Establishment and validation of a nomogram model for predicting adverse pregnancy outcomes of pregnant women with adenomyosis

Abstract

Purpose To establish a reliable nomogram model to predict the risk of major adverse pregnancy outcomes in pregnant women with adenomyosis, and to provide a reference tool for the hierarchical management and the prenatal examination of pregnant women. Methods We collected the clinical data of pregnant women with adenomyosis who were treated in the First Affiliated Hospital of Chongqing Medical University and the Women and Children’s Hospital of Chongqing Medical University from January 2014 to June 2020. They were divided into the training cohort and the validation cohort, respectively. In the training cohort, we screened out risk factors associated with major adverse pregnancy outcomes and established a model, which was subsequently validated. Results In the training cohort, we found that natural conception or not, type of adenomyosis, previous parity, history of infertility or adverse pregnancy outcomes, history of uterine body surgerywere associated with major adverse pregnancy outcomes of pregnant women with adenomyosis, and based on these factors, a nomogram model was constructed. The calibration curves of the model were well fitted in both the training and validation cohorts. The receiver operating characteristic curve (ROC curve) showed that the area under the curve (AUC) was 0.862 and 0.836 in the training and validation cohorts, respectively. The optimal risk threshold of the model was 0.24, and this threshold can be applied to risk stratification of pregnant women. Conclusion The nomogram model established in this study can reliably predict the risk of major APO in pregnant women with AD.

Development and Validation of a Nomogram model for Predicting One-Year Unplanned Readmission in Patients with Chronic Obstructive Pulmonary Disease

“…Considering treatment impact, individual parameters, and laboratory tests, it is crucial to construct an effective, convenient, and intuitive clinical predictive model enables healthcare professionals to estimate the probability of unplanned readmission based on speci c patient conditions [20]. The nomogram model quanti es, visualizes, and graphically represents the logistic regression results, enabling inference of variable values by graph and displaying continuous prediction probabilities thus can provide reference for the medical staff to take preventive treatment for high-risk patients, has been widely used in clinical practice [20][21].…”

“…Considering treatment impact, individual parameters, and laboratory tests, it is crucial to construct an effective, convenient, and intuitive clinical predictive model enables healthcare professionals to estimate the probability of unplanned readmission based on speci c patient conditions [20]. The nomogram model quanti es, visualizes, and graphically represents the logistic regression results, enabling inference of variable values by graph and displaying continuous prediction probabilities thus can provide reference for the medical staff to take preventive treatment for high-risk patients, has been widely used in clinical practice [20][21]. A previous study develop a nomogram model based on education level, smoking status, number of acute exacerbations of COPD hospitalizations in the past 1 year, regular use of medication, rehabilitation and exercise, nutritional status and seasonal, the model has good prediction effect for acute exacerbation readmission risk within 30 days in elderly patients with COPD [22].Another predictive model constructed by the number of acute exacerbation hospitalizations in the previous year, increased GOLD grade and systemic use of glucocorticoids during hospitalization can predict the readmission risk of AECOPD patients within 1 year, providing a basis for clinical identi cation of high-risk readmission COPD patients [23].…”