Identification and Validation of a Novel Machine Learning Model for Predicting Severe Pelvic Endometriosis: A Retrospective Study

Identification and Validation of a Novel Machine Learning Model for Predicting Severe Pelvic Endometriosis: A Retrospective Study | 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 Article Identification and Validation of a Novel Machine Learning Model for Predicting Severe Pelvic Endometriosis: A Retrospective Study Siqi Cao, Xingzhe Li, Xin Zheng, Jiaxin Zhang, Ziyao Ji, yanjun liu This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5309546/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 19 Apr, 2025 Read the published version in Scientific Reports → Version 1 posted 10 You are reading this latest preprint version Abstract Background Severe endometriosis significantly impacts the quality of life, particularly in women of reproductive age. Though numerous studies have conducted predictive models with preoperative clinical data for endometriosis, most risk models focus on diagnosis rather than disease staging. This study aimed to explore potential factors for endometriosis severity and to develop a classification model to assess the accuracy of predicting the risk of severe endometriosis. Methods A total of 308 patients with endometriosis were retrospectively analyzed. The stage of endometriosis was classified according to the scoring system of the revised American Society for Reproductive Medicine (rASRM) system, through surgical visualization,which is the most widely used staging system globally. All patients underwent preoperative transabdominal and transvaginal ultrasound, based on four steps screening approach proposed by The International Deep Endometriosis Analysis (IDEA) consensus. We randomly divided these data into training and testing datasets at a ratio of 8:2. Least absolute shrinkage and selection operator (LASSO) was performed to identify the potential risk factors for severe endometriosis. Then, we used 7 machine learning(ML) models to construct the predictive models. The area under the receiver-operating-characteristics curve (AUC) and accuracy were used to evaluate and determine the most effective model. Finally, SHapley Additive exPlanations (SHAP) interpretation was calculated to evaluate each parameter's contribution to risk prediction. Results In this retrospective study, about 59.2% (183/308) of endometriosis patients were diagnosed with severe endometriosis. The predictors of severe endometriosis occurrence were found to be compliance of 18 factors such as the negative sliding sign, pelvic fluid, bilateral OE, serum CA125 level and severe dysmenorrhea according to LASSO. The random forest (RF) model performed best in discriminative ability among the 7 ML models. After reducing features according to feature importance rank, an explainable final RF model was established with 6 features. The final model could accurately predict severe endometriosis with the area under curve (AUC) of 0.744 and an accuracy of 0.667 in the test set. From the SHAP map, it was found that the negative sliding sign had the greatest impact on the diagnostic performance of the RF model. Conclusions We constructed a predictive model based on the ML model, and the RF model showed a better performance. we also provided a personalized risk assessment for the development of stage IV in endometriosis patients explained by SHAP. This can help clinicians to treat severe endometriosis. Health sciences/Diseases/Endocrine system and metabolic diseases/Endocrine reproductive disorders Health sciences/Diseases/Endocrine system and metabolic diseases/Gonadal disorders Health sciences/Diseases/Endocrine system and metabolic diseases/Multihormonal system disorders Health sciences/Diseases/Reproductive disorders/Infertility Health sciences/Risk factors Health sciences/Medical research Severe endometriosis Transvaginal ultrasound Machine learning Prediction model SHAP Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 Figure 6 Figure 7 Figure 8 INTRODUCTION As a common chronic inflammatory disease, endometriosis is defined by the presence of endometrial-like tissue outside the uterus and is closely associated with dysmenorrhea, pelvic pain, infertility, dysuria, and deep dyspareunia 1 , 2 . It poses a significant threat to quality of life, especially in women of reproductive age, with an increasing prevalence rate of 10% 3 . Endometriosis can be categorized into different phenotypes, such as ovarian endometriosis (OE), peritoneal endometriosis (PE), deep endometriosis (DE), and other types 4 . To adequately describe this complex, multifaceted disease, several classification systems for endometriosis have been developed, with the revised American Society for Reproductive Medicine (rASRM) being the most extensively used. The rASRM classification system takes into account mainly the location, size, and depth of the implants and the degree of adhesions that are visualized during laparoscopic surgery. Based on these morphological descriptions, the rASRM classified the extent of endometriosis into four stages: minimal, mild, moderate, and severe (from Stage I to Stage IV) 5 , 6 . Treatment options, including medication, surgery, or a combination of both, largely depend on the extent and location of the disease, severity of symptoms, and desire of the patient to become pregnant. Pharmacological therapies are effective only for endometriosis-related pain 7 . Currently, laparoscopic surgery remains the main therapeutic approach for endometriosis. Significantly, abdominal surgery for severe endometriosis is far more complicated due to altered pelvic anatomy and extensive adhesions. Furthermore, laparoscopic surgery for severe endometriosis is associated with a high risk of complications 8 – 11 . In 2022, the new European Society of Human Reproduction and Embryology (ESHRE) guidelines challenged laparoscopy as the gold standard diagnostic test and recommended that clinicians use imaging during the diagnostic work-up for endometriosis 10 . Thus, if severe endometriosis can be identified with preoperative clinical data before surgery, clinicians should be able to fully understand the patient’s condition and make justifiable perioperative surgery protocols and treatment decisions, such as preoperatively utilizing gonadotropin-releasing hormone (GnRH) agonists before surgery. Therefore, we developed severe endometriosis risk prediction models using existing clinical and imaging data through machine learning and artificial intelligence. METHODS 2.1 Study population and design The data for this single-center retrospective study were obtained from 471 patients who sought consultation from the Department of Gynecology and Ultrasound at the First Hospital of China Medical University between December 2019 and December 2023. Patients underwent surgical treatment and were diagnosed with endometriosis by postoperative pathology. The inclusion criteria were as follows: (a) patients whose pathology confirmed a diagnosis of endometriosis, (b) patients who underwent surgical treatment, and (c) patients who were older than 18 years and who underwent transvaginal ultrasonography and urinary system ultrasonography before surgery (demographic characteristics and pathological, laboratory and sonographic imaging data were available). The exclusion criteria were as follows: (a) had endometriotic lesions located beyond the pelvic area, (b) had malignant tumors, and (c) had a surgical history of endometriosis. This research protocol followed the principles outlined in the Declaration of Helsinki and received approval from the Ethics Committee of the First Affiliated Hospital of China Medical University ([2023]577). All participant information was kept confidential. No names or other identifying information was included in the study. The flowchart of the study is presented in Fig. 1 . 2.2 Method of staging endometriosis In this study, the stage of endometriosis was determined according to the scoring system of the revised American Society for Reproductive Medicine (rASRM) 5 . Patients with stage IV disease (score > 40) were categorized as the severe group. The diagnosis of severe endometriosis relies on visualization during surgery (typically involving laparoscopy) and pathology. 2.3 Ultrasound examination Ultrasonic examination was performed with a GE Voluson E8, a GE Voluson E10 (GE Healthcare, Chicago, IL, USA), or a Philips EPIQ7 (Philips EPIQ7, Bothell Everett Highway, Washington, USA) with a 1.0–5.0 MHz transabdominal probe and a 5.0–9.0 MHz transvaginal probe. All patients underwent preoperative transabdominal and transvaginal ultrasound based on four four-step screening approaches proposed by the International Deep Endometriosis Analysis (IDEA) consensus 12 . 2.4 Clinical characteristics A total of 39 variables were evaluated, including basic information such as age; complaints, including dysmenorrhea and chronic pelvic pain; and other menstrual cycle-related symptoms, such as constipation, diarrhea, urinary frequency, and urgency. Menstrual history included menopausal status, parity, gravidity, number of abortions, age at menarche, and period and cycle length. Laboratory examination results included prothrombin time (PT), prothrombin time activity (PTA), international normalized ratio (INR), and CA125 levels. Ultrasound data included pelvic endometriosis nodules, adenomyosis, retroverted uterus, negative sliding sign, peritoneal fluid, bilateral OEs, number of OE cavities, number of OEs with hyperechoic attachment to the cyst wall, maximum OE diameter, and ovarian mobility. Typical sonographic signs of the ultrasound data are shown in Fig. 2 . 2.5 Statistical analysis We performed feature selection using the least absolute shrinkage and selection operator (LASSO), which compresses variable coefficients to prevent overfitting and address severe covariance problems. Subsequently, seven ML algorithms, including logistic regression (LR), recursive partitioning and regression trees (rpart), random forest (RF), extreme gradient boosting (XGBoost), support vector machine (SVM), k-nearest neighbors (KNN), and neural network (NNET), were used to develop the predictive model. The performance of the model in predicting severe endometriosis was evaluated using the area under the receiver operating characteristic curve (AUROC) and accuracy analysis. The final model was determined after hyperparameter tuning via grid search and 10-fold cross-validation for each algorithm. Characteristic importance was assessed using Shapley additive interpretation (SHAP), which provides the degree of influence of each feature in the sample on the model and the positive and negative effects on the model. Higher absolute SHAP values were associated with features that had the greatest impact on the model's predictive scores. All predictive models were implemented using R (version 4.3.1) software with the mlr3 package. The study participants were divided into a severe group (n = 183) and a nonsevere group (n = 125) according to the rASRM system. Patients were randomly divided into training and testing groups at a ratio of 8:2. The testing dataset was used to evaluate and compare the performance of each model. Continuous variables are described as the mean ± standard deviation (‾ x ± s), and comparations between groups were performed using the t-test for continuous variables. For continuous variables that did not follow a normal distribution, medians and quartiles are presented, and Wilcoxon tests were used to compare groups. Categorical variables are expressed as frequencies (percentages), and comparisons between groups of unordered categorical variables were made using the χ 2 test or Fisher's exact probability method. For missing data, the random forest algorithm was used for interpolation. A P < 0.05 indicated a significant difference. RESULTS 3.1 Baseline information of training and test sets A total of 308 patients were included in this study. A comparison of the preoperative variables and detailed information on the features of the demographics between the severe and nonsevere groups is presented in Table 1 , which indicates that there was no statistically significant difference between the two groups (p > 0.05). Among the women screened, the rate of severe endometriosis was approximately 59.2% (183/308). The study population (n = 308) was randomly divided into a training set (246) and a testing set (62), which were used to further validate the predictive models. No statistically significant difference existed between the patient characteristics in the training and testing datasets. Table 1 demographics characteristics between the severe and nonsevere endometriosis groups Variable Overall, N = 308 1 Non-severe group N = 125 1 Severe group, N = 183 1 P 2 Age 0.03 18–35 113 (37%) 56 (45%) 57 (31%) 36–45 142 (46%) 47 (38%) 95 (52%) > 46 53 (17%) 22 (18%) 31 (17%) Menopausal status 0.075 Premenopausal Postmenopausal 12 (3.9%) 8 (6.4%) 4 (2.2%) Age at