Prediction model of therapeutic effect on children with idiopathic short stature based on vitamin K2,IGFBP-3 and Omentin-1 / 国际检验医学杂志

Objective To investigate the relationship between vitamin K2,insulin-like growth factor bind-ing protein 3(IGFBP-3),Omentin-1 and the therapeutic effect on children with idiopathic short stature(ISS),and to build a prediction model.Methods A total of 242 ISS children in Jinan Second Maternal and Child Health Hospital from 2019 to 2021 were selected.All of them received recombinant human growth hormone(rhGH)treatment and were divided into effective group and ineffective group according to the therapeutic effect after 12 months of treatment.The general data,vitamin K2,IGFBP-3 and Omentin-1 in the two groups were analyzed.The influencing factors of ISS children's therapeutic effect were analyzed by Logistic regression model and decision tree model.The predictive performance of two models was analyzed by using receiver oper-ating characteristic(ROC)curve.Results There were statistically significant differences in 25-hydroxy vita-min D[25(OH)D],parathyroid hormone(PTH),thyroid stimulating hormone(TSH),vitamin K2,IGFBP-3,Omentin-1,rhGH dosage and weekly outdoor exercise time between the two groups(P＜0.05).Logistic re-gression showed that PTH(OR=7.011,95％CI:2.456-20.014),vitamin K2(OR=0.605,95％CI:.0.465-0.788),IGFBP-3(OR=0.458,95％CI:0.321-0.654),Omentin-1(OR=0.514,95％CI:0.389-0.679)and rhGH dose(OR=0.563,95％CI:0.445-0.712)]were the influential factors for treatment ineffectiveness in ISS children(P＜0.05).The decision tree model showed that vitamin K2,IGFBP-3 and Omentin-1 were the factors influencing the therapeutic effect of ISS,and IGFBP-3 had the most significant impact.ROC curve re-sults showed that the area under the curve of decision tree model and Logistic regression model were 0.922 and 0.908,respectively,with good classification effect.Conclusion The therapeutic effect of ISS children is in-fluenced by factors such as vitamin K2,IGFBP-3,Omentin-1,and so on,and IGFBP-3 has the most significant impact.Logistic regression model and decision tree model could complement each other so as to provide refer-ence for improving the therapeutic effect of ISS children from different aspects.

Cost-utility analysis of edaravone dexborneol for acute ischemic stroke / 药物流行病学杂志

Objective To evaluate the cost-effectiveness of edaravone dexborneol versus edaravone alone combined with conventional therapy in patients with acute ischemic stroke(AIS).Methods From the perspective of the healthcare systems,a decision tree model was constructed using the data from the randomized double-blind comparative trial of edaravone dexborneol in the treatment of acute ischemic stroke(TASTE trial).Cost-utility analysis was used to evaluate the health benefits of edaravone dexborneol at 1 month and 5 years.The robustness of the results was tested by single factor sensitivity analysis and probability sensitivity analysis.Results For AIS patients,the 1-month incremental cost-utility ratio was 53 212.89 yuan/quality-adjusted life-year(QALY),and the 5-year incremental cost-utility ratio was 49 631.25 yuan/QALY,both of which were smaller than China's per capita GDP in 2022(85 698 yuan).Univariate sensitivity analysis showed that the change of NIHSS score in 2 groups of improved patients,the probability of improvement in 2 groups and the probability of deterioration in edaravone group were the most influential factors on the outcome of incremental cost effectiveness.The results of probabilistic sensitivity analysis showed that edaravone dexcborneol was more economical when WTP was 1 times China's per capita GDP in 2022.Conclusion Edaravon dexborneol is a more effective and economical treatment for acute ischemic stroke patients than edaravone alone.

