Comparison of Indications for Hysterectomy in Our Clinic With Recommendations of the Artificial Intelligence Program

Comparison of Indications for Hysterectomy in Our Clinic With Recommendations of the Artificial Intelligence Program | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Comparison of Indications for Hysterectomy in Our Clinic With Recommendations of the Artificial Intelligence Program Saltuk Buğra Arıkan, can dinç, Mustafa Özer, M. Ilkin Yeral This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6260219/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Objective : This study aims to compare and analyze the medical data and clinical indications of patients who have been decided for hysterectomy in our clinic with the recommendations of the artificial intelligence program ChatGPT. The recommendations generated by ChatGPT, based on scientific articles and studies, are used to assess its potential and limitations in clinical decision-making processes. The research investigates how effective and reliable Artificial Intelligence (AI) based systems can be in planning major surgical interventions such as hysterectomy. Furthermore, the study examines how AI technology can be integrated into current medical practices and its extent of contribution to clinical decision-making processes. In this context, the study aims to provide significant insights into the future use of AI in the medical field. Materials and Methods : The study was conducted on a total of 87 patients aged between 40-65 years, who applied to the Akdeniz University Department of Obstetrics and Gynecology and were decided for hysterectomy between June 1, 2023, and November 1, 2023. The detailed anamneses and information of the patients included in the study were systematically collected and evaluated by the research staff of our clinic. The collected data were entered into the AI program ChatGPT, aiming to determine the most effective treatment option suitable for each patient's scenario. During this process, the program was requested to interpret the medical condition of each patient, considering the current literature, and to explain the reasons for its recommendations. This methodology was designed to assess the contribution of AI to clinical decision-making processes and to examine its potential effectiveness. Results : The data of 87 patients who presented to the Akdeniz University Department of Obstetrics and Gynecology and were decided for hysterectomy between June 1, 2023, and November 1, 2023, were analyzed in this study. The average age of the patients was found to be 48.71, with the most common complaints being irregular menstruation (31.00%) and heavy menstrual bleeding (HMB) (27.60%). The most frequent additional disease histories were obesity (13.80%) and hypertension (HT) (14.90%). A low proportion of patients had a history of breast cancer and Tamoxifen usage (5.70% and 4.60% respectively). When comparing the treatment options recommended by the AI program ChatGPT with the decisions of clinicians, it was observed that the program recommended hysterectomy in 70.10% of the cases. Other recommended treatments included myomectomy (10.30%), hysteroscopy (8.00%), and medical treatment (4.60%). These recommendations correlated with the clinical and demographic characteristics of the patients. Notably, the AI’s recommendations for hysterectomy were highly consistent with situations involving abnormal uterine bleeding and the presence of myomas. Conclusions : The alignment between ChatGPT's recommendations and clinical decisions demonstrates the potential of AI in medical decision-making processes. However, the presence of some differences between the recommendations of AI and actual clinical practices highlights that AI should not yet be used as an independent decision-making tool and should continue to be employed as a supportive technology in medical applications. Furthermore, the study brings to light the potential and limitations of AI in medical decision-making processes. Despite the recommendations of AI programs being based on medical data and current literature, the importance of clinical experience and evaluating the individual condition of the patient is emphasized. In conclusion, this study demonstrates that AI-based systems can be an effective support tool in clinical decision-making processes. However, the use of such systems should be to assist and complement the clinical decisions of physicians. These findings provide a foundation for better understanding the future role and integration of AI in the medical field. Artificial Intelligence and Machine Learning Surgical Obstetrics & Gynecology Obstetrics & Gynecology Artificial Intelligence Abnormal Uterine Bleeding Hysterectomy Gynecology Introduction Artificial intelligence (AI) has rapidly become an integral and evolving part of contemporary medical practices [ 1 ]. The role of AI in clinical decision-making processes offers significant opportunities for both physicians and patients. This study aims to compare and analyze the recommendations of the AI program ChatGPT with clinical indications for patients scheduled for hysterectomy at Akdeniz University’s Gynecology and Obstetrics Clinic. Hysterectomy is a commonly performed procedure in gynecological surgery with various indications [ 2 ]. In this context, evaluating the potential and limitations of AI in this field holds significant importance for modern medical practice. AI systems are designed to identify patterns, trends, and insights from large datasets, detect inefficiencies, or predict future outcomes based on chronological trends. Unlike other data science applications, an important feature of these systems is their ability to re-balance and demonstrate sustainable learning when exposed to new datasets. In response to the rapidly increasing data volume in the evolving healthcare system and technologies, AI applications have begun to be used in various medical practices. How this technology can be integrated into medical decision-making processes and its contribution to clinical applications has become a growing area of interest. This research is based on scenarios where detailed anamnesis of patients scheduled for hysterectomy in our clinic are presented to the AI program ChatGPT, which then chooses one of the treatment options. The aim of this study is to thoroughly analyze ChatGPT's success in evaluating hysterectomy indications and its alignment with clinical decisions. The study aims to investigate how effective and reliable AI-based systems can be in clinical decision-making processes and how these technologies can be integrated into existing medical practices. AI systems can process large datasets quickly and efficiently, evaluate a patient’s condition using the most up-to-date information from the literature, and provide potential treatment options. However, to understand the role of AI in clinical applications, it is necessary to compare and analyze AI's recommendations with real-world data [ 3 ]. Another important aspect of this study is to examine the extent and potential limitations of AI's contribution to clinical decision-making processes. The results of the study can provide valuable insights into the future use of AI in the medical field and help shape the direction of technological advancements in this area. Materials And Methods Between June 1, 2023, and November 1, 2023, a total of 87 patients aged 40–65, who were scheduled for hysterectomy at Akdeniz University's Gynecology and Obstetrics Clinic, were included in this study. The patients' anamneses and detailed information were systematically collected and evaluated by our clinic's research assistants. The obtained data were then provided to the AI program, which was tasked with interpreting this information, taking into account each patient's medical condition and the current literature, in order to develop the most appropriate option for each patient's scenario. The AI program was also asked to provide a rationale for its recommendations. The study was initiated with the ethical approval of the Akdeniz University Faculty of Medicine Clinical Research Ethics Committee, dated May 10, 2023, with the approval number KAEK-390. Allocation And Sample Size Estimation Between June 1, 2023, and November 1, 2023, a total of 87 patients aged 40–65, who presented with abnormal uterine bleeding (AUB) and were scheduled for hysterectomy at Akdeniz University's Gynecology and Obstetrics Clinic, were included in this study. We chose our patients by time. Our study is a comparative prospective study. Procedures In this study, we utilized the ChatGPT-4 model developed by OpenAI. As the fourth iteration of the GPT series, this model has been trained on extensive textual data and possesses natural language processing capabilities. ChatGPT can comprehend text-based inputs and generate human-like responses in natural language. For our study, the model was trained using deep learning techniques with information obtained from a broad medical literature database, thereby acquiring a comprehensive understanding of medical terminology, disease symptoms, diagnostic methods, and treatment options. The patient scenarios used in this study encompass various clinical details to construct comprehensive patient histories. These details include the patient's age, number of pregnancies, mode of delivery, menopausal status, current complaints, medical history, past surgical interventions, medications used, coexisting conditions, prior medical or surgical treatments for current complaints, history of breast cancer, family history of cancer, transvaginal ultrasound findings (e.g., presence, type, and size of fibroids, endometrial characteristics), laboratory results, pathology findings, and options presented to the AI system. Based on these constructed scenarios, the AI program was presented with various treatment options, including hysterectomy, myomectomy, hysteroscopy, medical management with follow-up, levonorgestrel releasing intrauterine device (LNG-IUD) application, and hysterectomy following hysteroscopy. The AI program was tasked with selecting the most appropriate option among these choices and providing a rationale supported by relevant scientific sources. Statistical analysis The data were analyzed using IBM SPSS Statistics 23.0 (IBM Corp. Released 2015. IBM SPSS Statistics for Windows, Version 23.0. Armonk, NY: IBM Corp.). Continuous data were reported as Mean ± Standard Deviation, while categorical data were presented as percentages (%). The normality of the data was assessed using the Shapiro-Wilk test, revealing that the data did not follow a normal distribution. Cross-tabulation analyses were conducted using Pearson's Chi-square and Pearson's Exact Chi-square tests. A significance level of p < 0.05 was adopted to determine statistical significance. Results In the study, demographic data and histories of 87 women who were followed and underwent surgical interventions were analyzed. The demographic, clinical, and laboratory data of the patients are shown in Table 1. The average age of the participants was found to be 48.71 years. Previous pregnancy history reveals that the most common condition among the studied patients was that 37 patients (42.50%) had experienced two pregnancies, and 51 patients (58.60%) had undergone vaginal delivery. Regarding menopausal status, 67 participants (77.00%) were found not to be in menopause. The chief complaints, family history, and medical history of the patients are shown in Table 2. The most common complaints included irregular menstruation (31.00%) and heavy menstrual bleeding (HMB) (27.60%). Other frequent complaints included pelvic mass (20.70%), intermenstrual bleeding (IMB) (10.30%), and IMB with HMB (9.20%). In terms of additional medical history, 44 individuals (50.60%) did not have any additional diseases. The most frequently encountered additional conditions were hypertension (HT) (14.90%) and obesity (13.80%). Polycystic ovary syndrome (PCOS) was observed in only 2 patients (2.30%). Among the patients, 82 (94.30%) did not have a history of breast cancer, and 83 (95.40%) were not using tamoxifen. Among the 21 patients (24.10%) with a family history of cancer, gynecological cancer predominated in 13 patients (14.90%), while colon and other cancer types were present in 3 patients (3.40%), and breast cancer history was observed in 2 patients (2.30%). Additionally, 41 patients (47.10%) had previously received medical treatment for their current complaints. When examining the types of medical treatments previously received for their current complaints, it was found that 22 patients (25.30%) had undergone hormone therapy, and 18 patients (20.70%) had received Combined Oral Contraceptive (COC) therapy. Additionally, 11 patients (13.80%) had received Levonorgestrel Intrauterine Device (LNG- IUD) therapy. A total of 35 patients (40.20%) had undergone abdominal surgery in the past, with 25 of these surgeries (28.70%) being laparotomies. The number of patients who underwent hysterectomy/salpingectomy for therapeutic purposes was 21 (24.10%). The physical examination and ultrasonography findings of the patients are shown in Table 3. Regarding transvaginal ultrasound (TV-US) findings: 38 patients (43.70%) did not have Endometrial Hyperplasia, 27 patients (31.10%) had Endometrial Hyperplasia, 18 patients (20.70%) had Irregular Endometrium, 4 patients (4.60%) had Suspicious Masses. In 61 patients (70.10%), the presence of myomas was observed, with Type 5 myoma being the most common at 24.10%. The distribution of other myoma types was as follows: Type 6 myoma in 11 patients (12.60%), Type 3 and Type 4 myomas in 7 patients each (8.00%), adenomyotic appearance in 5 patients (5.70%), Type 2 myoma in 4 patients (4.60%), and Type 7 and Type 0 myomas in 3 patients each (3.40%). Type 1 myoma was not observed in any patient. The most frequently observed myoma size was 10 cm and above in 16 patients (18.40%), followed by sizes ranging from 3–5 cm in 16 patients (18.40%). Other observed myoma sizes included 5–10 cm in 15 patients (17.20%), multiple intramural myomas in 12 patients (13.80%), and less than 3 cm in 2 patients (2.30%). Among the patients, polyp presence was suspected in 14 (16.20%) based on transvaginal ultrasound (TVUS). Anemia (Hb deficiency) was detected in 30 patients (34.50%). The biopsy findings and treatments options recommended by AI are shown in Table 4. Following endometrial biopsy, pathological findings revealed that 58 patients (66.70%) mostly had normal endometrial biopsies. Other findings included 11 patients (12.60%) with EIN (-) and polyps, 4 patients (4.60%) with EIN (+), and malignancy in 3 patients (3.40%). When the conditions of 87 patients who underwent hysterectomy were evaluated by artificial intelligence (AI), it was seen that hysterectomy was recommended for 61 patients (70.10%). Other recommended treatment methods were preferred less frequently; Myomectomy was offered for 9 patients (10.30%), hysteroscopy for 7 patients (8.00%), and medical treatment for 4 patients (4.60%). Additionally, hysterectomy after hysteroscopy was recommended for 3 patients (3.40%), LNG-IUD use was recommended for 2 patients (2.30%), and follow-up was recommended for only 1 patient (1.10%). Comparison of Symptoms and Medical Treatments Based on TV-US Myoma Types in Patients for Whom AI Recommended Myomectomy are shown in Table 5. The presence and types of fibroids were evaluated using transvaginal ultrasonography (TV-US) in nine patients for whom AI recommended myomectomy, based on their abnormal uterine bleeding (AUB) complaints and medical treatment histories. Among patients with heavy menstrual bleeding (HMB) who had received treatment but showed no improvement and had fibroids, 2 patients (1.60%) had type 2 fibroids, 1 patient (0.80%) had a type 3 fibroid, and 1 patient (0.80%) had a type 5 fibroid. In contrast, among patients with HMB who had no prior treatment history, 1 patient (0.20%) had a type 6 fibroid. Among 4 patients with irregular menstruation and no history of medical treatment, 2 patients (2.00%) had type 5 fibroids, while 1 had a type 4 fibroid and another had a type 6 fibroid. Comparison of symptoms, fibroid types, and fibroid sizes in patients for whom AI recommended myomectomy based on tv-us findings are shown in Table 6. The fibroid types and sizes were evaluated using TV-US in nine patients for whom AI recommended myomectomy, based on their AUB complaints and medical treatment histories. All nine patients for whom myomectomy was recommended were found to have fibroids on TV-US. Among patients with HMB who had received treatment but showed no improvement, 2 patients (2.00%) with type 2 fibroids had fibroid sizes between 3–5 cm, 1 patient (1.00%) with a type 3 fibroid had a fibroid size between 3–5 cm, and 1 patient (1.00%) with a type 5 fibroid had a fibroid size between 3–5 cm. Among patients with HMB who had no prior treatment history, 1 patient (1.00%) with a type 6 fibroid had a fibroid size larger than 10 cm. Among four patients with irregular menstruation and no history of medical treatment, 2 patients (2.00%) with type 5 fibroids had different fibroid characteristics: one had a fibroid size between 5–10 cm, while the other had multiple intramural fibroids. Additionally, 1 patient (1.00%) with a type 4 fibroid had a fibroid size between 3–5 cm, and 1 patient (1.00%) with a type 6 fibroid had a fibroid size larger than 10 cm. Comparison of current symptoms, medical treatment history, and TV-US endometrial findings in patients for whom AI recommended hysteroscopy based on symptom status are shown in Table 7. The patients with AUB for whom AI recommended hysteroscopy were examined based on their medical treatment histories and endometrial findings, and 7 patients were identified. Among the 4 patients who presented with HMB, 1 patient (0.30%) had a medical treatment history for the current complaint and was found to have endometrial hyperplasia. The other 3 patients (2.30%) had no medical treatment history for the current complaint, but irregular endometrium was observed in their TV-US findings. Among the 2 patients with irregular menstruation, both had a medical treatment history for the current complaint. Upon examining their endometrial findings, 1 patient had irregular endometrium, and the other had endometrial hyperplasia. The patient presenting with PMB had no medical treatment history or endometrial hyperplasia for the current complaint. Comparison of endometrial findings and AI-recommended treatment based on menopausal status in patients with polyps on TV-US are shown in Table 8. In patients with polyps on TV-US, the endometrial findings and AI-recommended treatment methods were examined according to menopausal status. Among the patients, 3 were postmenopausal and 11 were premenopausal. In postmenopausal patients, with endometrial findings of irregular endometrium, absence of endometrial hyperplasia, and presence of a suspicious mass, AI recommended hysterectomy. In premenopausal patients, AI recommended hysterectomy for 2 patients (2.70%) with irregular endometrium, hysteroscopy for 2 patients (1.40%), and hysteroscopy followed by hysterectomy for 1 patient (0.90%). For the patient without endometrial hyperplasia, hysterectomy was recommended for 1 patient (0.50%), while among the 4 patients with endometrial hyperplasia, hysterectomy was recommended for 3 patients (2.20%), and hysteroscopy for 1 patient (1.10%). For 1 patient (0.20%) with a suspicious mass, hysteroscopy followed by hysterectomy was recommended. Comparison of endometrial biopsy and AI-recommended treatment based on menopausal status in patients with polyps on TV-US are shown in Table 9. In patients with polyps on TV-US, the endometrial biopsy and AI-recommended treatment