Font Size: a A A

Construction Of Nomogram Visualized Prediction Model For Endometrial Polyps In Nurses Based On Occupational Health Cohort

Posted on:2022-02-18Degree:MasterType:Thesis
Country:ChinaCandidate:Y Y GuoFull Text:PDF
GTID:2504306563950469Subject:Nursing
Abstract/Summary:PDF Full Text Request
Objective: Establish an individualized early warning model equation for nurses’ endometrial polyps,and further establish a Nomogram visual early warning model.The Nomogram visual warning model can obtain the predicted incidence of disease by quantifying each statistically significant variable.This study aims to identify high-risk nurse groups,improve nurses’ self-prevention,and provide guidance for nursing managers to formulate precise intervention strategies.Methods: 1.Extract the physical examination data and questionnaire survey information of on-the-job nursing staff for seven consecutive years,and analyze the trend of endometrial polyps.2.Univariate analysis of variables with statistical significance in the occurrence of endometrial polyps in nurses was included in the multivariate Logistic regression.Through single factor and multivariate logistic regression analysis,the risk factors and protective factors of endometrial polyps were screened out.3.Use R language software to establish a risk warning model for the selected risk factors and protective factors,obtain the early warning model equation,and further draw the Nomogram visual warning model for the occurrence of endometrial polyps in nurses,and assign each risk factor and protective factor The corresponding score.The total score obtained by adding the scores of various risk factors and protective factors corresponds to the predicted incidence of endometrial polyps in nurses.4.The Bootstrap method was used to verify the model,and the ROC curve was used to explore the prediction efficiency of the Nomogram model for the occurrence of endometrial polyps in nurses.Results: 1.The incidence of endometrial polyps among nurses in a tertiary hospital for seven consecutive years was 4.21%,5.12%,5.16%,5.15%,6.12%,6.33%,7.11%,showing a tortuous upward trend.2.BMI [OR=14.994,95%CI(7.0821,31.745)],number of shift years [OR=6.6478,95%CI(2.7835,15.877)],irregular menstrual cycle [OR=8.3761,95%CI(2.9021,24.175)],dysmenorrhea [OR=6.4547,95%CI(2.0324,20.5)],increased total cholesterol [OR=6.3024,95%CI(3.3206,11.962)] are independent risk factors for endometrial polyps in nurses,Waist circumference[OR=0.36609,95%CI(0.17871,0.74996)],age at menarche increased [OR=0.1557,95%CI(0.084201,0.28791)],pregnancy times increased [OR=0.081376,95%CI(0.025238,0.26238))] is a protective factor for endometrial polyps.3.The early warning model equation is: Logit P =-13.29+0.6017 × BMI-0.0914 × waist circumference+0.2105 × the number of years involved in shifts so far-1.8598 ×menarche age+2.1254×menstrual cycle+1.8648×dysmenorrhea-1.2543×pregnancy times+ 1.4846 x total cholesterol.Further visualize the early warning equation and draw the Nomogram early warning model.4.Using Bootstrap method to repeat self-sampling 1000 times to verify the Nomogram model that predicts the risk of endometrial polyps in nurses.The calibration curve of the Nomogram model shows that the model has good accuracy in predicting the risk of endometrial polyps in nurses.The ROC curve was used to analyze the efficiency of the Nomogram model to predict the risk of endometrial polyps in nurses.The AUC was 0.803(95%CI:0.759~0.892),and the model had a good degree of discrimination.Conclusion: Based on 8 independent risk factors of BMI,waist circumference,number of shifts,menarche age,menstrual cycle,dysmenorrhea,pregnancy times,and total cholesterol,a visual early warning model for nurses ’ endometrial polyps is established.It has good discrimination and accuracy,and is useful for screening For high-risk nurse groups,improving nurses’ self-prevention and formulating precise intervention strategies for nursing managers are of guiding significance.
Keywords/Search Tags:nurse, endometrial polyps, early warning model, precise prevention
PDF Full Text Request
Related items