scholarly journals Decision Tree Analysis: A Retrospective Analysis of Postoperative Recurrence of Adhesions in Patients with Moderate-to-Severe Intrauterine

2019 ◽  
Vol 2019 ◽  
pp. 1-8 ◽  
Author(s):  
Ru Zhu ◽  
Hua Duan ◽  
Sha Wang ◽  
Lu Gan ◽  
Qian Xu ◽  
...  
Keyword(s):  
Logistic Regression ◽  
Decision Tree ◽  
Endometrial Thickness ◽  
Characteristic Curve ◽  
Multivariate Logistic Regression Analysis ◽  
Decision Tree Model ◽  
Classification And Regression Tree ◽  
Multivariate Logistic Regression Model ◽  
Multivariate Logistic Regression ◽  
Tree Model

Objective. To establish and validate a decision tree model to predict the recurrence of intrauterine adhesions (IUAs) in patients after separation of moderate-to-severe IUAs. Design. A retrospective study. Setting. A tertiary hysteroscopic center at a teaching hospital. Population. Patients were retrospectively selected who had undergone hysteroscopic adhesion separation surgery for treatment of moderate-to-severe IUAs. Interventions. Hysteroscopic adhesion separation surgery and second-look hysteroscopy 3 months later. Measurements and Main Results. Patients’ demographics, clinical indicators, and hysteroscopy data were collected from the electronic database of the hospital. The patients were randomly apportioned to either a training or testing set (332 and 142 patients, respectively). A decision tree model of adhesion recurrence was established with a classification and regression tree algorithm and validated with reference to a multivariate logistic regression model. The decision tree model was constructed based on the training set. The classification node variables were the risk factors for recurrence of IUAs: American Fertility Society score (root node variable), isolation barrier, endometrial thickness, tubal opening, uterine volume, and menstrual volume. The accuracies of the decision tree model and multivariate logistic regression analysis model were 75.35% and 76.06%, respectively, and areas under the receiver operating characteristic curve were 0.763 (95% CI 0.681–0.846) and 0.785 (95% CI 0.702–0.868). Conclusions. The decision tree model can readily predict the recurrence of IUAs and provides a new theoretical basis upon which clinicians can make appropriate clinical decisions.

scholarly journals Clinical features and risk factors analysis of bronchitis obliterans due to refractory Mycoplasma pneumoniae pneumonia in children: a nomogram prediction model

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Qi Cheng ◽  
Han Zhang ◽  
Yunxiao Shang ◽  
Yuetong Zhao ◽  
Ye Zhang ◽  
...  
Keyword(s):  
Logistic Regression ◽  
Mycoplasma Pneumoniae ◽  
Characteristic Curve ◽  
Acute Infection ◽  
Multivariate Logistic Regression Analysis ◽  
Multivariate Logistic Regression Model ◽  
Early Prediction ◽  
Multivariate Logistic Regression ◽  
Fiber Bronchoscopy ◽  
Wbc Count

Abstract Background Early prediction of bronchitis obliterans (BO) is of great significance to the improvement of the long-term prognosis of children caused by refractory Mycoplasma pneumoniae pneumonia (RMPP). This study aimed to establish a nomogram model to predict the risk of BO in children due to RMPP. Methods A retrospective observation was conducted to study the clinical data of children with RMPP (1–14 years old) during acute infection. According to whether there is BO observed in the bronchoscope, children were divided into BO and the non-BO groups. The multivariate logistic regression model was used to construct the nomogram model. Results One hundred and forty-one children with RMPP were finally included, of which 65 (46.0%) children with RMPP were complicated by BO. According to the multivariate logistic regression analysis, WBC count, ALB level, consolidation range exceeding 2/3 of lung lobes, timing of macrolides, glucocorticoids or fiber bronchoscopy and plastic bronchitis were independent influencing factors for the occurrence of BO and were incorporated into the nomogram. The area under the receiver operating characteristic curve (AUC-ROC) value of nomogram was 0.899 (95% confidence interval [CI] 0.848–0.950). The Hosmer–Lemeshow test showed good calibration of the nomogram (p = 0.692). Conclusion A nomogram model found by seven risk factor was successfully constructed and can use to early prediction of children with BO due to RMPP.