menarche 0.171 ≤ 14 41 (13%) 21 (17%) 20 (11%) > 14 period 0.595 ≤ 4 58 (19%) 22 (18%) 36 (20%) 5–6 123 (40%) 47 (38%) 76 (42%) ≥ 7 127 (41%) 56 (45%) 71 (39%) Cycle-length 0.371 <25 94 (31%) 39 (31%) 55 (30%) 25–29 74 (24%) 25 (20%) 49 (27%) 30–34 140 (45%) 61 (49%) 79 (43%) Number of parities 0.833 0 84 (27%) 36 (29%) 48 (26%) 1 89 (29%) 33 (26%) 56 (31%) 2 67 (22%) 30 (24%) 37 (20%) 3 51 (17%) 18 (14%) 33 (18%) 4 13 (4.2%) 6 (4.8%) 7 (3.8%) 5 4 (1.3%) 2 (1.6%) 2 (1.1%) Number of gravidities 0.6 0 102 (33%) 45 (36%) 57 (31%) 1 185 (60%) 73 (58%) 112 (61%) 2 21 (6.8%) 7 (5.6%) 14 (7.7%) Number of abortions 0.741 0 170 (55%) 67 (54%) 103 (56%) 1 76 (25%) 33 (26%) 43 (23%) 2 45 (15%) 16 (13%) 29 (16%) 3 13 (4.2%) 7 (5.6%) 6 (3.3%) 4 4 (1.3%) 2 (1.6%) 2 (1.1%) severe dysmenorrhea 0.026 Yes 130 (42%) 43 (34%) 87 (48%) No Menstrual-cycle-related-symptoms (MCRS) 0.068 Yes 35 (11%) 9 (7.2%) 26 (14%) No PT 13.16 (0.85) 13.18 (0.96) 13.14 (0.77) 0.334 PTA 100 (11) 99 (11) 101 (11) 0.027 INR 1.00 (0.06) 1.01 (0.07) 1.00 (0.06) 0.101 APTT 36.3 (4.0) 36.7 (4.4) 36.0 (3.7) 0.066 Fg 3.05 (0.76) 3.01 (0.70) 3.08 (0.80) 0.611 TT 16.55 (1.01) 16.54 (1.03) 16.56 (1.00) 0.673 D_D_ln -1.31 (-1.51, -0.94) -1.41 (-1.51, -1.02) -1.20 (-1.51, -0.88) 0.02 WBC 5.89 (4.89, 7.20) 6.06 (4.97, 7.25) 5.81 (4.83, 7.10) 0.566 Neutrophil 60 (52, 65) 59 (51, 65) 60 (52, 66) 0.327 Lymphocyte 31 (25, 38) 32 (26, 39) 31 (25, 37) 0.288 Monocyte 7.08 (1.68) 6.98 (1.72) 7.14 (1.66) 0.55 Eosinophil% 1.60 (0.80, 2.50) 1.50 (0.70, 2.30) 1.60 (0.90, 2.70) 0.134 Red blood cells 4.17 (0.47) 4.23 (0.47) 4.14 (0.47) 0.202 Hemoglobin 117 (18) 117 (18) 117 (19) 0.878 PLT 259 (213, 301) 261 (210, 296) 259 (218, 301) 0.864 Platelet-to-lymphocyte ratio 146 (113, 190) 135 (112, 189) 152 (116, 195) 0.336 Neutrophil -to-lymphocyte ratio 1.91 (1.35, 2.54) 1.84 (1.31, 2.48) 1.93 (1.42, 2.69) 0.278 CA12-5 48 (30, 80) 37 (25, 61) 58 (34, 91) < 0.001 Pelvic endometriosis nodules 0.012 Yes 43 (14%) 10 (8.0%) 33 (18%) No Adenomyosis 0.039 Yes 48 (16%) 13 (10%) 35 (19%) No Retroverted uterus 0.046 Yes 78 (25%) 24 (19%) 54 (30%) No Sliding sign(negative) < 0.001 Yes 107 (35%) 12 (9.8%) 95 (52%) No Pelvic fluid < 0.001 No 113 (37%) 62 (50%) 51 (28%) Yes Bilateral OE < 0.001 No 214 (69%) 108 (86%) 106 (58%) Yes 94 (31%) 17 (14%) 77 (42%) Number of OE cavities 0.019 0 23 (7.5%) 7 (5.6%) 16 (8.7%) 1 167 (54%) 80 (64%) 87 (48%) 2 or more 118 (38%) 38 (30%) 80 (44%) papillary projections of OE 0.357 Yes 21 (6.8%) 6 (4.8%) 15 (8.2%) No OME diameter 6.6(4.7, 8.3) 6.3 (4.4, 8.0) 6.7 (4.9, 8.3) 0.45 Ovarian mobility < 0.001 No 182 (59%) 92 (74%) 90 (49%) Yes (one ovary) 98 (32%) 29 (23%) 69 (38%) Yes (two ovaries) 28 (9.1%) 4 (3.2%) 24 (13%) 1 Mean (SD); Median (Q1, Q3); n (%) 2 Fisher’s exact test; Wilcoxon rank sum test 3.2 Predictive model independent feature selection A LASSO regression analysis was conducted using 39 independent variables with vertical lines plotted at values selected using tenfold cross-validation, resulting in 18 features with nonzero coefficients(Fig. 2 a, b), including negative sliding signs, bilateral OE, pelvic fluid, dysmenorrhea, EO%, menstrual cycle-related symptoms (MCRS), TT, period, retroverted uterus, ovarian mobility, PTA, D-D (ln), CA125, maximum OE diameter, and menopausal status. 3.3 Comprehensive analysis of the multiple models The data of 18 features selected by LASSO regression analyses were used to generate 7 ML models to predict severe endometriosis. The AUROC curves and accuracy of the7 ML models are presented in Fig. 3 . The performances of these 7 models are listed in Table 2 . Comparative analysis revealed that RF and logistic regression models exhibited the most robust performance in predicting severe endometriosis. Figure 5 visually illustrates the relationship between the actual feature values and their corresponding SHAP values in the RF model, showing how each feature contributes to the predicted probability. The "negative sliding sign" emerged as the most influential feature in this model. Variable importance in projection (VIP) scores were used to rank the variables in terms of their importance to the predictive model; the variables are presented in Fig. 5 b. Table 2 The performances of 7ML models set model accuracy roc_auc train logistic 0.734 0.815 train rpart 0.734 0.826 train random forest 0.749 0.840 train xgboost 0.722 0.804 train svm 0.587 0.813 train knn 0.710 0.779 train nnet 0.720 0.790 test logistic 0.692 0.767 test rpart 0.603 0.699 test random forest 0.667 0.744 test xgboost 0.641 0.714 test svm 0.590 0.778 test knn 0.679 0.737 test nnet 0.679 0.731 3.4 Identification of the final model The final model was identified by reducing features of the RF model. Among the 18 features, 6 were significant (Fig. 6 ). The 6 features were put in the predictive model to reduce the number of features, and the AUC for the ROC curve is shown in Fig. 7 . Hence, we focused on the 6-feature RF model, which included negative sliding signs, pelvic fluid, bilateral OE, severe dysmenorrhea, EO, and MCRS, as the final model for further analysis. The final model outperformed the image-based DL model and clinical model and achieved AUROCs of 0.865 and 0.720 in the training and testing datasets, respectively(Table 3 ). We examined the variance inflation factor (VIF) to detect multicollinearity (ordered by importance) (Table 4 ). All predictor variables had a variance inflation factor (VIF) values of less than 10, indicating no multicollinearity. Table 3 The performances of the final models Model set metric value 6-feature prediction model train accuracy 0.776 train ROC-AUC 0.865 test accuracy 0.718 test ROC-AUC 0.720 Table 4 variance inflation factor (VIF) to predictors VIF model Sliding-sign 1.279137 Bilateral-OME 1.070493 MCRS 1.055951 UPI 1.219260 pain 1.041372 EO 1.093235 3.6 Interpretation of the final model To ensure the clinical utility and transparency of the model, we employed the SHAP method for interpretability, which quantifies the contribution of each variable to the prediction. This allowed us to understand the model's decision-making process at both global and individual levels. The SHAP summary plot (Fig. 3 A & B) visualize the average contribution of each feature, ranked in descending order, providing a global understanding of their influence. Additionally, individual Shapley values (Fig. 4 ), known as "Local Shapley values," reveal how specific features contribute to the prediction for each patient, allowing clinicians to understand the reasoning behind the model's output on an individual level. By leveraging the SHAP method, we provided a clear and interpretable framework for clinicians to understand the model's predictions and foster trust and confidence in its application. DISCUSSION Compared with nonsevere endometriosis, severe endometriosis is characterized by more altered pelvic anatomy and extensive adhesions 13 . Laparoscopy is costly and undoubtedly risky for patients with severe endometriosis. The diagnostic value of US images and clinical parameters for endometriosis have been explored previously. However, little is known about the diagnostic capacity of endometriosis staging. Therefore, we proposed a predictive model based on the ML model to easily and reliably predict severe endometriosis. In this study, we identified and evaluated a novel ML model for the prediction of severe pelvic endometriosis that comprised routinely available clinical sonographic and laboratory data. The model achieved high performance on both the training and testing datasets. As shown in Fig. 8 , we found that a negative sliding sign with a negative pelvic fluid was beneficial for the diagnosis of severe endometriosis. In terms of ultrasound parameters, a negative sliding sign and negative pelvic fluid had positive effects on the diagnosis of severe endometriosis in the model, since these ultrasonic signs can reflect an obliterated cul-de-sac in patients. Previous studies have shown that the TVS sliding sign has good diagnostic performance for predicting an obliterated cul-de-sac. In a more recent meta-analysis published in 2022 (12) , the pooled estimated sensitivity and specificity of TVS for detecting obliterated cul-de-sac were 88% (95% CI: 81%-93%) and 94% (95% CI: 91%-96%), respectively. In recent years, researchers have suggested utilizing the sliding sign to predict paraphimosis and the fertility index in patients with endometriosis 14 , 15 . Additionally, we can visualize a triangle-shaped accumulation of pelvic fluid in a unobliterated cul-de-sac. In an abnormal setting in which there is obliteration, we cannot elicit the triangle sign because the fluid cannot fill the densely adherent cul-de-sac. According to the American Society for Reproductive Medicine (ASRM) classification, if an obliterated cul-de-sac is observed, the disease is classified as severe endometriosis 5 , 6 . In this study, we also assessed the contribution of certain scoring items in the ASRM system, including bilateral OE, to the predictive model. Similarly, Zhao et al 16 attempted to identify predictors of preoperative endometriosis severity and proposed a prediction formula. This retrospective study included patients with dysmenorrhea, which is consistent with our findings. Among the clinical manifestations, other clinical variables related to menstruation in addition to dysmenorrhea, such as menstrual constipation and diarrhea, were included in the prediction model. The strength of this study is that we developed a predictive model for severe endometriosis. These predictors are readily available and provide new insights into the pathogenesis of endometriosis. In terms of laboratory indices, patients with severe endometriosis had higher D-dimer levels, indicating hypercoagulability, than those with nonsevere endometriosis. This may be attributed to activation of the intrinsic coagulation system by recurrent bleeding in patients. Coagulation-related factors have excellent diagnostic value in endometriosis and are correlated with disease prognosis and endometriotic cyst diameter 17 , 18 . A multicenter prospective study reported lower EO patients with endometriosis than in controls (p = 0.045), which differs from the results of this study 19 . Although promising, this study has some limitations that warrant consideration. This retrospective, single-center design and relatively small sample size limit the generalizability of the findings. External validation of the prediction model is essential to assess its performance in different populations and settings. Furthermore, while repeatability analysis within the training and testing sets demonstrated high consistency, some degree of error might be present owing to the inherent uncertainties in segmentation. CONCLUSIONS In this study, we developed a predictive model for stage IV endometriosis using machine learning, with a random forest model demonstrating superior performance to predict the severity of this disease before surgery. The SHAP method provides personalized risk assessments that enhance the interpretability and clinical utility of the model. This computer-aided approach holds potential for assisting clinicians in managing severe endometriosis, potentially improving noninvasive diagnostics, reducing delays, and optimizing surgical outcomes. Future research should focus on the external validation of the model with larger, multi-center datasets to explore the impact of different data sources and feature engineering strategies. Additionally, investigating the application of the model in various clinical scenarios and assessing its cost-effectiveness will further enhance its impact on patient care. Declarations Fund This work was supported by Natural Science Foundation of Liaoning Province, grant number (FWZR2020005) Author Contributions Statement (I) Conception and design: Siqi Cao, Yanjun Liu (II) Administrative support: Yanjun Liu (III) Provision of study materials or patients: Xingzhe Li, Ziyao Ji , Yanjun Liu (IV) Collection and assembly of data: Siqi Cao, Xin Zheng, Jiaxin Zhang (V) Data analysis and interpretation: Siqi Cao (VI) Manuscript writing: All authors (VII) Final approval of manuscript: All authors Competing interests The author(s) declare no competing interests. Ethical Statement The study was conducted in accordance with the Declaration of Helsinki (as revised in 2013). The study was approved by the Ethics Committee of the First Affiliated Hospital of China Medical University ([2023]577) and informed consent was taken from all individual participants. Additional information Data availability: The data that support the findings of this study are available on request from the corresponding author, Dr Yanjun Liu, Department of Ultrasound, The First Hospital of China Medical University, People's Republic of China, Shenyang, 110001, Liaoning Province, China. e-mail: [email protected] . References Smyk, J. M. et al. Cardiovascular risks and endothelial dysfunction in reproductive-age women with endometriosis. Sci. Rep. 14 , 24127. 