Introduction: This study aimed to evaluate the accuracy, completeness, precision, and readability of outputs generated by three large language models (LLMs); these are GPT by OpenAI, BARD by Google, and Bing by Microsoft, in comparison to patient education material on pelvic organ prolapse (POP) provided by the Royal College of Obstetricians and Gynecologists (RCOG). Methods: A total of 15 questions were retrieved from the RCOG website and input into the three LLMs. Two independent reviewers evaluated the outputs for accuracy, completeness, and precision. Readability was assessed using the Simplified Measure of Gobbledygook (SMOG) score and the Flesch-Kincaid Grade Level (FKGL) score. Results: Significant differences were observed in completeness and precision metrics. ChatGPT ranked highest in completeness (66.7%), while Bing led in precision (100%). No significant differences were observed in accuracy across all models. In terms of readability, ChatGPT exhibited higher difficulty than BARD, Bing, and the original RCOG answers. Conclusion: While all models displayed a variable degree of correctness, ChatGPT excelled in completeness, significantly surpassing BARD and Bing. However, Bing led in precision, providing the most relevant and concise answers. Regarding readability, ChatGPT exhibited higher difficulty. We observed that while all LLMs showed varying degrees of correctness in answering RCOG questions on patient information for POP, ChatGPT was the most comprehensive, but its answers were harder to read. Bing, on the other hand, was the most precise. The findings highlight the potential of LLMs in health information dissemination and the need for careful interpretation of their outputs.
1 December 2023 in Journal of the Turkish-German Gynecological Association
Objective: Initially, medical treatment options are preferred in patients with abnormal uterine bleeding (AUB) who are hemodynamically stable. The aim of the present study was to investigate the effectiveness of a levonorgestrel-releasing intrauterine device (LNG-IUD) in reducing bleeding symptoms in patients with AUB stratified by underlying pathology. Material and Methods: In line with the polyp, adenomyosis, leiomyoma, malignancy (and hyperplasia), coagulopathy, ovulatory disorders, endometrial, iatrogenic and not otherwise classified classification system, patients who were administered LNG-IUD due to adenomyosis, endometrial hyperplasia, leiomyoma and AUB due to not otherwise classified causes were included in the study. Results: A total of 172 otherwise patients with a mean age of 42.58 +/- 5.00 years were included. The distributions in the adenomyosis, endometrial hyperplasia, leiomyoma and otherwise unclassified groups were 30.8%, 12.8%, 26.2%, and 30.2%, respectively. Overall effectiveness of LNG-IUD in reducing menstrual bleeding was 82%. The proportion whose bleeding decreased was 95.50% in the endometrial hyperplasia group, 88.70% in the adenomyosis group, 55.60% in the leiomyoma group and 92.30% in the not otherwise classified group. The power of the current study was 99%. The efficacy of LNG-IUD was significantly less in the leiomyoma group (p<0.05) and thus this group were more likely to require surgical intervention. The overall incidence of spotting was 50%. Amenorrhea developed in 14% of patients. Conclusion: While LNG-IUD was more effective in reducing symptoms of AUB in patients with adenomyosis, endometrial hyperplasia and not otherwise classified causes, LNG-IUD was less effective in cases of leiomyoma. (J Turk Ger Gynecol Assoc 2023; 24: 246-51)
Dear Editor,We are glad to have the opportunity to address the feedback on our study “The Emerging Role of AI in Patient Education: A Comparative Analysis
Backgrounds/Objectives: Modern technology and educational activities, such as antenatal classes (ACs), increase patient informedness in medicine and improve collaboration between physicians and patients. The present study aimed to evaluate and compare the impact of maternal health literacy (HL) on delivery outcomes between nulliparous and multiparous women who attended antenatal classes. Methods: This prospective study recruited 281 pregnant women who regularly attended ACs, but only 188 who gave birth at our academic tertiary hospital were included in the final analysis. Socio-demographic characteristics, peripartum data (cervical dilatation at the time of admission to the hospital, duration of labor, and mode of delivery), and obstetric interventions (cesarean section (C/S) rate and rate of instrumental vaginal birth and episiotomy) were recorded, and the level of HL was assessed using the European Health Literacy Survey Questionnaire (HLS-EU-Q16). HL levels did not significantly affect peripartum and postpartum outcomes. Results: The study results showed that HL levels did not impact labor duration and newborn Apgar scores (p > 0.05). Patient education levels and employment status affected the peripartum duration of labor (p = 0.048 and p = 0.001, respectively). There were no differences in the HL total score and subscale scores (p > 0.05) between nulliparous and multiparous patients, and the rate of primary C/S was similar in both groups. Conclusions: HL levels did not impact delivery (peripartum) outcomes in pregnant women who attended antenatal classes. However, the primary C/S rate was similar between the nulliparous and multiparous groups, which may indicate that antenatal education services can correct the negative impact of low HL levels on the primary C/S rate.
