective review was performed using exophthalmometry, clinical activity score (CAS), and orbital imaging before and after teprotumumab treatment. The lateral rectus (LR), medial rectus (MR), superior rectus (SR), inferior rectus (IR) muscles, and the globe were manually segmented individually. Individual and total EOM volumes were calculated and compared between pre- and post-treatment magnetic resonance imaging (MRI). Mean proptosis reduction after teprotumumab treatment was 3.69 mm (95% CI: 2.82, 4.17, p < 0.001), with an improvement in all orbits. Significant muscle volume reductions occurred in the MR (-20%, p < 0.001) and IR (-28%, p = 0.002) but not the LR (-11%, p = 0.063) or SR (-19%, p = 0.053). Total EOM volume decreased by 20%, while globe volume remained unchanged. CAS and proptosis improved post-treatment, but changes in total EOM volume did not significantly correlate with changes in CAS or proptosis. Pre-treatment IR, MR, and SR volumes showed moderate correlation with total EOM volume reduction. Teprotumumab significantly reduces EOM volumes, CAS, and proptosis in TED. Weak correlations with clinical outcomes suggest that additional factors, such as orbital fat, influence treatment response.