10.1038/s41598-024-73841-7 (2024). Taylor, H. S., Kotlyar, A. M. & Flores, V. A. Endometriosis is a chronic systemic disease: clinical challenges and novel innovations. Lancet 397 , 839–852. 10.1016/s0140-6736(21)00389-5 (2021). Zizolfi, B. et al. Endometriosis and dysbiosis: State of art. Front. Endocrinol. (Lausanne) . 14 , 1140774. 10.3389/fendo.2023.1140774 (2023). Powell, S. G. et al. Vascularisation in Deep Endometriosis: A Systematic Review with Narrative Outcomes. Cells 12 10.3390/cells12091318 (2023). Revised American Society for Reproductive Medicine classification of endometriosis. Fertil Steril 67, 817–821, doi: (1996). 10.1016/s0015-0282(97)81391-x (1997). Keckstein, J. & Hudelist, G. Classification of deep endometriosis (DE) including bowel endometriosis: From r-ASRM to #Enzian-classification. Best Pract. Res. Clin. Obstet. Gynaecol. 71 , 27–37. 10.1016/j.bpobgyn.2020.11.004 (2021). França, P. R. C., Lontra, A. C. P. & Fernandes, P. D. Endometriosis: A Disease with Few Direct Treatment Options. Molecules 27 10.3390/molecules27134034 (2022). Goldberg, J. M., Falcone, T. & Diamond, M. P. Current controversies in tubal disease, endometriosis, and pelvic adhesion. Fertil. Steril. 112 , 417–425. 10.1016/j.fertnstert.2019.06.021 (2019). Koninckx, P. R., Ussia, A., Adamyan, L., Wattiez, A. & Donnez, J. Deep endometriosis: definition, diagnosis, and treatment. Fertil. Steril. 98 , 564–571. 10.1016/j.fertnstert.2012.07.1061 (2012). Becker, C. M. et al. ESHRE guideline: endometriosis. Hum Reprod Open hoac009, doi: (2022). 10.1093/hropen/hoac009 (2022). Clark, N. V. et al. Laparoscopic treatment of endometriosis and predictors of major complications: A retrospective cohort study. Acta Obstet. Gynecol. Scand. 99 , 317–323. 10.1111/aogs.13762 (2020). Guerriero, S. et al. Systematic approach to sonographic evaluation of the pelvis in women with suspected endometriosis, including terms, definitions and measurements: a consensus opinion from the International Deep Endometriosis Analysis (IDEA) group. Ultrasound Obstet. Gynecol. 48 , 318–332. 10.1002/uog.15955 (2016). Sanchez, A. M. et al. Is the oocyte quality affected by endometriosis? A review of the literature. J. Ovarian Res. 10 10.1186/s13048-017-0341-4 (2017). Guerriero, S. et al. Accuracy of transvaginal ultrasound for diagnosis of deep endometriosis in uterosacral ligaments, rectovaginal septum, vagina and bladder: systematic review and meta-analysis. Ultrasound Obstet. Gynecol. 46 , 534–545. 10.1002/uog.15667 (2015). Alfaraj, S. et al. Negative Sliding Sign during Dynamic Ultrasonography Predicts Low Endometriosis Fertility Index at Laparoscopy. J. Minim. Invasive Gynecol. 28 , 249–258e242. 10.1016/j.jmig.2020.05.003 (2021). Zhao, H. et al. A preoperative predictive model for stage IV endometriosis. J. Obstet. Gynaecol. 43 , 2188072. 10.1080/01443615.2023.2188072 (2023). Li, Y. et al. The effects of coagulation factors on the risk of endometriosis: a Mendelian randomization study. BMC Med. 21 , 195. 10.1186/s12916-023-02881-z (2023). Ling, X. & Wang, T. Diagnostic and prognostic value of coagulation-related factors in endometriosis. Am. J. Transl Res. 14 , 7924–7931 (2022). Chen, T., Wei, J. L., Leng, T., Gao, F. & Hou, S. Y. The diagnostic value of the combination of hemoglobin, CA199, CA125, and HE4 in endometriosis. J. Clin. Lab. Anal. 35 , e23947. 10.1002/jcla.23947 (2021). Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 19 Apr, 2025 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Revision requested 06 Jan, 2025 Reviews received at journal 31 Dec, 2024 Reviewers agreed at journal 20 Dec, 2024 Reviews received at journal 12 Dec, 2024 Reviewers agreed at journal 02 Dec, 2024 Reviewers invited by journal 30 Nov, 2024 Editor assigned by journal 30 Nov, 2024 Editor invited by journal 15 Nov, 2024 Submission checks completed at journal 14 Nov, 2024 First submitted to journal 22 Oct, 2024 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-5309546","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":386590983,"identity":"fd113821-fab4-42f4-87d8-82e7c4eaa9de","order_by":0,"name":"Siqi Cao","email":"","orcid":"","institution":"Department of Ultrasound, The First Hospital of China Medical University","correspondingAuthor":false,"prefix":"","firstName":"Siqi","middleName":"","lastName":"Cao","suffix":""},{"id":386590984,"identity":"9f2a95f9-09e7-45eb-b770-8ba230774a1c","order_by":1,"name":"Xingzhe Li","email":"","orcid":"","institution":"Department of Ultrasound, The First Hospital of China Medical University","correspondingAuthor":false,"prefix":"","firstName":"Xingzhe","middleName":"","lastName":"Li","suffix":""},{"id":386590985,"identity":"7eced351-b50e-4c99-87bd-1d988af6d562","order_by":2,"name":"Xin Zheng","email":"","orcid":"","institution":"Department of Ultrasound, The First Hospital of China Medical University","correspondingAuthor":false,"prefix":"","firstName":"Xin","middleName":"","lastName":"Zheng","suffix":""},{"id":386590986,"identity":"3dfacb53-bb90-47fe-aa9c-c0e647726424","order_by":3,"name":"Jiaxin Zhang","email":"","orcid":"","institution":"Department of Ultrasound, The First Hospital of China Medical University","correspondingAuthor":false,"prefix":"","firstName":"Jiaxin","middleName":"","lastName":"Zhang","suffix":""},{"id":386590987,"identity":"68cc0431-a84a-4205-aedd-65119c2bcb7e","order_by":4,"name":"Ziyao Ji","email":"","orcid":"","institution":"Department of Ultrasound, The First Hospital of China Medical University","correspondingAuthor":false,"prefix":"","firstName":"Ziyao","middleName":"","lastName":"Ji","suffix":""},{"id":386590988,"identity":"81795810-1d1f-40e2-9bb3-3408bb6871b8","order_by":5,"name":"yanjun liu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA1ElEQVRIie3QMQrCMBSA4SeF6vCwTlLo0BMIrxSKQw+TUqhLhR7BA3iAFC/h1DnSoYsHEFwKgnPGgoKmbk7JKJh/yRveR0gAbLYfbA6weQyUqtERQg4GxAVgAVTFOGanem9GIADZqgPjduaaEJ/1cUVOuOKlggihtxRawnJObtRctse2WkNUH5ieCCRkyUg4AqOrnmQ7JF+Rsm/RNSO5g0QjAUOCfTHhxKLmfCf1yb7+Ld60LEA+X2HS5TcphzT0Ag2BRfm14WvWP9d0wmDLZrPZ/ro329VFLR++qxcAAAAASUVORK5CYII=","orcid":"","institution":"Department of Ultrasound, The First Hospital of China Medical University","correspondingAuthor":true,"prefix":"","firstName":"yanjun","middleName":"","lastName":"liu","suffix":""}],"badges":[],"createdAt":"2024-10-22 07:53:06","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5309546/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5309546/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-025-96093-5","type":"published","date":"2025-04-19T15:57:23+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":71690137,"identity":"d7662971-b015-4f32-8ce5-c7a2b017ba0b","added_by":"auto","created_at":"2024-12-17 17:57:37","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":3530703,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eTypical ultrasonography of related ultrasound data\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eA negative sliding sign; B bilateral OE; C retroverted uterus; D adenomyosis;\u003c/p\u003e\n\u003cp\u003eE Papillary projections (arrow heads); F OE cavities (arrow heads); G pelvic fluid\u003c/p\u003e\n\u003cp\u003eH anteversion of uterus; I OE\u003c/p\u003e","description":"","filename":"Onlinefigure1.png","url":"https://assets-eu.researchsquare.com/files/rs-5309546/v1/b0681bcf3dc7615f3aa4632d.png"},{"id":71690144,"identity":"11eb1e7f-6700-4e6b-a69e-505ce93a3aeb","added_by":"auto","created_at":"2024-12-17 17:57:37","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":1502320,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eFlowchart of the study design\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"Onlinefigure2.png","url":"https://assets-eu.researchsquare.com/files/rs-5309546/v1/eb6e16b490f556b655686e80.png"},{"id":71690138,"identity":"346bb2c6-40e2-40d6-bca8-7382955fab40","added_by":"auto","created_at":"2024-12-17 17:57:37","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":586547,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eDemographic and clinical feature selection using LASSO regression\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"Onlinefigure3.png","url":"https://assets-eu.researchsquare.com/files/rs-5309546/v1/821cd2f1594383c8b1e6198f.png"},{"id":71690502,"identity":"360d4d0d-cc9b-42c7-8e0e-fb7b0b4157fa","added_by":"auto","created_at":"2024-12-17 18:05:37","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":509290,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eReceiver–operating characteristic curves of 7 machine learning models.\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"Onlinefigure4.png","url":"https://assets-eu.researchsquare.com/files/rs-5309546/v1/0a5b2462b638cbb9985725ed.png"},{"id":71690141,"identity":"08c28a5c-cda6-4c39-bb71-54f7cc3ad8f9","added_by":"auto","created_at":"2024-12-17 17:57:37","extension":"png","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":614484,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eSHAP analysis of the RF model. \u003c/strong\u003eA visual representation of each feature of the RF model showing the relationship between the importance of each feature.\u003c/p\u003e","description":"","filename":"Onlinefigure5.png","url":"https://assets-eu.researchsquare.com/files/rs-5309546/v1/07558fb02db131dd1989b774.png"},{"id":71690140,"identity":"14851bbc-a193-4230-a59f-49ee28f23752","added_by":"auto","created_at":"2024-12-17 17:57:37","extension":"png","order_by":6,"title":"Figure 6","display":"","copyAsset":false,"role":"figure","size":284496,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eForest plot of\u003c/strong\u003e \u003cstrong\u003ethe RF model.\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"figure6.png","url":"https://assets-eu.researchsquare.com/files/rs-5309546/v1/cc07800846f47d939ce9e917.png"},{"id":71690503,"identity":"a03fe90a-13c9-4337-ba69-1c20e9df76ab","added_by":"auto","created_at":"2024-12-17 18:05:37","extension":"png","order_by":7,"title":"Figure 7","display":"","copyAsset":false,"role":"figure","size":269303,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eReceiver–operating characteristic curves of the final model\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"Onlinefigure7.png","url":"https://assets-eu.researchsquare.com/files/rs-5309546/v1/4f6667fb609fc4161e689b80.png"},{"id":71690145,"identity":"fd17680f-220a-477a-b847-fe4b27a276f6","added_by":"auto","created_at":"2024-12-17 17:57:38","extension":"png","order_by":8,"title":"Figure 8","display":"","copyAsset":false,"role":"figure","size":288886,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eLocal Shapley values for interpretation of the final model.\u003c/strong\u003e The horizontal ordinate represents the decision score. f is the function of the predictive model, f(x) is the final decision probability for input x, and E[f(x)] is the expected value (mean value) of the final model’s decision probabilities for all training samples (which is 0.396). For sample (a), the negative sliding sign and bilateral OE make +0.181 and +0.105 contributions, respectively, supporting the decision to apply severe endometriosis. For sample (b), the contributions of the sliding sign, negative bilateral OE, were -0.268 and -0.214, respectively, supporting the decision to treat nonsevere endometriosis\u003c/p\u003e","description":"","filename":"Onlinefigure8.png","url":"https://assets-eu.researchsquare.com/files/rs-5309546/v1/f88b24eae1de70e98e70cbc6.png"},{"id":81050956,"identity":"00f7ecff-bfaf-4581-be62-e2bb1f0d46f2","added_by":"auto","created_at":"2025-04-21 16:08:43","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2313136,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5309546/v1/0a2fdc33-a9f0-4958-8d25-2449411efdf8.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Identification and Validation of a Novel Machine Learning Model for Predicting Severe Pelvic Endometriosis: A Retrospective Study","fulltext":[{"header":"INTRODUCTION","content":"\u003cp\u003eAs a common chronic inflammatory disease, endometriosis is defined by the presence of endometrial-like tissue outside the uterus and is closely associated with dysmenorrhea, pelvic pain, infertility, dysuria, and deep dyspareunia\u003csup\u003e\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e,\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e\u003c/sup\u003e. It poses a significant threat to quality of life, especially in women of reproductive age, with an increasing prevalence rate of 10%\u003csup\u003e3\u003c/sup\u003e.