scholarly journals Decision Tree Model Predicts Live Birth after Surgery for Moderate-to-Severe Intrauterine Adhesions

2021 ◽  
Author(s):  
Ru Zhu ◽  
Hua Duan ◽  
Wenbin Xu ◽  
Sha Wang ◽  
Lu Gan ◽  
...  
Keyword(s):  
Decision Tree ◽  
Predictive Model ◽  
Live Birth ◽  
Decision Tree Model ◽  
Classification And Regression Tree ◽  
Multivariate Logistic Regression Model ◽  
Tree Model ◽  
Intrauterine Adhesions ◽  
Final Population ◽  
Menstrual Pattern

Abstract Background: After treatment of intrauterine adhesions, the rate of re-adhesion is high and the pregnancy outcome unpredictable and unsatisfactory. This study established and verified a decision tree predictive model of live birth in patients after surgery for moderate-to-severe intrauterine adhesions (IUAs).Methods: A retrospective observational study initially comprised 394 patients with moderate-to-severe IUAs diagnosed via hysteroscopy. The patients underwent hysteroscopic adhesiolysis from January 2013 to January 2017, in a university-affiliated hospital. Follow-ups to determine the rate of live birth were conducted by telephone for at least the first postoperative year. A classification and regression tree algorithm was applied to establish a decision tree model of live birth after surgery.Results: Within the final population of 374 patients, the total live birth rate after treatment was 29.7%. The accuracy of the model was 83.8%, and the area under the receiver operating characteristic curve (AUC) was 0.870 (95% CI 7.699-0.989). The root node variable was postoperative menstrual pattern. The predictive accuracy of the multivariate logistic regression model was 70.3%, and the AUC was 0.835 (95% CI 0.667-0.962).Conclusions: The decision tree predictive model is useful for predicting live birth after surgery for IUAs; postoperative menstrual pattern is a key factor in the model. This model will help clinicians make appropriate clinical decisions during patient consultations.

scholarly journals The severity and risk factors for mortality in immunocompromised adult patients hospitalized with influenza-related pneumonia

2021 ◽  
Vol 20 (1) ◽  
Author(s):  
Liang Chen ◽  
Xiudi Han ◽  
YanLi Li ◽  
Chunxiao Zhang ◽  
Xiqian Xing
Keyword(s):  
Risk Factors ◽  
Logistic Regression ◽  
Operating Characteristic ◽  
Characteristic Curve ◽  
Multivariate Logistic Regression Analysis ◽  
Neuraminidase Inhibitor ◽  
Teaching Hospitals ◽  
Multivariate Logistic Regression Model ◽  
Multivariate Logistic Regression ◽  
Optimal Cutoff

Abstract Objective To explore disease severity and risk factors for 30-day mortality of adult immunocompromised (IC) patients hospitalized with influenza-related pneumonia (Flu-p). Method A total of 122 IC and 1191 immunocompetent patients hospitalized with Flu-p from January 2012 to December 2018 were recruited retrospectively from five teaching hospitals in China. Results After controlling for confounders, multivariate logistic regression analysis showed that immunosuppression was associated with increased risks for invasive ventilation [odds ratio: (OR) 2.475, 95% confidence interval (CI): 1.511–4.053, p < 0.001], admittance to the intensive care unit (OR: 3.247, 95% CI 2.064–5.106, p < 0.001), and 30-day mortality (OR: 3.206, 95% CI 1.926–5.335, p < 0.001) in patients with Flu-p. Another multivariate logistic regression model revealed that baseline lymphocyte counts (OR: 0.993, 95% CI 0.990–0.996, p < 0.001), coinfection (OR: 5.450, 95% CI 1.638–18.167, p = 0.006), early neuraminidase inhibitor therapy (OR 0.401, 95% CI 0.127–0.878, p = 0.001), and systemic corticosteroid use at admission (OR: 6.414, 95% CI 1.348–30.512, p = 0.020) were independently related to 30-day mortality in IC patients with Flu-p. Based on analysis of the receiver operating characteristic curve (ROC), the optimal cutoff for lymphocyte counts was 0.6 × 109/L [area under the ROC (AUROC) = 0.824, 95% CI 0.744—0.887], sensitivity: 97.8%, specificity: 73.7%]. Conclusions IC conditions are associated with more severe outcomes in patients with Flu-p. The predictors for mortality that we identified may be valuable for the management of Flu-p among IC patients.

