The aim of this study was to investigate the influence of body mass index (BMI) on the in vitro fertilization (IVF) treatment outcomes in a cohort of women undergoing their first IVF, using an intracytoplasmic sperm injection (ICSI). This retrospective cohort study included 298 cycles from women younger than 38 years old undergoing IVF-ICSI at a university infertility clinic. The treatment cycles were divided into three groups according to the BMI of the women involved: normal weight (18.5 ≤ BMI < 25 kg/m2, 164 cycles), overweight (25 ≤ BMI < 30 kg/m2, 70 cycles), and obese (BMI ≥ 30 kg/m2, 64 cycles). The underweight women (BMI < 18.5 kg/m2) were not included in the analysis due to small sample size (n = 22). The patient characteristics and IVF-ICSI treatment outcomes were compared between the BMI groups. The total gonadotropin dose (p 0.05 for each). Additionally, clinical pregnancy, spontaneous abortion, and the ongoing pregnancy rates per transfer were found to be comparable between the normal weight, overweight, and obese women (p >0.05 for each). Obese women might require a significantly higher dose of gonadotropins and longer stimulation durations, without greatly affecting the pregnancy outcomes.

Background and objective: Artificial intelligence (AI) has emerged as a promising tool for clinical decision support in reproductive medicine, yet the performance of general-purpose large language models (LLMs) in predicting in vitro fertilization (IVF) outcomes remains insufficiently characterized. This exploratory proof-of-concept study aimed to evaluate and compare the out-of-the-box performance of three widely accessible LLM-based systems (ChatGPT, DeepSeek, and Gemini) in forecasting key clinical and laboratory outcomes of IVF treatments. Methods: This retrospective single-center study used data from 1473 autologous IVF/ICSI cycles, each representing a unique patient. For each cycle, relevant clinical and laboratory variables were incorporated into a standardized anonymized patient-level vignette and submitted via the publicly available web interfaces of three LLMs (ChatGPT, DeepSeek, Gemini) without any fine-tuning or internal customization. The models were asked to predict stimulation protocol, ovulation trigger type, total and mature oocyte counts, usable embryo counts, and clinical pregnancy. Predictive performance was evaluated using accuracy and tolerance-based accuracy for categorical and count-based outcomes, mean absolute error for numerical predictions, and the area under the receiver operating characteristic (ROC) curve for clinical pregnancy. Results: Gemini achieved the highest accuracy in predicting stimulation protocols (51.26%) and embryo counts (68.22%), while DeepSeek demonstrated the lowest numerical error for oocyte count predictions. Clinical pregnancy prediction was the most challenging task; all models showed only moderate discrimination, with Gemini achieving the highest AUC (0.711), followed by ChatGPT (0.690) and DeepSeek (0.676). Overall, model performance varied considerably across tasks and remained below thresholds that would be considered sufficient for reliable stand-alone clinical use. Conclusions: In this exploratory proof-of-concept setting, general-purpose AI systems showed variable and overall suboptimal performance in predicting IVF outcomes from standardized clinical vignettes. Although certain models demonstrated relative strengths in specific tasks, none reached the reliability, consistency, or interpretability required for safe clinical implementation. These findings indicate that, in their current form, such models should not be used as clinical decision-support tools for IVF decision-making and that their use should remain restricted to carefully controlled research settings until they have been prospectively validated in multicenter cohorts and systematically compared with rigorously developed, task-specific prediction models. This study provides comparative insight into how these AI systems behave in IVF-related prediction tasks and underscores the need for cautious interpretation of AI-generated outputs.

The aim of this study was to describe characteristics and outcomes of assisted reproductive technology (ART) cycles performed in 2019 in Turkey. One-hundred and sixty-five ART centers in Turkey were invited to submit data. The survey was sent to center directors via e-mail with anonymous links by Qualtrics™. The survey involved questions about their patient characteristics, clinical practices, and outcomes. Forty-one (24.8%) centers responded to e-mails, and data gathered from 25 centers was included in the analyses. In 25 centers, 18,127 fresh or frozen transfers were carried out during the study period, of which 7796 (43.0%) were fresh and the rest were either frozen (45.2%) or embryo transfers (ET) with preimplantation genetic testing (PGT) (11.8%). The live birth rate per ET was as 30.6%, 40.1%, and 50.7% in fresh, frozen and PGT cycles, respectively. A single embryo was transferred in 65.3% of all transfers and singleton live births comprised 86.1% of all deliveries. For cycles with intrauterine insemination, 1407 were started in 2019, and 195 clinical pregnancies, 150 live births with 19 multiple pregnancies occurred. A total of 1513 ART cycles were initiated for foreign patients. Russia (29.6%), Germany (7.4%), Iraq (4.6%), Uzbekistan (3.1%), and Syria (1.4%) were the top five countries with most patients coming to Turkey for ART. The survey results are in parallel with the reports of international institutions and organizations. With repeated editions, the data collected with annual surveys can be used to inform ART practices in the coming years.

Aim. To investigate the effect of the triggering method on the results of fresh embryo transfer in patients who underwent gonadotropin‐releasing hormone antagonist cycles. Methods. The study was conducted retrospectively at a university‐based tertiary reproductive center. The sample consisted of a total of 295 patients, of whom 111 were in the human chorionic gonadotropin (hCG) trigger group and 184 were in the dual trigger group. The main outcome measure of this study was the live birth rate, and secondary outcomes were the implantation rate, clinical pregnancy rate, miscarriage rate, and good‐quality embryo rate. Results. Patient demographics and baseline characteristics did not significantly differ between the dual and hCG trigger groups. The results also indicated statistically nonsignificant differences between the two groups in terms of the number of oocytes retrieved (p > 0.05), the number of mature oocytes (p > 0.05), and the fertilization rate (p > 0.05). The number of good‐quality embryos (p = 0.002) was higher in the dual trigger group compared with the hCG trigger group. However, the rates of clinical pregnancy and live births did not significantly differ between the groups (p > 0.05). Conclusions. Although the number of total and high‐quality embryos obtained was higher in the dual trigger group, there were no significant differences between the two groups in terms of pregnancy outcomes. The fresh embryo transfer yielded similar rates of implantation and live births in both trigger groups.