Your browser doesn't support javascript.
Show: 20 | 50 | 100
Results 1 - 20 de 259
International Journal of Oral Science ; (4): 41-41, 2023.
Article in English | WPRIM | ID: wpr-1010696


Maxillary sinus floor augmentation using lateral window and crestal technique is considered as predictable methods to increase the residual bone height; however, this surgery is commonly complicated by Schneiderian membrane perforation, which is closely related to anatomical factors. This article aimed to assess anatomical factors on successful augmentation procedures. After review of the current evidence on sinus augmentation techniques, anatomical factors related to the stretching potential of Schneiderian membrane were assessed and a decision tree for the rational choice of surgical approaches was proposed. Schneiderian membrane perforation might occur when local tension exceeds its stretching potential, which is closely related to anatomical variations of the maxillary sinus. Choice of a surgical approach and clinical outcomes are influenced by the stretching potential of Schneiderian membrane. In addition to the residual bone height, clinicians should also consider the stretching potential affected by the membrane health condition, the contours of the maxillary sinus, and the presence of antral septa when evaluating the choice of surgical approaches and clinical outcomes.

Sinus Floor Augmentation , Decision Trees
Chinese Journal of Epidemiology ; (12): 85-91, 2022.
Article in Chinese | WPRIM | ID: wpr-935354


Objective: To investigate the influencing factors of HBV intrauterine transmission and their interaction effects by integrating logistic regression model and Chi-squared automatic interaction detector (CHAID) decision tree model. Methods: A total of 689 pairs of HBsAg-positive mothers and their neonates in the obstetrics department of the Third People's Hospital of Taiyuan from 2007 to 2013 were enrolled, and the basic information of mothers and their neonates were obtained by questionnaire survey and medical record review, such as the general demographic characteristics, gestational week and delivery mode. HBV DNA and HBV serological markers of the mothers and newborns were detected by fluorescence quantitative PCR and electrochemiluminescence immunoassay respectively. The CHAID decision tree model and unconditional logistic regression analysis were used to explore the factors influencing HBV intrauterine transmission in neonates of HBsAg-positive mothers. Results: Among the 689 neonates, the incidence of HBV intrauterine transmission was 11.47% (79/689). After adjusted for confounding factors, the first and second logistic multivariate analysis showed that cesarean delivery was a protective factor for HBV intrauterine transmission (OR=0.25, 95%CI: 0.14-0.43; OR=0.27, 95%CI: 0.15-0.46); both models indicated that maternal HBeAg positivity and HBV DNA load ≥2×105 IU/ml before delivery were risk factors of HBV intrauterine transmission (OR=3.89, 95%CI: 2.32-6.51; OR=3.48, 95%CI: 2.12-5.71), respectively. The CHAID decision tree model screened three significant factors influencing HBV intrauterine transmission, the most significant one was maternal HBeAg status, followed by delivery mode and maternal HBV DNA load. There were interactions between maternal HBeAg status and delivery modes, as well as delivery mode and maternal HBV DNA load before delivery. The rate of HBV intrauterine transmission in newborns of HBeAg-positive mothers by vaginal delivery increased from 19.08% to 29.37%; among HBeAg-positive mothers with HBV DNA ≥2×105 IU/ml, the rate of HBV intrauterine transmission increased to 33.33% in the newborns by vaginal delivery. Conclusions: Maternal HBeAg positivity,maternal HBV DNA ≥2×105 IU/ml and vaginal delivery could be risk factors for HBV intrauterine transmission in newborns. Interaction effects were found between maternal HBeAg positivity and vaginal delivery, as well as vaginal delivery and high maternal HBV DNA load. Logistic regression model and the CHAID decision tree model can be used in conjunction to identify the high-risk populations and develop preventive strategies accurately.

Female , Humans , Infant, Newborn , Pregnancy , DNA, Viral/genetics , Decision Trees , Hepatitis B Surface Antigens , Hepatitis B e Antigens , Hepatitis B virus/genetics , Infectious Disease Transmission, Vertical , Logistic Models , Mothers , Pregnancy Complications, Infectious/epidemiology
Chinese Journal of Contemporary Pediatrics ; (12): 255-260, 2022.
Article in English | WPRIM | ID: wpr-928596


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.

Child, Preschool , Humans , Asian People , Attention Deficit Disorder with Hyperactivity/diagnosis , Decision Trees , Mass Screening , Prospective Studies
urol. colomb. (Bogotá. En línea) ; 31(4): 162-169, 2022. ilus
Article in Spanish | LILACS, COLNAL | ID: biblio-1412092


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.

Humans , Surgical Procedures, Operative , Costs and Cost Analysis , Nephrolithiasis , Lasers, Solid-State , Nephrolithotomy, Percutaneous , Technology , Effectiveness , Decision Trees , Kidney Calculi , Colombia
Rev. Esc. Enferm. USP ; 55: e03682, 2021. tab, graf
Article in English | BDENF, LILACS | ID: biblio-1287934


ABSTRACT Objective: To generate a Classification Tree for the correct inference of the Nursing Diagnosis Fluid Volume Excess (00026) in chronic renal patients on hemodialysis. Method: Methodological, cross-sectional study with patients undergoing renal treatment. The data were collected through interviews and physical evaluation, using an instrument with socio-demographic variables, related factors, associated conditions and defining characteristics of the studied diagnosis. The classification trees were generated by the Chi-Square Automation Interaction Detection method, which was based on the Chi-square test. Results: A total of 127 patients participated, of which 79.5% (101) presented the diagnosis studied. The trees included the elements "Excessive sodium intake" and "Input exceeds output", which were significant for the occurrence of the event, as the probability of occurrence of the diagnosis in the presence of these was 0.87 and 0.94, respectively. The prediction accuracy of the trees was 63% and 74%, respectively. Conclusion: The construction of the trees allowed to quantify the probability of the occurrence of Fluid Volume Excess (00026) in the studied population and the elements "Excessive sodium intake" and "Input exceeds output" were considered predictors of this diagnosis in the sample.