methods were examined based on menopausal status. In postmenopausal patients, AI recommended hysterectomy for one patient with a normal endometrial biopsy, one with EIN (-), and one with a polyp. In premenopausal patients, AI recommended hysteroscopy for 2 patients (2.70%) with a normal endometrial biopsy, and hysteroscopy followed by hysterectomy for 1 patient (1.50%). For patients with EIN (-) on endometrial biopsy, hysterectomy was recommended for 1 patient (0.50%), while for 5 patients with a polyp on endometrial biopsy, hysterectomy was recommended for 3 patients (3.80%), hysteroscopy for 1 patient (1.90%), and hysteroscopy followed by hysterectomy for 1 patient (1.30%). Comparison of fibroid presence and medical treatment history for the current complaint in patients recommended for hysterectomy with normal endometrial biopsy and Endometrial Intraepithelial Neoplasia (EIN) (-) are shown in Table 10. The comparison was made between the presence of fibroids and the medical treatment history for the current complaint in patients for whom AI recommended hysterectomy, with normal endometrial biopsy and EIN (-). Among patients with a normal endometrial biopsy and fibroids, 15 (14.70%) had a medical treatment history for the current complaint, while 19 (19.30%) did not. Among patients with a normal endometrial biopsy and no fibroids, 1 (1.30%) had a medical treatment history for the current complaint, while 2 (1.70%) did not. For patients with EIN (-) and fibroids, 1 patient was found, and this patient did not have a medical treatment history for the current complaint. Among patients with EIN (-) and no fibroids, 4 (3.60%) had a medical treatment history for the current complaint, while 4 (4.40%) did not have a medical treatment history. Comparison of fibroid type and history of medical treatment for existing complaints in patients with normal endometrial biopsy and EIN (-) who were recommended for hysterectomy are shown in Table 11. The history of medical treatment for the existing complaint was compared according to the fibroid type in patients for whom AI recommended hysterectomy and whose endometrial biopsy results were normal and EIN (-). Among the patients for whom AI recommended hysterectomy, 1 patient (1.80%) with a normal endometrial biopsy and fibroid type 3 had a history of medical treatment for the existing complaint, while three patients (2.20%) did not. Among patients with fibroid type 4, two (1.30%) had a history of medical treatment for the existing complaint, whereas 1 patient (1.70%) did not. Among patients with fibroid type 5, 6 (4.90%) had a history of medical treatment, while 5 (6.10%) did not. Among patients with fibroid type 6, 2 (2.60%) had a history of medical treatment, whereas 4 (3.40%) did not. Among patients with fibroid type 7, 3 (1.70%) did not have a history of medical treatment. In patients with type 0 fibroids, 1 (0.90%) had a history of medical treatment for the existing complaint, while 1 patient (1.10%) did not. Regarding the adenomyotic fibroid type, 3 patients (1.80%) had a history of medical treatment, while 1 (2.20%) did not. Additionally, 1 patient (1.00%) with an EIN (-) endometrial biopsy was identified, and their fibroid type was classified as type 6. Furthermore, this patient had no history of medical treatment for the existing complaint. Comparison of complaints and medical treatment history for existing complaints in patients with hemoglobin deficiency recommended for hysterectomy are shown in Table 12. It was observed that 21 patients were recommended for hysterectomy and had low hemoglobin levels. The patients' AUB complaints and medical treatment history for the existing complaint were compared. Among the 4 patients with IMB complaints, 3 (2.30%) had a history of medical treatment for the existing complaint, while 1 (1.70%) did not. Among the 8 patients presenting with HMB complaints, 6 (4.60%) had a history of medical treatment for the existing complaint, while 2 (3.40%) did not. Only two patients presented with both HMB & IMB complaints, and both of these patients had a history of medical treatment for the existing complaint. Among the 2 patients with irregular menstruation complaints, 1 (1.10%) had a history of medical treatment, while 1 (1.90%) did not. None of the 5 patients presenting with postmenopausal bleeding (PMB) complaints had a history of medical treatment for the existing complaint (2.10%). A statistically significant difference was observed between the complaints and medical treatment history for the existing complaint in patients recommended for hysterectomy with low hemoglobin levels ( p = 0.011). Discussion This study focuses on the indications for hysterectomy operations performed in our clinic and compares the preferences of the options presented to AI based on patient scenarios created according to these indications. Our study aims to evaluate the potential role and effectiveness of AI in modern medical decision-making processes and to demonstrate how its use in healthcare, especially in complex medical decisions and treatment options. The analyses conducted show that the recommendations of AI are generally consistent with the decisions made by the doctors in our clinic. However, in some cases, it has been observed that AI suggests different treatment options. This suggests that AI's data-driven approach and algorithmic reasoning in the decision-making process could serve as an alternative or complement to the experience and clinical judgment of physicians. It is understood that the suggestions made by AI can support the decision-making processes of doctors and, in some cases, offer alternative perspectives. However, it should also be emphasized that the use of this technology must be integrated in a balanced way with physicians' clinical judgment and patient preferences. Hysterectomy is one of the most commonly performed surgical treatments by gynecologists both in our country and worldwide, and its indications are quite broad. Some of these indications include AUB, uterine leiomyoma, infections, endometriosis, atony, chronic pelvic pain, endometrial hyperplasia/cancer, and uterine prolapse [ 4 ]. Among the consultations to gynecology clinics, complaints related to AUB, HMB, IMB, irregular menstruation, and PMB, are among the most commonly encountered symptoms. The prevalence of these symptoms varies between approximately 11–13% across all age groups [ 5 ]. AUB, which affects approximately 25% of the population, is one of the most common indications for hysterectomy, accounting for about 16% of hysterectomy procedures in the United States [ 6 – 7 ]. In the United States, the lifetime risk of a woman undergoing a hysterectomy is reported to be 45%. Among women who undergo this surgery, 75% are between the ages of 20 and 49, with an average age of 42.7 years [ 8 ]. In our study, the average age of the 87 patients who were recommended for hysterectomy in our clinic was determined to be 48.7 years. With the onset of premenopausal changes after the age of 40, an increase in AUB complaints and, consequently, surgical rates in the 40–52 age range is expected. In our study, 90% of the patients who underwent surgery due to AUB were over 40 years old, which is consistent with the literature. The reasons for these patients' visits to our clinic were: 27% (24 patients) for HMB, 10% (9 patients) for IMB, 31% (27 patients) for irregular menstruation, 20.7% (18 patients) for PMB, and 10% (9 patients) for both HMB and IMB complaints. Of these patients, 41 (47.1%) had previously presented with similar complaints and had received medical treatment. However, due to the persistence of the symptoms, these patients returned for further consultation. When the patients included in the study were examined, it was found that 43 patients (49%) had at least one comorbidity including diabetes mellitus (DM), hypertension (HT), DM + HT, polycystic ovary syndrome (PCOS), obesity, and 35 patients (40%) had a history of at least one previous surgery. The most common tumors in women of reproductive age are uterine leiomyomas. Approximately 20–50% of patients present with symptoms such as AUB, anemia, and pressure-related symptoms [ 9 ]. Medical and interventional treatments are available for symptomatic patients. While hysterectomy is the most effective and definitive treatment, uterine artery embolization is an alternative option for some patients who wish to preserve the uterus [ 10 ]. In our study, according to the PALM-COEIN classification system, leiomyomas were identified as the most common cause of AUB in 61 patients (70%). Leiomyomas are common benign fibromuscular tumors of the myometrium, and they are found in nearly 70% of women of reproductive age [ 11 – 12 ]. The results of a study by Baird et al., which aimed to determine the incidence of uterine fibroids in 1,364 women, support our findings [ 13 ]. In our study, patients with fibroids identified by TVUS were evaluated using AI. AI recommended myomectomy for 9 patients (10%) with AUB and fibroids, medical treatment for 6 patients (6.9%), and hysterectomy for 46 patients (52.9%). It was observed that the patients for whom AI recommended medical treatment had never received medical treatment before. This indicates that AI made decisions by considering the patients' previous treatment histories. On the other hand, 4 of the patients recommended for myomectomy had previously received medical treatment but had not benefited from it, while 5 had never received medical treatment. Among the patients recommended for myomectomy, 3 had type 5, 2 had type 6, and 4 had type 4 fibroids. Notably, patients with type 0, 1, 2, and 3 fibroids were not recommended for myomectomy. The three main factors AI considered when recommending myomectomy were the necessity of preserving the uterus, the patients' age, and the ease of surgical intervention. This shows that AI assessed individual patient needs and their suitability for surgical intervention when determining treatment options. Additionally, this decision-making process highlights the importance of uterine preservation and the need for different treatment strategies based on the type of fibroids. Endometrial biopsy is an important tool for evaluating AUB, malignancy screening, endometrial sampling, and infertility assessment. An endometrial thickness of 4 mm or less has a negative predictive value of over 99% for endometrial cancer, eliminating the need for further testing. In our study, the notation of no endometrial thickness on TVUS was based on measurements of 4 mm or less. According to ACOG guidelines, endometrial sampling is recommended for patients over 45 years old with AUB and for those younger than 45 who have risk factors for endometrial hyperplasia and who either have failed medical treatment or exhibit persistent bleeding symptoms [ 14 – 15 ]. In the study conducted by Vijayaraghavan et al., which examined the endometrial sampling results of 160 patients with menorrhagia complaints, proliferative phase endometrium was observed as the most common histopathological pattern in AUB cases across all age groups, with a prevalence of 35%. The second most common pattern was non-atypical endometrial hyperplasia at 20.6%, followed by secretory phase endometrium at 18.8%. Less frequently observed conditions included atypical endometrial hyperplasia (5.7%), endometrial polyp (4%), and endometrial carcinoma (1.2%) (16). In our study, endometrial biopsies were performed on all patients, revealing proliferative or secretory phase endometrium in 58 patients (66.7%), which is a higher rate than that reported by Vijayaraghavan and colleagues. The prevalence of non-atypical endometrial hyperplasia was found to be 12.6% (11 patients), which is lower than the rate reported in their study. The incidence of atypical endometrial hyperplasia in our cohort was 4.6% (4 patients), while the prevalence of endometrial polyps and endometrial carcinoma was 12.6% (11 patients) and 3.4% (3 patients), respectively. When compared with the findings of Vijayaraghavan and colleagues, our results demonstrate similar histopathological patterns but some variations in proportional distribution. This comparison suggests that, despite employing similar methodologies, differences in patient populations, geographical locations, and other demographic factors may contribute to the observed disparities in outcomes. A more detailed analysis of these variations is crucial for a deeper understanding of endometrial pathologies and for the development of more effective treatment strategies. The prevalence of adenomyosis varies between 5% and 70%, and its association with AUB remains unclear (17). In our study, adenomyosis was suspected based on TVUS findings in 5.7% of patients who underwent surgery for AUB. The lifetime prevalence of endometrial polyps varies between 8% and 35% in the literature, with incidence increasing with age [ 18 ]. In our study, the presence of polyps was detected via TVUS in 14 patients (16.1%). Endometrial sampling results revealed endometrial polyps in 11 patients (12.6%). Among these patients, two were in the postmenopausal period, and the AI recommended hysteroscopy for one and hysterectomy for the other. The fact that the patient recommended for hysteroscopy had not undergone this procedure before demonstrates the AI’s consistency in selecting among available options. For the patient who had previously undergone hysteroscopy, hysterectomy was suggested as a second-line treatment. This finding indicates that the AI considers clinical history in its decision-making process. The AI’s ability to suggest different treatment options despite similar patient histories highlights its capacity to account for the unique circumstances of each case. Premalignant conditions and malignancies are among the significant causes of AUB. The literature reports that the prevalence of endometrial hyperplasia and malignancies is approximately 26% [ 16 ]. In our study, TVUS evaluations of the endometrium identified endometrial hyperplasia in 27 patients (31.1%) and a suspicious mass appearance in 4 patients (4.6%). These findings suggest a higher prevalence of endometrial hyperplasia than generally reported in the literature. Upon reviewing the endometrial biopsy results of patients diagnosed with endometrial hyperplasia, simple (non-atypical) endometrial hyperplasia was observed in 5 patients (5.7%), atypical endometrial hyperplasia in 4 patients (4.6%), and endometrial polyps in 2 patients (2.3%). Additionally, no pathological findings were detected in 16 patients (18.4%). None of the patients with suspicious mass appearances were found to have malignancy. These results emphasize the importance of diagnostic tools such as TVUS and endometrial biopsy in evaluating AUB and highlight their effectiveness in detecting premalignant and malignant conditions. Furthermore, the higher frequency of endometrial hyperplasia and suspicious masses in our study compared to literature reports suggests that regional or demographic factors may contribute to these differences. When examining the co-occurrence rates of organic causes in the PALM-COEIN classification, studies on the malignancy risk of polyps stand out. A systematic review conducted by Anna Uglietti and colleagues, which included data from 48–51 studies covering 35,345 women, determined the prevalence of malignant polyps to be 2.73%. This rate reflects the high heterogeneity observed among the studies. Significant differences were noted in the prevalence of malignant polyps between premenopausal and postmenopausal women. The prevalence was found to be 1.12% in premenopausal women and 4.93% in postmenopausal women. Additionally, the malignancy risk was 5.14% in symptomatic women, whereas it was 1.89% in asymptomatic women [ 19 ]. These findings indicate that the risk of polyp malignancy varies depending on menopausal status and the presence of symptoms. The higher prevalence of malignant polyps in postmenopausal women and symptomatic cases underscores the necessity for more vigilant monitoring and evaluation in these patient groups. These results may serve as a crucial guide in the assessment and treatment planning of AUB cases. In our study, no patients diagnosed with malignancy or atypical endometrial hyperplasia through endometrial biopsy were found to have polyp features on TVUS. This can be considered a limitation of our study and suggests that further large-scale research is needed to investigate this issue in greater detail. The inability to detect polyps via TVUS in cases of malignancy or atypical endometrial hyperplasia raises the possibility that this diagnostic method may have limitations in such cases. Therefore, the importance of comprehensive and multifaceted diagnostic approaches in AUB cases is once again highlighted. Moreover, the AI’s preference for recommending hysterectomy as the first-line option in postmenopausal patients with detected polyps suggests that malignancy screening was a primary consideration in its decision-making process. In our study, a total of 7 patients (%8) were diagnosed with malignancy. Among these patients, 2 (%28) were observed to have accompanying fibroids. This finding may serve as an intriguing indicator of the potential impact of fibroids in malignancy cases. Additionally, in 5 of these patients (%55), hemoglobin (Hb) levels were found to be 6 or below, indicating severe anemia. This condition provides significant insights into the severity of the malignancy and the overall health status of the patients. The term "coagulopathy" is used to refer to systemic hemostatic disorders. These disorders can be detected in 24% of women with HMB, with the most commonly identified disorder being mild Von Willebrand Disease [ 20 ]. This data highlights the significance of coagulopathy disorders' impact on menstrual bleeding problems. In our study, 8 patients (%9,2) who underwent hysterectomy were found to have a history of medication use related to coagulopathy. Of these patients, 5 (%5,7) presented with HMB complaints, and 3 (%3,5) with PMB complaints. Additionally, fibroids were observed in 6 (%6,9) of these patients. This emphasizes the importance of the coexistence of fibroids and coagulopathy disorders. Our study has some limitations. Although AI has access to a broad range of information, it may not incorporate the deep expertise, experience, and patient-specific details required for medical decision-making processes. The detailed and comprehensive presentation of patient histories may be limited. The scope and level of detail of the patient data used in the study may affect the accuracy and generalizability of the results. The absence of factors such as socio-cultural, psychological, and personal preferences in patient histories may influence the outcomes. In the decision-making processes of physicians, individual experience, intuition, and patient interaction play a crucial role. It is challenging for AI to fully replicate or consider these human factors. The AI algorithm and data processing capacity may not fully reflect the complexities of the medical decision-making process. Furthermore, AI algorithms require continuous updates and improvements. The sample size and selection criteria of the study may limit the applicability of the results to the broader medical community. The protection of patients' personal information and compliance with ethical standards during AI use is an important limitation. To increase the accuracy of AI systems in the future, it is important to use more comprehensive and diverse datasets. These datasets could include information such as patient demographics, socio-cultural background, psychological factors, and medical history. AI decision support systems should be developed in a way that better understands and replicates the clinical