scholarly journals The severity and risk factors for mortality in immunocompromised adult patients hospitalized with influenza-related pneumonia

2021 ◽  
Author(s):  
Liang Chen ◽  
Xiudi Han ◽  
YanLi Li ◽  
Chunxiao Zhang ◽  
Xiqian Xing
Keyword(s):  
Risk Factors ◽  
Logistic Regression ◽  
Roc Analysis ◽  
Operating Characteristic ◽  
Characteristic Curve ◽  
Multivariate Logistic Regression Analysis ◽  
Neuraminidase Inhibitor ◽  
Teaching Hospitals ◽  
Multivariate Logistic Regression Model ◽  
Multivariate Logistic Regression

Abstract Objective To explore disease severity and risk factors for 30-day mortality of adult immunocompromised (IC) patients hospitalized with influenza-related pneumonia (Flu-p).Method A total of 122 IC and 1,191 immunocompetent patients hospitalized with Flu-p from January 2012 to December 2018 were recruited retrospectively from five teaching hospitals in China. Results After controlling for confounders, multivariate logistic regression analysis showed that immunosuppression was associated with increased risks for invasive ventilation [odds ratio: (OR) 2.475, 95% confidence interval (CI): 1.511-4.053, p < 0.001], admittance to the intensive care unit (OR: 3.247, 95% CI: 2.064-5.106, p < 0.001), and 30-day mortality (OR: 3.206, 95% CI: 1.926-5.335, p < 0.001) in patients with Flu-p. Another multivariate logistic regression model revealed that baseline lymphocyte counts (OR: 0.993, 95% CI: 0.990-0.996, p < 0.001), coinfection (OR: 5.450, 95% C:I 1.638-18.167, p = 0.006), early neuraminidase inhibitor therapy (OR 0.401, 95% CI 0.127-0.878, p = 0.001), and systemic corticosteroid use at admission (OR: 6.414, 95% C:I 1.348-30.512, p = 0.020) were independently related to 30-day mortality in IC patients with Flu-p. Based on receiver operating characteristic curve (ROC) analysis, the optimal cutoff for lymphocyte counts was 0.6×109/L [area under the ROC (AUROC) = 0.824, 95% CI: 0.744 - 0.887], sensitivity: 97.8%, specificity: 73.7%].Conclusions IC conditions are associated with more severe outcomes in patients with Flu-p. The predictors for mortality that we identified may be valuable for the management of Flu-p among IC patients.

scholarly journals Clinical Features and Risk Factors Analysis of Bronchitis Obliterans Due to Refractory Mycoplasma Pneumoniae Pneumonia in Children: A Nomogram Prediction Model

2021 ◽  
Author(s):  
Qi Cheng ◽  
Han Zhang ◽  
Yunxiao Shang ◽  
Yuetong Zhao ◽  
Ye Zhang ◽  
...  
Keyword(s):  
Logistic Regression ◽  
Mycoplasma Pneumoniae ◽  
Characteristic Curve ◽  
Acute Infection ◽  
Multivariate Logistic Regression Analysis ◽  
Multivariate Logistic Regression Model ◽  
Multivariate Logistic Regression ◽  
Fiber Bronchoscopy ◽  
Wbc Count ◽  
Mycoplasma Pneumoniae Pneumonia