RESUMEN Objetivo: Generar un Árbol de Clasificación para la inferencia correcta del Diagnóstico de Enfermería Volumen de Líquido Excesivo (00026) en pacientes renales crónicos que hacen hemodiálisis. Método: Se trata de un estudio metodológico transversal con pacientes en tratamiento renal. Los datos se recogieron mediante entrevistas y evaluación física, utilizando un instrumento con variables sociodemográficas, factores relacionados, condición asociada y características definidoras del diagnóstico estudiado. Los árboles de clasificación se generaron por el método Detección de Interacción Automática del Chi-cuadrado, basado en la prueba del Chi-cuadrado. Resultados: Participaron 127 pacientes, de los cuales el 79,5% (101) presentaba el diagnóstico mencionado; los árboles incluían los elementos "Ingestión excesiva de sodio" e "Ingestión superior a la eliminación", ambos significativos para el acaecimiento del evento. Los pacientes con estos indicadores tenían probabilidades de presentar el diagnóstico de 0,87 y 0,94, y la capacidad de predicción de los árboles era del 63% y 74%, respectivamente. Conclusión: La construcción de los árboles ha permitido cuantificar la probabilidad del acaecimiento del Volumen de Líquido Excesivo (00026) en la población estudiada. Los elementos "Ingestión excesiva de sodio" e "Ingestión superior a la eliminación" están considerados como premonitores del referido diagnóstico en la muestra.

RESUMO Objetivo: Gerar Árvore de Classificação para correta inferência do Diagnóstico de Enfermagem Volume de Líquido Excessivo (00026) em pacientes renais crônicos hemodialíticos. Método: Estudo metodológico, transversal, com pacientes em tratamento renal. Os dados foram coletados por meio de entrevista e avaliação física, utilizando instrumento com variáveis sociodemográficas, fatores relacionados, condição associada e características definidoras do Diagnóstico estudado. As árvores de classificação foram geradas pelo método Chi-Square Automation Interaction Detection, que se baseou no teste do Qui-quadrado. Resultados: Participaram 127 pacientes. Apresentaram o referido diagnóstico 79,5% (101), e as árvores incluíram os elementos "Ingesta excessiva de sódio" e "Ingestão maior que a eliminação" significativos para ocorrência do evento. Os pacientes com esses indicadores tiveram probabilidade de apresentar o diagnóstico de 0.87 e 0.94, e a capacidade de predição das árvores foi de 63% e 74%, respectivamente. Conclusão: A construção das árvores permitiu quantificar a probabilidade de ocorrência de Volume de Líquido Excessivo (00026) na população estudada. Os elementos "Ingesta excessiva de sódio" e "Ingestão maior que a eliminação" foram considerados preditores do referido diagnóstico na amostra.

Nursing Diagnosis , Decision Making , Renal Insufficiency, Chronic , Decision Trees , Classification , Validation Study
Psicol. ciênc. prof ; 41: e225481, 2021. tab, graf
Article in Portuguese | LILACS, INDEXPSI | ID: biblio-1346795


O desenvolvimento das atividades do psicólogo no contexto hospitalar é marcado predominantemente pela atuação subjetiva a partir de um embasamento teórico-científico, visto que, por vezes, os profissionais são carentes de conhecimentos e práticas sistemáticas de gestão exigidos pelas instituições hospitalares. A aplicabilidade de protocolos operacionais pode ser um efetivo instrumento para sistematização da rotina hospitalar, rastreamento fidedigno e embasamento de indicadores consistentes das demandas atendidas. Nesse sentido, o presente estudo teve como objetivo realizar a validação de conteúdo e avaliação de usabilidade dos protocolos "Avaliação Psicológica" e "Indicadores de Atendimentos da Psicologia" para serem implantados no serviço de psico-oncologia de um hospital oncológico. Para tanto, foram selecionados juízes especialistas para proceder com a validação dos instrumentos. Os dados foram avaliados com base no Índice de Validação de Conteúdo (IVC) e System Usability Scale (SUS). Percebeu-se maior validação dos aspectos Avaliação do Estado Geral, Histórico Psiquiátrico e Atitudes Frente à Doença (100%) no protocolo "Avaliação Psicológica", em contrapartida, os itens referentes aos Aspectos Cognitivos (97,7%) e ao Estado Emocional (91,7%), se apresentaram em menores percentuais, porém ainda assim, estatisticamente significativos. Os índices do protocolo "Indicadores de Atendimentos da Psicologia" atingiram 100% de validação. As avaliações de usabilidade dos protocolos indicam maior adesão ao "Indicadores de Atendimentos da Psicologia", entretanto, ambos os protocolos atingiram alto grau de efetividade, eficiência e satisfação. A implantação dos protocolos permitirá a avaliação psicológica e o registro logístico do atendimento, auxiliando o psicólogo no acompanhamento do paciente e na construção de indicadores do serviço de psicologia hospitalar.(AU)

The practice of the psychologist within the hospital context is predominantly marked by the subjective action based on a theoretical-scientific foundation, often lacking the systematic knowledge and management practices required by these institutions. In this context, operational protocols may be an effective tool to systematize hospital routine, provide reliable tracking, and support consistent indicators of the demands met. This study sought to validate the content and usability of the protocols "Psychological Assessment" and "Care Indicators in Psychology," to be implemented in the Psycho-Oncology Service of a cancer hospital. Instrument validation was performed by specialized judges, based on the Content Validation Index (CVI) and System Usability Scale (SUS). Regarding the "Psychological Assessment" protocol, the validation of the General Assessment, Psychiatric History, and Attitudes towards Disease aspects reached 100%, whereas items referring to the Cognitive Aspects (97.7%) and the Emotional State (91.7%) reached lower percentages - although still statistically significant. The "Care Indicators in Psychology" indexes reached 100% validation, besides indicating greater usability. Both protocols reached a high degree of effectiveness, efficiency, and satisfaction. Implementing these protocols will enable psychological evaluation and logistic registration of the service, helping psychologists in patient follow-up and in the construction of indicators of the Hospital Psychology service.(AU)