\u003c/p\u003e \u003cp\u003eEndometriosis can be categorized into different phenotypes, such as ovarian endometriosis (OE), peritoneal endometriosis (PE), deep endometriosis (DE), and other types\u003csup\u003e\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e\u003c/sup\u003e. To adequately describe this complex, multifaceted disease, several classification systems for endometriosis have been developed, with the revised American Society for Reproductive Medicine (rASRM) being the most extensively used. The rASRM classification system takes into account mainly the location, size, and depth of the implants and the degree of adhesions that are visualized during laparoscopic surgery. Based on these morphological descriptions, the rASRM classified the extent of endometriosis into four stages: minimal, mild, moderate, and severe (from Stage I to Stage IV)\u003csup\u003e\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e,\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e\u003c/sup\u003e. Treatment options, including medication, surgery, or a combination of both, largely depend on the extent and location of the disease, severity of symptoms, and desire of the patient to become pregnant. Pharmacological therapies are effective only for endometriosis-related pain\u003csup\u003e\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e\u003c/sup\u003e. Currently, laparoscopic surgery remains the main therapeutic approach for endometriosis. Significantly, abdominal surgery for severe endometriosis is far more complicated due to altered pelvic anatomy and extensive adhesions. Furthermore, laparoscopic surgery for severe endometriosis is associated with a high risk of complications \u003csup\u003e\u003cspan additionalcitationids=\"CR9 CR10\" citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e\u003c/sup\u003e.\u003c/p\u003e \u003cp\u003eIn 2022, the new European Society of Human Reproduction and Embryology (ESHRE) guidelines challenged laparoscopy as the gold standard diagnostic test and recommended that clinicians use imaging during the diagnostic work-up for endometriosis\u003csup\u003e\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e\u003c/sup\u003e. Thus, if severe endometriosis can be identified with preoperative clinical data before surgery, clinicians should be able to fully understand the patient\u0026rsquo;s condition and make justifiable perioperative surgery protocols and treatment decisions, such as preoperatively utilizing gonadotropin-releasing hormone (GnRH) agonists before surgery. Therefore, we developed severe endometriosis risk prediction models using existing clinical and imaging data through machine learning and artificial intelligence.\u003c/p\u003e"},{"header":"METHODS","content":"\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e \u003ch2\u003e2.1 Study population and design\u003c/h2\u003e \u003cp\u003e The data for this single-center retrospective study were obtained from 471 patients who sought consultation from the Department of Gynecology and Ultrasound at the First Hospital of China Medical University between December 2019 and December 2023. Patients underwent surgical treatment and were diagnosed with endometriosis by postoperative pathology.\u003c/p\u003e \u003cp\u003eThe inclusion criteria were as follows: (a) patients whose pathology confirmed a diagnosis of endometriosis, (b) patients who underwent surgical treatment, and (c) patients who were older than 18 years and who underwent transvaginal ultrasonography and urinary system ultrasonography before surgery (demographic characteristics and pathological, laboratory and sonographic imaging data were available). The exclusion criteria were as follows: (a) had endometriotic lesions located beyond the pelvic area, (b) had malignant tumors, and (c) had a surgical history of endometriosis.\u003c/p\u003e \u003cp\u003e This research protocol followed the principles outlined in the Declaration of Helsinki and received approval from the Ethics Committee of the First Affiliated Hospital of China Medical University ([2023]577). All participant information was kept confidential. No names or other identifying information was included in the study. The flowchart of the study is presented in Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003c/div\u003e\n\u003ch3\u003e2.2 Method of staging endometriosis\u003c/h3\u003e\n\u003cp\u003eIn this study, the stage of endometriosis was determined according to the scoring system of the revised American Society for Reproductive Medicine (rASRM)\u003csup\u003e\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e\u003c/sup\u003e. Patients with stage IV disease (score \u0026gt; 40) were categorized as the severe group. The diagnosis of severe endometriosis relies on visualization during surgery (typically involving laparoscopy) and pathology.\u003c/p\u003e\n\u003ch3\u003e2.3 Ultrasound examination\u003c/h3\u003e\n\u003cp\u003eUltrasonic examination was performed with a GE Voluson E8, a GE Voluson E10 (GE Healthcare, Chicago, IL, USA), or a Philips EPIQ7 (Philips EPIQ7, Bothell Everett Highway, Washington, USA) with a 1.0–5.0 MHz transabdominal probe and a 5.0–9.0 MHz transvaginal probe. All patients underwent preoperative transabdominal and transvaginal ultrasound based on four four-step screening approaches proposed by the International Deep Endometriosis Analysis (IDEA) consensus\u003csup\u003e\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e\u003c/sup\u003e.\u003c/p\u003e\n\u003ch3\u003e2.4 Clinical characteristics\u003c/h3\u003e\n\u003cp\u003eA total of 39 variables were evaluated, including basic information such as age; complaints, including dysmenorrhea and chronic pelvic pain; and other menstrual cycle-related symptoms, such as constipation, diarrhea, urinary frequency, and urgency. Menstrual history included menopausal status, parity, gravidity, number of abortions, age at menarche, and period and cycle length. Laboratory examination results included prothrombin time (PT), prothrombin time activity (PTA), international normalized ratio (INR), and CA125 levels. Ultrasound data included pelvic endometriosis nodules, adenomyosis, retroverted uterus, negative sliding sign, peritoneal fluid, bilateral OEs, number of OE cavities, number of OEs with hyperechoic attachment to the cyst wall, maximum OE diameter, and ovarian mobility. Typical sonographic signs of the ultrasound data are shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003e.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e\n\u003ch3\u003e2.5 Statistical analysis\u003c/h3\u003e\n\u003cp\u003eWe performed feature selection using the least absolute shrinkage and selection operator (LASSO), which compresses variable coefficients to prevent overfitting and address severe covariance problems. Subsequently, seven ML algorithms, including logistic regression (LR), recursive partitioning and regression trees (rpart), random forest (RF), extreme gradient boosting (XGBoost), support vector machine (SVM), k-nearest neighbors (KNN), and neural network (NNET), were used to develop the predictive model. The performance of the model in predicting severe endometriosis was evaluated using the area under the receiver operating characteristic curve (AUROC) and accuracy analysis. The final model was determined after hyperparameter tuning via grid search and 10-fold cross-validation for each algorithm. Characteristic importance was assessed using Shapley additive interpretation (SHAP), which provides the degree of influence of each feature in the sample on the model and the positive and negative effects on the model. Higher absolute SHAP values were associated with features that had the greatest impact on the model's predictive scores. All predictive models were implemented using R (version 4.3.1) software with the mlr3 package.\u003c/p\u003e \u003cp\u003eThe study participants were divided into a severe group (n = 183) and a nonsevere group (n = 125) according to the rASRM system. Patients were randomly divided into training and testing groups at a ratio of 8:2. The testing dataset was used to evaluate and compare the performance of each model. Continuous variables are described as the mean ± standard deviation (‾\u003cem\u003ex\u003c/em\u003e ± s), and comparations between groups were performed using the t-test for continuous variables. For continuous variables that did not follow a normal distribution, medians and quartiles are presented, and Wilcoxon tests were used to compare groups. Categorical variables are expressed as frequencies (percentages), and comparisons between groups of unordered categorical variables were made using the χ\u003csup\u003e\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e\u003c/sup\u003e test or Fisher's exact probability method. For missing data, the random forest algorithm was used for interpolation. A \u003cem\u003eP\u003c/em\u003e \u0026lt; \u003cem\u003e0.05\u003c/em\u003e indicated a significant difference.\u003c/p\u003e \u003cdiv id=\"Sec8\" class=\"Section2\"\u003e \u003cdiv id=\"Sec9\" class=\"Section3\"\u003e \u003c/div\u003e \u003c/div\u003e\n\n \u003cdiv id=\"Sec13\" class=\"Section2\"\u003e \u003cp\u003e \u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec14\" class=\"Section2\"\u003e \u003cp\u003e \u003c/p\u003e \u003c/div\u003e "},{"header":"RESULTS","content":"\u003ch2\u003e3.1 Baseline information of training and test sets\u003c/h2\u003e\u003cp\u003eA total of 308 patients were included in this study. A comparison of the preoperative variables and detailed information on the features of the demographics between the severe and nonsevere groups is presented in Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e, which indicates that there was no statistically significant difference between the two groups (p \u0026gt; 0.05). Among the women screened, the rate of severe endometriosis was approximately 59.2% (183/308). The study population (n = 308) was randomly divided into a training set (246) and a testing set (62), which were used to further validate the predictive models. No statistically significant difference existed between the patient characteristics in the training and testing datasets.\u003c/p\u003e\u003cp\u003e \u003c/p\u003e\u003cdiv class=\"gridtable\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e\u003ctable float=\"Yes\" id=\"Tab1\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003edemographics characteristics between the severe and nonsevere endometriosis groups\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e\u003ccolgroup cols=\"5\"\u003e\u003c/colgroup\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eVariable\u003c/p\u003e \u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOverall, N = 308\u003csup\u003e\u003cem\u003e1\u003c/em\u003e\u003c/sup\u003e\u003c/p\u003e \u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eNon-severe group N = 125\u003csup\u003e\u003cem\u003e1\u003c/em\u003e\u003c/sup\u003e\u003c/p\u003e \u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eSevere group,\u003c/p\u003e \u003cp\u003eN = 183\u003csup\u003e\u003cem\u003e1\u003c/em\u003e\u003c/sup\u003e\u003c/p\u003e \u003c/th\u003e\u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003eP\u003csup\u003e\u003cem\u003e\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e\u003c/em\u003e\u003c/sup\u003e\u003c/p\u003e \u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAge\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.03\u003c/p\u003e \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e18–35\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e113 (37%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e56 (45%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e57 (31%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e36–45\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e142 (46%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e47 (38%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e95 (52%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u0026gt; 46\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e53 (17%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e22 (18%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e31 (17%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMenopausal status\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.075\u003c/p\u003e \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePremenopausal\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePostmenopausal\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e12 (3.9%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e8 (6.4%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e4 (2.2%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAge at menarche\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.171\u003c/p\u003e \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e≤ 14\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e41 (13%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e21 (17%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e20 (11%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u0026gt; 14\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eperiod\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.595\u003c/p\u003e \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e≤ 4\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e58 (19%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e22 (18%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e36 (20%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e5–6\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e123 (40%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e47 (38%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e76 (42%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e≥ 7\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e127 (41%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e56 (45%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e71 (39%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCycle-length\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.371\u003c/p\u003e \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u0026lt;25\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e94 (31%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e39 (31%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e55 (30%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e25–29\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e74 (24%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e25 (20%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e49 (27%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e30–34\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e140 (45%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e61 (49%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e79 (43%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNumber of parities\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.833\u003c/p\u003e \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e84 (27%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e36 (29%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e48 (26%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e1\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e89 (29%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e33 (26%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e56 (31%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e2\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e67 (22%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e30 (24%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e37 (20%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e3\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e51 (17%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e18 (14%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e33 (18%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e4\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e13 (4.2%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e6 (4.8%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e7 (3.8%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e5\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e4 (1.3%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2 (1.6%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e2 (1.1%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNumber of gravidities\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.6\u003c/p\u003e \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e102 (33%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e45 (36%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e57 (31%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e1\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e185 (60%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e73 (58%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e112 (61%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e2\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e21 (6.8%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e7 (5.6%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e14 (7.7%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNumber of abortions\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.741\u003c/p\u003e \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e170 (55%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e67 (54%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e103 (56%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e1\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e76 (25%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e33 (26%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e43 (23%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e2\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e45 (15%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e16 (13%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e29 (16%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e3\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e13 (4.2%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e7 (5.6%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e6 (3.3%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e4\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e4 (1.3%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e2 (1.6%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e2 (1.1%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003esevere dysmenorrhea\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.026\u003c/p\u003e \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eYes\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e130 (42%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e43 (34%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e87 (48%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNo\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMenstrual-cycle-related-symptoms\u003c/p\u003e \u003cp\u003e(MCRS)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.068\u003c/p\u003e \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eYes\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e35 (11%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e9 (7.2%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e26 (14%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNo\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePT\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e13.16 (0.85)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e13.18 (0.96)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e13.14 (0.77)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.334\u003c/p\u003e \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePTA\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e100 (11)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e99 (11)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e101 (11)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.027\u003c/p\u003e \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eINR\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1.00 (0.06)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1.01 (0.07)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.00 (0.06)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.101\u003c/p\u003e \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAPTT\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e36.3 (4.0)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e36.7 (4.4)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e36.0 (3.7)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.066\u003c/p\u003e \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eFg\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e3.05 (0.76)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e3.01 (0.70)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e3.08 (0.80)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.611\u003c/p\u003e \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eTT\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e16.55 (1.01)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e16.54 (1.03)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e16.56 (1.00)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.673\u003c/p\u003e \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eD_D_ln\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e-1.31 (-1.51, -0.94)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e-1.41 (-1.51, -1.02)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e-1.20 (-1.51, -0.88)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.02\u003c/p\u003e \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eWBC\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e5.89 (4.89, 7.20)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e6.06 (4.97, 7.25)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e5.81 (4.83, 7.10)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.566\u003c/p\u003e \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNeutrophil\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e60 (52, 65)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e59 (51, 65)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e60 (52, 66)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.327\u003c/p\u003e \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLymphocyte\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e31 (25, 38)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e32 (26, 39)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e31 (25, 37)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.288\u003c/p\u003e \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMonocyte\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e7.08 (1.68)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e6.98 (1.72)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e7.14 (1.66)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.55\u003c/p\u003e \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eEosinophil%\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1.60 (0.80, 2.50)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1.50 (0.70, 2.30)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.60 (0.90, 2.70)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.134\u003c/p\u003e \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eRed blood cells\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e4.17 (0.47)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e4.23 (0.47)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e4.14 (0.47)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.202\u003c/p\u003e \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHemoglobin\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e117 (18)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e117 (18)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e117 (19)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.878\u003c/p\u003e \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePLT\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e259 (213, 301)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e261 (210, 296)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e259 (218, 301)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.864\u003c/p\u003e \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePlatelet-to-lymphocyte ratio\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e146 (113, 190)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e135 (112, 189)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e152 (116, 195)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.336\u003c/p\u003e \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNeutrophil -to-lymphocyte ratio\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1.91 (1.35, 2.54)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1.84 (1.31, 2.48)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.93 (1.42, 2.69)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.278\u003c/p\u003e \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCA12-5\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e48 (30, 80)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e37 (25, 61)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e58 (34, 91)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e\u0026lt; 0.001\u003c/p\u003e \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePelvic endometriosis nodules\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.012\u003c/p\u003e \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eYes\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e43 (14%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e10 (8.0%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e33 (18%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNo\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAdenomyosis\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.039\u003c/p\u003e \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eYes\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e48 (16%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e13 (10%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e35 (19%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNo\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eRetroverted uterus\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.046\u003c/p\u003e \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eYes\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e78 (25%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e24 (19%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e54 (30%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNo\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSliding sign(negative)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e\u0026lt; 0.001\u003c/p\u003e \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eYes\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e107 (35%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e12 (9.8%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e95 (52%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNo\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePelvic fluid\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e\u0026lt; 0.001\u003c/p\u003e \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNo\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e113 (37%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e62 (50%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e51 (28%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eYes\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eBilateral OE\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e\u0026lt; 0.001\u003c/p\u003e \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNo\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e214 (69%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e108 (86%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e106 (58%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eYes\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e94 (31%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e17 (14%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e77 (42%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNumber of OE cavities\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.019\u003c/p\u003e \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e23 (7.5%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e7 (5.6%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e16 (8.7%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e1\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e167 (54%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e80 (64%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e87 (48%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e2 or more\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e118 (38%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e38 (30%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e80 (44%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003epapillary projections of OE\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.357\u003c/p\u003e \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eYes\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e21 (6.8%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e6 (4.8%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e15 (8.2%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNo\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eOME diameter\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e6.6(4.7, 8.3)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e6.3 (4.4, 8.0)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e6.7 (4.9, 8.3)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.45\u003c/p\u003e \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eOvarian mobility\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e\u0026lt; 0.001\u003c/p\u003e \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNo\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e182 (59%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e92 (74%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e90 (49%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eYes\u003c/p\u003e \u003cp\u003e(one ovary)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e98 (32%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e29 (23%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e69 (38%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eYes\u003c/p\u003e \u003cp\u003e(two ovaries)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e28 (9.1%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e4 (3.2%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e24 (13%)\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003ctfoot\u003e\u003ctr\u003e\u003ctd colspan=\"5\"\u003e\u003csup\u003e\u003cem\u003e\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e\u003c/em\u003e\u003c/sup\u003eMean (SD); Median (Q1, Q3); n (%)\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd colspan=\"5\"\u003e\u003csup\u003e\u003cem\u003e\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e\u003c/em\u003e\u003c/sup\u003eFisher’s exact test; Wilcoxon rank sum test\u003c/td\u003e\u003c/tr\u003e\u003c/tfoot\u003e\u003c/table\u003e\u003c/div\u003e\u003cp\u003e\u003c/p\u003e\u003ch3\u003e3.2 Predictive model independent feature selection\u003c/h3\u003e\u003cp\u003eA LASSO regression analysis was conducted using 39 independent variables with vertical lines plotted at values selected using tenfold cross-validation, resulting in 18 features with nonzero coefficients(Fig.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003ea, b), including negative sliding signs, bilateral OE, pelvic fluid, dysmenorrhea, EO%, menstrual cycle-related symptoms (MCRS), TT, period, retroverted uterus, ovarian mobility, PTA, D-D (ln), CA125, maximum OE diameter, and menopausal status.\u003c/p\u003e\u003ch2\u003e3.3 Comprehensive analysis of the multiple models\u003c/h2\u003e\u003cp\u003eThe data of 18 features selected by LASSO regression analyses were used to generate 7 ML models to predict severe endometriosis. The AUROC curves and accuracy of the7 ML models are presented in Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003e. The performances of these 7 models are listed in Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e. Comparative analysis revealed that RF and logistic regression models exhibited the most robust performance in predicting severe endometriosis. Figure\u0026nbsp;\u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e5\u003c/span\u003e visually illustrates the relationship between the actual feature values and their corresponding SHAP values in the RF model, showing how each feature contributes to the predicted probability. The \"negative sliding sign\" emerged as the most influential feature in this model. Variable importance in projection (VIP) scores were used to rank the variables in terms of their importance to the predictive model; the variables are presented in Fig.\u0026nbsp;\u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e5\u003c/span\u003eb.\u003c/p\u003e\u003cp\u003e \u003c/p\u003e\u003cp\u003e \u003c/p\u003e\u003cdiv class=\"gridtable\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003ctable float=\"Yes\" id=\"Tab2\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 2\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eThe performances of 7ML models\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e\u003ccolgroup cols=\"4\"\u003e\u003c/colgroup\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eset\u003c/p\u003e \u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003emodel\u003c/p\u003e \u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eaccuracy\u003c/p\u003e \u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eroc_auc\u003c/p\u003e \u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003etrain\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003elogistic\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.734\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.815\u003c/p\u003e \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003etrain\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003erpart\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.734\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.826\u003c/p\u003e \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003etrain\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003erandom forest\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.749\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.840\u003c/p\u003e \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003etrain\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003exgboost\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.722\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.804\u003c/p\u003e \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003etrain\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003esvm\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.587\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.813\u003c/p\u003e \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003etrain\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eknn\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.710\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.779\u003c/p\u003e \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003etrain\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003ennet\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.720\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.790\u003c/p\u003e \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003etest\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003elogistic\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.692\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.767\u003c/p\u003e \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003etest\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003erpart\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.603\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.699\u003c/p\u003e \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003etest\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003erandom forest\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.667\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.744\u003c/p\u003e \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003etest\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003exgboost\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.641\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.714\u003c/p\u003e \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003etest\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003esvm\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.590\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.778\u003c/p\u003e \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003etest\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eknn\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.679\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.737\u003c/p\u003e \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003etest\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003ennet\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0.679\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.731\u003c/p\u003e \u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/table\u003e\u003c/div\u003e\u003cp\u003e\u003c/p\u003e\u003cp\u003e \u003c/p\u003e\u003ch2\u003e3.4 Identification of the final model\u003c/h2\u003e\u003cp\u003eThe final model was identified by reducing features of the RF model. Among the 18 features, 6 were significant (Fig.\u0026nbsp;\u003cspan refid=\"Fig5\" class=\"InternalRef\"\u003e6\u003c/span\u003e). The 6 features were put in the predictive model to reduce the number of features, and the AUC for the ROC curve is shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig6\" class=\"InternalRef\"\u003e7\u003c/span\u003e. Hence, we focused on the 6-feature RF model, which included negative sliding signs, pelvic fluid, bilateral OE, severe dysmenorrhea, EO, and MCRS, as the final model for further analysis. The final model outperformed the image-based DL model and clinical model and achieved AUROCs of 0.865 and 0.720 in the training and testing datasets, respectively(Table\u0026nbsp;\u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\u003e). We examined the variance inflation factor (VIF) to detect multicollinearity (ordered by importance) (Table\u0026nbsp;\u003cspan refid=\"Tab4\" class=\"InternalRef\"\u003e4\u003c/span\u003e). All predictor variables had a variance inflation factor (VIF) values of less than 10, indicating no multicollinearity.