Abstract BackgroundEarly prediction of bronchitis obliterans (BO) is of great significance to the improvement of the long-term prognosis of children caused by refractory mycoplasma pneumoniae pneumonia (RMPP). This study aimed to establish a nomogram model to predict the risk of BO in children due to RMPP.MethodsA retrospective observation was conducted to study the clinical data of children with RMPP (1-14 years old) during acute infection. According to whether there is BO observed in the bronchoscope, children were divided into BO and the non-BO groups. The multivariate logistic regression model was used to construct the nomogram model.Results141 children with RMPP were finally included, of which 65 (46.0%) children with RMPP were complicated by BO. According to the multivariate logistic regression analysis, WBC count, ALB level, consolidation range exceeding 2/3 of lung lobes, timing of macrolides, glucocorticoids or fiber bronchoscopy and plastic bronchitis were independent influencing factors for the occurrence of BO and were incorporated into the nomogram. The area under the receiver operating characteristic curve (AUC-ROC) value of nomogram was 0.899 (95% confidence interval [CI]: 0.848~0.950). The Hosmer-Lemeshow test showed good calibration of the nomogram (p=0.692).Conclusion: A nomogram model found by seven risk factor was successfully constructed and can use to early prediction of children with BO due to RMPP.

scholarly journals Predicting Metabolic Syndrome With Machine Learning Models Using a Decision Tree Algorithm: Retrospective Cohort Study (Preprint)

2019 ◽  
Author(s):  
Cheng-Sheng Yu ◽  
Yu-Jiun Lin ◽  
Chang-Hsien Lin ◽  
Sen-Te Wang ◽  
Shiyng-Yu Lin ◽  
...  
Keyword(s):  
Machine Learning ◽  
Metabolic Syndrome ◽  
Logistic Regression ◽  
Decision Tree ◽  
Characteristic Curve ◽  
Significant Risk ◽  
Machine Learning Algorithms ◽  
Machine Learning Techniques ◽  
Health Examination ◽  
Multivariate Logistic Regression

BACKGROUND Metabolic syndrome is a cluster of disorders that significantly influence the development and deterioration of numerous diseases. FibroScan is an ultrasound device that was recently shown to predict metabolic syndrome with moderate accuracy. However, previous research regarding prediction of metabolic syndrome in subjects examined with FibroScan has been mainly based on conventional statistical models. Alternatively, machine learning, whereby a computer algorithm learns from prior experience, has better predictive performance over conventional statistical modeling. OBJECTIVE We aimed to evaluate the accuracy of different decision tree machine learning algorithms to predict the state of metabolic syndrome in self-paid health examination subjects who were examined with FibroScan. METHODS Multivariate logistic regression was conducted for every known risk factor of metabolic syndrome. Principal components analysis was used to visualize the distribution of metabolic syndrome patients. We further applied various statistical machine learning techniques to visualize and investigate the pattern and relationship between metabolic syndrome and several risk variables. RESULTS Obesity, serum glutamic-oxalocetic transaminase, serum glutamic pyruvic transaminase, controlled attenuation parameter score, and glycated hemoglobin emerged as significant risk factors in multivariate logistic regression. The area under the receiver operating characteristic curve values for classification and regression trees and for the random forest were 0.831 and 0.904, respectively. CONCLUSIONS Machine learning technology facilitates the identification of metabolic syndrome in self-paid health examination subjects with high accuracy.

scholarly journals Predicting Metabolic Syndrome With Machine Learning Models Using a Decision Tree Algorithm: Retrospective Cohort Study

