Decision tree model predicts live birth after surgery for moderate-to-severe intrauterine adhesions

Advancing intrauterine adhesion severity prediction: Integrative machine learning approach with hysteroscopic cold knife system, clinical characteristics and hematological parameters

Intrauterine Adhesion (IUA) constitute a significant determinant impacting female fertility, potentially leading to infertility, miscarriage, menstrual irregularities, and placental complications. The precise assessment of the severity of IUA is pivotal for the customization of personalized treatment plans, aimed at enhancing the success rate of treatments and mitigating reproductive health risks. This study proposes bTLSMA-SVM-FS, a novel feature selection machine learning model that integrates an enhanced slime mould algorithm (SMA), termed TLSMA, with support vector machines (SVM), aiming to develop a predictive model for assessing the severity of IUA. Initially, a series of optimization comparative experiments were conducted on the TLSMA using the CEC 2017 benchmark functions. By comparing it with eleven meta-heuristic algorithms as well as eleven SOTA algorithms, the experimental outcomes corroborated the superior performance of the TLSMA. Subsequently, the developed bTLSMA-SVM-FS model was employed to conduct a thorough analysis of the clinical features of 107 IUA patients from Wenzhou People's Hospital, comprising 61 cases of moderate IUA and 46 cases of severe IUA. The evaluation results of the model demonstrated exceptional performance in predicting the severity of IUA, achieving an accuracy of 86.700 % and a specificity of 87.609 %. Moreover, the model successfully identified critical factors influencing the prediction of IUA severity, including the preoperative Chinese IUA score, production times, thrombin time, preoperative endometrial thickness, and menstruation. The identification of these key factors not only further validated the efficacy of the proposed model but also provided vital scientific evidence for a deeper understanding of the pathogenesis of IUA and the enhancement of targeted treatment strategies.

Multimodal learning system integrating electronic medical records and hysteroscopic images for reproductive outcome prediction and risk stratification of endometrial injury: a multicenter diagnostic study

OBJECTIVE

To develop a multimodal learning application system that integrates electronic medical records (EMR) and hysteroscopic images for reproductive outcome prediction and risk stratification of patients with intrauterine adhesions (IUAs) resulting from endometrial injuries.

MATERIALS AND METHODS

EMR and 5014 revisited hysteroscopic images of 753 post hysteroscopic adhesiolysis patients from the multicenter IUA database we established were randomly allocated to training, validation, and test datasets. The respective datasets were used for model development, tuning, and testing of the multimodal learning application. MobilenetV3 was employed for image feature extraction, and XGBoost for EMR and image feature ensemble learning. The performance of the application was compared against the single-modal approaches (EMR or hysteroscopic images), DeepSurv and ElasticNet models, along with the clinical scoring systems. The primary outcome was the 1-year conception prediction accuracy, and the secondary outcome was the assisted reproductive technology (ART) benefit ratio after risk stratification.

RESULTS

The multimodal learning system exhibited superior performance in predicting conception within 1-year, achieving areas under the curves of 0.967 (95% CI: 0.950-0.985), 0.936 (95% CI: 0.883-0.989), and 0.965 (95% CI: 0.935-0.994) in the training, validation, and test datasets, respectively, surpassing single-modal approaches, other models and clinical scoring systems (all P<0.05). The application of the model operated seamlessly on the hysteroscopic platform, with an average analysis time of 3.7±0.8 s per patient. By employing the application's conception probability-based risk stratification, mid-high-risk patients demonstrated a significant ART benefit (odds ratio=6, 95% CI: 1.27-27.8, P=0.02), while low-risk patients exhibited good natural conception potential, with no significant increase in conception rates from ART treatment (P=1).

CONCLUSIONS

The multimodal learning system using hysteroscopic images and EMR demonstrates promise in accurately predicting the natural conception of patients with IUAs and providing effective postoperative stratification, potentially contributing to ART triage after IUA procedures.

Artificial intelligence-driven prognostic system for conception prediction and management in intrauterine adhesions following hysteroscopic adhesiolysis: a diagnostic study using hysteroscopic images

Introduction

Intrauterine adhesions (IUAs) caused by endometrial injury, commonly occurring in developing countries, can lead to subfertility. This study aimed to develop and evaluate a DeepSurv architecture-based artificial intelligence (AI) system for predicting fertility outcomes after hysteroscopic adhesiolysis.

Methods

This diagnostic study included 555 intrauterine adhesions (IUAs) treated with hysteroscopic adhesiolysis with 4,922 second-look hysteroscopic images from a prospective clinical database (IUADB, NCT05381376) with a minimum of 2 years of follow-up. These patients were randomly divided into training, validation, and test groups for model development, tuning, and external validation. Four transfer learning models were built using the DeepSurv architecture and a code-free AI application for pregnancy prediction was also developed. The primary outcome was the model's ability to predict pregnancy within a year after adhesiolysis. Secondary outcomes were model performance which evaluated using time-dependent area under the curves (AUCs) and C-index, and ART benefits evaluated by hazard ratio (HR) among different risk groups.

