Gestational diabetes mellitus (GDM) is a prevalent condition requiring accurate patient education, yet the reliability and readability of large language models (LLMs) in this context remain uncertain. This study evaluated the performance of four LLMs—ChatGPT-4o, Gemini 2.5 Pro, Grok 3.0, and DeepSeek R-1—using 25 patient-oriented questions derived from clinical scenarios. Seven endocrinologists independently rated the responses with the modified DISCERN (mDISCERN) instrument and the Global Quality Score (GQS). Readability was analyzed using the Flesch Reading Ease (FRES), Flesch–Kincaid Grade Level (FKGL), Gunning Fog Index (GFI), Coleman–Liau Index (CLI), and Simple Measure of Gobbledygook (SMOG), while lexical diversity was assessed through type–token ratio (TTR). Grok and Gemini obtained the highest mDISCERN and GQS scores, whereas ChatGPT performed significantly lower (p < 0.05). DeepSeek generated the most readable outputs, while Grok provided the longest and most complex responses. All models scored below the FRES threshold of 60 recommended for lay audiences. Response length showed strong positive correlations with mDISCERN and GQS, while TTR was inversely related to quality but positively associated with readability. These findings highlight variability among LLMs in GDM education and emphasize the need for model-specific improvements to ensure reliable patient-facing health information.

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.

The aim of this study was to evaluate the efficacy of cabergoline in normalizing plasma IGF-I levels in acromegaly patients with elevated IGF-I levels after surgery and/or SRL therapy. Acromegaly patients (n: 143) were evaluated retrospectively. Patients with elevated IGF-I levels after surgery and/or SRLs therapy and a fixed dose of SRLs treatment for the last six months with no history of radiotherapy in the last three years were included in the study (n: 12). Previous treatment regimens, baseline PRL and IGF-I levels (ULNR), sella MRI, and immunohistochemical findings were evaluated. Cabergoline was used as an add on (n: 11) or single medical treatment (n: 1). The median duration of treatment with SRL alone was 12 months (range 6–48 months). The mean IGF-I value before cabergoline therapy was 1.45±0.4 ULNR. The mean cabergoline dose and duration of treatment were 1.55±0.75 mg/week and 9±6.3 months, respectively. IGF-I normalization was only achieved in patients with serum IGF-I concentration<1.5×ULNR before the onset of cabergoline treatment (n: 9). In some of the patients with IGF-I normalization, baseline prolactin levels were normal (n: 3). Immunopositivity for prolactin in adenoma tissue was found in three patients with IGF-I normalization. Cabergoline therapy is effective in the normalization of IGF-I levels even in normoprolactinemic acromegaly patients when IGF-I levels are mildly or moderately elevated during SRL therapy.