A nomogram model predicting the risk of postpartum stress urinary incontinence in primiparas: A multicenter study

Machine-Learning-Based Predictive Model for Bothersome Stress Urinary Incontinence Among Parous Women in Southeastern China

INTRODUCTION AND HYPOTHESIS

Accurate identification of female populations at high risk for urinary incontinence (UI) and early intervention are potentially effective initiatives to reduce the prevalence of UI. We aimed to apply machine-learning techniques to establish, internally validate, and provide interpretable risk assessment tools.

METHODS

Data from a cross-sectional epidemiological survey of female urinary incontinence conducted in 2022 were used. Sociodemographic and obstetrics-related characteristics, comorbidities, and urinary incontinence questionnaire results were used to develop multiple prediction models. Seventy percent of the individuals in the study cohort were employed in model training, and the remainder were used for internal validation. Model performance was characterized by area under the receiver-operating characteristic curve (AUC) and calibration curves, as well as Brier scores. The best-performing model was finally selected to develop an online prediction tool.

RESULTS

The results showed that bothersome stress urinary incontinence (BSUI) occurred in 9.6% (849 out of 8,830) of parous women. The XGBoost model achieved the best prediction performance (training set: AUC 0.796, 95% confidence interval [CI]: 0.778-0.815, validation set: AUC 0.720, 95% CI: 0.686-0.754). Additionally, the XGBoost model achieved the lowest (best) Brier score among the models, with sensitivity of 0.657, specificity of 0.690, accuracy of 0.688, positive predictive value of 0.231, and negative predictive value of 0.948. Based on this model, the top five risk factors for the development of BSUI among parous women were ranked as follows: body mass index, age, vaginal delivery, constipation, and maximum fetal birth weight. An online calculator was provided for clinical use.

CONCLUSION

The application of machine-learning algorithms provides an acceptable, though not perfect, prediction of BSUI risk among parous women, requiring further validation and improvement in future research.

Nomogram model for predicting medication adherence in patients with various mental disorders based on the Dryad database

OBJECTIVE

Treatment compliance among psychiatric patients is related to disease outcomes. How to assess patient compliance remains a concern. Here, we established a predictive model for medication compliance in patients with psychotic disorders to provide a reference for early intervention in treatment non-compliance behaviour.

DESIGN

Clinical information for 451 patients with psychotic disorders was downloaded from the Dryad database. The Least Absolute Shrinkage and Selection Operator regression and logistic regression were used to establish the model. Bootstrap resampling (1000 iterations) was used for internal validation and a nomogram was drawn to predict medication compliance. The consistency index, Brier score, receiver operating characteristic curve and decision curve were used for model evaluation.

SETTING

35 Italian Community Psychiatric Services.

PARTICIPANTS

451 patients prescribed with any long-acting intramuscular (LAI) antipsychotic were consecutively recruited, and assessed after 6 months and 12 months, from December 2015 to May 2017.

RESULTS

432 patients with psychotic disorders were included for model construction; among these, the compliance rate was 61.3%. The Drug Attitude Inventory-10 (DAI-10) and Brief Psychiatric Rating Scale (BPRS) scores, multiple hospitalisations in 1 year and a history of long-acting injectables were found to be independent risk factors for treatment noncompliance (all p<0.01). The concordance statistic of the nomogram was 0.709 (95% CI 0.652 to 0.766), the Brier index was 0.215 and the area under the ROC curve was 0.716 (95% CI 0.669 to 0.763); decision curve analysis showed that applying this model between the threshold probabilities of 44% and 63% improved the net clinical benefit.

CONCLUSION

A low DAI-10 score, a high BPRS score, multiple hospitalisations in 1 year and the previous use of long-acting injectable drugs were independent risk factors for medication noncompliance in patients with psychotic disorders. Our nomogram for predicting treatment adherence behaviour in psychiatric patients exhibited good sensitivity and specificity.