experience, intuition, and patient interactions of physicians. Research, education, and therapeutic treatment can benefit from well-established and practical AI programs like ChatGPT. The primary issue, however, is the accuracy of the generated data. Plagiarism and inappropriate behavior are concerns that need to be addressed [ 1 ]. Continuous updates and improvements to AI algorithms are critical to better reflect the complexities of medical decision-making processes. Large-scale, multi-center studies with data collected from diverse geographic locations can enhance the generalizability and reliability of AI. To improve the integration of AI-based decision support systems into clinical practices, training and awareness programs for physicians and healthcare workers on the use of these systems can be implemented. Physicians are able to make more comprehensive evaluations by considering patients' individual preferences, cultural, and emotional aspects. These factors in the decision-making processes of doctors can lead to an expansion of indications, which may result in differences between AI suggestions and clinical decisions. Conclusi̇on In this study, a detailed examination was conducted on 87 patients scheduled for hysterectomy at our clinic. The patients' medical histories, demographic information, complaints, previous medical treatment histories, and ultrasonographic findings were analyzed using an AI-based program. Scenarios regarding the patients' conditions were created and presented to the program for evaluation. The program was asked to determine treatment options appropriate for each patient's condition and explain the reasons for its choices. Among the patients for whom hysterectomy was decided by our clinic, 61 patients (71%) were in agreement with the AI program's recommendation for hysterectomy. The AI program preferred myomectomy for 9 patients (10.3%). A detailed review of the patient histories showed that myomectomy could also be a suitable option. The AI program suggested hysteroscopy for 7 patients (8.0%). Although hysteroscopy was a viable option for these patients, hysterectomy appeared to be more appropriate for the current patients. For 3 patients (3.4%), the AI recommended hysterectomy after hysteroscopy. This was interpreted as a feasible decision by our team. This study provides insights into the interaction between AI systems and physicians in medical decision-making processes and the support these systems provide in such processes. The study sheds light on how AI systems can be integrated into medical practices and how this integration can contribute to clinical decision-making. It has demonstrated that AI-based decision support systems can bring an additional dimension to doctors' clinical judgments and can consistently provide responses in complex medical situations. In conclusion, this study can be considered an important step in understanding the future potential of AI applications in the medical field and the impact of this technology on patient care. It is concluded that AI systems, by complementing physicians' experience and clinical judgment, can enhance the quality of patient care and improve the efficiency of healthcare services. Declarations Acknowledgements We thank all the staff of Akdeniz University Hospital. Contributions Saltuk Buğra Arıkan and M. Ilkin Yeral conceived and designed the study. Saltuk Buğra Arıkan, Can Dinç, and Mustafa Özer collected and analysed the data. Saltuk Buğra Arıkan wrote the manuscript, and Saltuk Buğra Arıkan and M. Ilkin Yeral edited the manuscript. All authors reviewed and approved the manuscript. Ethics Approval Approval for the study was obtained from the Akdeniz University Faculty of Medicine Ethics Committee on 10.05.2023 (KAEK-390) Consent to Participate Written informed consent was obtained from all patients. Consent for Publication All authors have read the manuscript and agreed to submit it to Conflict of interest The authors declare no conflicts of interest. Funds No funds were used for this study. Data The data of this study are available at the Department of Gynecology and Obstetrics, Akdeniz University. For the data of this manuscript you may contact Prof. Dr. M. Ilkin YERAL and Dr. Saltuk Buğra Arıkan. E mail adresses are; i̇lki̇nyeraldr@hotmai̇l.com [email protected] References Kleebayoon A, Wiwanitkit V (2023) Artificial intelligence, chatbots, plagiarism and basic honesty: comment. Cell Mol Bioeng 16(2):173–174 Wu JM et al (2007) Hysterectomy rates in the United States, 2003. Obstet Gynecol 110(5):1091–1095 Patel SB, Lam K (2023) ChatGPT: the future of discharge summaries? Lancet Digit Health 5(3):e107–e108 Lefebvre G et al Hysterectomy. SOGC Clinical Practice Guidelines, 2002. 109: pp. 1–12 Selvanathan S, Acharya N, Singhal S (2019) Quality of life after hysterectomy and uterus-sparing hysteroscopic management of abnormal uterine bleeding or heavy menstrual bleeding. J Mid-Life Health 10(2):63 Fraser IS, Langham S, Uhl-Hochgraeber K (2009) Health-related quality of life and economic burden of abnormal uterine bleeding. Expert Rev Obstet Gynecol 4(2):179–189 Merrill RM, Hysterectomy surveillance in the United States (1997), through 2005. Medical science monitor: international medical journal of experimental and clinical research, 2008. 14(1): p. CR24-31 Rock J, Jones H (2005) The Linde’s Operative Gynecology, Tavmergen E. Izmir Guven Kitabevi, Izmir, : pp. 731–755 Vilos GA et al (2015) The management of uterine leiomyomas. J Obstet Gynecol Can 37(2):157–178 Silberzweig JE et al (2016) Management of uterine fibroids: a focus on uterine-sparing interventional techniques. Radiology 280(3):675–692 Whitaker L, Critchley HO (2016) Abnormal uterine bleeding. Best Pract Res Clin Obstet Gynecol 34:54–65 Baird DD et al (2003) High cumulative incidence of uterine leiomyoma in black and white women: ultrasound evidence. Am J Obstet Gynecol 188(1):100–107 Baird DD et al (2003) High cumulative incidence of uterine leiomyoma in black and white women: ultrasound evidence. Am J Obstet Gynecol 188(1):100–107 Obstetricians AC (2012) .o.P.B.G.A.C.o. and Gynecologists, Diagnosis of Abnormal uterine bleeding in reproductive aged women. Pract Bull No 128:197–206 Obstetricians ACo, Gynecologists Diagnosis of abnormal uterine bleeding in reproductive-aged women. Pract Bull, 2012(128): p. 197–206 Vijayaraghavan Sr A et al (2022) A histopathological study of endometrial biopsy samples in abnormal uterine bleeding. Cureus, 14(11) Taran F, Stewart E, Brucker S (2013) Adenomyosis: epidemiology, risk factors, clinical phenotype and surgical and interventional alternatives to hysterectomy. Geburtshilfe Frauenheilkd 73(09):924–931 Salim S et al (2011) Diagnosis and management of endometrial polyps: a critical review of the literature. J Minim Invasive Gynecol 18(5):569–581 Uglietti A et al (2019) The risk of malignancy in uterine polyps: A systematic review and meta-analysis. Eur J Obstet Gynecol Reproductive Biology 237:48–56 Shankar M et al (2004) von Willebrand disease in women with menorrhagia: a systematic review. BJOG: Int J Obstet Gynecol 111(7):734–740 Tables Table 1. Demographic, clinical and laboratory data of patients Mean ± SD N (%) Age 48,71±7,51 N (%) Gravida 1 10 (11,50) 2 37 (42,50) 3 23 (26,40) 4 8 (9.20) 5 and more 6 (6,90) Mode of Delivery Vaginal Delivery 51 (58,60) Cesarean Section 16 (18,40) Vaginal Delivery& Cesarean Section 17 (19,50) Menopausal Status Yes 20 (23,00) No 67 (77,00) Table 2. Chief complaints, family and medical history of the patients. Mean ± SD N (%) Current Chief Complaint IMB 9 (10,30) HMB 24 (27,60) IMB&HMB 8 (9,20) Irregular Menstruation 27 (31,00) PMB 18 (20,70) Medical History of Coexisting Conditions Obesity 12 (13,80) HT 13 (14,90) DM 9 (10,30) PCOS 2 (2,30) NONE 44 (50,60) HT&DM 7 (8,00) HT&DM&Obesity N/A Presence of Breast Cancer Yes 5 (5,70) No 82 (94,30) Use of Tamoxifen Yes 4 (4,60) No 83 (95,40) Family History of Cancer Yes 21 (24,10) No 65 (74,70) If so, what type of cancer Gynecological 13 (14,90) Colon 3 (3,40) Breast 2 (2,30) Other 3 (3,40) Drug Use for Coagulopathy Yes (Anticoagulant) 8 (9,20) No 79 (90,80) Is there a history of medical treatment for the current complaint Yes 41 (47,10) No 46 (52,90) If yes, what type of medical treatment COC 18 (20,70) Hormonal 22 (25,30) LNG-IUD 11 ( 13.8) No 47 (54,00) Has there been any H/S (hysteroscopy) performed for treatment purposes? Yes 21 (24,10) No 66 (75,90) Combined Oral Contraceptive (COC), Diabetes Mellitus (DM), Heavy Menstrual Bleeding (HMB), Hypertension (HT), Intermenstrual Bleeding (IMB), Levonorgestrel-Releasing Intrauterine Device (LNG-IUD), Polycystic Ovary Syndrome (PCOS), Postmenopausal Bleeding (PMB). Table 3. Physical examination and usg findings of the patients. Mean ± SD N (%) TV-USG findings related to the endometrium Irregular Endometrium 18 (20,70) No Endometrial Hyperplasia 38 (43,70) Endometrial Hyperplasia Present 27 (31,10) Suspicious Mass 4 (4,60) Presence of uterine myoma Yes 61 (70,10) No 26 (29,90) Type of myoma (FIGO classification) Type 1 N/A Type 2 4 (4,60) Type 3 7 (8,00) Type 4 7 (8,00) Type 5 21 (24,10) Type 6 11 (12,60) Type 7 3 (3,40) Type 0 3 (3,40) Adenomyozis 5 (5,70) Myoma size 10 16 (18,40) Multiple intramural myoma 12 (13,80) Polip Yes 14 (16,10) No 72 (82,80) Low hemoglobin Yes 30 (34,50) No 57 (65,50) Table 4 . Biopsy findings, treatments and options recommended by AI Mean ± SD N (%) Endometrial biopsy findings Normal 58 (66,70) Endometrial Hyperplasia without atypia 11 (12,60) EIN (+) 4 (4,60) Polip 11 (12,60) Malignity 3 (3,40) Treatments Hysterectomy 87 (100,00) Myomectomy N/A Hysteroscopy N/A Medical Treatment N/A LNG-IUD N/A Follow-up N/A Hysterectomy after hysteroscopy N/A Options recommended by artificial intelligence Hysterectomy 61 (70,10) Myomectomy 9 (10,3) Hysteroscopy 7 (8,00) Medical Treatment 4 (4,60) LNG-IUD 2 (2,30) Follow-up 1 (1,10) Hysterectomy after hysteroscopy 3 (3,40) Table 5. Comparison of Symptoms and Medical Treatments Based on TV-US Myoma Types in Patients for Whom AI Recommended Myomectomy. Treatment = Myomectomy TV-US Myoma Present Medikal Treatment Myoma Type on TV-US N (%) p Symptom Type 2 Type 3 Type 4 Type 5 Type 6 HMB Present 2 (1,60) 1 (0,80) N/A 1 (0,80) 0 (0,80) 0,140 Absent 0 (0,40) 0 (0,20) N/A 0 (0,20) 1 (0,20) Irregular Menstruation Present N/A N/A N/A N/A N/A N/A Absent N/A N/A 1 (1,00) 2 (2,00) 1 (1,00) Table 6 . Comparison of Symptoms, Fibroid Types, and Fibroid Sizes in Patients for Whom AI Recommended Myomectomy Based on TV-US Findings Treatment=Myomectomy Fibroid Presence on TV-US = Present Medical Treatment Fibroid Type Fibroid Size N(%) p Complaint 3-5 cm 5-10 cm > 10 cm Multiple Intramural Fibroids HMB Present Tip 2 2 (2,00) N/A N/A N/A 0,140 Present Tip 3 1 (1,00) N/A N/A N/A Present Tip 5 1 (1,00) N/A N/A N/A Absent Tip 6 N/A N/A 1 (1,00) N/A Irregular Menstruation Absent Tip 4 1 (1,00) N/A N/A N/A N/A Absent Tip 5 N/A 1(1,00) N/A 1 (1,00) Absent Tip 6 N/A N/A 1 (1,00) N/A Table 7. Comparison of Current Symptoms, Medical Treatment History, and TV-US Endometrial Findings in Patients for Whom AI Recommended Hysteroscopy Based on Symptom Status Treatment = Hysteroscopy Medical Treatment History TV-US Endometrial Findings N (%) p Symptom Irregular Endometrium Endometrial Hyperplasia Absent Endometrial Hyperplasia Present HMB Present 0 (0,80) N/A 1 (0,30) 0,083 Absent 3 (2,30) N/A 0 (0,80) Irregular Menstruation Present 1 (1,00) N/A 1 (1,00) N/A PMB Absent N/A 1 (1,00) N/A N/A Table 8 . Comparison of Endometrial Findings and AI-Recommended Treatment Based on Menopausal Status in Patients with Polyps on TV-US TV-US Polyp Presence = Present TV-US Endometrial Findings AI-Recommended Treatment N (%) p Menopausal Status Hysterectomy Hysteroscopy Hysteroscopy Followed by Hysterectomy Present Irregular Endometrium 1 (1,00) N/A N/A N/A Endometrial Hyperplasia Absent 1 (1,00) N/A N/A Suspicious Mass 1 (1,00) N/A N/A Absent Irregular Endometrium 2 (2,70) 2 (1,40) 1 (0,90) 0,778 Endometrial Hyperplasia Absent 1 (0,50) 0 (0,30) 0 (0,20) Endometrial Hyperplasia Present 3 (2,20) 1 (1,10) 0 (0,70) Suspicious Mass 0 (0,50) 0 (0,30) 1 (0,20) Table 9. Comparison of endometrial biopsy and AI-recommended treatment based on menopausal status in patients with polyps on TV-US TV-US Polyp Presence = Present Endometrial Biopsy AI-Recommended Treatment N (%) p Menopausal Status Hysterectomy Hysteroscopy H/S followed by Hysterectomy Present Normal 1 (1,00) N/A N/A N/A EIN (-) 1 (1,00) N/A N/A Polip 1 (1,00) N/A N/A Absent Normal 0 (1,60) 2 (0,80) 1 (0,50) 0,251 EIN (-) 1 (0,50) 0 (0,30) 0 (0,20) Polip 5 (3,80) 1 (1,90) 1 (1,30) Table 10. Comparison of fibroid presence and medical treatment history for the current complaint in patients recommended for hysterectomy with normal endometrial biopsy and EIN (-) Treatment = Hysterectomy TV-US Fibroid Presence Current Complaint Medical Treatment History N (%) p Endometrial Biopsy Present Absent Normal Present 15 (14,70) 19 (19,30) 0,721 Absent 1 (1,30) 2 (1,70) EIN (-) Present 0 (0,40) 1 (0,60) 0,321 Absent 4 (3,60) 4 (4,40) Table 11. Comparison of fibroid type and history of medical treatment for existing complaints in patients with normal endometrial biopsy and EIN (-) who were recommended for hysterectomy Treatment = Hysterectomy Fibroid Type on TV-US History of Medical Treatment for Existing Complaint N (%) p Endometrial Biopsy Present Absent Normal Type 2 0 (0,40) 1 (0,60) 0,442 Type 3 1 (1,80) 3 (2,20) Type 4 2 (1,30) 1 (1,70) Type 5 6 (4,90) 5 (6,10) Type 6 2 (2,60) 4 (3,40) Type 7 0 (1,30) 3 (1,70) Type 0 1 (0,90) 1 (1,10) Adenomyotic 3 (1,80) 1 (2,20) EIN (-) Type 6 N/A 1 (1,00) N/A Table 12. Comparison of complaints and medical treatment history for existing complaints in patients with hemoglobin deficiency recommended for hysterectomy Treatment = Hysterectomy Hemoglobin Deficiency = Present Medical Treatment History for Existing Complaint N (%) p Complaint Present Absent IMB 3 (2,30) 1 (1,70) 0,011 HMB 6 (4,60) 2 (3,40) HMB&IMB 2 (1,10) 0 (0,90) Irregular Menstruation 1 (1,10) 1 (1,90) PMK 0 (2,90) 5 (2,10) Additional Declarations The authors declare no competing interests. Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-6260219","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":430963458,"identity":"746e28b7-daee-4ac3-8167-67d48baa9f16","order_by":0,"name":"Saltuk Buğra Arıkan","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABCklEQVRIiWNgGAWjYDCCAyCigIFBQgLMtUkAUwkFhLQYGMC0pCUwsIG0GBCv5TBECwMeLXy3DzB/+GHwJ3Hm7B7j1xU15/P45bsTPzwwYJDnFzuAVYvkuQQ2yR4Dg8TZMmfMLM8cu10s2ca7WQLoMMOZsxOwajE4A3QID1DLPIkcM8MGttuJG47xbgBpSTC4jVML88c/cC3/zoG0bP5BQAuDNMiW2RI5xg8b2w6AtGzDa4sk0GHSMgbGxjPnHCtjbOxLTpzZlrvNIsFAAqdf+EAOe1MhJzvjdvPmjw3f7BL7mc9uvvmjwkaeXxq7FgYG/g8wFpsEkrAEFqWYgPkDYTWjYBSMglEwEgEAazxfQAWmtyMAAAAASUVORK5CYII=","orcid":"https://orcid.org/0009-0003-8177-6774","institution":"akdeniz university","correspondingAuthor":true,"prefix":"","firstName":"Saltuk","middleName":"Buğra","lastName":"Arıkan","suffix":""},{"id":430963459,"identity":"f61252ec-4c02-41df-93e2-e573f1791da0","order_by":1,"name":"can dinç","email":"","orcid":"https://orcid.org/0000-0002-0634-9276","institution":"akdeniz university","correspondingAuthor":false,"prefix":"","firstName":"can","middleName":"","lastName":"dinç","suffix":""},{"id":430963460,"identity":"c9169e7f-560b-473d-9215-bd88ab36195d","order_by":2,"name":"Mustafa Özer","email":"","orcid":"https://orcid.org/0009-0000-5628-7854","institution":"akdeniz university","correspondingAuthor":false,"prefix":"","firstName":"Mustafa","middleName":"","lastName":"Özer","suffix":""},{"id":430963461,"identity":"5c41c573-63b9-42c9-bc68-7c54f3b2b40e","order_by":3,"name":"M. Ilkin Yeral","email":"","orcid":"https://orcid.org/0000-0001-8987-1336","institution":"akdeniz university","correspondingAuthor":false,"prefix":"","firstName":"M.","middleName":"Ilkin","lastName":"Yeral","suffix":""}],"badges":[],"createdAt":"2025-03-19 09:52:07","currentVersionCode":1,"declarations":{"humanSubjects":true,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":true,"humanSubjectConsent":true,"humanSubjectClinicalTrial":true,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-6260219/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6260219/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":78874807,"identity":"2883287a-4435-426d-8a65-6a593bf64e21","added_by":"auto","created_at":"2025-03-20 06:56:13","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":844696,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6260219/v1/b358926a-428c-4f4a-8c6d-63788c0bfb9d.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003e\u003cstrong\u003eComparison of Indications for Hysterectomy in Our Clinic With Recommendations of the Artificial Intelligence Program\u003c/strong\u003e\u003c/p\u003e","fulltext":[{"header":"Introduction","content":"\u003cp\u003eArtificial intelligence (AI) has rapidly become an integral and evolving part of contemporary medical practices [\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e]. The role of AI in clinical decision-making processes offers significant opportunities for both physicians and patients. This study aims to compare and analyze the recommendations of the AI program ChatGPT with clinical indications for patients scheduled for hysterectomy at Akdeniz University\u0026rsquo;s Gynecology and Obstetrics Clinic. Hysterectomy is a commonly performed procedure in gynecological surgery with various indications [\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e]. In this context, evaluating the potential and limitations of AI in this field holds significant importance for modern medical practice.\u003c/p\u003e \u003cp\u003eAI systems are designed to identify patterns, trends, and insights from large datasets, detect inefficiencies, or predict future outcomes based on chronological trends. Unlike other data science applications, an important feature of these systems is their ability to re-balance and demonstrate sustainable learning when exposed to new datasets. In response to the rapidly increasing data volume in the evolving healthcare system and technologies, AI applications have begun to be used in various medical practices. How this technology can be integrated into medical decision-making processes and its contribution to clinical applications has become a growing area of interest.\u003c/p\u003e \u003cp\u003eThis research is based on scenarios where detailed anamnesis of patients scheduled for hysterectomy in our clinic are presented to the AI program ChatGPT, which then chooses one of the treatment options. The aim of this study is to thoroughly analyze ChatGPT's success in evaluating hysterectomy indications and its alignment with clinical decisions. The study aims to investigate how effective and reliable AI-based systems can be in clinical decision-making processes and how these technologies can be integrated into existing medical practices. AI systems can process large datasets quickly and efficiently, evaluate a patient\u0026rsquo;s condition using the most up-to-date information from the literature, and provide potential treatment options. However, to understand the role of AI in clinical applications, it is necessary to compare and analyze AI's recommendations with real-world data [\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eAnother important aspect of this study is to examine the extent and potential limitations of AI's contribution to clinical decision-making processes. The results of the study can provide valuable insights into the future use of AI in the medical field and help shape the direction of technological advancements in this area.