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.

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.

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.

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.

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.

Arboles de Decisión como Metodología para Determinar el Rendimiento Académico en Educación Superior / Decision Trees as a Methodology to Determine Academic Performance in Higher Education / Árvores de Decisão como Metodologia para Determinar o Desempenho Acadêmico no Ensino Superior

Resumen Introducción. En este artículo se presentan los resultados finales de la investigación Árboles de decisión como metodología para determinar el rendimiento académico en educación superior. Objetivo. Explicar el rendimiento académico de los alumnos que cursan asignaturas relacionadas con la programación en una institución de nivel superior ubicada en la zona urbana de Pánuco, Veracruz, México. El rendimiento académico presenta una situación que no solamente preocupa a las instituciones educativas, sino también a los estudiantes, padres de familia, profesores y directores. Puede mencionarse que este presenta también una situación mundial y que es investigado en diferentes áreas de conocimiento. Materiales y Métodos. Se aplicó un cuestionario a 341 estudiantes repartidos en el segundo, cuarto y sexto semestre. Se utilizaron dos técnicas de modelado estadístico: árbol de decisión y regresión lineal múltiple, para definir qué variables independientes están asociadas al rendimiento académico. Resultados. Se ubica que las variables de aprendizaje en el aula y las tutorías externas están relacionadas con la variable de rendimiento académico y que el 48.1 % de los alumnos necesitan algún apoyo académico o capacitación externa para el reforzamiento de la programación. Conclusiones. Se recomienda implementar estrategias de mejora para reducir la sobrecarga de trabajo de los alumnos. También realizar una sensibilización antes de aplicar la encuesta y que los cuestionarios sean aplicados en fechas de exámenes ya que los alumnos se encuentran en niveles altos de estrés. En trabajos posteriores se tiene contemplado poder evaluar los efectos sobre el rendimiento académico, económico, social y cultural.

Abstract Introduction. This article presents the results of the Decision Trees research as a methodology to determine academic performance in higher education. Objective. Explain the academic performance of students taking subjects related to programming at a higher-level institution located in the urban area of Pánuco, Veracruz, Mexico. Academic performance presents a situation that not only concerns educational institutions, but also students, parents, teachers, and principals. It can be mentioned that this also presents a world situation and that it is investigated in different areas of knowledge. Materials and methods. A questionnaire was applied to 341 students distributed in the second, fourth and sixth semester. Two statistical modeling techniques were used: decision tree and multiple linear regression, to define which independent variables are associated with academic performance. Results. It is located that the learning variables in the classroom and the external tutorials are related to the academic performance variable and that 48.1 % of the students need some academic support or external training to reinforce the programming. Conclusions. It is recommended to implement improvement strategies to reduce the work overload of the students. Also make an awareness before applying the survey and that the questionnaires are applied on test dates since the students are at high levels of stress. Future research could evaluate the effect on academic, economic and cultural performance.

Resumo Introdução. Este artigo apresenta os resultados da pesquisa Árvores de Decisão como uma metodologia para determinar o desempenho acadêmico no ensino superior. Objetivo. Explique o desempenho acadêmico dos estudantes que cursam matérias relacionadas à programação em uma instituição de nível superior localizada na área urbana de Pánuco, Veracruz, México. O desempenho acadêmico apresenta uma situação que diz respeito não apenas às instituições de ensino, mas também a estudantes, pais, professores e diretores. Pode-se mencionar que isso também apresenta uma situação mundial e é investigada em diferentes áreas do conhecimento. Materiais e métodos. Foi aplicado um questionário a 341 alunos distribuídos no segundo, quarto e sexto semestre. Foram utilizadas duas técnicas de modelagem estatística: árvore de decisão e regressão linear múltipla, para definir quais variáveis independentes estão associadas ao desempenho acadêmico. Resultados. Fica localizado que as variáveis de aprendizagem em sala de aula e os tutoriais externos estão relacionados à variável desempenho acadêmico e que 48,1 % dos alunos precisam de algum apoio acadêmico ou treinamento externo para reforçar a programação. Conclusões. Recomenda-se implementar estratégias de melhoria para reduzir a sobrecarga de trabalho dos alunos. Lembre-se também antes de aplicar a pesquisa e que os questionários sejam aplicados nas datas dos testes, uma vez que os alunos estão em altos níveis de estresse.

Pharmacoeconomic Evaluation of Perospirone in the Treatment of Schizophrenia ：A Study Based on Major Adverse Events / 中国药房

OBJECTIVE：To evaluate the economy of pe rospirone in the treatment of schizophrenia ，to provide guidance for clinically proper use of medications more cost-effectively ，and related health decision-making . METHODS ：A short-term decision tree model was constructed from the perspective of medical insurance payer to calculate the cost and health outcomes of different treatment plans considering major adverse events including extrapyramidal reaction ，weight gain ，diabetes，hyperlipidemia. The cost-utility of perospirone were compared with quetiapine ，aripiprazole and olanzapine respectively ，using QALYs as the measure of health outcomes ，3 times GDP per capita as the willingness-to-pay threshold ；probability sensitivity analysis was performed. RESULTS：The results of base-case analysis showed that the cost of perospirone （6 688.25 yuan）was lower than those of quetiapine （9 887.45 yuan），aripiprazole（13 284.65 yuan）and olanzapine （15 332.80 yuan）. The utility of perospirone （0.79 QALYs）was better than those of quetiapine （0.76 QALYs），aripiprazole（0.77 QALYs）and olanzapine （0.75 QALYs）. Compared with quetiapine ， aripiprazole and olanzapine ，peropirone had lower cost and higher health outcome ，which indicated that strong dominance favors perospirone over the other 3 drugs. The results of sensitivity analysis were consistent with those of base-case analysis. CONCLUSIONS：Perospirone has economic advantages in treating schizophrenia patients compared to other commonly used atypical antipsychotic drugs.