Nested case-control study on the risk factors and interaction analysis of positive screening for infant motor development / 中国儿童保健杂志

【Objective】 To identify the influencing factors of infant motor development, and to explore the potential interactive factors, so as to provide scientific basis for early prediction and targeted prevention of infant motor developmental delay. 【Methods】 Data of infants receiving "0~1 motor development screening" at 21 community health service centers in Tongzhou District, from January 1st, 2020 to August 31st, 2021 were collected through the Beijing Maternal and Child Information System.Using the method of nested case-control study, 416 infants with positive screening results were selected as case group, 416 infants with negative screening result were selected into the control group by 1∶1 case-control matching of screening age.Chi-square test, Logistic regression analysis, and Exhaustive CHAID decision tree model were used to explore the influencing factors of infant motor development, the interaction effect was investigated by using the additive and multiplicative interaction models. 【Results】 Multivariate Logistic analysis showed that birth weight<2 500g (OR=3.28), cesarean section (OR=1.63), outdoor activity≤ 1h/d (OR=3.07), and no supplementation of vitamin D (OR=2.68) were risk factors for positive screening results of infant motor development (P<0.01).The Exhaustive CHAID decision tree showed that low birth weight was the primary risk factor for infant with positive screening results, followed by outdoor activity, vitamin D supplementation and delivery.The interaction analysis showed that there was a multiplicative interaction (OR=13.76, 95% CI:1.20 - 158.08) and an additive interaction (RERI=10.22, 95%CI:5.05 - 15.38) between non supplementation of vitamin D and low birth weight on infant motor development with positive screening results. 【Conclusions】 Attention should be paid to the early motor development of infants with low birth weight and those born by cesarean section, with emphasis on the dosage of vitamin D supplementation and outdoor activity duration.Moreover, the early screening and hierarchical management of infant motor development should also be strengthened.

HIV screening strategies in blood donors: a cost-effectiveness analysis / 中国输血杂志

【Objective】 To analyze the cost and effectiveness of different HIV screening strategies based on multi-center HIV residual risk study, so as to provide reference for blood centers to adopt appropriate HIV testing strategies. 【Methods】 According to the HIV screening and confirmation of blood donors in three blood centers in Anhui Province, the residual risk of different HIV screening strategies was estimated. A decision tree model was established to analyze the cost-effectiveness differences of three different screening strategies under current domestic policies. 【Results】 The residual risk of anti-HIV-1 +2 ELISA, HIV Ag/Ab1+2 ELISA and ELISA+NAT were 1.17×10-6,0.84×10-6 and 0.59×10-6, respectively. According to decision tree model analysis, HIV Ag/Ab1+2 ELISA had a cost-effectiveness advantage over anti-HIV 1+2 ELISA when there was no NAT, but the advantage of HIV Ag/Ab1+2 ELISA disappeared when there was one NAT. The cost of HIV reagents, the cost of HIV treatment and the cost of false positive discarding were sensitive factors of the model. 【Conclusion】 In this area, one anti-HIV 1+2 ELISA combined with one NAT has a cost-effectiveness advantage. Blood centers need to confirm and evaluate the ELISA reagents used before conducting HIV screening. Under the premise of ensuring sensitivity, reagent cost and reagent false positive rate are the key factors.

Comparison of the effects of Cox regression analysis model and decision tree model in identifying risk factors for the occurrence of hypertension in the elderly / 公共卫生与预防医学

Objective To explore the risk factors for the occurrence of hypertension in middle-aged and elderly residents in China using the Cox regression analysis model and decision tree model, and compare the differences between the two methods. Methods The 2011-2015 China Health and Retirement Longitudinal Study data were used. The study investigated the risk factors for hypertension using both a multivariate Cox regression model and a decision tree model. Results The results showed that the incidence rate of hypertension between 2011-2015 was 22.79%. Both the Cox regression model and decision tree model identified age, education level, body mass index, and diabetes as risk factors for hypertension. The Cox regression model also identified drinking status as a risk factor, while the decision tree model identified gender and marital status as additional risk factors. The area under the curve (AUC) suggested that the Cox regression model and decision tree model had comparable ability to predict hypertension. Conclusions The risk factors for hypertension include gender, age, education level, marital status, alcohol consumption, body mass index, and history of diabetes. The effectiveness of the hypertension prediction model established based on Cox regression model and decision tree model results is not different.

