Assessing the Utility of ChatGPT in Simplifying Text Complexity of Patient Educational Materials.

INTRODUCTION: AI chatbots are being increasingly used in healthcare settings. There is growing interest in using AI to assist in patient education. Currently, extensive healthcare information is found online but is often too complex to understand. Our objective is to determine if physicians can recommend the free version of ChatGPT version 3.5 (OpenAI, San Francisco, CA, USA) for patients to simplify text from the American Academy of Ophthalmology (AAO) in English and Spanish. This version of ChatGPT was assessed in this study due to its increased accessibility across various patient populations. METHODS: Fifteen articles were chosen from AAO in both languages and simplified with ChatGPT 10 times each. The readability of original and simplified articles was assessed with the Flesch Reading Ease and Gunning Fog Index for English and Fernández Huerta, Gutiérrez, Szigriszt-Pazo, INFLESZ, and Legibilidad-µ for Spanish. Grade levels to assess readability were calculated with Flesch Kincaid Grade Level and Crawford Nivel-de-Grado. Mean, standard deviation, and two-tailed t-tests were performed to assess differences before and after simplification. RESULTS: Average grade levels before and after simplification were as follows: English 8.43±1.17 to 8.9±2.1 (p=0.41) and Spanish 5.3±0.34 to 4.1±1.1 (p=0.0001). Spanish articles were significantly simplified per Legibilidad-µ (p=0.003). No significant difference was noted for other scales. CONCLUSIONS: The readability of AAO articles in English worsened without significance but significantly improved in Spanish. This may result from simpler syllable structures and a lesser overall vocabulary in Spanish. With increased testing, physicians can recommend ChatGPT for Spanish-speaking patients to improve health literacy.

Optimizing the Postoperative Management of Children Undergoing Resection of High-Risk Abdominal Neuroblastoma.

BACKGROUND: Surgical resection is a mainstay of treatment in high-risk neuroblastoma (HR-NB), but there exists wide variability in perioperative management practices. The aim of this study was to evaluate two standardized adult perioperative enhanced recovery practices (ERPs) in pediatric patients undergoing open resection of abdominal HR-NB. METHODS: All patients with abdominal HR-NB surgically resected at a free-standing children's hospital between 12/2010 and 7/2020 were retrospectively reviewed. Perioperative ERPs of interest included avoidance of routine nasogastric tube (NGT) use and the use of neuraxial anesthesia. Primary outcomes included time to enteral intake, urinary catheter use, opioid utilization, and length of stay (LOS). RESULTS: Overall, 37 children, median age 33 months (IQR: 20-48 months), were identified. Avoidance of an NGT allowed for earlier feeding after surgery (P = .03). Neuraxial anesthesia use more frequently required an indwelling urinary catheter (P < .01) for a longer duration (P = .02), with no difference in total opioid utilization (P = .77) compared to patients without neuraxial anesthesia. Postoperative LOS was unaffected by avoidance of routine NGT use (P = .68) or use of neuraxial anesthesia (P = .89). CONCLUSION: Children undergoing open resection of abdominal HR-NB initiated diet sooner when an NGT was not left postoperatively, and the need for a urinary catheter was significantly higher in patients who received neuraxial anesthesia. However, these two ERP components did not decrease postoperative LOS. To optimize the postoperative management of NB patients, postoperative NGTs should be avoided, while the benefit of neuraxial anesthesia is less clear as it necessitates the placement of a urinary catheter without decreasing opioid utilization.

Bias and Inaccuracy in AI Chatbot Ophthalmologist Recommendations.