El desarrollo de la actuación del psicólogo en el contexto hospitalario tiene predominio de la práctica subjetiva con base en el marco teórico-científico, y en muchas ocasiones los profesionales carecen de conocimientos y prácticas sistemáticas de gestión requeridas por las instituciones hospitalarias. La aplicación de protocolos operativos puede ser una herramienta eficaz en la sistematización de la rutina hospitalaria, el seguimiento fiable y los indicadores consistentes con las demandas procuradas. En este sentido, este estudio tuvo como objetivo realizar una validez de contenido y evaluación de la utilidad de los protocolos "Evaluación Psicológica" e "Indicadores de Atención en Psicología" para que sean aplicados en el servicio de psicooncología de un hospital oncológico. Para ello, se seleccionaron expertos para que validen los instrumentos. Para el análisis de datos se utilizaron el Índice de Validez de Contenido (IVC) y el System Usability Scale (SUS). Se observó una mayor validez en los ítems Evaluación del Estado General, Historia Psiquiátrica y Actitudes Ante la Enfermedad (100%) del protocolo "Evaluación Psicológica", mientras que Aspectos cognitivos (97,7%), Estado Emocional (91,7%) tuvieron los menores porcentuales aunque fueron estadísticamente significativos. Las tasas del protocolo "Indicadores de Atención en Psicología" alcanzaron el 100% de validez. Las evaluaciones de utilidad de los protocolos apuntaron a una alta adherencia en los "Indicadores de Atención en Psicología". Sin embargo, ambos protocolos tuvieron un alto grado de efectividad, eficacia y satisfacción. Estos protocolos pueden ayudar al psicólogo en el seguimiento del paciente y en la construcción de indicadores de servicio de Psicología Hospitalaria.(AU)

Humans , Male , Female , Behavioral Medicine , Decision Trees , Indicators of Health Services , Hospital Care , Psycho-Oncology , Patients , Psychology , Unified Health System , Cancer Care Facilities , Family , Disease , Health Management , Diagnosis , Hospitals
Rev. enferm. UERJ ; 28: e42285, jan.-dez. 2020.
Article in English, Portuguese | BDENF, LILACS | ID: biblio-1120154


Objetivo: comparar o custo entre coberturas com filme transparente versus gaze estéril e fita adesiva microporosa em curativos de acesso venoso central. Método: estudo estatístico, prospectivo, observacional, com abordagem quantitativa à luz da avaliação econômica de saúde. Foram avaliadas 109 coberturas com filme e 168 com gaze, durante 27 dias. Na análise utilizouse o Software Tree Age para se calcular a probabilidade de cada decisão. Resultado: a média de uso das coberturas por dia foi de 2,22 inserções cobertas com filme e 3,43 com gaze. Houve necessidade de troca extra em 38 (23%) das coberturas com gaze e em 16 (15%) das coberturas com filme transparente. Observou-se custo final médio para gaze (R$389,44) 3,7 vezes maior que o filme transparente (R$104,95) durante o período estudado. Conclusão: cobertura com filme transparente tem menor custo quando comparado com cobertura com gaze estéril.

Objective: to compare the cost of transparent film and sterile gauze fixed by microporous adhesive tape in central venous access dressings. Method: quantitative, prospective, observational, statistical study in the light of health economics. A total of 109 film and 168 gauze covers were evaluated for 27 days. Tree Age software was used to calculate the probability of each decision. Results: coverings used per day averaged 2.22 with transparent film-covered inserts and 3.43 with gauze. Additional changes were necessary in 38 (23%) coverings with gauze and 16 (15%) with transparent film. During the study period, the average final cost of gauze (R$ 389.44) was 3.7 times higher than transparent film (R$104.95). Conclusion: transparent film dressing is less expensive than sterile gauze covering.

Objetivo: comparar el costo de la película transparente y la gasa estéril fijada con cinta adhesiva microporosa en apósitos de acceso venoso central. Método: estudio cuantitativo, prospectivo, observacional, estadístico a la luz de la economía de la salud. Se evaluaron un total de 109 películas y 168 cubiertas de gasa durante 27 días. Se utilizó el software Tree Age para calcular la probabilidad de cada decisión. Resultados: los recubrimientos utilizados por día promediaron 2,22 con inserciones transparentes recubiertas con película y 3,43 con gasas. Fueron necesarios cambios adicionales en 38 (23%) revestimientos con gasa y 16 (15%) con película transparente. Durante el período de estudio, el costo final promedio de la gasa (R $ 389,44) fue 3,7 veces superior al de la película transparente (R $ 104,95). Conclusión: el apósito de película transparente es menos costoso que el recubrimiento de gasa estéril.

Humans , Health Evaluation/economics , Central Venous Catheters , Occlusive Dressings/economics , Brazil , Decision Trees , Prospective Studies , Costs and Cost Analysis , Observational Study , Occlusive Dressings/statistics & numerical data
Colomb. med ; 51(4): e4134365, Oct.-Dec. 2020. tab, graf
Article in English | LILACS | ID: biblio-1154009


Abstract The liver is the most commonly affected solid organ in cases of abdominal trauma. Management of penetrating liver trauma is a challenge for surgeons but with the introduction of the concept of damage control surgery accompanied by significant technological advancements in radiologic imaging and endovascular techniques, the focus on treatment has changed significantly. The use of immediately accessible computed tomography as an integral tool for trauma evaluations for the precise staging of liver trauma has significantly increased the incidence of conservative non-operative management in hemodynamically stable trauma victims with liver injuries. However, complex liver injuries accompanied by hemodynamic instability are still associated with high mortality rates due to ongoing hemorrhage. The aim of this article is to perform an extensive review of the literature and to propose a management algorithm for hemodynamically unstable patients with penetrating liver injury, via an expert consensus. It is important to establish a multidisciplinary approach towards the management of patients with penetrating liver trauma and hemodynamic instability. The appropriate triage of these patients, the early activation of an institutional massive transfusion protocol, and the early control of hemorrhage are essential landmarks in lowering the overall mortality of these severely injured patients. To fear is to fear the unknown, and with the management algorithm proposed in this manuscript, we aim to shed light on the unknown regarding the management of the patient with a severely injured liver.