Prediction models for postpartum stress urinary incontinence: A systematic review

Background

Postpartum stress urinary incontinence significantly impacts the quality of life and the physical and mental health of women. A reliable predictive model for postpartum stress urinary incontinence can serve as a preventive tool. Currently, there have been numerous studies developing predictive models to assess the risk of postpartum stress urinary incontinence, but the quality and clinical applicability of these models remain unknown.

Objective

To systematically review and evaluate existing models for predicting stressful postpartum risks.

Methods

PubMed, EBSCO, The Cochrane Library, Embase, Web of Science, China National Knowledge Infrastructure, WanFang Data, SinoMed, and VIP Data databases were systematically searched from the time of database construction to October 2023. Two researchers used Critical appraisal and data extraction for systematic reviews of prediction modeling studies: the CHARMS checklist for data extraction. Three researchers used The Prediction Model Risk of Bias Assessment Tool (PROBAST) checklist for bias and applicability assessment.

Results

Eight papers including ten postpartum stress urinary incontinence prediction models were finalized. The most common predictors in the prediction models were urinary incontinence (UI) during pregnancy, followed by mode of delivery, Maternal age, parity, and UI before pregnancy. Nine of the prediction models reported discrimination with an area under the ROC curve (AUC) or C-index between 0.680 and 0.850. All included studies were at high risk of bias, mainly due to mishandling of continuous predictors, unreported or mishandled missing data, and inadequate assessment of predictive model performance.

Conclusions

Postpartum stress urinary incontinence risk prediction models are in the initial development stage, and existing prediction models have a high risk of bias and poor modeling methodological quality, which may hinder their clinical application. In the future, healthcare practitioners should follow the norms of predictive model development and reporting to develop risk prediction models with superior predictive performance, low risk of bias, and easy clinical application.

Development and external validation of clinical predictive model for stress urinary incontinence in Chinese women : a multicenter retrospective study

BACKGROUND

Stress urinary incontinence (SUI), the prevalent form of urinary incontinence, significantly impairs women's quality of life. This study aims to create a visual nomogram to estimate the risk of SUI within one year postpartum for early intervention in high-risk Chinese women.

METHODS

We recruited 1,531 postpartum women who gave birth at two hospitals in Kunshan City from 2021 to 2022. Delivery details were meticulously extracted from the hospitals' medical records system, while one-year postpartum follow-ups were conducted via phone surveys specifically designed to ascertain SUI status. Utilizing data from one hospital as the training set, logistic regression analysis was performed to pinpoint significant factors and subsequently construct the nomogram. To ensure robustness, an independent dataset sourced from the second hospital served as the external validation cohort. The model's performance was rigorously evaluated using calibration plots, ROC curves, AUC values, and DCA curves.

RESULTS

The study population was 1,125 women. The SUI incidence within one year postpartum was 26% (293/1125). According to the regression analysis, height, pre-pregnancy BMI, method of induction, mode of delivery, perineal condition, neonatal weight, SUI during pregnancy, and SUI during the first pregnancy were incorporated into the nomogram. The AUC of the nomogram was 0.829 (95% CI 0.790-0.867), and the external validation set was 0.746 (95% CI 0.689-0.804). Subgroup analysis based on parity showed good discrimination. The calibration curve indicated concordance. The DCA curve showed a significant net benefit.

CONCLUSION

Drawing from real-world data, we have successfully developed an SUI predictive model tailored for postpartum Chinese women. Upon successful external validation, this model holds immense potential as an effective screening tool for SUI, enabling timely interventions and ultimately may improve women's quality of life.

Prognostic value analysis and survival model construction of different treatment methods for advanced intestinal type gastric adenocarcinoma

Background

Intestinal-type gastric adenocarcinoma, representing 95 % of gastric malignancies, originates from the malignant transformation of gastric gland cells. Despite its prevalence, existing methods for prognosis evaluation of this cancer subtype are inadequate. This study aims to enhance patient-specific prognosis evaluation by analyzing the clinicopathological characteristics and prognostic risk factors of intestinal-type gastric adenocarcinoma patients using data from the Surveillance, Epidemiology, and End Results (SEER) Program of the National Cancer Institute (NCI).