PURPOSE AND DESIGN: To evaluate the accuracy and bias of ophthalmologist recommendations made by three AI chatbots, namely ChatGPT 3.5 (OpenAI, San Francisco, CA, USA), Bing Chat (Microsoft Corp., Redmond, WA, USA), and Google Bard (Alphabet Inc., Mountain View, CA, USA). This study analyzed chatbot recommendations for the 20 most populous U.S. cities. METHODS: Each chatbot returned 80 total recommendations when given the prompt "Find me four good ophthalmologists in (city)." Characteristics of the physicians, including specialty, location, gender, practice type, and fellowship, were collected. A one-proportion z-test was performed to compare the proportion of female ophthalmologists recommended by each chatbot to the national average (27.2% per the Association of American Medical Colleges (AAMC)). Pearson's chi-squared test was performed to determine differences between the three chatbots in male versus female recommendations and recommendation accuracy. RESULTS: Female ophthalmologists recommended by Bing Chat (1.61%) and Bard (8.0%) were significantly less than the national proportion of 27.2% practicing female ophthalmologists (p<0.001, p<0.01, respectively). ChatGPT recommended fewer female (29.5%) than male ophthalmologists (p<0.722). ChatGPT (73.8%), Bing Chat (67.5%), and Bard (62.5%) gave high rates of inaccurate recommendations. Compared to the national average of academic ophthalmologists (17%), the proportion of recommended ophthalmologists in academic medicine or in combined academic and private practice was significantly greater for all three chatbots. CONCLUSION: This study revealed substantial bias and inaccuracy in the AI chatbots' recommendations. They struggled to recommend ophthalmologists reliably and accurately, with most recommendations being physicians in specialties other than ophthalmology or not in or near the desired city. Bing Chat and Google Bard showed a significant tendency against recommending female ophthalmologists, and all chatbots favored recommending ophthalmologists in academic medicine.

Glioblastoma remodelling of human neural circuits decreases survival.

Gliomas synaptically integrate into neural circuits1,2. Previous research has demonstrated bidirectional interactions between neurons and glioma cells, with neuronal activity driving glioma growth1-4 and gliomas increasing neuronal excitability2,5-8. Here we sought to determine how glioma-induced neuronal changes influence neural circuits underlying cognition and whether these interactions influence patient survival. Using intracranial brain recordings during lexical retrieval language tasks in awake humans together with site-specific tumour tissue biopsies and cell biology experiments, we find that gliomas remodel functional neural circuitry such that task-relevant neural responses activate tumour-infiltrated cortex well beyond the cortical regions that are normally recruited in the healthy brain. Site-directed biopsies from regions within the tumour that exhibit high functional connectivity between the tumour and the rest of the brain are enriched for a glioblastoma subpopulation that exhibits a distinct synaptogenic and neuronotrophic phenotype. Tumour cells from functionally connected regions secrete the synaptogenic factor thrombospondin-1, which contributes to the differential neuron-glioma interactions observed in functionally connected tumour regions compared with tumour regions with less functional connectivity. Pharmacological inhibition of thrombospondin-1 using the FDA-approved drug gabapentin decreases glioblastoma proliferation. The degree of functional connectivity between glioblastoma and the normal brain negatively affects both patient survival and performance in language tasks. These data demonstrate that high-grade gliomas functionally remodel neural circuits in the human brain, which both promotes tumour progression and impairs cognition.

Epidemiology of pediatric trauma during the coronavirus disease-2019 pandemic.

BACKGROUND/PURPOSE: We aimed to describe the epidemiology of trauma activations and variations in injury patterns, injury severity, and hospital length-of-stay for injured children in Los Angeles (LA) County during the coronavirus-disease-19 (COVID-19) pandemic. METHODS: We conducted a retrospective cross-sectional study of children aged < 18-years evaluated in 15 trauma centers from 2019 to 2020 and entered in the LA County trauma registry. We defined 01/01/2019-03/18/2020 as pre-pandemic and 03/19/2020-12/31/2020 as the pandemic period. Our primary outcome was pediatric trauma activations. We analyzed demographic and clinical data, including types and severity of injuries sustained. We conducted unadjusted bivariate analyzes of injury patterns between periods. Segmented linear regression models were used to test rates (per 100,000 LA County children) of trauma activations pre-pandemic versus the pandemic period. RESULTS: We studied 4399 children with trauma activations, 2695 of which occurred pre-pandemic and 1701 in the pandemic period. Motor vehicle collisions, gunshot wounds, and burns increased during the pandemic (all p-values< 0.05), while sports injuries decreased (p < 0.001). Median injury severity scores (p = 0.323) and Glasgow Coma Scales (p = 0.558) did not differ between periods, however mortality (p = 0.023) decreased during the pandemic. Segmented linear regression estimates demonstrated that rates of trauma activations pre-pandemic were similar to the pandemic period (p = 0.384). CONCLUSION: Pediatric trauma activations in LA County did not significantly differ during the COVID-19 pandemic, but types and severity of injuries varied between pre-pandemic and pandemic periods. With lockdown restrictions being lifted and novel SARS-CoV-2 variants circulating, our investigation describes this recent epidemiologic phenomenon to aid future preparation for healthcare systems. LEVEL OF EVIDENCE: Level III TYPE OF STUDY: Retrospective cross-sectional study.