\u003c/p\u003e\u003cp\u003e \u003c/p\u003e\u003cp\u003e \u003c/p\u003e\u003cp\u003e \u003c/p\u003e\u003cdiv class=\"gridtable\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003ctable float=\"Yes\" id=\"Tab3\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 3\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eThe performances of the final models\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e\u003ccolgroup cols=\"4\"\u003e\u003c/colgroup\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eModel\u003c/p\u003e \u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eset\u003c/p\u003e \u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003emetric\u003c/p\u003e \u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003evalue\u003c/p\u003e \u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e6-feature prediction model\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003etrain\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eaccuracy\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.776\u003c/p\u003e \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003etrain\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eROC-AUC\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.865\u003c/p\u003e \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003etest\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eaccuracy\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.718\u003c/p\u003e \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003etest\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eROC-AUC\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0.720\u003c/p\u003e \u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/table\u003e\u003c/div\u003e\u003cp\u003e\u003c/p\u003e\u003cp\u003e \u003c/p\u003e\u003cdiv class=\"gridtable\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003ctable float=\"Yes\" id=\"Tab4\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 4\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003evariance inflation factor (VIF) to predictors\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e\u003ccolgroup cols=\"2\"\u003e\u003c/colgroup\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eVIF\u003c/p\u003e \u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003emodel\u003c/p\u003e \u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSliding-sign\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e1.279137\u003c/p\u003e \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eBilateral-OME\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e1.070493\u003c/p\u003e \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMCRS\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e1.055951\u003c/p\u003e \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eUPI\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e1.219260\u003c/p\u003e \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003epain\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e1.041372\u003c/p\u003e \u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eEO\u003c/p\u003e \u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e1.093235\u003c/p\u003e \u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/table\u003e\u003c/div\u003e\u003cp\u003e\u003c/p\u003e\u003ch2\u003e3.6 Interpretation of the final model\u003c/h2\u003e\u003cp\u003eTo ensure the clinical utility and transparency of the model, we employed the SHAP method for interpretability, which quantifies the contribution of each variable to the prediction. This allowed us to understand the model's decision-making process at both global and individual levels. The SHAP summary plot (Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003eA \u0026amp; B) visualize the average contribution of each feature, ranked in descending order, providing a global understanding of their influence. Additionally, individual Shapley values (Fig.\u0026nbsp;\u003cspan refid=\"Fig7\" class=\"InternalRef\"\u003e4\u003c/span\u003e), known as \"Local Shapley values,\" reveal how specific features contribute to the prediction for each patient, allowing clinicians to understand the reasoning behind the model's output on an individual level. By leveraging the SHAP method, we provided a clear and interpretable framework for clinicians to understand the model's predictions and foster trust and confidence in its application.\u003c/p\u003e"},{"header":"DISCUSSION","content":"\u003cp\u003eCompared with nonsevere endometriosis, severe endometriosis is characterized by more altered pelvic anatomy and extensive adhesions\u003csup\u003e\u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e\u003c/sup\u003e. Laparoscopy is costly and undoubtedly risky for patients with severe endometriosis. The diagnostic value of US images and clinical parameters for endometriosis have been explored previously. However, little is known about the diagnostic capacity of endometriosis staging.\u003c/p\u003e\u003cp\u003eTherefore, we proposed a predictive model based on the ML model to easily and reliably predict severe endometriosis. In this study, we identified and evaluated a novel ML model for the prediction of severe pelvic endometriosis that comprised routinely available clinical sonographic and laboratory data. The model achieved high performance on both the training and testing datasets. As shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig8\" class=\"InternalRef\"\u003e8\u003c/span\u003e, we found that a negative sliding sign with a negative pelvic fluid was beneficial for the diagnosis of severe endometriosis. In terms of ultrasound parameters, a negative sliding sign and negative pelvic fluid had positive effects on the diagnosis of severe endometriosis in the model, since these ultrasonic signs can reflect an obliterated cul-de-sac in patients.\u003c/p\u003e\u003cp\u003ePrevious studies have shown that the TVS sliding sign has good diagnostic performance for predicting an obliterated cul-de-sac. In a more recent meta-analysis published in 2022\u003csup\u003e(12)\u003c/sup\u003e, the pooled estimated sensitivity and specificity of TVS for detecting obliterated cul-de-sac were 88% (95% CI: 81%-93%) and 94% (95% CI: 91%-96%), respectively. In recent years, researchers have suggested utilizing the sliding sign to predict paraphimosis and the fertility index in patients with endometriosis\u003csup\u003e\u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e,\u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e\u003c/sup\u003e. Additionally, we can visualize a triangle-shaped accumulation of pelvic fluid in a unobliterated cul-de-sac. In an abnormal setting in which there is obliteration, we cannot elicit the triangle sign because the fluid cannot fill the densely adherent cul-de-sac. According to the American Society for Reproductive Medicine (ASRM) classification, if an obliterated cul-de-sac is observed, the disease is classified as severe endometriosis \u003csup\u003e\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e,\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e\u003c/sup\u003e. In this study, we also assessed the contribution of certain scoring items in the ASRM system, including bilateral OE, to the predictive model.\u003c/p\u003e\u003cp\u003eSimilarly, Zhao et al\u003csup\u003e\u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e\u003c/sup\u003e attempted to identify predictors of preoperative endometriosis severity and proposed a prediction formula. This retrospective study included patients with dysmenorrhea, which is consistent with our findings. Among the clinical manifestations, other clinical variables related to menstruation in addition to dysmenorrhea, such as menstrual constipation and diarrhea, were included in the prediction model.\u003c/p\u003e\u003cp\u003eThe strength of this study is that we developed a predictive model for severe endometriosis. These predictors are readily available and provide new insights into the pathogenesis of endometriosis.\u003c/p\u003e\u003cp\u003eIn terms of laboratory indices, patients with severe endometriosis had higher D-dimer levels, indicating hypercoagulability, than those with nonsevere endometriosis. This may be attributed to activation of the intrinsic coagulation system by recurrent bleeding in patients. Coagulation-related factors have excellent diagnostic value in endometriosis and are correlated with disease prognosis and endometriotic cyst diameter\u003csup\u003e\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e,\u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e\u003c/sup\u003e. A multicenter prospective study reported lower EO patients with endometriosis than in controls (p = 0.045), which differs from the results of this study\u003csup\u003e\u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e\u003c/sup\u003e.\u003c/p\u003e\u003cp\u003eAlthough promising, this study has some limitations that warrant consideration. This retrospective, single-center design and relatively small sample size limit the generalizability of the findings. External validation of the prediction model is essential to assess its performance in different populations and settings. Furthermore, while repeatability analysis within the training and testing sets demonstrated high consistency, some degree of error might be present owing to the inherent uncertainties in segmentation.\u003c/p\u003e"},{"header":"CONCLUSIONS","content":"\u003cp\u003eIn this study, we developed a predictive model for stage IV endometriosis using machine learning, with a random forest model demonstrating superior performance to predict the severity of this disease before surgery. The SHAP method provides personalized risk assessments that enhance the interpretability and clinical utility of the model. This computer-aided approach holds potential for assisting clinicians in managing severe endometriosis, potentially improving noninvasive diagnostics, reducing delays, and optimizing surgical outcomes. Future research should focus on the external validation of the model with larger, multi-center datasets to explore the impact of different data sources and feature engineering strategies. Additionally, investigating the application of the model in various clinical scenarios and assessing its cost-effectiveness will further enhance its impact on patient care.\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003eFund\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThis work was supported by Natural Science Foundation of Liaoning Province, grant number (FWZR2020005)\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAuthor Contributions Statement\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e(I) Conception and design: Siqi Cao, Yanjun Liu\u003cbr\u003e\u0026nbsp;(II) Administrative support: Yanjun Liu\u003cbr\u003e(III) Provision of study materials or patients: Xingzhe Li, Ziyao Ji\u003csup\u003e\u0026nbsp;\u003c/sup\u003e, Yanjun Liu\u003cbr\u003e\u0026nbsp;(IV) Collection and assembly of data: Siqi Cao, Xin Zheng, Jiaxin Zhang\u003cbr\u003e\u0026nbsp;(V) Data analysis and interpretation: Siqi Cao\u003cbr\u003e\u0026nbsp;(VI) Manuscript writing: All authors\u003cbr\u003e\u0026nbsp;(VII) Final approval of manuscript: All authors\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eCompeting interests\u003c/strong\u003e\u003cstrong\u003e\u003cbr\u003e\u003c/strong\u003eThe author(s) declare no competing interests.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eEthical Statement\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe study was conducted in accordance with the Declaration of Helsinki (as revised in 2013). The study was approved by the Ethics Committee of the First Affiliated Hospital of China Medical University ([2023]577) and informed consent was taken from all individual participants.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAdditional information\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eData availability:\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe data that support the findings of this study are available on request from the corresponding author, Dr Yanjun Liu, Department of Ultrasound, The First Hospital of China Medical University, People\u0026apos;s Republic of China, Shenyang, 110001, Liaoning Province, China. e-mail: [email protected].\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003eSmyk, J. M. et al. Cardiovascular risks and endothelial dysfunction in reproductive-age women with endometriosis. \u003cem\u003eSci. Rep.\u003c/em\u003e \u003cb\u003e14\u003c/b\u003e, 24127. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1038/s41598-024-73841-7\u003c/span\u003e\u003cspan address=\"10.1038/s41598-024-73841-7\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2024).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eTaylor, H. S., Kotlyar, A. M. \u0026amp; Flores, V. A. Endometriosis is a chronic systemic disease: clinical challenges and novel innovations. \u003cem\u003eLancet\u003c/em\u003e \u003cb\u003e397\u003c/b\u003e, 839\u0026ndash;852. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/s0140-6736(21)00389-5\u003c/span\u003e\u003cspan address=\"10.1016/s0140-6736(21)00389-5\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2021).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZizolfi, B. et al. Endometriosis and dysbiosis: State of art. \u003cem\u003eFront. Endocrinol. (Lausanne)\u003c/em\u003e. \u003cb\u003e14\u003c/b\u003e, 1140774. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.3389/fendo.2023.1140774\u003c/span\u003e\u003cspan address=\"10.3389/fendo.2023.1140774\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2023).