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.

Background/aim: Studies have shown an increased depression rate in patients with type 2 diabetes mellitus (T2DM) compared to the normal population. It is now acknowledged that patients suffer from distress rather than depression. Our aim was to validate the Turkish version of the Diabetes Distress Scale (DDS) and to show distress levels of the participants. Materials and methods: The scale was translated from English to Turkish by the authors and translated back to English. Between August 2015 and January 2016 all the patients who were referred to the T2DM Clinic of Istanbul Medeniyet University were screened, and eligible patients were recruited. For calculating internal consistency Cronbach's alpha coefficient was used. Results: A total of 205 patients [120 females (58.5%), 85 males (41.5%)] were included. Cronbach's alpha coefficient was 0.874, showing internal consistency. The Spearman Brown correlation coefficient was calculated between the first 9 and second 8 questions as 0.884. Thetotal variances were explained at a level of 66.2% with 4 factors. Sixty-three patients (30%) had a score of >= 3, indicating diabetic distress. Correlation analysis showed a significant correlation between total score and HbA1c levels (r = 0.152 and P = 0.038). Conclusion: The Turkish version of the DDS for type 2 diabetes is a reliable tool for assessment of distress levels.

With more studies investigating effects of high serum lipid levels, new findings are emerging regarding the damage these biomolecules may cause. In this study we aimed to find a relation between neuropathy and hypertriglyceridemia in patients with metabolic syndrome (MS). One hundred and twenty subjects (Ninety subjects with metabolic syndrome and 30 healthy controls) were included in the study. Subjects with MS were divided into three groups. HbA1C levels of the subjects were < 5.7% in group A, ≥ 5.7% - < 6.5% in group B, and ≥ 6.5% - < 8.0% in group C. Pin-Prick test and Semmes- Weinstein Monofilament were used for neurological examination. Electromyography was performed to patients with neuropathy to support the diagnosis. Neuropathy prevalence was found to be higher in the subjects with metabolic syndrome compared to control group. (9.9 %; 16.65 %; 23.31 % vs. 3.3%; in group A, group B, group C vs. healthy control group respectively) (p=0.003 for group A, p=0.0002 for group B, p=0.0002 for group C). There was an association between triglyceride levels and neuropathy in group C. Patients with MS may have more neuropathy risk than we estimate.