Identification of medically and forensically relevant flies using a decision treelearning method

@#Blow flies, flesh flies, and house flies can provide excellent evidence for forensic entomologists and are also essential to the fields of public health, medicine, and animal health. In all questions, the correct identification of fly species is an important initial step. The usual methods based on morphology or even molecular approaches can reach their limits here, especially when dealing with larger numbers of specimens. Since machine learning already plays a major role in many areas of daily life, such as education, business, industry, science, and medicine, applications for the classification of insects have been reported. Here, we applied the decision tree method with wing morphometric data to construct a model for discriminating flies of three families [Calliphoridae, Sarcophagidae, Muscidae] and seven species [Chrysomya megacephala (Fabricius), Chrysomya rufifacies (Macquart), Chrysomya (Ceylonomyia) nigripes Aubertin, Lucilia cuprina (Wiedemann), Hemipyrellia ligurriens (Wiedemann), Musca domestica Linneaus, and Parasarcophaga (Liosarcophaga) dux Thomson]. One hundred percent overall accuracy was obtained at a family level, followed by 83.33% at a species level. The results of this study suggest that non-experts might utilize this identification tool. However, more species and also samples per specimens should be studied to create a model that can be applied to the different fly species in Thailand.

Analysis on constructing a risk prediction model for premature ovarian function failure in patients with uterine fibroids complicated with hypertension after surgery based on decision tree method / 中华内分泌外科杂志

Objective:The decision tree Chi-square automatic interactive detection (CHAID) algorithm and binary Logistic regression analysis were used to construct the risk prediction model of premature ovarian failure (POF) in patients with uterine fibroids complicated with hypertension after surgery, and the results of the risk prediction model were compared and analyzed.Methods:Patients with uterine fibroids complicated with hypertension admitted to Taizhou Hospital of Zhejiang Province from Jan. 2019 to Sep. 2022 were retrospectively analyzed as the research objects. CHAID algorithm and Logistic regression analysis were used to establish risk prediction models, respectively. The area under the curve (AUC) of receiver operating characteristic curve (ROC) was used to compare and evaluate the prediction effects of the two models.Results:A total of 860 patients were collected, including 56 patients with premature ovarian function failure after operation, and the incidence of premature ovarian function failure was 6.51%. CHAID method and Logistic regression analysis showed that uterine myoma surgery, hypertension, smoking or passive smoking, family history of premature ovarian failure, sleep status, physical exercise and history of induced curettage were important influencing factors of premature ovarian failure. The accuracy of risk prediction of decision tree model was 88.2%, and the fitting effect of the model was good. The Logistic regression model Hosmer-Leme-show goodness of fit test showed that the model fit was good. The AUC of Logistic regression model was 0.893 (95% CI: 0.862-0.899), and the AUC of decision tree model was 0.882 (95% CI: 0.856-0.899). The predictive value of the two models was moderate, and there was no significant difference between them ( Z=0.254, P>0.05) . Conclusions:The combination of decision tree and Logistic regression model can find the influencing factors of premature ovarian function failure in patients with uterine fibroids complicated with hypertension after operation from different levels, and the relationship between the factors can be more fully understood. The establishment of a risk model for premature ovarian function failure in patients with uterine fibroids complicated with hypertension after surgery can provide a reference for postoperative intervention in patients with uterine fibroids complicated with hypertension, and more effectively help patients actively prevent and slow down the occurrence and development of POF.

Study on DRG grouping of acute myeloid leukemia based on decision tree model / 中华医院管理杂志

Objective:To explore the influencing factors of hospitalization cost of acute myeloid leukemia, to group the cases based on decision tree model and to provide reference for improving the DRG management in this regard.Methods:Homepage data were retrieved from the medical records with acute myeloid leukemia as the main diagnosis (the top four ICD codes were C92.0, C92.4, C92.5, and C93.0). These patients were discharged from the clinical hematology department of the Fujian Institute of Hematology from January 2020 to December 2021. Then the influencing factors of hospitalization expenses were identified using Wilcoxon rank sum test or Kruskal-Wallis rank sum test and multiple linear stepwise regression analysis, with such factors used as classification nodes. The decision tree model of χ2 automatic interactive testing method was used to group the cases so included. At the same time, the included cases were grouped according to the trial run C-DRG version in Fujian province, for comparison of the differences between the two grouping methods. Results:The length of stay, the type of treatment, whether associated complications and age of patients were found as the influencing factors for the hospitalization costs of patients with acute myeloid leukemia, and such factors were included in the decision tree model to form 9 case mixes. The variance reduction of this model was 75.77%, featuring a high inter-group heterogeneity, and the coefficient of variation was 0.33-0.61, featuring a low in-group difference. The patients were divided into two groups according to the C-DRG version in Fujian province. The variance reduction of this method was 27.57%, featuring a low inter-group heterogeneity, and the coefficients of variation were 0.59 and 1.25, featuring high in-group difference.Conclusions:The cases of acute myeloid leukemia were grouped based on length of stay, type of treatment, whether accompanied by complications, and age proved reasonable enough to serve as reference for DRG management and cost control of this disease.