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePowell, S. G. et al. Vascularisation in Deep Endometriosis: A Systematic Review with Narrative Outcomes. \u003cem\u003eCells\u003c/em\u003e \u003cb\u003e12\u003c/b\u003e \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.3390/cells12091318\u003c/span\u003e\u003cspan address=\"10.3390/cells12091318\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2023).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRevised American Society for Reproductive Medicine classification of endometriosis. \u003cem\u003eFertil Steril\u003c/em\u003e 67, 817\u0026ndash;821, doi: (1996). \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/s0015-0282(97)81391-x\u003c/span\u003e\u003cspan address=\"10.1016/s0015-0282(97)81391-x\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (1997).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKeckstein, J. \u0026amp; Hudelist, G. Classification of deep endometriosis (DE) including bowel endometriosis: From r-ASRM to #Enzian-classification. \u003cem\u003eBest Pract. Res. Clin. Obstet. Gynaecol.\u003c/em\u003e \u003cb\u003e71\u003c/b\u003e, 27\u0026ndash;37. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/j.bpobgyn.2020.11.004\u003c/span\u003e\u003cspan address=\"10.1016/j.bpobgyn.2020.11.004\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2021).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eFran\u0026ccedil;a, P. R. C., Lontra, A. C. P. \u0026amp; Fernandes, P. D. Endometriosis: A Disease with Few Direct Treatment Options. \u003cem\u003eMolecules\u003c/em\u003e \u003cb\u003e27\u003c/b\u003e \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.3390/molecules27134034\u003c/span\u003e\u003cspan address=\"10.3390/molecules27134034\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2022).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGoldberg, J. M., Falcone, T. \u0026amp; Diamond, M. P. Current controversies in tubal disease, endometriosis, and pelvic adhesion. \u003cem\u003eFertil. Steril.\u003c/em\u003e \u003cb\u003e112\u003c/b\u003e, 417\u0026ndash;425. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/j.fertnstert.2019.06.021\u003c/span\u003e\u003cspan address=\"10.1016/j.fertnstert.2019.06.021\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2019).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKoninckx, P. R., Ussia, A., Adamyan, L., Wattiez, A. \u0026amp; Donnez, J. Deep endometriosis: definition, diagnosis, and treatment. \u003cem\u003eFertil. Steril.\u003c/em\u003e \u003cb\u003e98\u003c/b\u003e, 564\u0026ndash;571. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/j.fertnstert.2012.07.1061\u003c/span\u003e\u003cspan address=\"10.1016/j.fertnstert.2012.07.1061\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2012).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBecker, C. M. et al. ESHRE guideline: endometriosis. \u003cem\u003eHum Reprod Open\u003c/em\u003e hoac009, doi: (2022). \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1093/hropen/hoac009\u003c/span\u003e\u003cspan address=\"10.1093/hropen/hoac009\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2022).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eClark, N. V. et al. Laparoscopic treatment of endometriosis and predictors of major complications: A retrospective cohort study. \u003cem\u003eActa Obstet. Gynecol. Scand.\u003c/em\u003e \u003cb\u003e99\u003c/b\u003e, 317\u0026ndash;323. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1111/aogs.13762\u003c/span\u003e\u003cspan address=\"10.1111/aogs.13762\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2020).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGuerriero, S. et al. Systematic approach to sonographic evaluation of the pelvis in women with suspected endometriosis, including terms, definitions and measurements: a consensus opinion from the International Deep Endometriosis Analysis (IDEA) group. \u003cem\u003eUltrasound Obstet. Gynecol.\u003c/em\u003e \u003cb\u003e48\u003c/b\u003e, 318\u0026ndash;332. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1002/uog.15955\u003c/span\u003e\u003cspan address=\"10.1002/uog.15955\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2016).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSanchez, A. M. et al. Is the oocyte quality affected by endometriosis? A review of the literature. \u003cem\u003eJ. Ovarian Res.\u003c/em\u003e \u003cb\u003e10\u003c/b\u003e \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1186/s13048-017-0341-4\u003c/span\u003e\u003cspan address=\"10.1186/s13048-017-0341-4\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2017).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGuerriero, S. et al. Accuracy of transvaginal ultrasound for diagnosis of deep endometriosis in uterosacral ligaments, rectovaginal septum, vagina and bladder: systematic review and meta-analysis. \u003cem\u003eUltrasound Obstet. Gynecol.\u003c/em\u003e \u003cb\u003e46\u003c/b\u003e, 534\u0026ndash;545. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1002/uog.15667\u003c/span\u003e\u003cspan address=\"10.1002/uog.15667\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2015).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAlfaraj, S. et al. Negative Sliding Sign during Dynamic Ultrasonography Predicts Low Endometriosis Fertility Index at Laparoscopy. \u003cem\u003eJ. Minim. Invasive Gynecol.\u003c/em\u003e \u003cb\u003e28\u003c/b\u003e, 249\u0026ndash;258e242. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/j.jmig.2020.05.003\u003c/span\u003e\u003cspan address=\"10.1016/j.jmig.2020.05.003\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2021).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZhao, H. et al. A preoperative predictive model for stage IV endometriosis. \u003cem\u003eJ. Obstet. Gynaecol.\u003c/em\u003e \u003cb\u003e43\u003c/b\u003e, 2188072. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1080/01443615.2023.2188072\u003c/span\u003e\u003cspan address=\"10.1080/01443615.2023.2188072\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2023).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLi, Y. et al. The effects of coagulation factors on the risk of endometriosis: a Mendelian randomization study. \u003cem\u003eBMC Med.\u003c/em\u003e \u003cb\u003e21\u003c/b\u003e, 195. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1186/s12916-023-02881-z\u003c/span\u003e\u003cspan address=\"10.1186/s12916-023-02881-z\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2023).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLing, X. \u0026amp; Wang, T. Diagnostic and prognostic value of coagulation-related factors in endometriosis. \u003cem\u003eAm. J. Transl Res.\u003c/em\u003e \u003cb\u003e14\u003c/b\u003e, 7924\u0026ndash;7931 (2022).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChen, T., Wei, J. L., Leng, T., Gao, F. \u0026amp; Hou, S. Y. The diagnostic value of the combination of hemoglobin, CA199, CA125, and HE4 in endometriosis. \u003cem\u003eJ. Clin. Lab. Anal.\u003c/em\u003e \u003cb\u003e35\u003c/b\u003e, e23947. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1002/jcla.23947\u003c/span\u003e\u003cspan address=\"10.1002/jcla.23947\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2021).\u003c/span\u003e\u003c/li\u003e \u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Severe endometriosis, Transvaginal ultrasound, Machine learning, Prediction model, SHAP","lastPublishedDoi":"10.21203/rs.3.rs-5309546/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5309546/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003ch2\u003eBackground\u003c/h2\u003e \u003cp\u003eSevere endometriosis significantly impacts the quality of life, particularly in women of reproductive age. Though numerous studies have conducted predictive models with preoperative clinical data for endometriosis, most risk models focus on diagnosis rather than disease staging. This study aimed to explore potential factors for endometriosis severity and to develop a classification model to assess the accuracy of predicting the risk of severe endometriosis.\u003c/p\u003e\u003ch2\u003eMethods\u003c/h2\u003e \u003cp\u003eA total of 308 patients with endometriosis were retrospectively analyzed. The stage of endometriosis was classified according to the scoring system of the revised American Society for Reproductive Medicine (rASRM) system, through surgical visualization,which is the most widely used staging system globally. All patients underwent preoperative transabdominal and transvaginal ultrasound, based on four steps screening approach proposed by The International Deep Endometriosis Analysis (IDEA) consensus. We randomly divided these data into training and testing datasets at a ratio of 8:2. Least absolute shrinkage and selection operator (LASSO) was performed to identify the potential risk factors for severe endometriosis. Then, we used 7 machine learning(ML) models to construct the predictive models. The area under the receiver-operating-characteristics curve (AUC) and accuracy were used to evaluate and determine the most effective model. Finally, SHapley Additive exPlanations (SHAP) interpretation was calculated to evaluate each parameter's contribution to risk prediction.\u003c/p\u003e\u003ch2\u003eResults\u003c/h2\u003e \u003cp\u003eIn this retrospective study, about 59.2% (183/308) of endometriosis patients were diagnosed with severe endometriosis. The predictors of severe endometriosis occurrence were found to be compliance of 18 factors such as the negative sliding sign, pelvic fluid, bilateral OE, serum CA125 level and severe dysmenorrhea according to LASSO. The random forest (RF) model performed best in discriminative ability among the 7 ML models. After reducing features according to feature importance rank, an explainable final RF model was established with 6 features. The final model could accurately predict severe endometriosis with the area under curve (AUC) of 0.744 and an accuracy of 0.667 in the test set. From the SHAP map, it was found that the negative sliding sign had the greatest impact on the diagnostic performance of the RF model.\u003c/p\u003e\u003ch2\u003eConclusions\u003c/h2\u003e \u003cp\u003eWe constructed a predictive model based on the ML model, and the RF model showed a better performance. we also provided a personalized risk assessment for the development of stage IV in endometriosis patients explained by SHAP. This can help clinicians to treat severe endometriosis.\u003c/p\u003e","manuscriptTitle":"Identification and Validation of a Novel Machine Learning Model for Predicting Severe Pelvic Endometriosis: A Retrospective Study","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-12-17 17:57:32","doi":"10.21203/rs.3.rs-5309546/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-01-06T12:15:53+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-12-31T13:44:34+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"275083511504656365761255467089026218585","date":"2024-12-20T13:49:12+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-12-12T13:00:40+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"12493827171756926152198094873016865818","date":"2024-12-02T15:29:55+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-11-30T07:19:13+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-11-30T07:16:23+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2024-11-15T06:15:42+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-11-14T10:14:31+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2024-10-22T07:37:15+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"85a63690-a425-49df-a31f-d40e6d249cf6","owner":[],"postedDate":"December 17th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":41192328,"name":"Health sciences/Diseases/Endocrine system and metabolic diseases/Endocrine reproductive disorders"},{"id":41192329,"name":"Health sciences/Diseases/Endocrine system and metabolic diseases/Gonadal disorders"},{"id":41192330,"name":"Health sciences/Diseases/Endocrine system and metabolic diseases/Multihormonal system disorders"},{"id":41192331,"name":"Health sciences/Diseases/Reproductive disorders/Infertility"},{"id":41192332,"name":"Health sciences/Risk factors"},{"id":41192333,"name":"Health sciences/Medical research"}],"tags":[],"updatedAt":"2025-04-21T16:03:03+00:00","versionOfRecord":{"articleIdentity":"rs-5309546","link":"https://doi.org/10.1038/s41598-025-96093-5","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2025-04-19 15:57:23","publishedOnDateReadable":"April 19th, 2025"},"versionCreatedAt":"2024-12-17 17:57:32","video":"","vorDoi":"10.1038/s41598-025-96093-5","vorDoiUrl":"https://doi.org/10.1038/s41598-025-96093-5","workflowStages":[]},"version":"v1","identity":"rs-5309546","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5309546","identity":"rs-5309546","version":["v1"]},"buildId":"M1DPXKE8UapkOyQliHcFZ","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}