RESUMEN

Abstract Introduction Cardiovascular disease (CVD) is the lead-ing cause of death globally, with a high proportion of hospitalizations and costs. In view of this, it is essential to understand the main CVDs in patients admitted to hospital emergency services and the role of physiotherapists, in order to plan and direct health services, and to denote participation and encourage specific physiotherapy training in the context of tertiary care. Objective To outline the profile of cardiovascular emergencies and to evaluate physiotherapy in adult patients in the emergency department of a hospital in the interior of the state of São Paulo. Methods This was an observational study which analyzed 1,256 on-call records over a period of eight months. The data collected included age, gender, cardiovascular diagnostic hypothesis and physiotherapy treatment carried out. Results A total of 75 patients with cardiovascular emergencies were included, the most prevalent of which were: heart failure (n = 21), acute coronary syndrome (n = 14), acute myocardial infarction (n = 13), bradyarrhythmia (n = 6) and hypertensive crisis (n = 5). Regarding physiotherapeutic actions and their applications, the most frequent were invasive mechanical ventilation management (n = 34), lung re-expansion maneuvers (n = 17), orotracheal intubation assistance (n = 17), non-invasive mechanical ventilation (n = 14), bronchial hygiene maneuvers (n = 12), kinesiotherapy (n = 10) and sedation (n = 10). Conclusion Heart failure and acute coronary syndrome were the cardiovascular diseases that caused the most admissions to the hospital emergency department and that the procedures with an emphasis on the respiratory system were the most applied.

Resumo Introdução As doenças cardiovasculares (DCV) repre-sentam a principal causa de morte global, destacando-se em internações e gastos. Diante disso, é essencial compreender as principais DCV em pacientes admitidos em serviços de emergência hospitalar e a atuação do fisioterapeuta para planejamento e direcionamento dos serviços de saúde e para denotar a participação e incentivar formações fisioterapêuticas específicas no contexto da atenção terciária. Objetivo Traçar o perfil de emergências cardiovasculares e avaliar a atuação fisioterapêutica em pacientes adultos de serviço de emergência de um hospital no interior do estado de São Paulo. Métodos Trata-se de um estudo observacional, em que foram analisadas 1.256 fichas de passagem de plantão, no período de oito meses. Os dados coletados foram idade, sexo, hipótese diagnóstica cardiovascular e tratamento fisioterapêutico realizado. Resultados Foram incluídos 75 pacientes que apresentavam o perfil de emergências cardiovasculares, sendo as mais prevalentes: insuficiência cardíaca (n = 21), síndrome corona-riana aguda (n = 14), infarto agudo do miocárdio (n = 13), bradarritmia (n = 6) e crise hipertensiva (n = 5). Em relação à atuação fisioterapêutica e suas aplicações, as mais frequentes foram manejo da ventilação mecânica invasiva (n = 34), manobras de reexpansão pulmonar (n = 17), auxílio a intubação orotraqueal (n = 17), ventila-ção mecânica não invasiva (n = 14), manobras de higiene brônquica (n = 12), cinesioterapia (n = 10) e sedestação (n = 10). Conclusão A insuficiência cardíaca e a síndrome coronária aguda foram as doenças cardiovasculares que mais ocasionaram internação no serviço de emergência hospitalar e as condutas com ênfase no aparelho respiratório foram as mais aplicadas.

RESUMEN

BACKGROUND: Temporomandibular disorders (TMD) do not only occur in adults but also in adolescents, with negative impacts on their development. AIM: To propose a predictive model for TMD in adolescents using a decision tree (DT) analysis and to identify groups at high and low risk of developing TMD in the city of Recife, PE, Brazil. DESIGN: This cross-sectional study was conducted in Recife on 1342 schoolchildren of both sexes aged 10-17 years. The analyses were performed using Pearson's chi-squared test and Fisher's exact test, as well as the CHAID algorithm for the construction of the DT. The SPSS statistical program was used. RESULTS: The prevalence of TMD was 33.2%. Statistically significant associations were observed between TMD and sex, depression, self-reported orofacial pain, and orofacial pain on clinical examination. The DT consisted of self-reported orofacial pain, orofacial pain on physical examination, and depression, with an overall predictive power of 73.0%. CONCLUSION: The proposed tree has a good predictive capacity and permits to identify groups at high risk of developing TMD among adolescents, such as those with self-reported orofacial pain or orofacial pain on examination associated with depression.