Resumen El hígado es el órgano solido más comúnmente lesionado en casos de trauma abdominal. El manejo del trauma penetrante hepático es un dilema para los cirujanos. Sin embargo, con la introducción del concepto de la cirugía de control de daños y los avances tecnológicos en imagenología y técnicas endovasculares han permitido que el enfoque del tratamiento cambie. La disponibilidad inmediata de la tomografía computarizada permite estadificar el grado de la lesión e incrementar la posibilidad de un manejo conservador en pacientes hemodinámicamente estables con trauma hepático. El trauma hepático severo que se asocia con inestabilidad hemodinámica tiene una alta mortalidad debido a la hemorragia activa. El objetivo de este artículo es proponer un algoritmo de manejo producto de un consenso de expertos acerca del abordaje de los pacientes hemodinámicamente inestables con trauma hepático penetrante. El manejo debe ser por parte de un equipo multidisciplinario que comienza desde la evaluación inicial de los pacientes, la activación temprana de protocolo de transfusión masiva y el control temprano de la hemorragia, siendo estos aspectos esenciales para disminuir la mortalidad. El miedo a lo desconocido es el dilema quirúrgico donde existen pocas opciones y es imperante decisiones rápidas y oportunas; por esta razón, se propone dar una luz de guía sobre lo desconocido respecto al manejo del paciente con trauma hepático severo.

Humans , Wounds, Penetrating/surgery , Liver/surgery , Liver/injuries , Decision Trees
Aval. psicol ; 19(1): 87-96, jan.-abr. 2020. tab, il
Article in English | LILACS, INDEXPSI | ID: biblio-1089026


The CART algorithm has been extensively applied in predictive studies, however, researchers argue that CART produces variable selection bias. This bias is reflected in the preference of CART in selecting predictors with large numbers of cutpoints. Considering this problem, this article compares the CART algorithm to an unbiased algorithm (CTREE), in relation to their predictive power. Both algorithms were applied to the 2011 National Exam of High School Education, which includes many categorical predictors with a large number of categories, which could produce a variable selection bias. A CTREE tree and a CART tree were generated, both with 16 leaves, from a predictive model with 53 predictors and the students' writing essay achievement as the outcome. The CART algorithm yielded a tree with a better outcome prediction. This result suggests that for large data sets, called big data, the CART algorithm might give better results than the CTREE algorithm.(AU)

O algoritmo CART tem sido aplicado de forma extensiva em estudos preditivos. Porém, pesquisadores argumentam que o CART apresenta sério viés seletivo. Esse viés aparece na preferência do CART pelos preditores com grande número de categorias. Este artigo considera esse problema e compara os algoritmos CART e CTREE, este considerado não enviesado, tomando como resultado seu poder preditivo. Os algoritmos foram aplicados no Exame Nacional do Ensino Médio de 2011, no qual estão incluídos vários preditores nominais e ordinais com muitas categorias, o que pode produzir um viés seletivo. Foram geradas uma árvore do CTREE e outra do CART, ambas com 16 folhas, provenientes de um modelo com 53 variáveis preditoras e a nota da redação, como desfecho. A árvore do algoritmo CART apresentou uma melhor predição. Para grandes bancos de dados, possivelmente o algoritmo CART é mais indicado do que o algoritmo CTREE.(AU)

El algoritmo CART es ampliamente utilizado en análisis predictivos. Sin embargo, los investigadores argumentan que el CART presenta un fuerte sesgo de selección. Este sesgo se refleja en el CART en la preferencia de seleccionar predictores con elevado número de categorías. Teniendo en cuenta este problema, el presente artículo compara el algoritmo CART y un algoritmo imparcial (CTREE) con relación a su poder predictivo. Ambos algoritmos se aplicaron en el Examen Nacional de la Enseñanza Secundaria de 2011, incluyendo predictores nominales y ordinales con diversas categorías, un escenario susceptible de producir el sesgo de selección de variables mencionado. Fueron generados un árbol CTREE y un árbol CART, ambos con 16 hojas, provenientes de un modelo predictivo con 53 variables y la nota del comentario de texto. El árbol del algoritmo CART presentó mejor predicción. Para grandes bases de datos el algoritmo CART puede proporcionar mejores resultados que el CTREE.(AU)

Algorithms , Decision Trees , Education, Primary and Secondary , Educational Measurement , Selection Bias , Predictive Value of Tests
Geriatr., Gerontol. Aging (Online) ; 14(1): 52-60, 31-03-2020. tab, graf
Article in English, Portuguese | LILACS | ID: biblio-1097168


INTRODUÇÃO: Idosos com 80 anos ou mais, ou longevos, são o subgrupo etário que mais cresce no mundo. Nesse segmento, a incapacidade funcional (IF) é mais prevalente que em outras faixas etárias. OBJETIVO: Caracterizar a capacidade funcional e analisar potenciais associações em idosos longevos de uma capital brasileira, com base em um modelo de decisão. MÉTODO: Estudo transversal com 100 idosos longevos, não institucionalizados, assistidos pela Estratégia Saúde da Família do Recife (PE), selecionados por amostra probabilística. Foram avaliados dados sociodemográficos, econômicos e clínicos coletados por meio de entrevistas domiciliares, aferição de medidas antropométricas e buscas nos prontuários. Para análise bivariada, foi empregado o teste χ2 de Pearson, considerando o nível de significância p < 0,05, e para a multivariada foi construída uma árvore de decisão com base em um algoritmo Exhaustive CHAID. RESULTADOS: A prevalência de IF na amostra correspondeu a 67,0%. Na análise bivariada, contribuíram para esse desfecho: renda (p = 0,032), situação previdenciária (p < 0,01), situação nutricional (p = 0,010), doenças neurológicas (p < 0,01), neoplasias (p < 0,01), saúde autopercebida (p = 0,025) e rede de apoio social (p = 0,032), permanecendo na análise multivariada: renda (p = 0,003), rede de apoio social (p = 0,032) e situação nutricional (p = 0,040). A árvore de decisão possibilitou a identificação das variáveis mais associadas ao desfecho, sendo capaz de prever adequadamente a dependência moderada, com assertividade de 72,1%. CONCLUSÃO: O modelo de decisão mostrou-se uma ferramenta oportuna na dedução dos determinantes mais relevantes da IF. Seu uso potencialmente contribui para ampliar a precisão diagnóstica e identificação de populações de risco.