\u003c/p\u003e"},{"header":"Materials And Methods","content":"\u003cp\u003eBetween June 1, 2023, and November 1, 2023, a total of 87 patients aged 40\u0026ndash;65, who were scheduled for hysterectomy at Akdeniz University's Gynecology and Obstetrics Clinic, were included in this study. The patients' anamneses and detailed information were systematically collected and evaluated by our clinic's research assistants. The obtained data were then provided to the AI program, which was tasked with interpreting this information, taking into account each patient's medical condition and the current literature, in order to develop the most appropriate option for each patient's scenario. The AI program was also asked to provide a rationale for its recommendations. The study was initiated with the ethical approval of the Akdeniz University Faculty of Medicine Clinical Research Ethics Committee, dated May 10, 2023, with the approval number KAEK-390.\u003c/p\u003e \u003cdiv id=\"Sec3\" class=\"Section2\"\u003e \u003ch2\u003eAllocation And Sample Size Estimation\u003c/h2\u003e \u003cp\u003eBetween June 1, 2023, and November 1, 2023, a total of 87 patients aged 40\u0026ndash;65, who presented with abnormal uterine bleeding (AUB) and were scheduled for hysterectomy at Akdeniz University's Gynecology and Obstetrics Clinic, were included in this study. We chose our patients by time. Our study is a comparative prospective study.\u003c/p\u003e \u003c/div\u003e\n\u003ch3\u003eProcedures\u003c/h3\u003e\n\u003cp\u003eIn this study, we utilized the ChatGPT-4 model developed by OpenAI. As the fourth iteration of the GPT series, this model has been trained on extensive textual data and possesses natural language processing capabilities. ChatGPT can comprehend text-based inputs and generate human-like responses in natural language. For our study, the model was trained using deep learning techniques with information obtained from a broad medical literature database, thereby acquiring a comprehensive understanding of medical terminology, disease symptoms, diagnostic methods, and treatment options.\u003c/p\u003e \u003cp\u003eThe patient scenarios used in this study encompass various clinical details to construct comprehensive patient histories. These details include the patient's age, number of pregnancies, mode of delivery, menopausal status, current complaints, medical history, past surgical interventions, medications used, coexisting conditions, prior medical or surgical treatments for current complaints, history of breast cancer, family history of cancer, transvaginal ultrasound findings (e.g., presence, type, and size of fibroids, endometrial characteristics), laboratory results, pathology findings, and options presented to the AI system.\u003c/p\u003e \u003cp\u003eBased on these constructed scenarios, the AI program was presented with various treatment options, including hysterectomy, myomectomy, hysteroscopy, medical management with follow-up, levonorgestrel releasing intrauterine device (LNG-IUD) application, and hysterectomy following hysteroscopy. The AI program was tasked with selecting the most appropriate option among these choices and providing a rationale supported by relevant scientific sources.\u003c/p\u003e \u003cdiv id=\"Sec5\" class=\"Section2\"\u003e \u003ch2\u003eStatistical analysis\u003c/h2\u003e \u003cp\u003eThe data were analyzed using IBM SPSS Statistics 23.0 (IBM Corp. Released 2015. IBM SPSS Statistics for Windows, Version 23.0. Armonk, NY: IBM Corp.). Continuous data were reported as Mean\u0026thinsp;\u0026plusmn;\u0026thinsp;Standard Deviation, while categorical data were presented as percentages (%). The normality of the data was assessed using the Shapiro-Wilk test, revealing that the data did not follow a normal distribution. Cross-tabulation analyses were conducted using Pearson's Chi-square and Pearson's Exact Chi-square tests. A significance level of \u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.05 was adopted to determine statistical significance.\u003c/p\u003e \u003c/div\u003e"},{"header":"Results","content":"\u003cp\u003eIn the study, demographic data and histories of 87 women who were followed and underwent surgical interventions were analyzed. The demographic, clinical, and laboratory data of the patients are shown in Table\u0026nbsp;1.\u003c/p\u003e \u003cp\u003eThe average age of the participants was found to be 48.71 years. Previous pregnancy history reveals that the most common condition among the studied patients was that 37 patients (42.50%) had experienced two pregnancies, and 51 patients (58.60%) had undergone vaginal delivery. Regarding menopausal status, 67 participants (77.00%) were found not to be in menopause.\u003c/p\u003e \u003cp\u003eThe chief complaints, family history, and medical history of the patients are shown in Table\u0026nbsp;2.\u003c/p\u003e \u003cp\u003eThe most common complaints included irregular menstruation (31.00%) and heavy menstrual bleeding (HMB) (27.60%). Other frequent complaints included pelvic mass (20.70%), intermenstrual bleeding (IMB) (10.30%), and IMB with HMB (9.20%).\u003c/p\u003e \u003cp\u003eIn terms of additional medical history, 44 individuals (50.60%) did not have any additional diseases. The most frequently encountered additional conditions were hypertension (HT) (14.90%) and obesity (13.80%). Polycystic ovary syndrome (PCOS) was observed in only 2 patients (2.30%).\u003c/p\u003e \u003cp\u003eAmong the patients, 82 (94.30%) did not have a history of breast cancer, and 83 (95.40%) were not using tamoxifen. Among the 21 patients (24.10%) with a family history of cancer, gynecological cancer predominated in 13 patients (14.90%), while colon and other cancer types were present in 3 patients (3.40%), and breast cancer history was observed in 2 patients (2.30%).\u003c/p\u003e \u003cp\u003eAdditionally, 41 patients (47.10%) had previously received medical treatment for their current complaints. When examining the types of medical treatments previously received for their current complaints, it was found that 22 patients (25.30%) had undergone hormone therapy, and 18 patients (20.70%) had received Combined Oral Contraceptive (COC) therapy. Additionally, 11 patients (13.80%) had received Levonorgestrel Intrauterine Device (LNG- IUD) therapy. A total of 35 patients (40.20%) had undergone abdominal surgery in the past, with 25 of these surgeries (28.70%) being laparotomies. The number of patients who underwent hysterectomy/salpingectomy for therapeutic purposes was 21 (24.10%).\u003c/p\u003e \u003cp\u003eThe physical examination and ultrasonography findings of the patients are shown in Table\u0026nbsp;3.\u003c/p\u003e \u003cp\u003eRegarding transvaginal ultrasound (TV-US) findings: 38 patients (43.70%) did not have Endometrial Hyperplasia, 27 patients (31.10%) had Endometrial Hyperplasia, 18 patients (20.70%) had Irregular Endometrium, 4 patients (4.60%) had Suspicious Masses.\u003c/p\u003e \u003cp\u003eIn 61 patients (70.10%), the presence of myomas was observed, with Type 5 myoma being the most common at 24.10%. The distribution of other myoma types was as follows: Type 6 myoma in 11 patients (12.60%), Type 3 and Type 4 myomas in 7 patients each (8.00%), adenomyotic appearance in 5 patients (5.70%), Type 2 myoma in 4 patients (4.60%), and Type 7 and Type 0 myomas in 3 patients each (3.40%). Type 1 myoma was not observed in any patient.\u003c/p\u003e \u003cp\u003eThe most frequently observed myoma size was 10 cm and above in 16 patients (18.40%), followed by sizes ranging from 3\u0026ndash;5 cm in 16 patients (18.40%). Other observed myoma sizes included 5\u0026ndash;10 cm in 15 patients (17.20%), multiple intramural myomas in 12 patients (13.80%), and less than 3 cm in 2 patients (2.30%).\u003c/p\u003e \u003cp\u003eAmong the patients, polyp presence was suspected in 14 (16.20%) based on transvaginal ultrasound (TVUS). Anemia (Hb deficiency) was detected in 30 patients (34.50%).\u003c/p\u003e \u003cp\u003eThe biopsy findings and treatments options recommended by AI are shown in Table\u0026nbsp;4.\u003c/p\u003e \u003cp\u003eFollowing endometrial biopsy, pathological findings revealed that 58 patients (66.70%) mostly had normal endometrial biopsies. Other findings included 11 patients (12.60%) with EIN (-) and polyps, 4 patients (4.60%) with EIN (+), and malignancy in 3 patients (3.40%).\u003c/p\u003e \u003cp\u003eWhen the conditions of 87 patients who underwent hysterectomy were evaluated by artificial intelligence (AI), it was seen that hysterectomy was recommended for 61 patients (70.10%). Other recommended treatment methods were preferred less frequently; Myomectomy was offered for 9 patients (10.30%), hysteroscopy for 7 patients (8.00%), and medical treatment for 4 patients (4.60%). Additionally, hysterectomy after hysteroscopy was recommended for 3 patients (3.40%), LNG-IUD use was recommended for 2 patients (2.30%), and follow-up was recommended for only 1 patient (1.10%).\u003c/p\u003e \u003cp\u003eComparison of Symptoms and Medical Treatments Based on TV-US Myoma Types in Patients for Whom AI Recommended Myomectomy are shown in Table\u0026nbsp;5.\u003c/p\u003e \u003cp\u003eThe presence and types of fibroids were evaluated using transvaginal ultrasonography (TV-US) in nine patients for whom AI recommended myomectomy, based on their abnormal uterine bleeding (AUB) complaints and medical treatment histories. Among patients with heavy menstrual bleeding (HMB) who had received treatment but showed no improvement and had fibroids, 2 patients (1.60%) had type 2 fibroids, 1 patient (0.80%) had a type 3 fibroid, and 1 patient (0.80%) had a type 5 fibroid. In contrast, among patients with HMB who had no prior treatment history, 1 patient (0.20%) had a type 6 fibroid. Among 4 patients with irregular menstruation and no history of medical treatment, 2 patients (2.00%) had type 5 fibroids, while 1 had a type 4 fibroid and another had a type 6 fibroid.\u003c/p\u003e \u003cp\u003eComparison of symptoms, fibroid types, and fibroid sizes in patients for whom AI recommended myomectomy based on tv-us findings are shown in Table\u0026nbsp;6.\u003c/p\u003e \u003cp\u003eThe fibroid types and sizes were evaluated using TV-US in nine patients for whom AI recommended myomectomy, based on their AUB complaints and medical treatment histories. All nine patients for whom myomectomy was recommended were found to have fibroids on TV-US. Among patients with HMB who had received treatment but showed no improvement, 2 patients (2.00%) with type 2 fibroids had fibroid sizes between 3\u0026ndash;5 cm, 1 patient (1.00%) with a type 3 fibroid had a fibroid size between 3\u0026ndash;5 cm, and 1 patient (1.00%) with a type 5 fibroid had a fibroid size between 3\u0026ndash;5 cm. Among patients with HMB who had no prior treatment history, 1 patient (1.00%) with a type 6 fibroid had a fibroid size larger than 10 cm. Among four patients with irregular menstruation and no history of medical treatment, 2 patients (2.00%) with type 5 fibroids had different fibroid characteristics: one had a fibroid size between 5\u0026ndash;10 cm, while the other had multiple intramural fibroids. Additionally, 1 patient (1.00%) with a type 4 fibroid had a fibroid size between 3\u0026ndash;5 cm, and 1 patient (1.00%) with a type 6 fibroid had a fibroid size larger than 10 cm.\u003c/p\u003e \u003cp\u003eComparison of current symptoms, medical treatment history, and TV-US endometrial findings in patients for whom AI recommended hysteroscopy based on symptom status are shown in Table\u0026nbsp;7.\u003c/p\u003e \u003cp\u003eThe patients with AUB for whom AI recommended hysteroscopy were examined based on their medical treatment histories and endometrial findings, and 7 patients were identified. Among the 4 patients who presented with HMB, 1 patient (0.30%) had a medical treatment history for the current complaint and was found to have endometrial hyperplasia. The other 3 patients (2.30%) had no medical treatment history for the current complaint, but irregular endometrium was observed in their TV-US findings. Among the 2 patients with irregular menstruation, both had a medical treatment history for the current complaint. Upon examining their endometrial findings, 1 patient had irregular endometrium, and the other had endometrial hyperplasia. The patient presenting with PMB had no medical treatment history or endometrial hyperplasia for the current complaint.\u003c/p\u003e \u003cp\u003eComparison of endometrial findings and AI-recommended treatment based on menopausal status in patients with polyps on TV-US are shown in Table\u0026nbsp;8.\u003c/p\u003e \u003cp\u003eIn patients with polyps on TV-US, the endometrial findings and AI-recommended treatment methods were examined according to menopausal status. Among the patients, 3 were postmenopausal and 11 were premenopausal. In postmenopausal patients, with endometrial findings of irregular endometrium, absence of endometrial hyperplasia, and presence of a suspicious mass, AI recommended hysterectomy. In premenopausal patients, AI recommended hysterectomy for 2 patients (2.70%) with irregular endometrium, hysteroscopy for 2 patients (1.40%), and hysteroscopy followed by hysterectomy for 1 patient (0.90%). For the patient without endometrial hyperplasia, hysterectomy was recommended for 1 patient (0.50%), while among the 4 patients with endometrial hyperplasia, hysterectomy was recommended for 3 patients (2.20%), and hysteroscopy for 1 patient (1.10%). For 1 patient (0.20%) with a suspicious mass, hysteroscopy followed by hysterectomy was recommended.\u003c/p\u003e \u003cp\u003eComparison of endometrial biopsy and AI-recommended treatment based on menopausal status in patients with polyps on TV-US are shown in Table\u0026nbsp;9.\u003c/p\u003e \u003cp\u003eIn patients with polyps on TV-US, the endometrial biopsy and AI-recommended treatment methods were examined based on menopausal status. In postmenopausal patients, AI recommended hysterectomy for one patient with a normal endometrial biopsy, one with EIN (-), and one with a polyp. In premenopausal patients, AI recommended hysteroscopy for 2 patients (2.70%) with a normal endometrial biopsy, and hysteroscopy followed by hysterectomy for 1 patient (1.50%). For patients with EIN (-) on endometrial biopsy, hysterectomy was recommended for 1 patient (0.50%), while for 5 patients with a polyp on endometrial biopsy, hysterectomy was recommended for 3 patients (3.80%), hysteroscopy for 1 patient (1.90%), and hysteroscopy followed by hysterectomy for 1 patient (1.30%).\u003c/p\u003e \u003cp\u003eComparison of fibroid presence and medical treatment history for the current complaint in patients recommended for hysterectomy with normal endometrial biopsy and Endometrial Intraepithelial Neoplasia (EIN) (-) are shown in Table\u0026nbsp;10.\u003c/p\u003e \u003cp\u003eThe comparison was made between the presence of fibroids and the medical treatment history for the current complaint in patients for whom AI recommended hysterectomy, with normal endometrial biopsy and EIN (-). Among patients with a normal endometrial biopsy and fibroids, 15 (14.70%) had a medical treatment history for the current complaint, while 19 (19.30%) did not. Among patients with a normal endometrial biopsy and no fibroids, 1 (1.30%) had a medical treatment history for the current complaint, while 2 (1.70%) did not. For patients with EIN (-) and fibroids, 1 patient was found, and this patient did not have a medical treatment history for the current complaint. Among patients with EIN (-) and no fibroids, 4 (3.60%) had a medical treatment history for the current complaint, while 4 (4.40%) did not have a medical treatment history.\u003c/p\u003e \u003cp\u003eComparison of fibroid type and history of medical treatment for existing complaints in patients with normal endometrial biopsy and EIN (-) who were recommended for hysterectomy are shown in Table\u0026nbsp;11.\u003c/p\u003e \u003cp\u003eThe history of medical treatment for the existing complaint was compared according to the fibroid type in patients for whom AI recommended hysterectomy and whose endometrial biopsy results were normal and EIN (-). Among the patients for whom AI recommended hysterectomy, 1 patient (1.80%) with a normal endometrial biopsy and fibroid type 3 had a history of medical treatment for the existing complaint, while three patients (2.20%) did not. Among patients with fibroid type 4, two (1.30%) had a history of medical treatment for the existing complaint, whereas 1 patient (1.70%) did not. Among patients with fibroid type 5, 6 (4.90%) had a history of medical treatment, while 5 (6.10%) did not. Among patients with fibroid type 6, 2 (2.60%) had a history of medical treatment, whereas 4 (3.40%) did not. Among patients with fibroid type 7, 3 (1.70%) did not have a history of medical treatment. In patients with type 0 fibroids, 1 (0.90%) had a history of medical treatment for the existing complaint, while 1 patient (1.10%) did not. Regarding the adenomyotic fibroid type, 3 patients (1.80%) had a history of medical treatment, while 1 (2.20%) did not. Additionally, 1 patient (1.00%) with an EIN (-) endometrial biopsy was identified, and their fibroid type was classified as type 6. Furthermore, this patient had no history of medical treatment for the existing complaint.\u003c/p\u003e \u003cp\u003eComparison of complaints and medical treatment history for existing complaints in patients with hemoglobin deficiency recommended for hysterectomy are shown in Table\u0026nbsp;12.\u003c/p\u003e \u003cp\u003eIt was observed that 21 patients were recommended for hysterectomy and had low hemoglobin levels. The patients' AUB complaints and medical treatment history for the existing complaint were compared. Among the 4 patients with IMB complaints, 3 (2.30%) had a history of medical treatment for the existing complaint, while 1 (1.70%) did not. Among the 8 patients presenting with HMB complaints, 6 (4.60%) had a history of medical treatment for the existing complaint, while 2 (3.40%) did not. Only two patients presented with both HMB \u0026amp; IMB complaints, and both of these patients had a history of medical treatment for the existing complaint. Among the 2 patients with irregular menstruation complaints, 1 (1.10%) had a history of medical treatment, while 1 (1.90%) did not. None of the 5 patients presenting with postmenopausal bleeding (PMB) complaints had a history of medical treatment for the existing complaint (2.10%). A statistically significant difference was observed between the complaints and medical treatment history for the existing complaint in patients recommended for hysterectomy with low hemoglobin levels (\u003cem\u003ep\u003c/em\u003e\u0026thinsp;=\u0026thinsp;0.011).\u003c/p\u003e"},{"header":"Discussion","content":"\u003cp\u003eThis study focuses on the indications for hysterectomy operations performed in our clinic and compares the preferences of the options presented to AI based on patient scenarios created according to these indications. Our study aims to evaluate the potential role and effectiveness of AI in modern medical decision-making processes and to demonstrate how its use in healthcare, especially in complex medical decisions and treatment options. The analyses conducted show that the recommendations of AI are generally consistent with the decisions made by the doctors in our clinic. However, in some cases, it has been observed that AI suggests different treatment options. This suggests that AI's data-driven approach and algorithmic reasoning in the decision-making process could serve as an alternative or complement to the experience and clinical judgment of physicians. It is understood that the suggestions made by AI can support the decision-making processes of doctors and, in some cases, offer alternative perspectives. However, it should also be emphasized that the use of this technology must be integrated in a balanced way with physicians' clinical judgment and patient preferences.