RESUMEN
OBJECTIVES: Evaluate and compare the ability of large language models (LLMs) to diagnose various ailments in otolaryngology. METHODS: We collected all 100 clinical vignettes from the second edition of Otolaryngology Cases-The University of Cincinnati Clinical Portfolio by Pensak et al. With the addition of the prompt "Provide a diagnosis given the following history," we prompted ChatGPT-3.5, Google Bard, and Bing-GPT4 to provide a diagnosis for each vignette. These diagnoses were compared to the portfolio for accuracy and recorded. All queries were run in June 2023. RESULTS: ChatGPT-3.5 was the most accurate model (89% success rate), followed by Google Bard (82%) and Bing GPT (74%). A chi-squared test revealed a significant difference between the three LLMs in providing correct diagnoses (p = 0.023). Of the 100 vignettes, seven require additional testing results (i.e., biopsy, non-contrast CT) for accurate clinical diagnosis. When omitting these vignettes, the revised success rates were 95.7% for ChatGPT-3.5, 88.17% for Google Bard, and 78.72% for Bing-GPT4 (p = 0.002). CONCLUSIONS: ChatGPT-3.5 offers the most accurate diagnoses when given established clinical vignettes as compared to Google Bard and Bing-GPT4. LLMs may accurately offer assessments for common otolaryngology conditions but currently require detailed prompt information and critical supervision from clinicians. There is vast potential in the clinical applicability of LLMs; however, practitioners should be wary of possible "hallucinations" and misinformation in responses. LEVEL OF EVIDENCE: 3 Laryngoscope, 2024.
RESUMEN
INTRODUCTION: The purpose of this study was to assess trends in consumer-product-related geriatric ocular injuries using National Electronic Injury Surveillance System (NEISS) data. Understanding the specific consumer products and settings coded in the NEISS dictionary that contribute to geriatric (≥ 65 years) ocular injuries, along with changing patterns during events like the COVID-19 pandemic, provides crucial insights for tailoring therapy and preventative strategies. This ultimately may reduce the burden of eye injuries on both older adults and healthcare systems. METHODS: This was a retrospective population-based cohort study. The NEISS database was used to study eye injuries in geriatric adults from 2010 to 2021. Patients were categorized by age groups (65-74, 75-84, 85-94, ≥ 95 years), and data on demographics, injury types, product categories, and COVID-19 impact were collected. Pearson's chi-squared test (with p < 0.001 taken to indicate significance) was used to assess differences in expected ratios between age groups. RESULTS: A total of 168,685 eye injury cases in adults aged 65 years and older were analyzed. Household items, tools, and gardening products accounted for over 75% of injuries. Most injuries occurred at home (65.3%). Contusions/abrasions (40.3%) and a foreign body (19.3%) were common diagnoses. Females had more household-item-related injuries, while males had more foreign body injuries. Regarding therapeutic disposition, 93.7% of all injuries were treated/examined and released, which showed a decreasing trend as age increased, while hospital admission/transfer rates increased with age. Compared to before COVID-19, the percentage of injuries during COVID-19 due to tools decreased (from 22.5% to 18.3%), while injuries due to gardening/lawn/landscaping/patio products increased (from 13.8% to 15.3%). CONCLUSIONS: Our study characterizes geriatric ocular injuries and COVID-19 impact, highlighting common products and locations. Different age groups showed different injury patterns. Understanding these trends can aid injury prevention strategies for consumers and healthcare providers. Demographics and injury frequencies differed based on age and sex. Future research should further explore post-COVID-19 trends.
RESUMEN
PURPOSE: To develop a neural network for the estimation of visual acuity from optical coherence tomography (OCT) images of patients with neovascular age-related macular degeneration (AMD) and to demonstrate its use to model the impact of specific controlled OCT changes on vision. DESIGN: Artificial intelligence (neural network) study. METHODS: We assessed 1400 OCT scans of patients with neovascular AMD. Fifteen physical features for each eligible OCT, as well as patient age, were used as input data and corresponding recorded visual acuity as the target data to train, validate, and test a supervised neural network. We then applied this network to model the impact on acuity of defined OCT changes in subretinal fluid, subretinal hyperreflective material, and loss of external limiting membrane (ELM) integrity. RESULTS: A total of 1210 eligible OCT scans were analyzed, resulting in 1210 data points, which were each 16-dimensional. A 10-layer feed-forward neural network with 1 hidden layer of 10 neurons was trained to predict acuity and demonstrated a root mean square error of 8.2 letters for predicted compared to actual visual acuity and a mean regression coefficient of 0.85. A virtual model using this network demonstrated the relationship of visual acuity to specific, programmed changes in OCT characteristics. When ELM is intact, there is a shallow decline in acuity with increasing subretinal fluid but a much steeper decline with equivalent increasing subretinal hyperreflective material. When ELM is not intact, all visual acuities are reduced. Increasing subretinal hyperreflective material or subretinal fluid in this circumstance reduces vision further still, but with a smaller gradient than when ELM is intact. CONCLUSIONS: The supervised machine learning neural network developed is able to generate an estimated visual acuity value from OCT images in a population of patients with AMD. These findings should be of clinical and research interest in macular degeneration, for example in estimating visual prognosis or highlighting the importance of developing treatments targeting more visually destructive pathologies.