Methods

We extracted clinical data for patients diagnosed with intestinal-type gastric adenocarcinoma between 2010 and 2015 from the SEER database, selecting 257 cases based on predefined inclusion and exclusion criteria. Independent risk factors for overall survival (OS) and cancer-specific survival (CSS) were identified using a Cox regression model. A nomogram model for predicting OS or CSS was developed from the Cox risk regression analysis and validated through the consistency index (C-index), ROC curve, and calibration curve.

Results

Age, primary tumor resection, chemotherapy, lymph node metastasis, and tumor size were identified as independent prognostic factors for OS and CSS (P < 0.05). The nomogram model, constructed from these indicators, demonstrated superior predictive consistency for OS and CSS compared to the AJCC-TNM staging system. ROC curve analysis confirmed the model's higher accuracy, and calibration curve analysis indicated good agreement between the nomogram's predictions and actual observed outcomes.

Conclusion

The nomogram model derived from SEER database analyses accurately predicts OS and CSS for patients with intestinal-type gastric adenocarcinoma. This model promises to facilitate more tailored treatments in clinical practice.

Development and Validation of a Risk Prediction Model for Female Stress Urinary Incontinence in Rural Fujian, China

Purpose

With China's rapidly aging population and the rising proportion of obese people, an increase in the number of women suffering from urinary incontinence (UI) is to be expected. In order to identify high-risk groups before leakage occurs, we aimed to develop and validate a model to predict the risk of stress UI (SUI) in rural women.

Patients and methods

This study included women aged 20-70 years in rural Fujian who participated in an epidemiologic survey of female UI conducted between June and October 2022. Subsequently the data was randomly divided into training and validation sets in a ratio of 7:3. Univariate and multivariate logistic regression analyses were used to identify independent risk factors as well as to further construct a nomogram for risk prediction. Finally, concordance index (C-index), calibration curve and decision curve analysis were applied to evaluate the performance of the predictive models.

Results

A total of 5290 rural females were enrolled, of whom 771 (14.6%) had SUI. Age, body mass index (BMI), postmenopausal status, number of vaginal deliveries, vaginal delivery of large infant, constipation and family history of pelvic organ prolapse (POP) and SUI were included in the nomogram. C-index of this prediction model for the training and validation sets was 0.835 (95% confidence interval [CI] = 0.818-0.851) and 0.829 (95% CI = 0.796-0.858), respectively, and the calibration curves and decision analysis curves for both the training and validation sets showed that the model was well-calibrated and had a positive net benefit.

Conclusion

This model accurately estimated the SUI risk of rural women in Fujian, which may serve as an effective primary screening tool for the early identification of SUI risk and provide a basis for further implementation of individualized early intervention. Moreover, the model is concise and intuitive, which makes it more operational for rural women with scarce medical resources.

Development and internal validation of a risk prediction model for stress urinary incontinence throughout pregnancy: A multicenter retrospective longitudinal study in Indonesia

BACKGROUND

This study aimed to develop a risk prediction model for stress urinary incontinence (SUI) throughout pregnancy in Indonesian women.

METHODS

We conducted a multicenter retrospective longitudinal study involving pregnant women in Indonesia, who sought care at obstetrics clinics from January 2023 to March 2023, encompassing all stages of pregnancy. We collected data on their predictive factors and SUI outcome. SUI was diagnosed based on responses to the "leaks when you are physically active/exercising" criterion in the ICIQ-UI-SF questionnaire during our investigation of the participants. The models underwent internal validation using a bootstrapping method with 1000 resampling iterations to assess discrimination and calibration.

RESULTS

A total of 660 eligible pregnant women were recruited from the two study centers, with an overall SUI prevalence of 39% (258/660). The final model incorporated three predictive factors: BMI during pregnancy, constipation, and previous delivery mode. The area under the curve (AUROC) was 0.787 (95% CI: 0.751-0.823). According to the max Youden index, the optimal cut-off point was 44.6%, with a sensitivity of 79.9% and specificity of 65.9%. A discrimination slope of 0.213 was found.