INTRODUCTION: The oldest old adults, aged 80 years and above, is the fastest growing age group in the world. In this section of the population, functional disability (FD) is more prevalent compared to other age groups. OBJECTIVE: To characterize functional capacity and analyze potential associations in the oldest old from a Brazilian capital city, based on a decision model. METHODS: Cross-sectional study of 100 non-institutionalized oldest old participants assisted at the Family Health Strategy of Recife, in the Brazilian northeastern state of Pernambuco, selected by probabilistic sample. Sociodemographic, economic, and clinical data were collected by means of home interviews, anthropometric measurements, and medical records. For bivariate analysis, Pearson's chi-square test was used, establishing significance at p < 0.05. For the multivariate analysis, a decision tree was built from the Exhaustive CHAID algorithm. RESULTS: The prevalence of FD in the sample corresponded to 67.0%. In the bivariate analysis, the following data contributed to this outcome: income (p = 0.032), social security status (p < 0.01), nutritional status (p = 0.010), neurological diseases (p < 0.01), neoplasms (p < 0.01), self-perceived health (p = 0.025) and social support network (p = 0.032), remaining in the multivariate analysis: income (p = 0.003), social support network (p = 0.032), and nutritional status (p = 0.040). The decision tree allowed the identification of the variables most strongly associated with the outcome, being able to adequately predict moderate dependence, with 72.1% assertiveness. CONCLUSION: The decision model proved to be a timely tool in deducing the most relevant determinants of FD. Its use potentially contributes to increase the accuracy of the diagnosis and to identify populations at risk.

Humans , Male , Female , Aged, 80 and over , Primary Health Care , Activities of Daily Living , Decision Trees , Geriatric Assessment/statistics & numerical data , Longevity/physiology , Social Support , Socioeconomic Factors , Health of the Elderly , Cross-Sectional Studies , Age Factors
Einstein (Säo Paulo) ; 18: eAO4745, 2020. tab, graf
Article in English | LILACS | ID: biblio-1039746


ABSTRACT Objective To estimate the prevalence of and factors associated with the use of methylphenidate for cognitive enhancement among undergraduate students. Methods Simple random sample of students of the Universidade Federal de Minas Gerais (n=438), invited to answer an online questionnaire about the use of methylphenidate. Data collection occurred from September 2014 to January 2015. The sample was described by means of proportions, means and standard deviations. A multivariate analysis was performed using the Classification and Regression Tree algorithm to classify the cases of use of methylphenidate for cognitive enhancement in groups, based on the exposure variables. Results Out of 378 students included, 5.8% (n=22) reported using methylphenidate for cognitive enhancement; in that, 41% (9/22) in the 4 weeks prior to the survey. The housing situation was the variable most often associated with the use of methylphenidate for cognitive enhancement. Eleven students reported using methylphenidate for cognitive enhancement and other purposes 4 weeks prior to the survey, 27% of whom had no medical prescription to purchase it. Conclusion The use of methylphenidate for cognitive enhancement is frequent among Brazilian undergraduate students and should be considered a serious public health problem, especially due to risks of harm and adverse effects associated with its use.

RESUMO Objetivo Estimar a prevalência e os fatores associados ao uso de metilfenidato para neuroaprimoramento entre estudantes universitários. Métodos Amostra aleatória simples de discentes da Universidade Federal de Minas Gerais (n=438), convidados a responder um questionário online sobre o consumo de metilfenidato. A coleta ocorreu de setembro de 2014 a janeiro de 2015. A amostra foi descrita em termos de proporções, médias e desvio padrão. A análise multivariada foi realizada utilizando o algoritmo Classification and Regression Tree para classificação dos casos de uso do metilfenidato para neuroaprimoramento em grupos, com base nas variáveis de exposição. Resultados Dos 378 alunos incluídos, 5,8% (n=22) declararam ter feito uso de metilfenidato para neuroaprimoramento, sendo 41% (9/22) nas 4 semanas anteriores à pesquisa. A situação da moradia foi a variável mais associada ao uso de metilfenidato para neuroaprimoramento. Relataram o uso do metilfenidato para neuroaprimoramento e outros fins nas 4 semanas anteriores à pesquisa 11 estudantes, sendo que 27% não apresentaram prescrição médica para adquiri-lo. Conclusão O uso de metilfenidato para neuroaprimoramento ocorre no meio acadêmico brasileiro e deve ser considerado sério problema de saúde pública, principalmente diante dos riscos de danos e efeitos adversos associados ao seu uso.

Humans , Male , Female , Adult , Young Adult , Students/statistics & numerical data , Universities/statistics & numerical data , Nootropic Agents/administration & dosage , Nootropic Agents/therapeutic use , Central Nervous System Stimulants/administration & dosage , Socioeconomic Factors , Students/psychology , Brazil/epidemiology , Decision Trees , Exercise/psychology , Residence Characteristics/statistics & numerical data , Prevalence , Cross-Sectional Studies , Surveys and Questionnaires , Risk Factors , Off-Label Use/statistics & numerical data , Methylphenidate/administration & dosage
Journal of Korean Academy of Oral Health ; : 55-63, 2020.
Article in Korean | WPRIM | ID: wpr-820816


OBJECTIVES: The decayed-missing-filled (DMFT) index is a representative oral health indicator. Prediction of DMFT index is an important basis for the development of public oral health care projects and strategies for caries prevention. In this study, we used data from the 2015 Korean children's oral health survey to predict DMFT index and caries risk groups using statistical techniques and four different machine-learning algorithms.METHODS: DMFT prediction models were constructed using multiple linear regression and four different machine-learning algorithms: decision tree regressor, decision tree classifier (DTC), random forest regressor, and random forest classifier (RFC). Thereafter, their accuracies were compared.RESULTS: For the DMFT predictive model, the prediction accuracy of multiple linear regression and RFC were 15.24% and 43.27%, respectively. The accuracy of DTC prediction was 2.84 times that of multiple linear regression. The important feature of the machine-learning model, which predicts DMFT index and the caries risk group, was the number of teeth with sealants.CONCLUSIONS: Using data from the 2015 Korean children's oral health survey, which is considered big data in the field of oral health survey in Korea, this study confirmed that machine-learning models are more useful than statistical models for predicting DMFT index and caries risk in 12-year-old children. Therefore, it is expected that the machine-learning model can be used to predict the DMFT score.