10.2196/17110 ◽  
2020 ◽  
Vol 8 (3) ◽  
pp. e17110 ◽  
Author(s):  
Cheng-Sheng Yu ◽  
Yu-Jiun Lin ◽  
Chang-Hsien Lin ◽  
Sen-Te Wang ◽  
Shiyng-Yu Lin ◽  
...  
Keyword(s):  
Machine Learning ◽  
Metabolic Syndrome ◽  
Logistic Regression ◽  
Decision Tree ◽  
Characteristic Curve ◽  
Significant Risk ◽  
Machine Learning Algorithms ◽  
Machine Learning Techniques ◽  
Health Examination ◽  
Multivariate Logistic Regression

Background Metabolic syndrome is a cluster of disorders that significantly influence the development and deterioration of numerous diseases. FibroScan is an ultrasound device that was recently shown to predict metabolic syndrome with moderate accuracy. However, previous research regarding prediction of metabolic syndrome in subjects examined with FibroScan has been mainly based on conventional statistical models. Alternatively, machine learning, whereby a computer algorithm learns from prior experience, has better predictive performance over conventional statistical modeling. Objective We aimed to evaluate the accuracy of different decision tree machine learning algorithms to predict the state of metabolic syndrome in self-paid health examination subjects who were examined with FibroScan. Methods Multivariate logistic regression was conducted for every known risk factor of metabolic syndrome. Principal components analysis was used to visualize the distribution of metabolic syndrome patients. We further applied various statistical machine learning techniques to visualize and investigate the pattern and relationship between metabolic syndrome and several risk variables. Results Obesity, serum glutamic-oxalocetic transaminase, serum glutamic pyruvic transaminase, controlled attenuation parameter score, and glycated hemoglobin emerged as significant risk factors in multivariate logistic regression. The area under the receiver operating characteristic curve values for classification and regression trees and for the random forest were 0.831 and 0.904, respectively. Conclusions Machine learning technology facilitates the identification of metabolic syndrome in self-paid health examination subjects with high accuracy.

scholarly journals Adherence to Mediterranean Diet among Students from Primary and Middle School in the Province of Taranto, 2016–2018

2020 ◽  
Vol 17 (15) ◽  
pp. 5437
Author(s):  
Guglielmo Bonaccorsi ◽  
Federica Furlan ◽  
Marisa Scocuzza ◽  
Chiara Lorini
Keyword(s):  
Logistic Regression ◽  
Nutritional Status ◽  
Mediterranean Diet ◽  
Eating Habits ◽  
Economic Status ◽  
Multivariate Logistic Regression Analysis ◽  
Multivariate Logistic Regression Model ◽  
Multivariate Logistic Regression ◽  
Predictive Role ◽  
The Mediterranean

The Mediterranean diet represents one of the healthiest dietary patterns, but nowadays it is increasingly being ignored in schools and by families. The aim of this study is to assess the adherence to the Mediterranean diet by pupils living in a small Southern Italian municipality, and whether it is a predictor of nutritional status.The degree of adherence to the Mediterranean diet, the socio-economic status and the nutritional status of 314 students (6–14 years) were tested during the 2016/2017 and 2017/2018 school years with the help of a questionnaire comprising the Mediterranean Diet Quality Index for Children and Adolescents (KIDMED) test. Multivariate logistic regression analysis was used to assess the predictive role of the KIDMED score and the other variables with respect to nutritional status. Adherence to the Mediterranean diet is high, medium and poor in, respectively, 24.8, 56.4 and 18.8% of students; it varies depending on gender and age, with females and older students showing higher values. In the multivariate logistic regression model, sex and KIDMED level are become significant predictors of nutritional status. This study highlights the need for intervention in the form of school projects—also involving families—to promote healthier eating habits in younger generations.

