Assessment of ChatGPT's adherence to ETA-thyroid nodule management guideline over two different time intervals 14 days apart: in binary and multiple-choice queries.

OBJECTIVE: Artificial intelligence (AI) has significant potential in healthcare, particularly in providing decision-support in specialized domains like thyroid nodule management. This study assesses the effectiveness of ChatGPT-v4, an advanced AI model, in aligning with the European Thyroid Association (ETA) - 2023 guidelines. METHODS: The study utilized a structured questionnaire comprising 100 questions, divided into true/false and multiple-choice formats, reflecting real-world clinical scenarios in thyroid nodule management. These questions encompassed diagnostic criteria, treatment options, follow-up protocols, and patient counseling. ChatGPT response was evaluated for accuracy, consistency, and comprehensiveness using a six-point Likert scale. The assessment occurred initially and was repeated after 14 days. RESULTS: In the binary queries, the AI model showed an ability to correct some initially incorrect responses. However, there was a noticeable regression in certain responses. 8 of the 11 previously non-compliant responses remained unchanged, while 3 non-compliant responses were rectified. Conversely, 6 initially compliant answers transitioned to non-compliance after 14 days. In multiple-choice queries, the AI's performance was more consistent. A majority of the responses, 43 (86% of the total), were initially correct and maintained their correctness upon re-assessment. However, 4 responses that were initially incorrect remained unchanged, and 3 correct responses shifted to non-compliance over time. CONCLUSION: ChatGPT exhibited improving potential as a clinical support tool in thyroid nodule management altgouh it showed varied performance for binary and multiple-choice questions. CLINICAL TRIAL REGISTRATION: N/A.

Subacute THYROiditis Related to SARS-CoV-2 VAccine and Covid-19 (THYROVAC Study): A Multicenter Nationwide Study.

CONTEXT: The aims of the study are to compare characteristics of subacute thyroiditis (SAT) related to different etiologies, and to identify predictors of recurrence of SAT and incident hypothyroidism. METHODS: This nationwide, multicenter, retrospective cohort study included 53 endocrinology centers in Turkey. The study participants were divided into either COVID-19-related SAT (Cov-SAT), SARS-CoV-2 vaccine-related SAT (Vac-SAT), or control SAT (Cont-SAT) groups. RESULTS: Of the 811 patients, 258 (31.8%) were included in the Vac-SAT group, 98 (12.1%) in the Cov-SAT group, and 455 (56.1%) in the Cont-SAT group. No difference was found between the groups with regard to laboratory and imaging findings. SAT etiology was not an independent predictor of recurrence or hypothyroidism. In the entire cohort, steroid therapy requirement and younger age were statistically significant predictors for SAT recurrence. C-reactive protein measured during SAT onset, female sex, absence of antithyroid peroxidase (TPO) positivity, and absence of steroid therapy were statistically significant predictors of incident (early) hypothyroidism, irrespective of SAT etiology. On the other hand, probable predictors of established hypothyroidism differed from that of incident hypothyroidism. CONCLUSION: Since there is no difference in terms of follow-up parameters and outcomes, COVID-19- and SARS-CoV-2 vaccine-related SAT can be treated and followed up like classic SATs. Recurrence was determined by younger age and steroid therapy requirement. Steroid therapy independently predicts incident hypothyroidism that may sometimes be transient in overall SAT and is also associated with a lower risk of established hypothyroidism.

Association of thiol/disulphide homeostasis with Bethesda classification of thyroid nodules and thyroid cancer.

BACKGROUND: Ultrasonography and fine-needle aspiration biopsy are frequently used to diagnose thyroid cancer. However, supportive data might be required in case of diagnostic difficulty. This study investigated whether there is a relationship between thiol/ disulphide homeostasis and cytological and histopathological diagnosis of thyroid nodules. METHODS: The patient group consisted of 81 individuals with euthyroid nodular (single/multiple) goiter scheduled for thyroidectomy, and the control group consisted of 28 age- and sex-matched healthy volunteers who had no thyroid nodule on ultrasonographic evaluation. All participants were selected among the admissions to the study clinic between June 2017 and June 2018, and venous blood samples were collected. The samples of the patients were taken before surgery. Thiol and disulphide levels were analysed with the automated spectrophotometric method. RESULTS: The mean age of the patient group was 45.66 ± 10.45 years, and the mean age of the control group was 43.53 ± 11.49 years (p = 0.365). The increasing Bethesda categories were positively correlated with the disulphide level (r = 0.281, p = 0.011), disulphide/native thiol ratio (r = 0.241, p = 0.030) and disulphide/total thiol ratio (r = 0.250, p = 0.024). Disulphide/native thiol ratio and disulphide/ total thiol ratio were significantly higher in the histopathologically malignant (euthyroid nodular goiter but final pathology reported malignant) compared to histopathologically benign (euthyroid nodular goiter but final pathology reported benign) (p = 0.012; p = 0.007, respectively) and control groups (p = 0.006; p = 0.004, respectively), but no significant difference was found in these ratios between benign and control group (p = 0.711; p = 0.749, respectively). DISCUSSION: Oxidative stress parameters were significantly higher in thyroid cancer. A positive correlation was detected between Bethesda categories with increased risk of malignancy and the disulphide/native thiol ratio and the disulphide/total thiol ratio.