Large language models and bariatric surgery patient education: a comparative readability analysis of GPT-3.5, GPT-4, Bard, and online institutional resources.

BACKGROUND: The readability of online bariatric surgery patient education materials (PEMs) often surpasses the recommended 6th grade level. Large language models (LLMs), like ChatGPT and Bard, have the potential to revolutionize PEM delivery. We aimed to evaluate the readability of PEMs produced by U.S. medical institutions compared to LLMs, as well as the ability of LLMs to simplify their responses. METHODS: Responses to frequently asked questions (FAQs) related to bariatric surgery were gathered from top-ranked health institutions. FAQ responses were also generated from GPT-3.5, GPT-4, and Bard. LLMs were then prompted to improve the readability of their initial responses. The readability of institutional responses, initial LLM responses, and simplified LLM responses were graded using validated readability formulas. Accuracy and comprehensiveness of initial and simplified LLM responses were also compared. RESULTS: Responses to 66 FAQs were included. All institutional and initial LLM responses had poor readability, with average reading levels ranging from 9th grade to college graduate. Simplified responses from LLMs had significantly improved readability, with reading levels ranging from 6th grade to college freshman. When comparing simplified LLM responses, GPT-4 responses demonstrated the highest readability, with reading levels ranging from 6th to 9th grade. Accuracy was similar between initial and simplified responses from all LLMs. Comprehensiveness was similar between initial and simplified responses from GPT-3.5 and GPT-4. However, 34.8% of Bard's simplified responses were graded as less comprehensive compared to initial. CONCLUSION: Our study highlights the efficacy of LLMs in enhancing the readability of bariatric surgery PEMs. GPT-4 outperformed other models, generating simplified PEMs from 6th to 9th grade reading levels. Unlike GPT-3.5 and GPT-4, Bard's simplified responses were graded as less comprehensive. We advocate for future studies examining the potential role of LLMs as dynamic and personalized sources of PEMs for diverse patient populations of all literacy levels.

Pediatric patients with malignant brain tumor treated at children's hospitals: association with fewer unplanned readmissions.

OBJECTIVE: Pediatric primary brain tumors are the leading cause of death among childhood cancers. Guidelines recommend specialized care with a multidisciplinary team and focused treatment protocols to optimize outcomes in this patient population. Furthermore, readmission is a key metric of patient outcomes and has been used to inform reimbursement. However, no prior study has analyzed national database-level records to evaluate the role of care in a designated children's hospital following pediatric tumor resection and its impact on readmission rates. The goal of this study was to investigate whether treatment at a children's hospital rather than a nonchildren's hospital has a significant effect on outcome. METHODS: The Nationwide Readmissions Database records from 2010 to 2018 were analyzed retrospectively to evaluate the effect of hospital designation on patient outcomes after craniotomy for brain tumor resection, and results are reported as national estimates. Univariate and multivariate regression analyses of patient and hospital characteristics were conducted to evaluate if craniotomy for tumor resection at a designated children's hospital was independently associated with 30-day readmissions, mortality rate, and length of stay. RESULTS: A total of 4003 patients who underwent craniotomy for tumor resection were identified using the Nationwide Readmissions Database, with 1258 of these cases (31.4%) treated at children's hospitals. Patients treated at children's hospitals were associated with decreased likelihood of 30-day hospital readmission (OR 0.68, 95% CI 0.48-0.97, p = 0.036) compared to patients treated at nonchildren's hospitals. There was no significant difference in index mortality between patients treated at children's hospitals and those treated at nonchildren's hospitals. CONCLUSIONS: The authors found that patients undergoing craniotomy for tumor resection at children's hospitals were associated with decreased rates of 30-day readmission, with no significant difference in index mortality. Future prospective studies may be warranted to confirm this association and identify components contributing to improved outcomes in care at children's hospitals.