scholarly journals Risk factors for peritoneal dialysis–associated peritonitis

2018 ◽  
Vol 16 ◽  
pp. 205873921877224
Author(s):  
Hongyue Wang ◽  
Xiangtuo Wang ◽  
Haichuan Dou ◽  
Chenhao Li ◽  
Mingji Cui ◽  
...  
Keyword(s):  
Risk Factors ◽  
Logistic Regression ◽  
Peritoneal Dialysis ◽  
Serum Albumin ◽  
Multivariate Logistic Regression Analysis ◽  
Roc Curves ◽  
Multivariate Logistic Regression Model ◽  
Phosphorus Concentration ◽  
Multivariate Logistic Regression ◽  
Gram Positive

The purpose of this study was to summarize the pathogens that cause peritoneal dialysis (PD)-associated peritonitis and to identify risk factors for PD-associated peritonitis. This retrospective study included 115 end-stage renal disease (ESRD) patients receiving PD therapy. Patients were categorized into two groups: peritonitis group (n = 41) and non-peritonitis group (n = 74). Clinical data and laboratory tests were collected from medical records. The multivariate logistic regression model was used to evaluate associations between PD-associated peritonitis and potential risk factors. PD-associated peritonitis occurred 54 times in 41 patients. The most frequently identified pathogen was Gram-positive cocci (57.78%). Multivariate logistic regression analysis showed that serum albumin (β = –0.208, P < 0.001), blood phosphorus concentration (β = –1.732, P = 0.001), gastrointestinal disorders (β = 1.624, P = 0.043), and use of calcitriol (β = –2.239, P = 0.048) were significantly correlated with PD-associated peritonitis. Receiver operating characteristic (ROC) curves showed that the areas under the curve were 0.832 for serum albumin and 0.700 for blood phosphorus concentration with optimal cut-off values of 29.1 g/L for serum albumin and 1.795 mmol/L for blood phosphorus concentration. Gram-positive coccus is the major pathogen responsible for PD-associated peritonitis. Serum albumin <29.1 g/L, blood phosphorus concentration <1.795 mmol/L, and intestinal disorders are risk factors for PD-associated peritonitis, whereas the use of calcitriol can reduce the risk of PD-associated peritonitis.

scholarly journals Prediction of health care expenditure increase: how does pharmacotherapy contribute?

2019 ◽  
Vol 19 (1) ◽  
Author(s):  
Annika M. Jödicke ◽  
Urs Zellweger ◽  
Ivan T. Tomka ◽  
Thomas Neuer ◽  
Ivanka Curkovic ◽  
...  
Keyword(s):  
Health Care ◽  
Logistic Regression ◽  
Decision Tree ◽  
Health Care Costs ◽  
Decision Tree Model ◽  
Tree Model ◽  
Physician Visits ◽  
Drug Classes ◽  
Swiss Health ◽  
Care Costs

Abstract Background Rising health care costs are a major public health issue. Thus, accurately predicting future costs and understanding which factors contribute to increases in health care expenditures are important. The objective of this project was to predict patients healthcare costs development in the subsequent year and to identify factors contributing to this prediction, with a particular focus on the role of pharmacotherapy. Methods We used 2014–2015 Swiss health insurance claims data on 373′264 adult patients to classify individuals’ changes in health care costs. We performed extensive feature generation and developed predictive models using logistic regression, boosted decision trees and neural networks. Based on the decision tree model, we performed a detailed feature importance analysis and subgroup analysis, with an emphasis on drug classes. Results The boosted decision tree model achieved an overall accuracy of 67.6% and an area under the curve-score of 0.74; the neural network and logistic regression models performed 0.4 and 1.9% worse, respectively. Feature engineering played a key role in capturing temporal patterns in the data. The number of features was reduced from 747 to 36 with only a 0.5% loss in the accuracy. In addition to hospitalisation and outpatient physician visits, 6 drug classes and the mode of drug administration were among the most important features. Patient subgroups with a high probability of increase (up to 88%) and decrease (up to 92%) were identified. Conclusions Pharmacotherapy provides important information for predicting cost increases in the total population. Moreover, its relative importance increases in combination with other features, including health care utilisation.

Sign in / Sign up

Export Citation Format

Share Document