Chatbots as Patient Education Resources for Aesthetic Facial Plastic Surgery: Evaluation of ChatGPT and Google Bard Responses.

Background: ChatGPT and Google Bard™ are popular artificial intelligence chatbots with utility for patients, including those undergoing aesthetic facial plastic surgery. Objective: To compare the accuracy and readability of chatbot-generated responses to patient education questions regarding aesthetic facial plastic surgery using a response accuracy scale and readability testing. Method: ChatGPT and Google Bard™ were asked 28 identical questions using four prompts: none, patient friendly, eighth-grade level, and references. Accuracy was assessed using Global Quality Scale (range: 1-5). Flesch-Kincaid grade level was calculated, and chatbot-provided references were analyzed for veracity. Results: Although 59.8% of responses were good quality (Global Quality Scale ≥4), ChatGPT generated more accurate responses than Google Bard™ on patient-friendly prompting (p < 0.001). Google Bard™ responses were of a significantly lower grade level than ChatGPT for all prompts (p < 0.05). Despite eighth-grade prompting, response grade level for both chatbots was high: ChatGPT (10.5 ± 1.8) and Google Bard™ (9.6 ± 1.3). Prompting for references yielded 108/108 of chatbot-generated references. Forty-one (38.0%) citations were legitimate. Twenty (18.5%) provided accurately reported information from the reference. Conclusion: Although ChatGPT produced more accurate responses and at a higher education level than Google Bard™, both chatbots provided responses above recommended grade levels for patients and failed to provide accurate references.

Altered extracellular matrix correlates with an immunosuppressive tumor microenvironment and disease progression in younger adults with oral cavity squamous cell carcinoma.

Introduction: Oral cavity squamous cell carcinoma (OSCC) occurs most frequently in patients >60 years old with a history of tobacco and alcohol use. Epidemiological studies describe increased incidence of OSCC in younger adults (<45 years). Despite its poor prognosis, knowledge of OSCC tumor microenvironment (TME) characteristics in younger adults is scarce and could help inform possible resistance to emerging treatment options. Methods: Patients with OSCC were evaluated using TCGA-HNSC (n=121) and a stage and subsite-matched institutional cohort (n=8) to identify differential gene expression focusing on the extracellular matrix (ECM) and epithelial-mesenchymal transition (EMT) processes in younger (≤45 years) vs. older adults (≥60 years). NanoString nCounter analysis was performed using isolated total RNA from formalin-fixed paraffin-embedded (FFPE) tumor samples. Stained tumor slides from young and old OSCC patients were evaluated for CD8+ T-cell counts using immunohistochemistry. Results: Younger OSCC patients demonstrated significantly increased expression of ECM remodeling and EMT process genes, as well as TME immunosuppression. Gene set enrichment analyses demonstrated increased ECM pathways and concurrent decreased immune pathways in young relative to old patients. Transcripts per million of genetic markers involved in ECM remodeling including LAMB3, VCAN, S100A9, COL5A1, and ITGB2 were significantly increased in tumors of younger vs. older patients (adjusted p-value < 0.10). Young patient TMEs demonstrated a 2.5-fold reduction in CD8+ T-cells as compared to older patients (p < 0.05). Conclusion: Differential gene expression impacting ECM remodeling and TME immunosuppression may contribute to disease progression in younger adult OSCC and has implications on response to evolving treatment modalities, such as immune checkpoint inhibitor therapy.