ChatGPT and other large language models have emerged as new tools for patient education, yet their clinical safety and reliability remain unclear. To assess the accuracy and safety of ChatGPT-4o's responses to common postoperative questions following rhinoplasty. Ten consensus-based postoperative questions were identified via a modified Delphi process. ChatGPT-4o responses were generated and evaluated by three independent otolaryngologists using a 10-point Likert scale. Reviewers also assessed the presence of critical errors. The average Likert score across responses was 8.87 (95% CI, 8.39 to 9.34), No critical errors were detected. Inter-rater reliability was high (ICC(2,k) = 0.876). ChatGPT-4o provided clinically accurate and safe answers to common rhinoplasty postoperative questions. These findings suggest that ChatGPT-4o may serve as a useful adjunct for postoperative patient counseling in structured settings, particularly when physician access is limited.

Background: We aimed to investigate the prognostic significance of hematological inflammatory indices and monocyte-to-high-density lipoprotein cholesterol ratio (MHR) in the diagnosis and prognosis of Bell’s palsy. Method: The study included 156 cases diagnosed with Bell’s palsy in the neurology clinic and 156 healthy controls. The patients diagnosed with Bell’s palsy were staged according to the House–Brackmann Scoring system. Hematological inflammatory parameters such as neutrophil-to-lymphocyte ratio (NLR), platelet-to-lymphocyte ratio (PLR), systemic immune-inflammation index (SII) and systemic inflammation response index (SIRI) levels, and MHR were calculated from the parameters in the patient files. Result: Hematological inflammatory parameters such as NLR, PLR, SII, SIRI, and MHR were found to be higher in Bell’s palsy patients. In addition, these parameters were found to be higher in patients with grade V and above Bell’s palsy and in patients who did not respond to treatment, compared to the grade IV group and patients who responded to treatment, respectively. SIRI was an independent predictor of both the diagnosis of the disease and the lack of response to treatment, and this was confirmed by LASSO analysis. Conclusions: This study is among the few that demonstrated predictive models based on hematological inflammatory indices that can aid in both the diagnosis and treatment response assessment of newly diagnosed Bell’s palsy patients, validated using the LOOCV method. The findings highlight the potential clinical utility of simple, inexpensive, and practical biomarkers such as NLR, PLR, SII, SIRI, and MHR. These easily accessible parameters may support early diagnosis and prognostic evaluation in routine clinical settings.