Construction of a rapid depression screening model for blood donors in Guangzhou based on decision tree / 中国输血杂志

【Objective】 To investigate the prevalence of depression in blood donors and analyze the related factors, so as to develop a rapid depression screening model for blood donors. 【Methods】 A total of 13 015 street whole blood donors in Guangzhou Blood Center during May to August, 2020 filled in an anonymous e-questionnaire, including social demography information and the Patient Health Questionnaire-9 before donation. The cut-off value for detecting depression was 10. Logistic regression by SPSS 26.0 was used to analyze depression related factors. 2-level decision tree with 30/10 as the minimum number of cases in parent/child node, 10-fold cross validation was used to cut items of PHQ-9 to form the depression screening model. 【Results】 364 out of 13 015 (2.80%) street whole blood donors reported a score ≥ 10. Donors with 18-29 years old (P <0.05), unmarried (P<0.05), less than 50 000 RMB household income per year (P< 0.05) were more prone to depression. 81.96% donors in "<10 scores" group, while 3.85%donors in "≥ 10 scores" group were in two terminal nodes formed by Item-6, 2 and 4 of PHQ-9. After verification by the 10 fold crossover method, the estimated misclassification risk of the model was 1.7%. 【Conclusion】 The screening prevalence of depression based on PHQ-9 in Guangzhou blood donors was 2.8%(95% CI: 2.52%-3.09%) . Donation frequency was not related to depression. A rapid and efficient depression screening model for blood donors based on item-6, 2 and 4 of PHQ-9 was developed.

Factors affecting microvascular complications among patients with type 2 diabetes mellitus / 预防医学

Objective @#To identify the factors affecting microvascular complications among patients with type 2 diabetes (T2DM), so as to provide insights into the management of microvascular complications of T2DM.@*Methods@#T2DM patients hospitalized in the Department of Endocrinology of a tertiary hospital in Weifang City, Shandong Province from January 2021 to January 2022 were enrolled, and subjects' basic information, lifestyle and medical history were collected using questionnaire surveys. Fasting insulin, fasting blood glucose and glycated hemoglobin were measured, and factors affecting microvascular complications were identified among T2DM patients using a multivariable logistic regression model and a decision tree model.@*Results@#Totally 1 003 T2DM inpatients were enrolled, including 515 men (51.35%) and 488 women (48.65%), and the prevalence of microvascular complications was 40.18%. Multivariable logistic regression analysis showed that age of 60 years and older (OR=2.510, 95%CI: 1.441-4.374), T2DM duration of 10 years and longer (OR=3.205, 95%CI: 2.242-4.581), fasting insulin of lower than 3.21 μIU/mL (OR=1.749, 95%CI: 1.239-2.469), using of agents or insulin to control blood glucose (OR=1.880, 95%CI: 1.143-3.092), glycated hemoglobin level of 7% and higher (OR=1.751, 95%CI: 1.172-2.615) as factors affecting microvascular complications among T2DM patients. Decision tree analysis identified course of T2DM as a major factor affecting the risk of microvascular complications among T2DM patients, and the prevalence of microvascular complications was 70.22% among T2DM patients with disease course of 10 years and longer and fasting insulin of lower than 3.21 μIU/mL or 16.32 μIU/mL and higher, 44.23% among T2DM patients with disease course of 5 to 10 years and at ages of 60 years and older, and 43.10% among T2DM patients with disease course of less than 5 years and fasting insulin of lower than 3.21 μIU/mL. @*Conclusion@#Advanced age, long course of T2DM, low fasting insulin and high glycated hemoglobin may increase the risk of microvascular complications among T2DM patients.

