Background:Obstructive sleep apnea(OSA) is prevalent during pregnancy and linked to an increasing risk of adverse maternal and fetal *** has been proposed that identifying and managing OSA in pregnant women could pote...
详细信息
Background:Obstructive sleep apnea(OSA) is prevalent during pregnancy and linked to an increasing risk of adverse maternal and fetal *** has been proposed that identifying and managing OSA in pregnant women could potentially improve pregnancy ***,the lack of screening tools for OSA in this population results in low diagnosis ***:The purpose of this study is to improve the performance of existing OSA screening tools for pregnant women with machine learning *** design:A total of 296 pregnant women who complained of snoring OSA were recruited to complete four traditional OSA screening questionnaires:Berlin,STOP,STOP-Bang questionnaires(SBQ) and Epworth Sleepiness Scale(ESS).OSA status was confirmed using an overnight type Ⅲ home sleep test,with an apneahypopnea index(AHI) of ≥ 5 events/h indicating OSA.76 of the participants repeated the procedure at different trimesters,generating a total of 402 *** participants were randomly split into a training set(n=207) and a test set(n=89) in a 7:3 *** applied logistic regression model to build Mixture of Models for OSA screen(MoMOSA) based on demographic data and selected questions from all the *** were evaluated by accuracy,area under the receiver-operating-characteristic curves(AUC),sensitivity,and *** ratios and corresponding 95%confidence intervals(CIs) were also ***,we transformed the MoMOSA into a new questionnaire with a nomogram for visualizable ***:Four improved model developed by machine learning algorithm demonstrated better predictive performance for OSA in pregnancy than four traditional *** with 13 features achieved the highest performance among the traditional questionnaires and built *** probability threshold was 0.506 which helped separate patients into high-and low-risk groups of *** accuracy,AUC,sensitivity,and specificity of MoMOSA in the test set are0.739,0.
暂无评论