Child , Humans , Decision Trees , Dental Caries , Forests , Korea , Linear Models , Machine Learning , Models, Statistical , Oral Health , Tooth
Biomédica (Bogotá) ; 39(3): 502-512, jul.-set. 2019. tab, graf
Article in English | LILACS | ID: biblio-1038810


Abstract Introduction: The use of an implantable cardioverter-defibrillator reduces the probability of sudden cardiac death in patients with heart failure. Objective: To determine the cost-utility relationship of an implantable cardioverterdefibrillator compared to optimal pharmacological therapy for patients with ischemic or nonischemic New York Heart Association class II or III (NYHA II-III) heart failure in Colombia. Materials and methods: We developed a Markov model including costs, effectiveness, and quality of life from the perspective of the Colombian health system. For the baseline case, we adopted a time horizon of 10 years and discount rates of 3% for costs and 3.5% for benefits. The transition probabilities were obtained from a systematic review of the literature. The outcome used was the quality-adjusted life years. We calculated the costs by consulting with the manufacturers of the device offered in the Colombian market and using national-level pricing manuals. We conducted probabilistic and deterministic sensitivity analyses. Results: In the base case, the incremental cost-effectiveness ratio for the implantable cardioverter-defibrillator was USD$ 13,187 per quality-adjusted life year gained. For a willingness-to-pay equivalent to three times the gross domestic product per capita as a reference (USD$ 19,139 in 2017), the device would be a cost-effective strategy for the Colombian health system. However, the result may change according to the time horizon, the probability of death, and the price of the device. Conclusions: The use of an implantable cardioverter-defibrillator for preventing sudden cardiac death in patients with heart failure would be a cost-effective strategy for Colombia. The results should be examined considering the uncertainty

Resumen Introducción. El uso del desfibrilador cardioversor implantable reduce la probabilidad de muerte súbita en pacientes con insuficiencia cardíaca. Objetivo. Determinar la relación de costo-utilidad de un desfibrilador cardioversor implantable comparado con la terapia farmacológica óptima para pacientes con insuficiencia cardíaca isquémica o no isquémica de clase II o III según la New York Heart Association (NYHA II-III) en Colombia. Materiales y métodos. Se desarrolló un modelo de Markov que incluyó los costos, la efectividad y la calidad de vida desde la perspectiva del sistema de salud colombiano. Para el caso de base, se adoptó un horizonte temporal de 10 años y una tasa de descuento de 3 % para los costos y de una 3,5 % para los beneficios. Las probabilidades de transición se obtuvieron de una revisión sistemática de la literatura. Los años de vida ajustados por calidad se usaron como resultado de salud. Para estimar los costos unitarios se usaron manuales tarifarios nacionales y, para los costos del dispositivo, se consultó a los fabricantes que lo comercializan en el mercado colombiano. Se hicieron análisis de sensibilidad probabilísticos y determinísticos. Resultados. En el caso base el costo adicional por año de vida ajustado por calidad ganado con el desfibrilador cardioversor implantable fue de USD$ 13,187. Usando un umbral de tres veces el producto interno bruto per cápita como referencia (USD$ 19.139 en 2017), el dispositivo sería costo-efectivo para el sistema de salud colombiano. Sin embargo, este resultado depende del horizonte temporal, de la probabilidad de muerte y del precio del dispositivo. Conclusiones. El uso de un desfibrilador cardioversor implantable sería una estrategia costo-efectiva para Colombia, aunque los resultados deben examinarse teniendo en cuenta la incertidumbre.

Humans , Middle Aged , Death, Sudden, Cardiac/prevention & control , Defibrillators, Implantable/economics , Quality-Adjusted Life Years , Heart Failure/therapy , Quality of Life , Time Factors , Decision Trees , Meta-Analysis as Topic , Cost-Benefit Analysis , Colombia , Systematic Reviews as Topic , Heart Failure/classification , National Health Programs/economics
Salud pública Méx ; 61(4): 456-460, Jul.-Aug. 2019.
Article in English | LILACS | ID: biblio-1099321


Abstract: Cervical cancer has decreased significantly over the past 30 years in some countries. However, it remains among the leading causes of cancer deaths in low-income, and racial/ethnic minority women. Cervical cancer prevention technologies are not always available. Laboratories are often not well equipped to use them. HPV information has not been widely disseminated. WHO guidelines, and US and Latin American data provide context for strategies on effective interventions to reduce cervical cancer disparities. Systemic, personal and cultural barriers, combined with decision-making guidelines, and impactful messaging can accelerate reductions in cervical cancer health inequities in the Americas.

Resumen: El cáncer cervicouterino ha disminuido significativamente en los últimos 30 años, pero sigue siendo una de las principales causas de muerte entre mujeres de bajos recursos y minorías raciales/étnicas. Las tecnologías preventivas del cáncer cervicouterino no están siempre disponibles y los laboratorios no están siempre bien equipados para utilizarlas. La información sobre el VPH no ha sido difundida ampliamente. La OMS y datos de EEUU y Latinoamérica ofrecen estrategias para reducir el cáncer cervicouterino. El entendimiento de las barreras sistémicas, personales y culturales, dentro de un marco de toma de decisiones, y mensajes innovadores puede reducir las barreras asociadas con el cáncer cervicouterino en las Américas.