Effectiveness of early warning management of nosocomial infection based on neural network model and decision tree model / 公共卫生与预防医学

Objective To predict the effectiveness of nosocomial infection management and effectively control the risk of nosocomial infection. Methods In this study, with the population of ICU patients in a Grade A hospital , 345 ICU patients seen from June 2020 to June 2021 were included in the analysis to collect the infection data in the hospital. Based on the use of the decision tree model to analyze the influencing factors of nosocomial infection, the neural network model was also used to predict the risk of developing nosocomial infection. Results The decision tree model showed that advanced age (age> 80 years) influenced the root node. Type 2 diabetes, gender by male, and BMI level were child nodes, which had different synergistic effects on the occurrence of nosocomial infection. At the same time, random forest (RF), support vector machine (SVM), logical regression (LR) and K nearest neighbor (KNN) algorithms were used to construct a neural network prediction model of nosocomial infection risk, suggesting that the condition, sex and body size of basic diseases are related to the occurrence of nosocomial infection. The combined use of the above model in parallel can effectively increase the specificity and reduce the missed diagnosis. Conclusion The neural network model joint decision tree model in parallel and joint early warning of nosocomial infection risk have excellent effect, and can effectively provide information support for the prevention, management and disposal of nosocomial infection.

Influencing factors of metabolic syndrome among adults in Nanjing， China： an analysis based on decision tree and logistic regress models / 上海预防医学

ObjectiveWe analyzed the prevalence of metabolic syndrome in adult residents of Nanjing and explored its influencing factors in order to provide technical references for the prevention of metabolic syndrome. MethodsBased on the data of the Nanjing adult chronic disease thematic survey from January 2017 to June 2018， the influencing factors of metabolic syndrome were analyzed using multifactorial logistic regression model and decision tree model. ResultsThe weighted prevalence of metabolic syndrome among people aged 18 years and over in Nanjing was 16.14%（95%CI：16.12%‒16.16%）. Prevalence of metabolic syndrome was statistically different（P<0.05）among respondents with different demographic characteristics. Logistic regression model analysis showed that age， gender， education， physical activity level， marriage status， smoking status， drinking status， weight status， diabetes and hypertension family history were the influencing factors for the prevalence of metabolic syndrome（P<0.05）. The results of the decision tree model showed that weight status was the most influential factor for metabolic syndrome， followed by age， gender， diabetes family history and smoking status. ConclusionThe prevalence of metabolic syndrome is high among the adult population in Nanjing， and special attention should be paid to middle-aged and elderly men who are overweight and obese， have a family history of diabetes and smoking.

Predição de choque séptico e hipovolêmico em pacientes de unidade de terapia intensiva com o uso de machine learning / Prediction of septic and hypovolemic shock in intensive care unit patients using machine learning

RESUMO Objetivo: Criar e validar um modelo de predição de choque séptico ou hipovolêmico a partir de variáveis de fácil obtenção coletadas na admissão de pacientes internados em uma unidade de terapia intensiva. Métodos: Estudo de modelagem preditiva com dados de coorte concorrente realizada em um hospital do interior do nordeste brasileiro. Foram incluídos pacientes com 18 anos ou mais sem uso de droga vasoativa no dia da admissão e que foram internados entre novembro de 2020 e julho de 2021. Foram testados os algoritmos de classificação do tipo Decision Tree, Random Forest, AdaBoost, Gradient Boosting e XGBoost para a construção do modelo. O método de validação utilizado foi o k-fold cross validation. As métricas de avaliação utilizadas foram recall, precisão e área sob a curva Receiver Operating Characteristic. Resultados: Foram utilizados 720 pacientes para criação e validação do modelo. Os modelos apresentaram alta capacidade preditiva com área sob a curva Receiver Operating Characteristic de 0,979; 0,999; 0,980; 0,998 e 1,00 para os algoritmos de Decision Tree, Random Forest, AdaBoost, Gradient Boosting e XGBoost, respectivamente. Conclusão: O modelo preditivo criado e validado apresentou elevada capacidade de predição do choque séptico e hipovolêmico desde o momento da admissão de pacientes na unidade de terapia intensiva.