Results

External validation revealed that using the DeepSurv architecture, InceptionV3+ DeepSurv, InceptionResNetV2+ DeepSurv, and ResNet50+ DeepSurv achieved AUCs of 0.94, 0.95, and 0.93, respectively, for one-year pregnancy prediction, outperforming other models and clinical score systems. A code-free AI application was developed to identify candidates for ART. Patients with lower natural conception probability indicated by the application had a higher ART benefit hazard ratio (HR) of 3.13 (95% CI: 1.22-8.02, p = 0.017).

Conclusion

InceptionV3+ DeepSurv, InceptionResNetV2+ DeepSurv, and ResNet50+ DeepSurv show potential in predicting the fertility outcomes of IUAs after hysteroscopic adhesiolysis. The code-free AI application based on the DeepSurv architecture facilitates personalized therapy following hysteroscopic adhesiolysis.

Intrauterine adhesion in ultrasound-guided manual vacuum aspiration (USG-MVA) versus electric vacuum aspiration (EVA): a randomised controlled trial

BACKGROUND

Intrauterine adhesion (IUA) can arise as a potential complication following uterine surgery, as the surgical procedure may damage the endometrial stratum basalis. The objective of this study was to assess and compare the occurrence of IUA in women who underwent ultrasound-guided manual vacuum aspiration (USG-MVA) versus electric vacuum aspiration (EVA) for managing first-trimester miscarriage.

METHODS

This was a prospective, single-centre, randomised controlled trial conducted at a university-affiliated tertiary hospital. Chinese women aged 18 years and above who had a delayed or incomplete miscarriage of ≤ 12 weeks of gestation were recruited in the Department of Obstetrics and Gynaecology at the Prince of Wales. Recruited participants received either USG-MVA or EVA for the management of their miscarriage and were invited for a hysteroscopic assessment to evaluate the incidence of IUA between 6 and 20 weeks after the surgery. Patients were contacted by phone at 6 months to assess their menstrual and reproductive outcomes.

RESULTS

303 patients underwent USG-MVA or EVA, of whom 152 were randomised to 'USG-MVA' and 151 patients to the 'EVA' group. Out of the USG-MVA group, 126 patients returned and completed the hysteroscopic assessment, while in the EVA group, 125 patients did the same. The incidence of intrauterine adhesion (IUA) was 19.0% (24/126) in the USG-MVA group and 32.0% (40/125) in the EVA group, showing a significant difference (p < 0.02) between the two groups. No significant difference in the menstrual outcomes at 6 months postoperatively between the two groups but more patients had miscarriages in the EVA group with IUA.

CONCLUSIONS

IUAs are a possible complication of USG-MVA. However, USG-MVA is associated with a lower incidence of IUA postoperatively at 6-20 weeks. USG-MVA is a feasible, effective, and safe alternative surgical treatment with less IUA for the management of first-trimester miscarriage.

TRIAL REGISTRATION

The study was registered with the Centre for Clinical Research and Biostatics- Clinical Trials Registry (CCRBCTR), which is a partner registry of the WHO Primary Registry-Chinese Clinical Trials Registry (ChiCTR) (Unique Trial Number: ChiCTR1900023198 with the first trial registration date on 16/05/2019).

Developing and validating a prediction model of live birth in patients with moderate-to-severe intrauterine adhesions: a new approach with endometrial morphology measurement by 3D transvaginal ultrasound

Background

There is no reliable method to predict the live birth rate among patients with moderate-to-severe intrauterine adhesions (IUA) after second-look hysteroscopy. Therefore, we aimed to construct a practical prediction model mainly based on the features of 3D transvaginal ultrasound (3D-TVUS). and other clinical characteristics.

Methods

From January 2018 to February 2020, a total of 870 IUA patients with fertility requirements were retrospectively enrolled based on the same method. First, the predictors were screened by logistic regression analysis. A nomogram was constructed based on the screened predictive factors in the derivation cohort. Next, receiver operating characteristic (ROC), calibration curve, and decision curve analysis (DCA) were used to assess the predictive accuracy and discriminability of the model. Finally, correlation analysis was performed to analyze the correlation between the results of 3D-TVUS and second-look hysteroscopy.

Results

A total of 558 (64.14%) participants had live births. Age, endometrial thickness, assisted reproductive technology, a homogeneous endometrial echo, a lower segment of scar contraction, and upper segmentation of the endometrial absence were included in the model. The predictive model showed good predictive performance in the derivation cohort (area under the curve, 0.837) and validation cohort (0.857). DCA demonstrated its clinical utility. A homogeneous endometrial echo was related to no segmentation of scar contraction (r=0.219; P<0.001) or no segmentation of the endometrial absence (r=0.226; P<0.001). Thicker endometrium was associated with no segmentation of the endometrial absence (r=-0.145; P=0.007).

Conclusions

The proposed method can effectively predict live birth. 3D-TVUS should be an important means for evaluating the endometrium of moderate-to-severe patients with IUA preparing for pregnancy after operation.