\u003c/p\u003e \u003cp\u003eHysterectomy is one of the most commonly performed surgical treatments by gynecologists both in our country and worldwide, and its indications are quite broad. Some of these indications include AUB, uterine leiomyoma, infections, endometriosis, atony, chronic pelvic pain, endometrial hyperplasia/cancer, and uterine prolapse [\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eAmong the consultations to gynecology clinics, complaints related to AUB, HMB, IMB, irregular menstruation, and PMB, are among the most commonly encountered symptoms. The prevalence of these symptoms varies between approximately 11\u0026ndash;13% across all age groups [\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e]. AUB, which affects approximately 25% of the population, is one of the most common indications for hysterectomy, accounting for about 16% of hysterectomy procedures in the United States [\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e]. In the United States, the lifetime risk of a woman undergoing a hysterectomy is reported to be 45%. Among women who undergo this surgery, 75% are between the ages of 20 and 49, with an average age of 42.7 years [\u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e]. In our study, the average age of the 87 patients who were recommended for hysterectomy in our clinic was determined to be 48.7 years. With the onset of premenopausal changes after the age of 40, an increase in AUB complaints and, consequently, surgical rates in the 40\u0026ndash;52 age range is expected. In our study, 90% of the patients who underwent surgery due to AUB were over 40 years old, which is consistent with the literature. The reasons for these patients' visits to our clinic were: 27% (24 patients) for HMB, 10% (9 patients) for IMB, 31% (27 patients) for irregular menstruation, 20.7% (18 patients) for PMB, and 10% (9 patients) for both HMB and IMB complaints. Of these patients, 41 (47.1%) had previously presented with similar complaints and had received medical treatment. However, due to the persistence of the symptoms, these patients returned for further consultation.\u003c/p\u003e \u003cp\u003eWhen the patients included in the study were examined, it was found that 43 patients (49%) had at least one comorbidity including diabetes mellitus (DM), hypertension (HT), DM\u0026thinsp;+\u0026thinsp;HT, polycystic ovary syndrome (PCOS), obesity, and 35 patients (40%) had a history of at least one previous surgery.\u003c/p\u003e \u003cp\u003eThe most common tumors in women of reproductive age are uterine leiomyomas. Approximately 20\u0026ndash;50% of patients present with symptoms such as AUB, anemia, and pressure-related symptoms [\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eMedical and interventional treatments are available for symptomatic patients. While hysterectomy is the most effective and definitive treatment, uterine artery embolization is an alternative option for some patients who wish to preserve the uterus [\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e]. In our study, according to the PALM-COEIN classification system, leiomyomas were identified as the most common cause of AUB in 61 patients (70%). Leiomyomas are common benign fibromuscular tumors of the myometrium, and they are found in nearly 70% of women of reproductive age [\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e]. The results of a study by Baird et al., which aimed to determine the incidence of uterine fibroids in 1,364 women, support our findings [\u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e]. In our study, patients with fibroids identified by TVUS were evaluated using AI. AI recommended myomectomy for 9 patients (10%) with AUB and fibroids, medical treatment for 6 patients (6.9%), and hysterectomy for 46 patients (52.9%). It was observed that the patients for whom AI recommended medical treatment had never received medical treatment before. This indicates that AI made decisions by considering the patients' previous treatment histories. On the other hand, 4 of the patients recommended for myomectomy had previously received medical treatment but had not benefited from it, while 5 had never received medical treatment. Among the patients recommended for myomectomy, 3 had type 5, 2 had type 6, and 4 had type 4 fibroids. Notably, patients with type 0, 1, 2, and 3 fibroids were not recommended for myomectomy. The three main factors AI considered when recommending myomectomy were the necessity of preserving the uterus, the patients' age, and the ease of surgical intervention. This shows that AI assessed individual patient needs and their suitability for surgical intervention when determining treatment options. Additionally, this decision-making process highlights the importance of uterine preservation and the need for different treatment strategies based on the type of fibroids.\u003c/p\u003e \u003cp\u003eEndometrial biopsy is an important tool for evaluating AUB, malignancy screening, endometrial sampling, and infertility assessment. An endometrial thickness of 4 mm or less has a negative predictive value of over 99% for endometrial cancer, eliminating the need for further testing. In our study, the notation of no endometrial thickness on TVUS was based on measurements of 4 mm or less. According to ACOG guidelines, endometrial sampling is recommended for patients over 45 years old with AUB and for those younger than 45 who have risk factors for endometrial hyperplasia and who either have failed medical treatment or exhibit persistent bleeding symptoms [\u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eIn the study conducted by Vijayaraghavan et al., which examined the endometrial sampling results of 160 patients with menorrhagia complaints, proliferative phase endometrium was observed as the most common histopathological pattern in AUB cases across all age groups, with a prevalence of 35%. The second most common pattern was non-atypical endometrial hyperplasia at 20.6%, followed by secretory phase endometrium at 18.8%. Less frequently observed conditions included atypical endometrial hyperplasia (5.7%), endometrial polyp (4%), and endometrial carcinoma (1.2%) (16). In our study, endometrial biopsies were performed on all patients, revealing proliferative or secretory phase endometrium in 58 patients (66.7%), which is a higher rate than that reported by Vijayaraghavan and colleagues. The prevalence of non-atypical endometrial hyperplasia was found to be 12.6% (11 patients), which is lower than the rate reported in their study. The incidence of atypical endometrial hyperplasia in our cohort was 4.6% (4 patients), while the prevalence of endometrial polyps and endometrial carcinoma was 12.6% (11 patients) and 3.4% (3 patients), respectively.\u003c/p\u003e \u003cp\u003eWhen compared with the findings of Vijayaraghavan and colleagues, our results demonstrate similar histopathological patterns but some variations in proportional distribution. This comparison suggests that, despite employing similar methodologies, differences in patient populations, geographical locations, and other demographic factors may contribute to the observed disparities in outcomes. A more detailed analysis of these variations is crucial for a deeper understanding of endometrial pathologies and for the development of more effective treatment strategies.\u003c/p\u003e \u003cp\u003eThe prevalence of adenomyosis varies between 5% and 70%, and its association with AUB remains unclear (17). In our study, adenomyosis was suspected based on TVUS findings in 5.7% of patients who underwent surgery for AUB.\u003c/p\u003e \u003cp\u003eThe lifetime prevalence of endometrial polyps varies between 8% and 35% in the literature, with incidence increasing with age [\u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e]. In our study, the presence of polyps was detected via TVUS in 14 patients (16.1%). Endometrial sampling results revealed endometrial polyps in 11 patients (12.6%). Among these patients, two were in the postmenopausal period, and the AI recommended hysteroscopy for one and hysterectomy for the other. The fact that the patient recommended for hysteroscopy had not undergone this procedure before demonstrates the AI\u0026rsquo;s consistency in selecting among available options. For the patient who had previously undergone hysteroscopy, hysterectomy was suggested as a second-line treatment. This finding indicates that the AI considers clinical history in its decision-making process. The AI\u0026rsquo;s ability to suggest different treatment options despite similar patient histories highlights its capacity to account for the unique circumstances of each case.\u003c/p\u003e \u003cp\u003ePremalignant conditions and malignancies are among the significant causes of AUB. The literature reports that the prevalence of endometrial hyperplasia and malignancies is approximately 26% [\u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e]. In our study, TVUS evaluations of the endometrium identified endometrial hyperplasia in 27 patients (31.1%) and a suspicious mass appearance in 4 patients (4.6%). These findings suggest a higher prevalence of endometrial hyperplasia than generally reported in the literature. Upon reviewing the endometrial biopsy results of patients diagnosed with endometrial hyperplasia, simple (non-atypical) endometrial hyperplasia was observed in 5 patients (5.7%), atypical endometrial hyperplasia in 4 patients (4.6%), and endometrial polyps in 2 patients (2.3%). Additionally, no pathological findings were detected in 16 patients (18.4%). None of the patients with suspicious mass appearances were found to have malignancy.\u003c/p\u003e \u003cp\u003eThese results emphasize the importance of diagnostic tools such as TVUS and endometrial biopsy in evaluating AUB and highlight their effectiveness in detecting premalignant and malignant conditions. Furthermore, the higher frequency of endometrial hyperplasia and suspicious masses in our study compared to literature reports suggests that regional or demographic factors may contribute to these differences.\u003c/p\u003e \u003cp\u003eWhen examining the co-occurrence rates of organic causes in the PALM-COEIN classification, studies on the malignancy risk of polyps stand out. A systematic review conducted by Anna Uglietti and colleagues, which included data from 48\u0026ndash;51 studies covering 35,345 women, determined the prevalence of malignant polyps to be 2.73%. This rate reflects the high heterogeneity observed among the studies. Significant differences were noted in the prevalence of malignant polyps between premenopausal and postmenopausal women. The prevalence was found to be 1.12% in premenopausal women and 4.93% in postmenopausal women. Additionally, the malignancy risk was 5.14% in symptomatic women, whereas it was 1.89% in asymptomatic women [\u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e]. These findings indicate that the risk of polyp malignancy varies depending on menopausal status and the presence of symptoms. The higher prevalence of malignant polyps in postmenopausal women and symptomatic cases underscores the necessity for more vigilant monitoring and evaluation in these patient groups. These results may serve as a crucial guide in the assessment and treatment planning of AUB cases.\u003c/p\u003e \u003cp\u003eIn our study, no patients diagnosed with malignancy or atypical endometrial hyperplasia through endometrial biopsy were found to have polyp features on TVUS. This can be considered a limitation of our study and suggests that further large-scale research is needed to investigate this issue in greater detail. The inability to detect polyps via TVUS in cases of malignancy or atypical endometrial hyperplasia raises the possibility that this diagnostic method may have limitations in such cases. Therefore, the importance of comprehensive and multifaceted diagnostic approaches in AUB cases is once again highlighted.\u003c/p\u003e \u003cp\u003eMoreover, the AI\u0026rsquo;s preference for recommending hysterectomy as the first-line option in postmenopausal patients with detected polyps suggests that malignancy screening was a primary consideration in its decision-making process.\u003c/p\u003e \u003cp\u003eIn our study, a total of 7 patients (%8) were diagnosed with malignancy. Among these patients, 2 (%28) were observed to have accompanying fibroids. This finding may serve as an intriguing indicator of the potential impact of fibroids in malignancy cases. Additionally, in 5 of these patients (%55), hemoglobin (Hb) levels were found to be 6 or below, indicating severe anemia. This condition provides significant insights into the severity of the malignancy and the overall health status of the patients.\u003c/p\u003e \u003cp\u003eThe term \"coagulopathy\" is used to refer to systemic hemostatic disorders. These disorders can be detected in 24% of women with HMB, with the most commonly identified disorder being mild Von Willebrand Disease [\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e]. This data highlights the significance of coagulopathy disorders' impact on menstrual bleeding problems. In our study, 8 patients (%9,2) who underwent hysterectomy were found to have a history of medication use related to coagulopathy. Of these patients, 5 (%5,7) presented with HMB complaints, and 3 (%3,5) with PMB complaints. Additionally, fibroids were observed in 6 (%6,9) of these patients. This emphasizes the importance of the coexistence of fibroids and coagulopathy disorders.\u003c/p\u003e \u003cp\u003eOur study has some limitations. Although AI has access to a broad range of information, it may not incorporate the deep expertise, experience, and patient-specific details required for medical decision-making processes. The detailed and comprehensive presentation of patient histories may be limited. The scope and level of detail of the patient data used in the study may affect the accuracy and generalizability of the results. The absence of factors such as socio-cultural, psychological, and personal preferences in patient histories may influence the outcomes. In the decision-making processes of physicians, individual experience, intuition, and patient interaction play a crucial role. It is challenging for AI to fully replicate or consider these human factors. The AI algorithm and data processing capacity may not fully reflect the complexities of the medical decision-making process. Furthermore, AI algorithms require continuous updates and improvements. The sample size and selection criteria of the study may limit the applicability of the results to the broader medical community. The protection of patients' personal information and compliance with ethical standards during AI use is an important limitation.\u003c/p\u003e \u003cp\u003eTo increase the accuracy of AI systems in the future, it is important to use more comprehensive and diverse datasets. These datasets could include information such as patient demographics, socio-cultural background, psychological factors, and medical history. AI decision support systems should be developed in a way that better understands and replicates the clinical experience, intuition, and patient interactions of physicians. Research, education, and therapeutic treatment can benefit from well-established and practical AI programs like ChatGPT. The primary issue, however, is the accuracy of the generated data. Plagiarism and inappropriate behavior are concerns that need to be addressed [\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e]. Continuous updates and improvements to AI algorithms are critical to better reflect the complexities of medical decision-making processes. Large-scale, multi-center studies with data collected from diverse geographic locations can enhance the generalizability and reliability of AI. To improve the integration of AI-based decision support systems into clinical practices, training and awareness programs for physicians and healthcare workers on the use of these systems can be implemented.\u003c/p\u003e \u003cp\u003ePhysicians are able to make more comprehensive evaluations by considering patients' individual preferences, cultural, and emotional aspects. These factors in the decision-making processes of doctors can lead to an expansion of indications, which may result in differences between AI suggestions and clinical decisions.\u003c/p\u003e"},{"header":"Conclusi̇on","content":"\u003cp\u003eIn this study, a detailed examination was conducted on 87 patients scheduled for hysterectomy at our clinic. The patients' medical histories, demographic information, complaints, previous medical treatment histories, and ultrasonographic findings were analyzed using an AI-based program. Scenarios regarding the patients' conditions were created and presented to the program for evaluation. The program was asked to determine treatment options appropriate for each patient's condition and explain the reasons for its choices. Among the patients for whom hysterectomy was decided by our clinic, 61 patients (71%) were in agreement with the AI program's recommendation for hysterectomy. The AI program preferred myomectomy for 9 patients (10.3%). A detailed review of the patient histories showed that myomectomy could also be a suitable option. The AI program suggested hysteroscopy for 7 patients (8.0%). Although hysteroscopy was a viable option for these patients, hysterectomy appeared to be more appropriate for the current patients. For 3 patients (3.4%), the AI recommended hysterectomy after hysteroscopy. This was interpreted as a feasible decision by our team.\u003c/p\u003e \u003cp\u003eThis study provides insights into the interaction between AI systems and physicians in medical decision-making processes and the support these systems provide in such processes. The study sheds light on how AI systems can be integrated into medical practices and how this integration can contribute to clinical decision-making. It has demonstrated that AI-based decision support systems can bring an additional dimension to doctors' clinical judgments and can consistently provide responses in complex medical situations.\u003c/p\u003e \u003cp\u003eIn conclusion, this study can be considered an important step in understanding the future potential of AI applications in the medical field and the impact of this technology on patient care. It is concluded that AI systems, by complementing physicians' experience and clinical judgment, can enhance the quality of patient care and improve the efficiency of healthcare services.\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003eAcknowledgements\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eWe thank all the staff of Akdeniz University Hospital.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eContributions\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eSaltuk Buğra Arıkan and M. Ilkin Yeral conceived and designed the study. Saltuk Buğra Arıkan,\u0026nbsp;Can Din\u0026ccedil;, and Mustafa \u0026Ouml;zer collected and analysed the data. Saltuk Buğra Arıkan wrote the manuscript, and Saltuk Buğra Arıkan and M. Ilkin Yeral edited the manuscript. All authors reviewed and approved the manuscript.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eEthics Approval\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eApproval for the study was obtained from the Akdeniz University Faculty of Medicine Ethics Committee on 10.05.2023 (KAEK-390)\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConsent to Participate\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eWritten informed consent was obtained from all patients.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConsent for Publication\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eAll authors have read the manuscript and agreed to submit it to\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConflict of interest\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe authors declare no conflicts of interest.