ABSTRACT Objective: To create and validate a model for predicting septic or hypovolemic shock from easily obtainable variables collected from patients at admission to an intensive care unit. Methods: A predictive modeling study with concurrent cohort data was conducted in a hospital in the interior of northeastern Brazil. Patients aged 18 years or older who were not using vasoactive drugs on the day of admission and were hospitalized from November 2020 to July 2021 were included. The Decision Tree, Random Forest, AdaBoost, Gradient Boosting and XGBoost classification algorithms were tested for use in building the model. The validation method used was k-fold cross validation. The evaluation metrics used were recall, precision and area under the Receiver Operating Characteristic curve. Results: A total of 720 patients were used to create and validate the model. The models showed high predictive capacity with areas under the Receiver Operating Characteristic curve of 0.979; 0.999; 0.980; 0.998 and 1.00 for the Decision Tree, Random Forest, AdaBoost, Gradient Boosting and XGBoost algorithms, respectively. Conclusion: The predictive model created and validated showed a high ability to predict septic and hypovolemic shock from the time of admission of patients to the intensive care unit.

Comparison Of Artificial Neural Network and Decision Tree Methods for Predicting the Maternal Outcome in A Tertiary Care Hospital in Odisha, India

Background: This study used an artificial neural network (ANN) and a decision tree to predict maternal outcomes and their major determinants. An artificial neural network (ANN) and a decision tree were used in this study to determine maternal outcomes and their significant determinants. Methods: Data was gathered from 955 pregnant women at a tertiary care hospital in Bhubaneswar, Od-isha. A popular machine learning algorithm, artificial neural networks (ANN), was used to predict mater-nal outcomes and their determinants. Results: In the bivariate analysis, we found gestational age is significantly associated with maternal out-come (p=<0.001). The accuracy of the ANN model and decision tree was 0.882 and 0.823, respectively. Based on the variable importance of ANN, the significant determinants of maternal outcome were birth weight, systolic blood pressure, haemoglobin, gestational age, age of mother, diastolic blood pressure etc. Conclusion: This model can be utilized in future for Proper precautions and medical check-ups required during the maternal period to avoid a negative maternal outcome.

Decision tree-based classification as a support to diagnosis in the Alzheimer's disease continuum using cerebrospinal fluid biomarkers: insights from automated analysis

Objective: Cerebrospinal fluid (CSF) biomarkers add accuracy to the diagnostic workup of cognitive impairment by illustrating Alzheimer's disease (AD) pathology. However, there are no universally accepted cutoff values for the interpretation of AD biomarkers. The aim of this study is to determine the viability of a decision-tree method to analyse CSF biomarkers of AD as a support for clinical diagnosis. Methods: A decision-tree method (automated classification analysis) was applied to concentrations of AD biomarkers in CSF as a support for clinical diagnosis in older adults with or without cognitive impairment in a Brazilian cohort. In brief, 272 older adults (68 with AD, 122 with mild cognitive impairment [MCI], and 82 healthy controls) were assessed for CSF concentrations of Aβ1-42, total-tau, and phosphorylated-tau using multiplexed Luminex assays; biomarker values were used to generate decision-tree algorithms (classification and regression tree) in the R statistical software environment. Results: The best decision tree model had an accuracy of 74.65% to differentiate the three groups. Cluster analysis supported the combination of CSF biomarkers to differentiate AD and MCI vs. controls, suggesting the best cutoff values for each clinical condition. Conclusion: Automated analyses of AD biomarkers provide valuable information to support the clinical diagnosis of MCI and AD in research settings.

PREDICTIVE THE HEART DISEASE USING THE WEIGHTED GAIN DECISION TREE ALGORTHIM

Data mining techniques have been mostly used in medical area for prediction and diagnosis of various diseases. These techniques discover the hidden pattern and relationship in medical data and therefore have been very important in designing clinical support. Now a day's data mining techniques are widely used in diagnosis of heart disease because of increasing death rate worldwide. The reason of this may be the complex and expensive tests conducted in labs to predict the heart disease. Systems based on these risk factors not only bene?t healthcare professionals, but warn them of the potential presence of heart disease even before a patient is admitted to the hospital or undergoes an expensive medical examination. This in order to reduce the risk of this disease a better approach would to identify risk factor the result in heart disease. This study is an effort in this direction. This approach to predict the heart disease in early stage is developed in present study by analyzing risk factors. This technique developed weighted gain decision tree predicts the risk of heart disease with an accuracy of 90%