Humans , Female , Uterine Cervical Neoplasms/diagnosis , Health Knowledge, Attitudes, Practice , Early Detection of Cancer/methods , World Health Organization , Americas , Decision Trees , Uterine Cervical Neoplasms/ethnology , Uterine Cervical Neoplasms/prevention & control , Mass Screening/methods , Practice Guidelines as Topic , Cultural Characteristics , Decision Making , Educational Status , Health Status Disparities , Consumer Health Information/methods , Language , Minority Groups
Arch. cardiol. Méx ; 89(1): 58-73, Jan.-Mar. 2019. tab, graf
Article in Spanish | LILACS | ID: biblio-1038478


Resumen Introducción: El presente artículo resume la guía de práctica clínica (GPC) para la evaluación y el tratamiento de pacientes con estenosis aórtica severa en el Seguro Social del Perú (EsSalud). Objetivo: Proveer recomendaciones para la evaluación y el tratamiento de pacientes con estenosis aórtica severa en el EsSalud basadas en evidencia científica. Métodos: Se conformó un grupo elaborador local (GEG-Local) que incluyó médicos especialistas y metodólogos. El GEG-Local formuló siete preguntas clínicas que ser respondidas en la presente GPC. Se realizaron búsquedas sistemáticas de revisiones sistemáticas y, cuando fue considerado pertinente, estudios primarios en PubMed durante el 2018. Se seleccionó la evidencia para responder cada una de las preguntas clínicas planteadas. La calidad de la evidencia fue evaluada usando la metodología Grading of Recommendations Assessment, Development, and Evaluation (GRADE). En reuniones de trabajo periódicas, el GEG-Local usó la metodología GRADE para revisar la evidencia y formular las recomendaciones, los puntos de buenas prácticas clínicas y el flujograma de evaluación y tratamiento. Finalmente, la GPC fue aprobada con Resolución N.° 47 — IETSI — ESSALUD — 2018. Resultados: La presente GPC abordó siete preguntas clínicas, respecto a dos temas: la evaluación inicial y el tratamiento de la estenosis aórtica severa. Con base en dichas preguntas se formularon nueve recomendaciones (una recomendación fuerte y ocho recomendaciones débiles), 16 puntos de buena práctica clínica y un flujograma. Conclusión: El presente artículo resume la metodología y las conclusiones de la GPC para la evaluación y el tratamiento de pacientes con estenosis aórtica severa en el EsSalud.

Abstract Introduction: This article summarizes the clinical practice guide (CPG) for the evaluation and management of patients with severe aortic stenosis in the Social Security of Peru (EsSalud). Objective: To provide clinical evidence-based recommendations for the evaluation and management of patients with severe aortic stenosis in the EsSalud. Methods: A local guideline development group (local GDG) was established, including medical specialists and methodologists. The local GDG formulated 7 clinical questions to be answered by this CPG. Systematic searches of systematic reviews and, when it was considered pertinent, primary studies, were conducted in PubMed during 2018. The evidence to answer each of the posed clinical questions was selected. The quality of the evidence was evaluated using the Grading of Recommendations Assessment, Development, and Evaluation (GRADE) methodology. In periodic work meetings, the local GDG used the GRADE methodology to review the evidence and formulate the recommendations, points of good clinical practice, and the flowchart of evaluation and management. Finally, the CPG was approved with Resolution N.° 47 — IETSI — ESSALUD — 2018. Results: This CPG addressed 7 clinical questions regarding two issues: the initial evaluation and the management of severe aortic stenosis. Based on these questions, 9 recommendations (1 strong recommendation and 8 weak recommendations), 16 points of good clinical practice, and 1 flowchart were formulated. Conclusion: This article summarizes the methodology and evidence-based conclusions from the CPG for the evaluation and management of patients with severe aortic stenosis in the EsSalud.

Humans , Aortic Valve Stenosis/diagnosis , Aortic Valve Stenosis/therapy , Peru , Social Security , Severity of Illness Index , Decision Trees , Practice Guidelines as Topic , Clinical Decision-Making
Ciênc. cuid. saúde ; 18(3): e45041, 2019-03-23.
Article in Portuguese | LILACS, BDENF | ID: biblio-1120738


Objective:To identify the risk factors for plantar ulcers in patients with leprosy.Methods:This is an epidemiological, observational, cross-sectional and analytical study. The population was composed of leprosy cases reported from 2005 to 2016. Pearson's Chi-square test or Fisher's exact test andMann-Whitney test were used for the univariate analysis, with a statistical significance of 5% (p < 0.05). In the multivariate analysis, a decision tree was elaborated using the CHAID algorithm. Results:Clinical form, degree of physical incapacity at discharge, affected nerve and the lack of insoles or adapted footwear before appearing to ulcer are risk factors for plantar ulcer. Conclusion:the need for an early diagnosis of leprosy was highlighted, as well as the efficient association of non-drug interventions with disability prevention techniques and the use of accommodating insoles and/or special shoes.

Objetivo:Identificar os fatores de risco para a ocorrência das úlceras plantares em pacientes com hanseníase. Métodos:Trata-se de um estudo epidemiológico, do tipo observacional, transversal e analítico. A população foi composta pelos casos de hanseníase notificados no período de 2005 a 2016. Para a análise univariada foram utilizados os testes Qui-quadrado de Pearson ou teste exato de Fisher e teste de Mann-Whitney, com significância estatística de 5% (p < 0,05). Na análise multivariada, foi elaborada árvore de decisão utilizando o algoritmo CHAID. Resultados: A forma clínica, grau de incapacidade física na alta, nervo acometido e o não uso de palmilhas ou calçado adaptado antes de surgir a úlcera são fatores de risco para a ocorrência de úlcera plantar. Conclusão:evidenciou a necessidade do diagnóstico precoce da hanseníase, como também da eficiente associação das intervenções medicamentosas e não medicamentosas por meio das técnicas de prevenção de incapacidade e uso de palmilhas acomodativas e/ou calçados especiais

Humans , Male , Female , Decision Trees , Foot Ulcer , Leprosy , Patients , Population , Shoes , Signs and Symptoms , Skin/injuries , Therapeutics , Pharmaceutical Preparations , Risk Factors , Disabled Persons , Diagnosis , Empathy , Disease Prevention
Ciênc. Saúde Colet. (Impr.) ; 24(3): 1021-1032, mar. 2019. tab, graf
Article in Portuguese | LILACS | ID: biblio-989630