CONCLUSION

The developed risk prediction model for SUI in pregnant women offers a valuable tool for early identification and intervention among high-risk SUI populations in Indonesian pregnant women throughout their pregnancies. These findings challenge the assumption that a high BMI and multiple previous deliveries are predictors of SUI in Indonesian women. Further research is recommended to validate the model in diverse populations and settings.

Machine learning in female urinary incontinence: A scoping review

Introduction and Hypothesis

The aim was to conduct a scoping review of the literature on the use of machine learning (ML) in female urinary incontinence (UI) over the last decade.

Methods

A systematic search was performed among the Medline, Google Scholar, PubMed, and Web of Science databases using the following keywords: [Urinary incontinence] and [(Machine learning) or (Predict) or (Prediction model)]. Eligible studies were considered to have applied ML model to explore different management processes of female UI. Data analyzed included the field of application, type of ML, input variables, and results of model validation.

Results

A total of 798 papers were identified while 23 finally met the inclusion criteria. The vast majority of studies applied logistic regression to establish models (91.3%, 21/23). Most frequently ML was applied to predict postpartum UI (39.1%, 9/23), followed by de novo incontinence after pelvic floor surgery (34.8%, 8/23).There are also three papers using ML models to predict treatment outcomes and three papers using ML models to assist in diagnosis. Variables for modeling included demographic characteristics, clinical data, pelvic floor ultrasound, and urodynamic parameters. The area under receiver operating characteristic curve of these models fluctuated from 0.56 to 0.95, and only 11 studies reported sensitivity and specificity, with sensitivity ranging from 20% to 96.2% and specificity from 59.8% to 94.5%.

Conclusion

Machine learning modeling demonstrated good predictive and diagnostic abilities in some aspects of female UI, showing its promising prospects in near future. However, the lack of standardization and transparency in the validation and evaluation of the models, and the insufficient external validation greatly diminished the applicability and reproducibility, thus a focus on filling this gap is strongly recommended for future research.

Prevalence and factors of urinary incontinence among postpartum: systematic review and meta-analysis

BACKGROUND

Postpartum urinary incontinence substantially impacts the psychophysical well-being of women. The influencing factors contributing to postpartum urinary incontinence remain a subject of contention in clinical investigation. By elucidating the factors contributing to postpartum urinary incontinence, more efficacious interventions for laboring women can be devised. Consequently, this review endeavored to scrutinize the repercussions of maternal postpartum urinary incontinence to furnish empirical references for the clinical advancement of preventive strategies.

METHOD

The investigation employed bibliographic databases: Embase, PubMed, Web of Science, Cochrane Library, CBM, VIP, CNKI, and Wan Fang Data for article retrieval. A comprehensive consideration of all study designs was undertaken during the examination of the effects of postpartum urinary incontinence. The temporal limitation was set at all articles prior to February 2023. Studies incorporated laboring mothers experiencing normative labor and parturition. A total of 28,303 women were encompassed in the reviewed investigations.

RESULTS

A total of 5,915 putative citations were identified, from which 32 articles were selected for evaluating the effects of postpartum urinary incontinence. Meta-analyses revealed that the incidence of postpartum urinary incontinence was 26% [95%CI: (21% ~ 30%)]. Twelve pivotal variables were identified to influence postpartum urinary incontinence: cesarean delivery, vaginal delivery, age ≥ 35 years, multiparty (number of deliveries ≥ 2), neonatal weight > 4 kg, perineal dystonia, antecedents of urological incontinence-related pathology, maternal pre-conception BMI ≥ 24 kg/m^2, perineal laceration, instrumental parturition, historical pelvic surgical procedures, and protracted second stage of labor. Among these, cesarean delivery was identified as a protective factor against postpartum urinary incontinence.