A prospective study of the decision tree prediction model for attention deficit hyperactivity disorder in preschool children / 中国当代儿科杂志

OBJECTIVES@#To study the clinical value of attention time combined with behavior scale in the screening of attention deficit hyperactivity disorder (ADHD) in preschool children.@*METHODS@#A total of 200 preschool children with ADHD diagnosed in Fujian Maternal and Child Health Hospital from February 2019 to March 2020 were enrolled as the ADHD group. A total of 200 children who underwent physical examination in the hospital or kindergartens during the same period were enrolled as the control group. Attention time was recorded. Chinese Version of Swanson Nolan and Pelham, Version IV Scale-Parent Form (SNAP-IV) scale was used to evaluate symptoms. With clinical diagnosis as the gold standard, the decision tree analysis was used to evaluate the clinical value of attention time combined with behavior scale in the screening of ADHD.@*RESULTS@#Compared with the control group, the ADHD group had significantly higher scores of SNAP-IV items 1, 4, 7, 8, 10, 11, 14, 15, 16, 18, 20, 21, and 22 (P<0.05) and a significantly shorter attention time (P<0.05). The variables with statistically significant differences between the two groups in univariate analysis were used as independent variables to establish a decision tree model. The accuracy of the model in predicting ADHD was 81%, that in predicting non-ADHD was 69%, and the overall accuracy was 75%, with an area under the ROC curve of 0.816 (95% CI: 0.774-0.857, P<0.001).@*CONCLUSIONS@#The decision tree model for screening ADHD in preschool children based on attention time and assessment results of behavior scale has a high accuracy and can be used for rapid screening of ADHD among children in clinical practice.

Application of decision tree model in predicting the risk of hypothermia after cardiopulmonary bypass in children with congenital heart disease / 中华实用儿科临床杂志

Objective:To analyze the influential factors of hypothermia in congenital heart disease (CHD) after cardiopulmonary bypass (CPB) rewarming using the decision tree model, thus providing theoretical basis for medical staff.Methods:A total of 711 CHD children who underwent surgery in the Shanghai Children′s Medical Center from January 1, 2019 to April 30, 2019 were retrospectively analyzed.A decision tree model was established to predict the risk factors for hypothermia in CHD children following CPB.Results:The decision tree model showed that CPB program, preoperative nutrition score and body surface area were the high-risk factors for hypothermia in CHD children after CPB rewarming.The accuracy, sensitivity, specificity of the decision tree model were 86.45%, 77.14% and 90.97%, respectively, and the area under the receiver operating characteristic curve was 0.851(95% CI: 0.798-0.904). Conclusions:Decision tree model has a high application value in predicting hypothermia in CHD children following CPB.It contributes to identify the influential factors of hypothermia, and provides references for performing preventive treatment and nursing measures to control the risk of hypothermia.

Objective Criteria for Judging Walking Independence in a Convalescent Rehabilitation Ward for Hemiparetic Stroke：A Study Using Decision Tree Analysis / The Japanese Journal of Rehabilitation Medicine

Objective：This study aimed to clarify the objective criteria for assessing walking independence using cane in patients with stroke in the convalescent rehabilitation ward.Methods：Participants were in-patients with hemiparetic stroke who could walk with a cane, and they were categorized into the independent (ID) and supervised (SV) walking groups. Stroke impairment assessment set-motor for lower extremity (SIAS-LE), trunk control test (TCT), Berg balance scale (BBS), 10-m walking speed (m/s), and functional independence measure-cognitive (FIM-C) were assessed. ID and SV used the scores at the time of independent walking and at the discharge time, respectively. Additionally, falls after independence were investigated. Statistical analysis was performed using univariate analysis and decision tree analysis.Results：In total, 148 patients (ID：n=101, 68±13 years, SV：n=47, 79±12) were included. Significant differences were observed in walking speed, TCT score, BBS score, and FIM-C score between the groups. Moreover, walking speed, FIM-C score, and BBS score were selected in the decision tree analysis in this order and divided into five groups namely：1) walking speed ≥ 0.42 and FIM-C ≥ 22 (percentage of independent patients 97％/percentage of fallers 5％), 2.) walking speed ≥ 0.42, FIM-C＜22, and BBS ≥ 50 (100％/0％), 3.) walking speed ≥ 0.42, FIM-C＜22, and BBS＜50 (52％/8％), 4.) walking speed＜0.42, and BBS ≥ 28 (49％/28％), and 5) walking speed＜0.42 and BBS＜28 (0％/0％). The overall percentage of fallers was 8.9％, with group 4 having the highest number of fallers.Conclusion：Walking speed, FIM-C, and BBS, in decreasing order, were involved in walking independence. Patients with low walking speed were more likely to fall. Therefore, careful assessment of walking independence is particularly required.