Objective: Based on the fact that Coronavirus Disease 2019 (COVID-19) is associated with many hemocytometric changes, we aimed to investigate the effect of this underlying inflammatory process on the frequency of early pregnancy loss (EPL) in this clinical trial. Methods: This is a retrospective cohort study. The patients with laboratory-confirmed COVID-19 infection before the 20 weeks of gestation were determined as the study group. Healthy pregnant women in their early pregnancy were determined as the control group. Hematological parameters of all patients included in the analysis were evaluated. Results: A total of 176 pregnant women with confirmed COVID-19 infections were evaluated, of which 117 were included in the analysis. One hundred and seventeen healthy pregnant women were determined as the control group. There was no difference between the groups according to demographic characteristics. The median white blood cell (WBC) and lymphocyte levels were lower in patients with COVID-19 infection (p<0.001 and p<0.001, respectively). The value of platelet/lymphocyte ratio (PLR) was higher in the group with COVID-19 infection (160.95 vs. 132.42, p<0.001). It was also determined that the median plateletcrit level was lower in the group with COVID-19 infection (p<0.001). The rate of EPL in the COVID-19 infection group and control group was 14.2% and 9.4%, respectively (p=0.220). Conclusion: COVID-19 infection presents with low lymphocyte count and plateletcrit values in pregnant women, and an increase in PLR rates in relation to the severity of the disease is observed. Although not statistically significant, COVID-19 infection was associated with increased EPL rates in our study.
31 August 2024 in Bulletin of Russian State Medical University
Adolescence represents a pivotal phase in the transition from childhood to adulthood. Adolescent gynecology is the clinical specialty that focuses on the management of gynecologic problems during this period. This study's primary objective is to emphasize the importance of adolescent gynecology by examining the gynecological causes of adolescent presentations and highlighting the differences that warrant consideration in the clinical approach to adolescent patients. The study was designed as a retrospective cohort study in an academic tertiary hospital and included adolescent individuals presenting to the obstetrics and gynecology emergency department or outpatient clinic. The analysis encompassed a range of factors, including age, presenting symptoms, examination findings, ultrasound results, laboratory data, and the necessity for hospital admission. The study cohort comprised 750 adolescent patients, 71.3% seeking gynecological care. Adolescents most frequently presented for menstrual irregularities (57.6%) and secondly for dysmenorrhea. The results of the gynecological clinical evaluations indicated that 62.9% of the patients had menstrual disorders. Of these, 53.4% had irregular menstrual cycles, 4.5% had prolonged and/or heavy bleeding, and 3% had amenorrhea. Ultrasound imaging revealed the presence of pathological findings in 25.8% of the patients. In conclusion, this study's findings indicate that irregular menstrual cycles are the most common gynecological condition in the adolescent population. The physiological characteristics of adolescents require a distinct approach to diagnosis and treatment compared to adult women, which can significantly impact future fertility and overall reproductive health.