Development and analysis of clinical prediction model of acupuncture and moxibustion treatment for stroke at recovery stage / 中国针灸

OBJECTIVE@#To develop the clinical prediction model of therapeutic effect in treatment with acupuncture and moxibustion for the patients with stroke at recovery stage under different conditions so as to provide a tool for predicting the therapeutic effect of acupuncture and moxibustion.@*METHODS@#A total of 1410 patients with stroke at recovery stage were collected from the Third Affiliated Hospital of Zhejiang Chinese Medical University from 2012 to 2019. The relevant data were extracted, i.e. sex, age, time of onset, neurological functional deficit score (NFDS) and acupuncture and moxibustion therapy. The difference of NFDS before and after treatment was adopted to evaluate the therapeutic effect in the patients. Using SPSS26.0 software and CART decision tree analysis, the clinical prediction model was developed.@*RESULTS@#The key variables in the prediction model of therapeutic effect in the patients with stroke at recovery stage under different conditions included age, time of onset, hypertension, cardiac disease, diabetes, TCM diagnosis, hemoglobin (HB), serum homocysteine (HCY) and acupuncture and moxibustion therapy. There were 12 main rules generated by the decision tree model, including 8 rules for predicting the improvements of therapeutic effect and 4 rules for predicting the absence of improvements (i.e. no change and deterioration). The accuracy rates of the model training set and test set were 80.0% and 72.8% respectively, the area under curve (AUC) of ROC was 0.797 and the model identification and classification results were satisfactory.@*CONCLUSION@#The clinical prediction model developed by CART decision tree analysis is high in accuracy for the prediction of the therapeutic effect in the patients with stroke at recovery stage under different conditions. Based on the therapeutic effect predicted in the hospital visit, the physicians may adopt the corresponding regimens of acupuncture and moxibustion therapy in patients.

Preparing anti-SARS-CoV-2 agent EIDD-2801 by a practical and scalable approach, and quick evaluation

EIDD-2801 is an orally bioavailable prodrug, which will be applied for emergency use authorization from the U.S. Food and Drug Administration for the treatment of COVID-19. To investigate the optimal parameters, EIDD-2801 was optimized

Decision Tree Based Salp Swarm Optimization for Multi Medical Data Classification with Feature Reduction Technique

Abstract The ambitious task in the domain of medical informatics is medical data classification. From medical datasets, intention to ameliorate human burden with the medical data classification entails to taking in classification designs. The medical data classification is the major focus of this paper, where a Decision Tree based Salp Swarm Optimization (DT-SWO) algorithm is proposed. After pre-processingthe hybrid feature selection method selects the medical data features. The high dimensional features are reduced by Discriminant Independent Component Analysis (DICA) and DT-SWO is to classify the most relevant class of medical data. The details of four datasets namely Leukemia, Diffuse Larger B-cell Lymphomas (DLBCL), Lung cancer and Colon relating to four diseases for heart, liver, cancer and lungs are collected from the UCI machine learning repository. Ultimately, the experimental outcomes demonstrated that the proposed DT-SWO algorithm is suitable for medical data classification than other algorithms.

Classification of hepatocellular carcinoma diameter by statistical technology and prognostic evaluation in patients after the combined use of transarterial chemoembolization and radiofrequency ablation

Objective: This study aimed to classify hepatocellular carcinomas (HCCs) according to their diameter using statistic technology and evaluate the prognosis of the classified groups after the combined use of transarterial chemoembolization (TACE) and radiofrequency ablation (RFA). Materials and Methods: Electronic medical records of 128 consecutive patients who underwent TACE-RFA as the initial treatment for HCC from January 2010 to April 2018 were retrospectively analyzed. TACE was initially performed with subsequent RFA performed after 3–7 days. The decision tree model was used to classify overall survival (OS), progression-free survival (PFS), local recurrence rate (LRR), and treatment complications in HCC. Results: The tumors were divided into three groups of sizes ≤2.9 cm, 2.9–4.8 cm, and >4.8 cm. The group of tumors >4.8 cm showed inferior OS, PFS, and LRR than the other two groups (P < 0.05) on long-term follow-up but not in thefirst 6 months (P > 0.05). The groups of tumors ≤2.9 cm and 2.9–4.8 cm showed no statistically significant difference in OS, PFS, and LRR (P > 0.05). Conclusions: The cutoff points of 2.9 and 4.8 cm were achieved using the objective decision tree model rather than the artificial division of 3 and 5 cm. The prognosis was not significantly different between the groups of tumors ≤2.9 cm and 2.9–4.8 cm, and the prognosis of the two groups was better than the group of tumors >4.8 cm in the long-term follow-up but not in thefirst 6 months

A Fuzzy Approach for Diabetes Mellitus Type 2 Classification

Abstract This paper proposes an automatic fuzzy classification system for glycemic index, which indicates the level of Diabetes Mellitus type 2. Diabetes is a chronic disease occurred when there is deficiency in insulin production or in its action, or both, causing complications. Neuro-fuzzy systems and Decision Trees are used to obtain, respectively, the numerical parameters of the membership functions and the linguistic based rules of the fuzzy classification system. The results goal to categorize the glycemic index into 4 classes: decrease a lot, decrease, stable and increase. Real database from [1] is used and the input attributes of the system are defined. In addition, the proposed automatic fuzzy classification system is compared with an "expert" fuzzy classification system, which is totally modeled using expert knowledge. From linguistic based rules obtained from fuzzy inference process, new scenarios are simulated in order to obtain a larger data set which provides a better evaluation of the classification systems. Results are promising, since they indicate the best treatment - intervention or comparative - for each patient, assisting in the decision-making process of the health care professional.