Comparación de la costo-efectividad de la nefrolitotomía percutánea y de la nefrolitotomía retrógrada flexible con láser de holmio en pacientes con litiasis renal de 20 a 30 mm en Colombia / Comparison of the Cost-effectiveness of Percutaneous Nephrolithotomy and Flexible Retrograde Holmium Laser Nephrolithotomy in Patients with Kidney Stones of 20 to 30 mm in Colombia

Introducción y Objetivo Con el advenimiento de nuevas tecnologías, vienen controversias respecto al espectro de sus aplicaciones. El costo derivado de estas tecnologías juega un papel muy importante en el momento de la toma de decisiones terapéuticas. Es por esto que consideramos relevante estimar la costo-efectividad de la nefrolitotomía percutánea comparada con la nefrolitotomía retrógrada flexible con láser de holmio en pacientes con litiasis renal de 20 mm a 30 mm en Colombia. Materiales y Métodos Por medio de la construcción de un modelo de árbol de decisión usando el programa Treeage (TreeAge Software, LLC, Williamstown, MA, EE.UU.), se realizó una comparación entre la nefrolitotomía percutánea y la nefrolitotomía retrógrada flexible con láser de holmio en pacientes con litiasis renal de 20 mm a 30 mm. La perspectiva fue la del tercer pagador, y se incluyeron los costos directos. Las cifras fueron expresadas en pesos colombianos de 2018. La mejoría clínica, definida como el paciente libre de cálculos, fue la unidad de resultado. Se hizo una extracción de datos de efectividad y seguridad por medio de una revisión sistemática de la literatura. La razón de costo-efectividad incremental fue calculada. Resultados El modelo final indica que la nefrolitotomía percutánea puede ser considerada como la alternativa más costo-efectiva. Los hallazgos fueron sensibles a la probabilidad de mejoría clínica de la nefrolitotomía percutánea. Conclusión Teniendo en cuenta las variables económicas, los supuestos del modelo y desde la perspectiva del tercer pagador, la nefrolitotomía percutánea para el tratamiento de pacientes con cálculos renales de 20 mm a 30 mm es costo-efectiva en nuestro país. Estos hallazgos fueron sensibles a los costos y a la efectividad de los procedimientos quirúrgicos.

Introduction and Objective The advent of new technologies leads to controversies regarding the spectrum of their applications and their cost. The cost of these technologies plays a very important role when making therapeutic decisions. Therefore, we consider it relevant to estimate the cost-effectiveness of percutaneous nephrolithotomy compared with flexible retrograde holmium laser nephrolithotomy in patients with kidney stones of 20 mm to 30 mm in Colombia. Materials and Methods Through the development of a decision tree model using the Treeage (TreeAge Software, LLC, Williamstown, MA, US) software, we compared percutaneous nephrolithotomy with flexible holmium laser retrograde nephrolithotomy in patients with kidney stones of 20 mm to 30 mm. The perspective was that of the third payer, and all direct costs were included. The figures were expressed in terms of 2018 Colombian pesos. Clinical improvement, which was defined as a stone-free patient, was the outcome unit. We extracted data on effectiveness and safety through a systematic review of the literature. The incremental cost-effectiveness ratio was calculated. Results In terms of cost-effectiveness the final model indicates that percutaneous nephrolithotomy may be considered the best alternative. These findings were sensitive to the probability of clinical improvement of the percutaneous nephrolithotomy. Conclusion Taking into account the economic variables, the assumptions of the model, and through the perspective of the third payer, percutaneous nephrolithotomy for the treatment of patients with kidney stones of 20 mm to 30mm is cost-effective in our country. These findings were sensitive to the costs and effectiveness of the surgical procedures.