CONCLUSION

The study corroborated that anamnestic factors pertinent to urinary incontinence, vaginal parturitions, and neonates with a weight exceeding 4 kg serve as significant risk factors for postpartum urinary incontinence. Cesarean delivery emerged as a protective factor against postpartum urinary incontinence. Based on the prevalence of postpartum urinary incontinence, proactive intervention is requisite to mitigate the risk of postpartum urinary incontinence in postpartum women possessing these risk factors.

TRIAL REGISTRATION

CRD42023412096.

Help-seeking behavior for nonsevere stress urinary incontinence among elderly women in communities, Beijing, China

INTRODUCTION AND HYPOTHESIS

Stress urinary incontinence (SUI) is a common health problem and influences women's quality of life significantly. In order to enhance health education according to a specific situation, it is essential to identify barriers to seeking help among elderly women with nonsevere SUI. The objectives were to investigate reasons for (not) seeking help for nonsevere SUI among women aged ≥60 years, and to analyze factors affecting help-seeking behavior.

METHODS

We enrolled 368 women aged ≥60 years with nonsevere SUI from communities. They were asked to filled out sociodemographic information, International Consultation on Incontinence Questionnaire Short Form (ICIQ-SF), Incontinence Quality of Life (I-QOL), and self-constructed questiones on help-seeking behavior. Mann-Whitney U tests were used to analyze the different factors between seeking group and nonseeking group.

RESULTS

Only 28 women (7.61%) had ever sought help from health professionals for SUI. The most frequent reason for seeking help was urine-soaked clothes (67.86%, 19 out of 28). The most frequent reason for not seeking help was that women thought it was normal (67.35%, 229 out of 340). Compared with the nonseeking group, the seeking group had higher total ICIQ-SF scores and lower total I-QOL scores.

CONCLUSION

Among elderly women with nonsevere SUI, the rate of seeking help was low. Lack of correct perception about the SUI kept women from doctor visits. Women who were bothered by more severe SUI and lower quality of life were more likely to seek help.

Establishment and validation of a simple nomogram for predicting early postpartum stress urinary incontinence among women with vaginal delivery: a retrospective study

BACKGROUND

Stress urinary incontinence (SUI) is a common public health issue that negatively impacts the quality of life for women worldwide, of which early detection and rehabilitation are consequently pivotal. The aim of this study is to establish a simple nomogram for identifying women at risk of postpartum SUI.

METHODS

A retrospective study was conducted in a tertiary specialized hospital in Shanghai, China. The study included only women with singleton, full-term, and vaginal deliveries. 2,441 women who delivered from July 2019 to November 2019 were included in the training cohort, and 610 women who delivered from January 2022 to February 2022 were included in the validation cohort. SUI was determined by the International Consultation on Incontinence Questionnaire-Urinary Incontinence Short Form (ICIQ-UI-SF). Univariate and multifactorial logistical regression were used to identify independent risk factors for postpartum SUI and further construct the nomogram accordingly. Based on concordance statistics (C-statistics), calibration curves, and decision curve analyses, we evaluated the performance of the nomogram in the training cohort and the validation cohort. In addition, the model was validated internally in the training cohort through cross-validation.

RESULTS

There were no significant statistically differences in important baseline data such as age, pre-pregnancy BMI, and parity between the training and validation cohorts. SUI was observed in 431 (17.6%) and 125 (20.5%) women in the training and validation cohorts, respectively. According to the regression analysis, age, parity, second stage of labor, infant weight, and forceps delivery were included in the nomogram. The nomogram had a C-statistic of 0.80 (95% confidence interval [CI] 0.74-0.85) for predicting SUI. C-statistics were stable in both internally cross-validated training cohort (mean 0.81) and validation cohort (0.83 [95% CI 0.79-0.87]). The nomogram's calibration curve was near the ideal diagonal line. Additionally, the model exhibited a positive net benefit from the decision curve analysis.

CONCLUSION

We have created a nomogram that can be utilized to quantify the risk of postpartum SUI for women with vaginal delivery. The model might contribute to predicting early postpartum SUI, thereby facilitating the management of SUI.