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u0026nbsp;Funds\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eNo funds were used for this study.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eData\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe data of this study are available at the Department of Gynecology and Obstetrics, Akdeniz University. For the data of this manuscript you may contact Prof. Dr. M. Ilkin YERAL and Dr. Saltuk Buğra Arıkan. E mail adresses are; i̇lki̇nyeraldr@hotmai̇l.com [email protected]\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003eKleebayoon A, Wiwanitkit V (2023) Artificial intelligence, chatbots, plagiarism and basic honesty: comment. Cell Mol Bioeng 16(2):173\u0026ndash;174\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWu JM et al (2007) Hysterectomy rates in the United States, 2003. Obstet Gynecol 110(5):1091\u0026ndash;1095\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePatel SB, Lam K (2023) ChatGPT: the future of discharge summaries? Lancet Digit Health 5(3):e107\u0026ndash;e108\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLefebvre G et al Hysterectomy. SOGC Clinical Practice Guidelines, 2002. 109: pp. 1\u0026ndash;12\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSelvanathan S, Acharya N, Singhal S (2019) Quality of life after hysterectomy and uterus-sparing hysteroscopic management of abnormal uterine bleeding or heavy menstrual bleeding. J Mid-Life Health 10(2):63\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eFraser IS, Langham S, Uhl-Hochgraeber K (2009) Health-related quality of life and economic burden of abnormal uterine bleeding. Expert Rev Obstet Gynecol 4(2):179\u0026ndash;189\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMerrill RM, Hysterectomy surveillance in the United States (1997), through 2005. Medical science monitor: international medical journal of experimental and clinical research, 2008. 14(1): p. CR24-31\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRock J, Jones H (2005) The Linde\u0026rsquo;s Operative Gynecology, Tavmergen E. Izmir Guven Kitabevi, Izmir, : pp. 731\u0026ndash;755\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eVilos GA et al (2015) The management of uterine leiomyomas. J Obstet Gynecol Can 37(2):157\u0026ndash;178\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSilberzweig JE et al (2016) Management of uterine fibroids: a focus on uterine-sparing interventional techniques. Radiology 280(3):675\u0026ndash;692\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWhitaker L, Critchley HO (2016) Abnormal uterine bleeding. Best Pract Res Clin Obstet Gynecol 34:54\u0026ndash;65\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBaird DD et al (2003) High cumulative incidence of uterine leiomyoma in black and white women: ultrasound evidence. Am J Obstet Gynecol 188(1):100\u0026ndash;107\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBaird DD et al (2003) High cumulative incidence of uterine leiomyoma in black and white women: ultrasound evidence. Am J Obstet Gynecol 188(1):100\u0026ndash;107\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eObstetricians AC (2012) .o.P.B.G.A.C.o. and Gynecologists, Diagnosis of Abnormal uterine bleeding in reproductive aged women. Pract Bull No 128:197\u0026ndash;206\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eObstetricians ACo, Gynecologists Diagnosis of abnormal uterine bleeding in reproductive-aged women. Pract Bull, 2012(128): p. 197\u0026ndash;206\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eVijayaraghavan Sr A et al (2022) A histopathological study of endometrial biopsy samples in abnormal uterine bleeding. Cureus, 14(11)\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eTaran F, Stewart E, Brucker S (2013) Adenomyosis: epidemiology, risk factors, clinical phenotype and surgical and interventional alternatives to hysterectomy. Geburtshilfe Frauenheilkd 73(09):924\u0026ndash;931\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSalim S et al (2011) Diagnosis and management of endometrial polyps: a critical review of the literature. J Minim Invasive Gynecol 18(5):569\u0026ndash;581\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eUglietti A et al (2019) The risk of malignancy in uterine polyps: A systematic review and meta-analysis. Eur J Obstet Gynecol Reproductive Biology 237:48\u0026ndash;56\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eShankar M et al (2004) von Willebrand disease in women with menorrhagia: a systematic review. BJOG: Int J Obstet Gynecol 111(7):734\u0026ndash;740\u003c/span\u003e\u003c/li\u003e\u003c/ol\u003e"},{"header":"Tables","content":"\u003cp\u003e\u003cstrong\u003eTable 1.\u003c/strong\u003e Demographic, clinical and laboratory data of patients\u003c/p\u003e\n\u003ctable border=\"1\" cellspacing=\"0\" cellpadding=\"0\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd colspan=\"2\" valign=\"top\" style=\"width: 461px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003eMean \u0026plusmn; SD\u003c/p\u003e\n \u003cp\u003eN (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd colspan=\"2\" rowspan=\"2\" valign=\"top\" style=\"width: 461px;\"\u003e\n \u003cp\u003eAge\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e48,71\u0026plusmn;7,51\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003eN (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd rowspan=\"5\" valign=\"top\" style=\"width: 240px;\"\u003e\n \u003cp\u003eGravida\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003e1\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e10 (11,50)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003e2\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e37 (42,50)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003e3\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e23 (26,40)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003e4\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e8 (9.20)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003e5 and more\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e6 (6,90)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd rowspan=\"3\" valign=\"top\" style=\"width: 240px;\"\u003e\n \u003cp\u003eMode of Delivery\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eVaginal Delivery\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e51 (58,60)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eCesarean Section\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e16 (18,40)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eVaginal Delivery\u0026amp; Cesarean Section\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e17 (19,50)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd rowspan=\"2\" valign=\"top\" style=\"width: 240px;\"\u003e\n \u003cp\u003eMenopausal Status\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eYes\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e20 (23,00)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eNo\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e67 (77,00)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003e\u003cbr\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eTable 2.\u003c/strong\u003e Chief complaints, family and medical history of the patients.\u003c/p\u003e\n\u003ctable border=\"1\" cellspacing=\"0\" cellpadding=\"0\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd colspan=\"2\" valign=\"top\" style=\"width: 461px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003eMean \u0026plusmn; SD\u003c/p\u003e\n \u003cp\u003eN (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd rowspan=\"5\" valign=\"top\" style=\"width: 240px;\"\u003e\n \u003cp\u003eCurrent Chief Complaint\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eIMB\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e9 (10,30)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eHMB\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e24 (27,60)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eIMB\u0026amp;HMB\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e8 (9,20)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eIrregular Menstruation\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e27 (31,00)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003ePMB\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e18 (20,70)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd rowspan=\"7\" valign=\"top\" style=\"width: 240px;\"\u003e\n \u003cp\u003eMedical History of Coexisting Conditions\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eObesity\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e12 (13,80)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eHT\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e13 (14,90)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eDM\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e9 (10,30)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003ePCOS\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e2 (2,30)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eNONE\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e44 (50,60)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eHT\u0026amp;DM\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e7 (8,00)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eHT\u0026amp;DM\u0026amp;Obesity\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003eN/A\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd rowspan=\"2\" valign=\"top\" style=\"width: 240px;\"\u003e\n \u003cp\u003ePresence of Breast Cancer\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eYes\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e5 (5,70)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eNo\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e82 (94,30)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd rowspan=\"2\" valign=\"top\" style=\"width: 240px;\"\u003e\n \u003cp\u003eUse of Tamoxifen\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eYes\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e4 (4,60)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eNo\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e83 (95,40)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd rowspan=\"2\" valign=\"top\" style=\"width: 240px;\"\u003e\n \u003cp\u003eFamily History of Cancer\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eYes\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e21 (24,10)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eNo\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e65 (74,70)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd rowspan=\"4\" valign=\"top\" style=\"width: 240px;\"\u003e\n \u003cp\u003eIf so, what type of cancer\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eGynecological\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e13 (14,90)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eColon\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e3 (3,40)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eBreast\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e2 (2,30)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eOther\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e3 (3,40)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 240px;\"\u003e\n \u003cp\u003eDrug Use for Coagulopathy\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eYes \u0026nbsp;(Anticoagulant)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e8 (9,20)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 240px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eNo\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e79 (90,80)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd rowspan=\"2\" valign=\"top\" style=\"width: 240px;\"\u003e\n \u003cp\u003eIs there a history of medical treatment for the current complaint\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eYes\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e41 (47,10)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eNo\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e46 (52,90)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd rowspan=\"4\" valign=\"top\" style=\"width: 240px;\"\u003e\n \u003cp\u003eIf yes, what type of medical treatment\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eCOC\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e18 (20,70)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eHormonal\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e22 (25,30)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eLNG-IUD\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e11 ( 13.8)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eNo\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e47 (54,00)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd rowspan=\"2\" valign=\"top\" style=\"width: 240px;\"\u003e\n \u003cp\u003eHas there been any H/S (hysteroscopy) performed for treatment purposes?\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eYes\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e21 (24,10)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eNo\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e66 (75,90)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003eCombined Oral Contraceptive (COC), Diabetes Mellitus (DM), Heavy Menstrual Bleeding (HMB), Hypertension (HT), Intermenstrual Bleeding (IMB), Levonorgestrel-Releasing Intrauterine Device (LNG-IUD), Polycystic Ovary Syndrome (PCOS), Postmenopausal Bleeding (PMB).\u003c/p\u003e\n\u003cp\u003e\u003cbr\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eTable 3.\u003c/strong\u003e Physical examination and usg findings of the patients.\u003c/p\u003e\n\u003ctable border=\"1\" cellspacing=\"0\" cellpadding=\"0\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd colspan=\"2\" valign=\"top\" style=\"width: 461px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003eMean \u0026plusmn; SD\u003c/p\u003e\n \u003cp\u003eN (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd rowspan=\"4\" valign=\"top\" style=\"width: 240px;\"\u003e\n \u003cp\u003eTV-USG findings related to the endometrium\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eIrregular Endometrium\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e18 (20,70)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eNo Endometrial Hyperplasia\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e38 (43,70)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eEndometrial Hyperplasia Present\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e27 (31,10)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eSuspicious Mass\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e4 (4,60)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd rowspan=\"2\" valign=\"top\" style=\"width: 240px;\"\u003e\n \u003cp\u003ePresence of uterine myoma\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eYes\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e61 (70,10)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eNo\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e26 (29,90)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd rowspan=\"9\" valign=\"top\" style=\"width: 240px;\"\u003e\n \u003cp\u003eType of myoma (FIGO classification)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eType 1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003eN/A\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003e\u0026nbsp;Type 2\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e4 (4,60)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eType 3\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e7 (8,00)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eType 4\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e7 (8,00)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eType 5\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e21 (24,10)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eType 6\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e11 (12,60)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eType 7\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e3 (3,40)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eType 0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e3 (3,40)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eAdenomyozis\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e5 (5,70)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd rowspan=\"5\" valign=\"top\" style=\"width: 240px;\"\u003e\n \u003cp\u003eMyoma size\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003e\u0026lt;3\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e2 (2,30)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003e3-5 cm\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e16 (18,40)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003e5-10 cm\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e15 (17,20)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003e\u0026gt;10\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e16 (18,40)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eMultiple intramural myoma\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e12 (13,80)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd rowspan=\"2\" valign=\"top\" style=\"width: 240px;\"\u003e\n \u003cp\u003ePolip\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eYes\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e14 (16,10)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eNo\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e72 (82,80)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd rowspan=\"2\" valign=\"top\" style=\"width: 240px;\"\u003e\n \u003cp\u003eLow hemoglobin\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eYes\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e30 (34,50)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eNo\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e57 (65,50)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003e\u003cbr\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eTable 4\u003c/strong\u003e. Biopsy findings, treatments and options recommended by AI\u003c/p\u003e\n\u003ctable border=\"1\" cellspacing=\"0\" cellpadding=\"0\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd colspan=\"2\" valign=\"top\" style=\"width: 461px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003eMean \u0026plusmn; SD\u003c/p\u003e\n \u003cp\u003eN (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd rowspan=\"5\" valign=\"top\" style=\"width: 240px;\"\u003e\n \u003cp\u003eEndometrial biopsy findings\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eNormal\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e58 (66,70)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eEndometrial Hyperplasia without atypia\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e11 (12,60)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eEIN (+)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e4 (4,60)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003ePolip\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e11 (12,60)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eMalignity\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e3 (3,40)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd rowspan=\"7\" valign=\"top\" style=\"width: 240px;\"\u003e\n \u003cp\u003eTreatments\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eHysterectomy\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e87 (100,00)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eMyomectomy\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003eN/A\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eHysteroscopy\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003eN/A\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eMedical Treatment\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003eN/A\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eLNG-IUD\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003eN/A\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eFollow-up\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003eN/A\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eHysterectomy after hysteroscopy\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003eN/A\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd rowspan=\"7\" valign=\"top\" style=\"width: 240px;\"\u003e\n \u003cp\u003eOptions recommended by artificial intelligence\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eHysterectomy\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e61 (70,10)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eMyomectomy\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e9 (10,3)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eHysteroscopy\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e7 (8,00)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eMedical Treatment\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e4 (4,60)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eLNG-IUD\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e2 (2,30)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eFollow-up\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e1 (1,10)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 221px;\"\u003e\n \u003cp\u003eHysterectomy after hysteroscopy\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 126px;\"\u003e\n \u003cp\u003e3 (3,40)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003e\u003cbr\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eTable 5.