Resumo Objetivou-se identificar fatores associados à falta de acesso aos serviços odontológicos. Estudo transversal, amostra complexa probabilística por conglomerados em dois estágios de 857 participantes, com mais de 18 anos em um município de grande porte populacional. Foram feitas análises múltiplas através da regressão logística e multivariada em árvores de decisão. Considerou-se como variável dependente o acesso aos serviços odontológicos. Identificou-se que 10,3% não obtiveram acesso. Nas análises múltipla e multivariada constataram-se associação com a idade, na regressão logística constatou-se maior chance de falta de acesso a cada ano de idade incrementado, entre aqueles com menor renda per capita e entre os que classificaram a aparência dos dentes e gengivas como "regular/ruim/péssima". A falta de acesso aos serviços odontológicos é maior entre os mais vulneráveis socialmente. Há necessidade de incremento na alocação de recursos públicos que promovam educação em saúde e gere conhecimento sobre como acessar os serviços quando necessitar, tendo em foco os cuidados odontológicos como um direito humano e que possibilitem que não ocorra a falta de acesso à medida que os usuários envelhecem ou entre os com baixa renda e também os insatisfeitos com a aparência bucal.

Abstract The scope of this study was to identify factors associated with lack of access to dental services. It involved a cross-sectional study and a probabilistic complex sample by conglomerates in two stages with 857 participants over 18 years of age in a large city. Multiple analyses by means of logistic and multivariate regression in decision trees were made. The lack of access to dental services was considered a dependent variable. It was identified that 10.3% did not have access. In the multiple and multivariate analyses an association with age was verified and in the logistic regression a greater possibility of lack of access was found for each year of increased age, among those with the lowest per capita income and those who ranked appearance of teeth and gums as "fair/poor/very poor." The lack of access to dental services was greater among the most socially vulnerable. There is a pressing need to increase the allocation of public resources to promote health education and provide knowledge about how to access services when they are needed, focusing on dental care as a human right and ensuring that lack of access does not occur as users get older or among those with low income and also those dissatisfied with their oral appearance.

Humans , Male , Female , Adolescent , Adult , Aged , Aged, 80 and over , Young Adult , Oral Health , Dental Care/statistics & numerical data , Dental Health Services/statistics & numerical data , Health Services Accessibility , Poverty , Decision Trees , Logistic Models , Cross-Sectional Studies , Multivariate Analysis , Age Factors , Dental Care/economics , Dental Health Services/economics , Vulnerable Populations/statistics & numerical data , Income , Middle Aged
Journal of Korean Medical Science ; : e211-2019.
Article in English | WPRIM | ID: wpr-765047


BACKGROUND: As Koreans adopt more Westernized diets, consumer demands for processed food products are growing. The Korean government implemented a food labeling system to help people reasonably choose processed foods. This study investigated the utilization of these food labels among Koreans, as well as demographic differences between users and non-users of food labels, ultimately presenting foundational data for strategies to enhance dietary lifestyles by facilitating the use of food labeling. METHODS: Data from the 2014–2017 Community Health Survey were used. The Cochran-Armitage trend test was performed to investigate whether food labeling awareness and utilization increase over time; a data mining technique called decision tree analysis was then used to examine the effects of sociodemographic factors on the use of food labeling for each of the 4 years. RESULTS: Food labeling awareness increased by 4.5% over 4 years; the Cochran–Armitage trend test showed that this increase was statistically significant (χ2 = 1,068.21; P < 0.001). Food labeling utilization increased significantly but marginally, by 0.3%, over 4 years (χ2 = 20.154; P < 0.001). Decision tree analysis showed that food labeling users comprised mainly women in their 30s–50s currently in graduate school or with a graduate degree; the non-user group comprised mainly divorced/widowed/separated people in their 70s who were elementary school grads or below. CONCLUSION: Education level, which could be related to health literacy, substantially affected the use of food labeling. Education level is a typical socioeconomic index, and if people who are less educated tend not to use food labeling, it can lead to health inequity. Thus, food labeling should be reformed with consideration of health literacy among the less-educated social classes. From a health communication perspective, images and pictures can boost consumers' understanding, which should be considered to improve comprehensibility of food labeling.

Female , Humans , Data Mining , Decision Trees , Diet , Education , Food Labeling , Health Communication , Health Literacy , Health Surveys , Korea , Life Style , Social Class
Journal of Korean Academy of Nursing ; : 575-585, 2019.
Article in Korean | WPRIM | ID: wpr-764697


PURPOSE: The purpose of this study was to develop predictive models for pressure ulcer incidence using electronic health record (EHR) data and to compare their predictive validity performance indicators with that of the Braden Scale used in the study hospital. METHODS: A retrospective case-control study was conducted in a tertiary teaching hospital in Korea. Data of 202 pressure ulcer patients and 14,705 non-pressure ulcer patients admitted between January 2015 and May 2016 were extracted from the EHRs. Three predictive models for pressure ulcer incidence were developed using logistic regression, Cox proportional hazards regression, and decision tree modeling. The predictive validity performance indicators of the three models were compared with those of the Braden Scale. RESULTS: The logistic regression model was most efficient with a high area under the receiver operating characteristics curve (AUC) estimate of 0.97, followed by the decision tree model (AUC 0.95), Cox proportional hazards regression model (AUC 0.95), and the Braden Scale (AUC 0.82). Decreased mobility was the most significant factor in the logistic regression and Cox proportional hazards models, and the endotracheal tube was the most important factor in the decision tree model. CONCLUSION: Predictive validity performance indicators of the Braden Scale were lower than those of the logistic regression, Cox proportional hazards regression, and decision tree models. The models developed in this study can be used to develop a clinical decision support system that automatically assesses risk for pressure ulcers to aid nurses.

Humans , Case-Control Studies , Data Mining , Decision Support Systems, Clinical , Decision Trees , Electronic Health Records , Hospitals, Teaching , Incidence , Korea , Logistic Models , Patient Safety , Pressure Ulcer , Proportional Hazards Models , Retrospective Studies , ROC Curve , Ulcer