ABSTRACT
Objective: Based on machine learning method, four types of early postoperative frailty risk prediction model of enterostomy patients were constructed to compare the performance of each model and provide the basis for preventing early postoperative frailty of elderly patients with enterostomy. Methods: The prospective convenience sampling method was conducted and 362 early postoperative enterostomy patients were selected in three hospitals from July 2020 to November 2023 in Shanghai, four different prediction models of Support Vector Machine (SVM), Bayes, XG Boost, and Logistic regression were used and compared the test effects of the four models (MCC, F1, AUC, and Brier index) to judge the classification performance of the four models in the data of this study. Results: A total of 21 variables were included in this study, and the predictors mainly covered demographic information, stoma-related information, quality of life, anxiety and depression, and frailty. The validated models on the test set are XGBoost, Logistic regression, SVM prediction model, and Bayes on the MCC and F1 scores; on the AUC, XGBoost, Logistic regression, Bayes, and SVM prediction model; on the Brier scores, Bayes, Logistic regression, and XGBoost. Conclusion: XGBoost based on machine learning method is better than SVM prediction model, Logistic regression model and Bayes in sensitivity and accuracy. Quality of life in the early postoperative period can help guide clinical patients to identify patients at high risk of frailty and reduce the incidence of early postoperative frailty in elderly patients with enterostomy.
ABSTRACT
Objective: This study aims to investigate the sleep quality of pregnant women in Xuhui District, Shanghai, and the related factors of sleep disturbances during pregnancy. Methods: From February 2019 to February 2021, we used online integrated sleep questionnaire (including PSQI, BQ, ESS, AIS) in Shanghai Jiao Tong University School of Medicine Affiliated Sixth People's Hospital, The International Peace Maternity and Child Health Hospitals of China Welfare Institution, and Shanghai Eighth People's Hospital, to investigate the sleep quality across pregnancy. We also collected maternal physical examination results, childbearing history, sociodemographic, and other clinical data. The prevalences and related factors of various sleep disturbances in pregnant women were analyzed, including insufficient/excessive nighttime sleep, low sleep efficiency, difficulty falling asleep, poor sleep quality, insomnia, daytime sleepiness, and high risk of sleep-disordered breathing (SDB). Results: This study includes 1 898 cases in the first trimester (T1), 3 099 cases in the second trimester (T2), and 1 539 cases in the third trimester (T3). Poor sleep quality (38.6%), daytime sleepiness (mild 41.9%, moderate 17.7%, severe 2.1%), and suspicious insomnia (32.3%) are most prevalent among women in T1 (P<0.01). In comparison, short sleep time (2.7%), long sleep time (8.6%), difficulty falling asleep (12.2%), poor sleep efficiency (35.4%), very poor sleep quality (6.7%), clinical insomnia (21.8%), and high-risk SDB (6.4%) are most prevalent among women in T3 (P<0.05). During pregnancy, late gestation (OR=1.016, 95%CI: 1.006-1.025) and multiple induced/drug abortions (OR=1.329, 95%CI: 1.043-1.692) are risk factors for poor sleep quality (PSQI>5), while multiple full-term deliveries (OR=0.800, 95%CI: 0.675-0.949) is its protective factor. Advanced maternal age (OR=0.976, 95%CI: 0.956-0.997), multiple full-term deliveries (OR=0.808, 95%CI: 0.680-0.959), late gestation (OR=0.983, 95%CI: 0.974-0.992) and hypertension (OR=0.572, 95%CI: 0.401-0.814) are protective factors for daytime sleepiness (ESS>6). The high-risk pregnancy category (OR=9.312, 95%CI: 1.156-74.978) is a risk factor for insomnia (AIS≥4), while multiple full-term deliveries (OR=0.815, 95%CI: 0.691-0.961) is its protective factor. High BMI (OR=1.334, 95%CI: 1.270-1.402) and hypertension (OR=4.427, 95%CI: 2.539-7.719) are risk factors for high-risk SDB in pregnant women. Conclusions: The prevalences of various sleep disturbances are high throughout pregnancy. Noticeably, symptoms of maternal SDB develop along with pregnancy. Different types of sleep disturbances are associated with different factors. Women of high-risk pregnancy category, in late gestation, with high BMI, hypertension, a history of induced/drug abortion, or without a history of full-term delivery can be at high risk of sleep disturbances during pregnancy.