\u003c/strong\u003e Comparison of Symptoms and Medical Treatments Based on TV-US Myoma Types in Patients for Whom AI Recommended Myomectomy.\u003c/p\u003e\n\u003ctable border=\"1\" cellspacing=\"0\" cellpadding=\"0\" width=\"595\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 170px;\"\u003e\n \u003cp\u003eTreatment = Myomectomy\u003c/p\u003e\n \u003cp\u003eTV-US Myoma Present\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 73px;\"\u003e\n \u003cp\u003eMedikal Treatment\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"5\" valign=\"top\" style=\"width: 298px;\"\u003e\n \u003cp\u003eMyoma Type on TV-US\u0026nbsp;\u003c/p\u003e\n \u003cp\u003eN (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 54px;\"\u003e\n \u003cp\u003ep\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 170px;\"\u003e\n \u003cp\u003eSymptom\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 73px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 53px;\"\u003e\n \u003cp\u003eType 2\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 61px;\"\u003e\n \u003cp\u003eType 3\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 61px;\"\u003e\n \u003cp\u003eType 4\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 61px;\"\u003e\n \u003cp\u003eType 5\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 61px;\"\u003e\n \u003cp\u003eType 6\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 54px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd rowspan=\"2\" valign=\"top\" style=\"width: 170px;\"\u003e\n \u003cp\u003eHMB\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 73px;\"\u003e\n \u003cp\u003ePresent\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 53px;\"\u003e\n \u003cp\u003e2\u0026nbsp;\u003c/p\u003e\n \u003cp\u003e(1,60)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 61px;\"\u003e\n \u003cp\u003e1\u0026nbsp;\u003c/p\u003e\n \u003cp\u003e(0,80)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 61px;\"\u003e\n \u003cp\u003eN/A\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 61px;\"\u003e\n \u003cp\u003e1\u0026nbsp;\u003c/p\u003e\n \u003cp\u003e(0,80)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 61px;\"\u003e\n \u003cp\u003e0\u0026nbsp;\u003c/p\u003e\n \u003cp\u003e(0,80)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd rowspan=\"2\" style=\"width: 54px;\"\u003e\n \u003cp\u003e0,140\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 73px;\"\u003e\n \u003cp\u003eAbsent\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 53px;\"\u003e\n \u003cp\u003e0\u0026nbsp;\u003c/p\u003e\n \u003cp\u003e(0,40)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 61px;\"\u003e\n \u003cp\u003e0\u0026nbsp;\u003c/p\u003e\n \u003cp\u003e(0,20)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 61px;\"\u003e\n \u003cp\u003eN/A\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 61px;\"\u003e\n \u003cp\u003e0\u0026nbsp;\u003c/p\u003e\n \u003cp\u003e(0,20)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 61px;\"\u003e\n \u003cp\u003e1\u0026nbsp;\u003c/p\u003e\n \u003cp\u003e(0,20)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd rowspan=\"2\" valign=\"top\" style=\"width: 170px;\"\u003e\n \u003cp\u003eIrregular Menstruation\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 73px;\"\u003e\n \u003cp\u003ePresent\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 53px;\"\u003e\n \u003cp\u003eN/A\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 61px;\"\u003e\n \u003cp\u003eN/A\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 61px;\"\u003e\n \u003cp\u003eN/A\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 61px;\"\u003e\n \u003cp\u003eN/A\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 61px;\"\u003e\n \u003cp\u003eN/A\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd rowspan=\"2\" style=\"width: 54px;\"\u003e\n \u003cp\u003eN/A\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 73px;\"\u003e\n \u003cp\u003eAbsent\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 53px;\"\u003e\n \u003cp\u003eN/A\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 61px;\"\u003e\n \u003cp\u003eN/A\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 61px;\"\u003e\n \u003cp\u003e1\u0026nbsp;\u003c/p\u003e\n \u003cp\u003e(1,00)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 61px;\"\u003e\n \u003cp\u003e2\u0026nbsp;\u003c/p\u003e\n \u003cp\u003e(2,00)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 61px;\"\u003e\n \u003cp\u003e1\u0026nbsp;\u003c/p\u003e\n \u003cp\u003e(1,00)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eTable 6\u003c/strong\u003e. Comparison of Symptoms, Fibroid Types, and Fibroid Sizes in Patients for Whom AI Recommended Myomectomy Based on TV-US Findings\u003c/p\u003e\n\u003ctable border=\"1\" cellspacing=\"0\" cellpadding=\"0\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 157px;\"\u003e\n \u003cp\u003eTreatment=Myomectomy\u003c/p\u003e\n \u003cp\u003eFibroid Presence on TV-US = Present\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 76px;\"\u003e\n \u003cp\u003eMedical Treatment\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 58px;\"\u003e\n \u003cp\u003eFibroid Type\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"4\" valign=\"top\" style=\"width: 264px;\"\u003e\n \u003cp\u003eFibroid Size\u0026nbsp;\u003c/p\u003e\n \u003cp\u003eN(%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 46px;\"\u003e\n \u003cp\u003ep\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 157px;\"\u003e\n \u003cp\u003eComplaint\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 76px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 58px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 64px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003cp\u003e3-5 cm\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 64px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003cp\u003e5-10 cm\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 64px;\"\u003e\n \u003cp\u003e\u0026gt; 10 cm\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 72px;\"\u003e\n \u003cp\u003eMultiple Intramural Fibroids\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 46px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd rowspan=\"4\" valign=\"top\" style=\"width: 157px;\"\u003e\n \u003cp\u003eHMB\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 76px;\"\u003e\n \u003cp\u003ePresent\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 58px;\"\u003e\n \u003cp\u003eTip 2\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 64px;\"\u003e\n \u003cp\u003e2 (2,00)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 64px;\"\u003e\n \u003cp\u003eN/A\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 64px;\"\u003e\n \u003cp\u003eN/A\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 72px;\"\u003e\n \u003cp\u003eN/A\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd rowspan=\"4\" style=\"width: 46px;\"\u003e\n \u003cp\u003e0,140\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 76px;\"\u003e\n \u003cp\u003ePresent\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 58px;\"\u003e\n \u003cp\u003eTip 3\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 64px;\"\u003e\n \u003cp\u003e1 (1,00)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 64px;\"\u003e\n \u003cp\u003eN/A\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 64px;\"\u003e\n \u003cp\u003eN/A\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 72px;\"\u003e\n \u003cp\u003eN/A\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 76px;\"\u003e\n \u003cp\u003ePresent\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 58px;\"\u003e\n \u003cp\u003eTip 5\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 64px;\"\u003e\n \u003cp\u003e1 (1,00)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 64px;\"\u003e\n \u003cp\u003eN/A\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 64px;\"\u003e\n \u003cp\u003eN/A\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 72px;\"\u003e\n \u003cp\u003eN/A\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 76px;\"\u003e\n \u003cp\u003eAbsent\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 58px;\"\u003e\n \u003cp\u003eTip 6\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 64px;\"\u003e\n \u003cp\u003eN/A\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 64px;\"\u003e\n \u003cp\u003eN/A\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 64px;\"\u003e\n \u003cp\u003e1 (1,00)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 72px;\"\u003e\n \u003cp\u003eN/A\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd rowspan=\"3\" valign=\"top\" style=\"width: 157px;\"\u003e\n \u003cp\u003eIrregular Menstruation\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 76px;\"\u003e\n \u003cp\u003eAbsent\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 58px;\"\u003e\n \u003cp\u003eTip 4\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 64px;\"\u003e\n \u003cp\u003e1 (1,00)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 64px;\"\u003e\n \u003cp\u003eN/A\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 64px;\"\u003e\n \u003cp\u003eN/A\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 72px;\"\u003e\n \u003cp\u003eN/A\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd rowspan=\"3\" style=\"width: 46px;\"\u003e\n \u003cp\u003eN/A\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 76px;\"\u003e\n \u003cp\u003eAbsent\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 58px;\"\u003e\n \u003cp\u003eTip 5\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 64px;\"\u003e\n \u003cp\u003eN/A\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 64px;\"\u003e\n \u003cp\u003e1(1,00)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 64px;\"\u003e\n \u003cp\u003eN/A\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 72px;\"\u003e\n \u003cp\u003e1 (1,00)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 76px;\"\u003e\n \u003cp\u003eAbsent\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 58px;\"\u003e\n \u003cp\u003eTip 6\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 64px;\"\u003e\n \u003cp\u003eN/A\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 64px;\"\u003e\n \u003cp\u003eN/A\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 64px;\"\u003e\n \u003cp\u003e1 (1,00)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 72px;\"\u003e\n \u003cp\u003eN/A\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eTable 7.\u003c/strong\u003e Comparison of Current Symptoms, Medical Treatment History, and TV-US Endometrial Findings in Patients for Whom AI Recommended Hysteroscopy Based on Symptom Status\u003c/p\u003e\n\u003ctable border=\"1\" cellspacing=\"0\" cellpadding=\"0\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 110px;\"\u003e\n \u003cp\u003eTreatment = Hysteroscopy\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 96px;\"\u003e\n \u003cp\u003eMedical Treatment History\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"3\" valign=\"top\" style=\"width: 317px;\"\u003e\n \u003cp\u003eTV-US Endometrial Findings N (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 78px;\"\u003e\n \u003cp\u003e\u003cstrong\u003ep\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 110px;\"\u003e\n \u003cp\u003eSymptom\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 96px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 106px;\"\u003e\n \u003cp\u003eIrregular Endometrium\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 106px;\"\u003e\n \u003cp\u003eEndometrial Hyperplasia Absent\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 106px;\"\u003e\n \u003cp\u003eEndometrial Hyperplasia Present\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 78px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd rowspan=\"2\" valign=\"top\" style=\"width: 110px;\"\u003e\n \u003cp\u003eHMB\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 96px;\"\u003e\n \u003cp\u003ePresent\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 106px;\"\u003e\n \u003cp\u003e0 (0,80)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 106px;\"\u003e\n \u003cp\u003eN/A\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 106px;\"\u003e\n \u003cp\u003e1 (0,30)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd rowspan=\"2\" style=\"width: 78px;\"\u003e\n \u003cp\u003e0,083\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 96px;\"\u003e\n \u003cp\u003eAbsent\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 106px;\"\u003e\n \u003cp\u003e3 (2,30)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 106px;\"\u003e\n \u003cp\u003eN/A\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 106px;\"\u003e\n \u003cp\u003e0 (0,80)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 110px;\"\u003e\n \u003cp\u003eIrregular \u0026nbsp; \u0026nbsp;Menstruation\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 96px;\"\u003e\n \u003cp\u003ePresent\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 106px;\"\u003e\n \u003cp\u003e1 (1,00)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 106px;\"\u003e\n \u003cp\u003eN/A\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 106px;\"\u003e\n \u003cp\u003e1 (1,00)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 78px;\"\u003e\n \u003cp\u003eN/A\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 110px;\"\u003e\n \u003cp\u003ePMB\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 96px;\"\u003e\n \u003cp\u003eAbsent\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 106px;\"\u003e\n \u003cp\u003eN/A\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 106px;\"\u003e\n \u003cp\u003e1 (1,00)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 106px;\"\u003e\n \u003cp\u003eN/A\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 78px;\"\u003e\n \u003cp\u003eN/A\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eTable 8\u003c/strong\u003e. Comparison of Endometrial Findings and AI-Recommended Treatment Based on Menopausal Status in Patients with Polyps on TV-US\u003c/p\u003e\n\u003ctable border=\"1\" cellspacing=\"0\" cellpadding=\"0\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 86px;\"\u003e\n \u003cp\u003eTV-US Polyp Presence = Present\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 128px;\"\u003e\n \u003cp\u003eTV-US Endometrial Findings\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"3\" valign=\"top\" style=\"width: 310px;\"\u003e\n \u003cp\u003eAI-Recommended Treatment \u0026nbsp;\u003c/p\u003e\n \u003cp\u003eN (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 61px;\"\u003e\n \u003cp\u003ep\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 86px;\"\u003e\n \u003cp\u003eMenopausal Status\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 128px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 103px;\"\u003e\n \u003cp\u003eHysterectomy\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 103px;\"\u003e\n \u003cp\u003eHysteroscopy\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 103px;\"\u003e\n \u003cp\u003eHysteroscopy Followed by Hysterectomy\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 61px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd rowspan=\"3\" valign=\"top\" style=\"width: 86px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003cp\u003ePresent\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 128px;\"\u003e\n \u003cp\u003eIrregular Endometrium\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 103px;\"\u003e\n \u003cp\u003e1 (1,00)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 103px;\"\u003e\n \u003cp\u003eN/A\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 103px;\"\u003e\n \u003cp\u003eN/A\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd rowspan=\"3\" style=\"width: 61px;\"\u003e\n \u003cp\u003eN/A\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 128px;\"\u003e\n \u003cp\u003eEndometrial Hyperplasia Absent\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 103px;\"\u003e\n \u003cp\u003e1 (1,00)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 103px;\"\u003e\n \u003cp\u003eN/A\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 103px;\"\u003e\n \u003cp\u003eN/A\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 128px;\"\u003e\n \u003cp\u003eSuspicious Mass\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 103px;\"\u003e\n \u003cp\u003e1 (1,00)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 103px;\"\u003e\n \u003cp\u003eN/A\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 103px;\"\u003e\n \u003cp\u003eN/A\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd rowspan=\"4\" valign=\"top\" style=\"width: 86px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003cp\u003eAbsent\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 128px;\"\u003e\n \u003cp\u003eIrregular Endometrium\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 103px;\"\u003e\n \u003cp\u003e2 (2,70)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 103px;\"\u003e\n \u003cp\u003e2 (1,40)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 103px;\"\u003e\n \u003cp\u003e1 (0,90)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd rowspan=\"4\" style=\"width: 61px;\"\u003e\n \u003cp\u003e0,778\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 128px;\"\u003e\n \u003cp\u003eEndometrial Hyperplasia Absent\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 103px;\"\u003e\n \u003cp\u003e1 (0,50)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 103px;\"\u003e\n \u003cp\u003e0 (0,30)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 103px;\"\u003e\n \u003cp\u003e0 (0,20)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 128px;\"\u003e\n \u003cp\u003eEndometrial Hyperplasia Present\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 103px;\"\u003e\n \u003cp\u003e3 (2,20)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 103px;\"\u003e\n \u003cp\u003e1 (1,10)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 103px;\"\u003e\n \u003cp\u003e0 (0,70)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 128px;\"\u003e\n \u003cp\u003eSuspicious Mass\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 103px;\"\u003e\n \u003cp\u003e0 (0,50)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 103px;\"\u003e\n \u003cp\u003e0 (0,30)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 103px;\"\u003e\n \u003cp\u003e1 (0,20)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003e\u003cbr\u003e\u003c/p\u003e\n\u003cp\u003eTable 9. Comparison of endometrial biopsy and AI-recommended treatment based on menopausal status in patients with polyps on TV-US\u003c/p\u003e\n\u003ctable border=\"1\" cellspacing=\"0\" cellpadding=\"0\" width=\"586\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 106px;\"\u003e\n \u003cp\u003eTV-US Polyp Presence = Present\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 121px;\"\u003e\n \u003cp\u003eEndometrial Biopsy\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"3\" valign=\"top\" style=\"width: 265px;\"\u003e\n \u003cp\u003eAI-Recommended Treatment\u003c/p\u003e\n \u003cp\u003eN (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 94px;\"\u003e\n \u003cp\u003e\u003cstrong\u003ep\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 106px;\"\u003e\n \u003cp\u003eMenopausal Status\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 121px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 92px;\"\u003e\n \u003cp\u003eHysterectomy\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 89px;\"\u003e\n \u003cp\u003eHysteroscopy\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 84px;\"\u003e\n \u003cp\u003eH/S followed by Hysterectomy\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 94px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd rowspan=\"3\" valign=\"top\" style=\"width: 106px;\"\u003e\n \u003cp\u003ePresent\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 121px;\"\u003e\n \u003cp\u003e\u003cem\u003eNormal\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 92px;\"\u003e\n \u003cp\u003e1 (1,00)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 89px;\"\u003e\n \u003cp\u003eN/A\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 84px;\"\u003e\n \u003cp\u003eN/A\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd rowspan=\"3\" style=\"width: 94px;\"\u003e\n \u003cp\u003eN/A\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 121px;\"\u003e\n \u003cp\u003e\u003cem\u003eEIN (-)\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 92px;\"\u003e\n \u003cp\u003e1 (1,00)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 89px;\"\u003e\n \u003cp\u003eN/A\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 84px;\"\u003e\n \u003cp\u003eN/A\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 121px;\"\u003e\n \u003cp\u003e\u003cem\u003ePolip\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 92px;\"\u003e\n \u003cp\u003e1 (1,00)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 89px;\"\u003e\n \u003cp\u003eN/A\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 84px;\"\u003e\n \u003cp\u003eN/A\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd rowspan=\"3\" valign=\"top\" style=\"width: 106px;\"\u003e\n \u003cp\u003eAbsent\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 121px;\"\u003e\n \u003cp\u003e\u003cem\u003eNormal\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 92px;\"\u003e\n \u003cp\u003e0 (1,60)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 89px;\"\u003e\n \u003cp\u003e2 (0,80)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 84px;\"\u003e\n \u003cp\u003e1 (0,50)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd rowspan=\"3\" style=\"width: 94px;\"\u003e\n \u003cp\u003e0,251\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 121px;\"\u003e\n \u003cp\u003e\u003cem\u003eEIN (-)\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 92px;\"\u003e\n \u003cp\u003e1 (0,50)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 89px;\"\u003e\n \u003cp\u003e0 (0,30)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 84px;\"\u003e\n \u003cp\u003e0 (0,20)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 121px;\"\u003e\n \u003cp\u003e\u003cem\u003ePolip\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 92px;\"\u003e\n \u003cp\u003e5 (3,80)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 89px;\"\u003e\n \u003cp\u003e1 (1,90)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 84px;\"\u003e\n \u003cp\u003e1 (1,30)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eTable 10. Comparison of fibroid presence and medical treatment history for the current complaint in patients recommended for hysterectomy with normal endometrial biopsy and EIN (-)\u0026nbsp;\u003c/p\u003e\n\u003ctable border=\"1\" cellspacing=\"0\" cellpadding=\"0\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 139px;\"\u003e\n \u003cp\u003eTreatment = Hysterectomy\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 94px;\"\u003e\n \u003cp\u003eTV-US Fibroid Presence\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" valign=\"top\" style=\"width: 227px;\"\u003e\n \u003cp\u003eCurrent Complaint Medical Treatment History\u0026nbsp;\u003c/p\u003e\n \u003cp\u003eN (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 141px;\"\u003e\n \u003cp\u003ep\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 139px;\"\u003e\n \u003cp\u003eEndometrial Biopsy\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 94px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 114px;\"\u003e\n \u003cp\u003ePresent\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 114px;\"\u003e\n \u003cp\u003eAbsent\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 141px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd rowspan=\"2\" valign=\"top\" style=\"width: 139px;\"\u003e\n \u003cp\u003eNormal\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 94px;\"\u003e\n \u003cp\u003ePresent\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 114px;\"\u003e\n \u003cp\u003e15 (14,70)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 114px;\"\u003e\n \u003cp\u003e19 (19,30)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd rowspan=\"2\" style=\"width: 141px;\"\u003e\n \u003cp\u003e0,721\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 94px;\"\u003e\n \u003cp\u003eAbsent\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 114px;\"\u003e\n \u003cp\u003e1 (1,30)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 114px;\"\u003e\n \u003cp\u003e2 (1,70)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd rowspan=\"2\" valign=\"top\" style=\"width: 139px;\"\u003e\n \u003cp\u003eEIN (-)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 94px;\"\u003e\n \u003cp\u003ePresent\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 114px;\"\u003e\n \u003cp\u003e0 (0,40)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 114px;\"\u003e\n \u003cp\u003e1 (0,60)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd rowspan=\"2\" style=\"width: 141px;\"\u003e\n \u003cp\u003e0,321\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 94px;\"\u003e\n \u003cp\u003eAbsent\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 114px;\"\u003e\n \u003cp\u003e4 (3,60)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 114px;\"\u003e\n \u003cp\u003e4 (4,40)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eTable 11. Comparison of fibroid type and history of medical treatment for existing complaints in patients with normal endometrial biopsy and EIN (-) who were recommended for hysterectomy\u003c/p\u003e\n\u003ctable border=\"1\" cellspacing=\"0\" cellpadding=\"0\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 142px;\"\u003e\n \u003cp\u003eTreatment = Hysterectomy\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 104px;\"\u003e\n \u003cp\u003eFibroid Type on TV-US\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" valign=\"top\" style=\"width: 224px;\"\u003e\n \u003cp\u003eHistory of Medical Treatment for Existing Complaint N (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 69px;\"\u003e\n \u003cp\u003e\u003cstrong\u003ep\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 142px;\"\u003e\n \u003cp\u003eEndometrial Biopsy\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 104px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 112px;\"\u003e\n \u003cp\u003e\u003cstrong\u003ePresent\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 112px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eAbsent\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd rowspan=\"8\" valign=\"top\" style=\"width: 142px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003cp\u003eNormal\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 104px;\"\u003e\n \u003cp\u003e\u003cem\u003eType 2\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 112px;\"\u003e\n \u003cp\u003e0 (0,40)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 112px;\"\u003e\n \u003cp\u003e1 (0,60)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd rowspan=\"8\" style=\"width: 69px;\"\u003e\n \u003cp\u003e0,442\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 104px;\"\u003e\n \u003cp\u003e\u003cem\u003eType 3\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 112px;\"\u003e\n \u003cp\u003e1 (1,80)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 112px;\"\u003e\n \u003cp\u003e3 (2,20)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 104px;\"\u003e\n \u003cp\u003e\u003cem\u003eType 4\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 112px;\"\u003e\n \u003cp\u003e2 (1,30)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 112px;\"\u003e\n \u003cp\u003e1 (1,70)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 104px;\"\u003e\n \u003cp\u003e\u003cem\u003eType 5\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 112px;\"\u003e\n \u003cp\u003e6 (4,90)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 112px;\"\u003e\n \u003cp\u003e5 (6,10)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 104px;\"\u003e\n \u003cp\u003e\u003cem\u003eType 6\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 112px;\"\u003e\n \u003cp\u003e2 (2,60)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 112px;\"\u003e\n \u003cp\u003e4 (3,40)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 104px;\"\u003e\n \u003cp\u003e\u003cem\u003eType 7\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 112px;\"\u003e\n \u003cp\u003e0 (1,30)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 112px;\"\u003e\n \u003cp\u003e3 (1,70)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 104px;\"\u003e\n \u003cp\u003e\u003cem\u003eType 0\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 112px;\"\u003e\n \u003cp\u003e1 (0,90)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 112px;\"\u003e\n \u003cp\u003e1 (1,10)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 104px;\"\u003e\n \u003cp\u003eAdenomyotic\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 112px;\"\u003e\n \u003cp\u003e3 (1,80)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 112px;\"\u003e\n \u003cp\u003e1 (2,20)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 142px;\"\u003e\n \u003cp\u003eEIN (-)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 104px;\"\u003e\n \u003cp\u003e\u003cem\u003eType 6\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 112px;\"\u003e\n \u003cp\u003eN/A\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 112px;\"\u003e\n \u003cp\u003e1 (1,00)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69px;\"\u003e\n \u003cp\u003eN/A\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003e\u003cbr\u003e\u003c/p\u003e\n\u003cp\u003eTable 12. Comparison of complaints and medical treatment history for existing complaints in patients with hemoglobin deficiency recommended for hysterectomy\u003c/p\u003e\n\u003ctable border=\"1\" cellspacing=\"0\" cellpadding=\"0\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 180px;\"\u003e\n \u003cp\u003eTreatment = Hysterectomy\u0026nbsp;\u003c/p\u003e\n \u003cp\u003eHemoglobin Deficiency = Present\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" valign=\"top\" style=\"width: 291px;\"\u003e\n \u003cp\u003eMedical Treatment History for Existing Complaint\u003c/p\u003e\n \u003cp\u003eN (%)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 69px;\"\u003e\n \u003cp\u003e\u003cstrong\u003ep\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 180px;\"\u003e\n \u003cp\u003eComplaint\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 146px;\"\u003e\n \u003cp\u003e\u003cstrong\u003ePresent\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 146px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eAbsent\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 69px;\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 180px;\"\u003e\n \u003cp\u003eIMB\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 146px;\"\u003e\n \u003cp\u003e3 (2,30)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 146px;\"\u003e\n \u003cp\u003e1 (1,70)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd rowspan=\"5\" style=\"width: 69px;\"\u003e\n \u003cp\u003e0,011\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 180px;\"\u003e\n \u003cp\u003eHMB\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 146px;\"\u003e\n \u003cp\u003e6 (4,60)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 146px;\"\u003e\n \u003cp\u003e2 (3,40)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 180px;\"\u003e\n \u003cp\u003eHMB\u0026amp;IMB\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 146px;\"\u003e\n \u003cp\u003e2 (1,10)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 146px;\"\u003e\n \u003cp\u003e0 (0,90)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 180px;\"\u003e\n \u003cp\u003eIrregular Menstruation\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 146px;\"\u003e\n \u003cp\u003e1 (1,10)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 146px;\"\u003e\n \u003cp\u003e1 (1,90)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 180px;\"\u003e\n \u003cp\u003ePMK\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 146px;\"\u003e\n \u003cp\u003e0 (2,90)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 146px;\"\u003e\n \u003cp\u003e5 (2,10)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"Akdeniz University","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Artificial Intelligence, Abnormal Uterine Bleeding, Hysterectomy, Gynecology","lastPublishedDoi":"10.21203/rs.3.rs-6260219/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6260219/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003e\u003cstrong\u003eObjective\u003c/strong\u003e: This study aims to compare and analyze the medical data and clinical indications of patients who have been decided for hysterectomy in our clinic with the recommendations of the artificial intelligence program ChatGPT. The recommendations generated by ChatGPT, based on scientific articles and studies, are used to assess its potential and limitations in clinical decision-making processes. The research investigates how effective and reliable Artificial Intelligence (AI) based systems can be in planning major surgical interventions such as hysterectomy. Furthermore, the study examines how AI technology can be integrated into current medical practices and its extent of contribution to clinical decision-making processes. In this context, the study aims to provide significant insights into the future use of AI in the medical field.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eMaterials and Methods\u003c/strong\u003e: The study was conducted on a total of 87 patients aged between 40-65 years, who applied to the Akdeniz University Department of Obstetrics and Gynecology and were decided for hysterectomy between June 1, 2023, and November 1, 2023. The detailed anamneses and information of the patients included in the study were systematically collected and evaluated by the research staff of our clinic. The collected data were entered into the AI program ChatGPT, aiming to determine the most effective treatment option suitable for each patient's scenario. During this process, the program was requested to interpret the medical condition of each patient, considering the current literature, and to explain the reasons for its recommendations. This methodology was designed to assess the contribution of AI to clinical decision-making processes and to examine its potential effectiveness.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eResults\u003c/strong\u003e: The data of 87 patients who presented to the Akdeniz University Department of Obstetrics and Gynecology and were decided for hysterectomy between June 1, 2023, and November 1, 2023, were analyzed in this study. The average age of the patients was found to be 48.71, with the most common complaints being irregular menstruation (31.00%) and heavy menstrual bleeding (HMB) (27.60%). The most frequent additional disease histories were obesity (13.80%) and hypertension (HT) (14.90%). A low proportion of patients had a history of breast cancer and Tamoxifen usage (5.70% and 4.60% respectively).\u003c/p\u003e\n\u003cp\u003eWhen comparing the treatment options recommended by the AI program ChatGPT with the decisions of clinicians, it was observed that the program recommended hysterectomy in 70.10% of the cases. Other recommended treatments included myomectomy (10.30%), hysteroscopy (8.00%), and medical treatment (4.60%). These recommendations correlated with the clinical and demographic characteristics of the patients. Notably, the AI’s recommendations for hysterectomy were highly consistent with situations involving abnormal uterine bleeding and the presence of myomas.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConclusions\u003c/strong\u003e: The alignment between ChatGPT's recommendations and clinical decisions demonstrates the potential of AI in medical decision-making processes. However, the presence of some differences between the recommendations of AI and actual clinical practices highlights that AI should not yet be used as an independent decision-making tool and should continue to be employed as a supportive technology in medical applications.\u003c/p\u003e\n\u003cp\u003eFurthermore, the study brings to light the potential and limitations of AI in medical decision-making processes. Despite the recommendations of AI programs being based on medical data and current literature, the importance of clinical experience and evaluating the individual condition of the patient is emphasized.\u003c/p\u003e\n\u003cp\u003eIn conclusion, this study demonstrates that AI-based systems can be an effective support tool in clinical decision-making processes. However, the use of such systems should be to assist and complement the clinical decisions of physicians. These findings provide a foundation for better understanding the future role and integration of AI in the medical field.\u003c/p\u003e","manuscriptTitle":"Comparison of Indications for Hysterectomy in Our Clinic With Recommendations of the Artificial Intelligence Program","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-03-20 06:48:07","doi":"10.21203/rs.3.rs-6260219/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"41e7793f-6686-446e-a050-80bcb92d7051","owner":[],"postedDate":"March 20th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":45948246,"name":"Artificial Intelligence and Machine Learning"},{"id":45948247,"name":"Surgical Obstetrics \u0026 Gynecology"},{"id":45948248,"name":"Obstetrics \u0026 Gynecology"}],"tags":[],"updatedAt":"2025-04-11T18:23:15+00:00","versionOfRecord":[],"versionCreatedAt":"2025-03-20 06:48:07","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6260219","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6260219","identity":"rs-6260219","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}