RESUMEN

INTRODUCTION: Gastric cancer (GC) is the fifth most diagnosed neoplasia and the third leading cause of cancer-related deaths. A substantial number of patients exhibit an advanced GC stage once diagnosed. Therefore, the search for biomarkers contributes to the improvement and development of therapies. OBJECTIVE: This study aimed to identify potential GC biomarkers making use of in silico tools. METHODS: Gastric tissue microarray data available in Gene Expression Omnibus and The Cancer Genome Atlas Program was extracted. We applied statistical tests in the search for differentially expressed genes between tumoral and non-tumoral adjacent tissue samples. The selected genes were submitted to an in-house tool for analyses of functional enrichment, survival rate, histological and molecular classifications, and clinical follow-up data. A decision tree analysis was performed to evaluate the predictive power of the potential biomarkers. RESULTS: In total, 39 differentially expressed genes were found, mostly involved in extracellular structure organization, extracellular matrix organization, and angiogenesis. The genes SLC7A8, LY6E, and SIDT2 showed potential as diagnostic biomarkers considering the differential expression results coupled with the high predictive power of the decision tree models. Moreover, GC samples showed lower SLC7A8 and SIDT2 expression, whereas LY6E was higher. SIDT2 demonstrated a potential prognostic role for the diffuse type of GC, given the higher patient survival rate for lower gene expression. CONCLUSION: Our study outlines novel biomarkers for GC that may have a key role in tumor progression. Nevertheless, complementary in vitro analyses are still needed to further support their potential.

Asunto(s)

RESUMEN

Fake news detection continues to be a major problem that affects our society today. Fake news can be classified using a variety of methods. Predicting and detecting fake news has proven to be challenging even for machine learning algorithms. This research employs Legitimacy, a unique ensemble machine learning model to accomplish the task of Credibility-Based Fake News Detection. The Legitimacy ensemble combines the learning potential of a Two-Class Boosted Decision Tree and a Two-Class Neural Network. The ensemble technique follows a pseudo-mixture-of-experts methodology. For the gating model, an instance of Two-Class Logistic Regression is implemented. This study validates Legitimacy using a standard dataset with features relating to the credibility of news publishers to predict fake news. These features are analysed using the ensemble algorithm. The results of these experiments are examined using four evaluation methodologies. The analysis of the results reveals positive performance with the use of the ensemble ML method with an accuracy of 96.9%. This ensemble's performance is compared with the performance of the two base machine learning models of the ensemble. The performance of the ensemble surpasses that of the two base models. The performance of Legitimacy is also analysed as the size of the dataset increases to demonstrate its scalability. Hence, based on our selected dataset, the Legitimacy ensemble model has proven to be most appropriate for Credibility-Based Fake News Detection.

RESUMEN

Decision trees are decision support data mining tools that create, as the name suggests, a tree-like model. The classical C4.5 decision tree, based on the Shannon entropy, is a simple algorithm to calculate the gain ratio and then split the attributes based on this entropy measure. Tsallis and Renyi entropies (instead of Shannon) can be employed to generate a decision tree with better results. In practice, the entropic index parameter of these entropies is tuned to outperform the classical decision trees. However, this process is carried out by testing a range of values for a given database, which is time-consuming and unfeasible for massive data. This paper introduces a decision tree based on a two-parameter fractional Tsallis entropy. We propose a constructionist approach to the representation of databases as complex networks that enable us an efficient computation of the parameters of this entropy using the box-covering algorithm and renormalization of the complex network. The experimental results support the conclusion that the two-parameter fractional Tsallis entropy is a more sensitive measure than parametric Renyi, Tsallis, and Gini index precedents for a decision tree classifier.

RESUMEN

Esta tese objetivou identificar estratégias de triagem para infecção latente por Mycobacterium tuberculosis (Mtb) ­ ILTB em profissionais de saúde que viabilizem o uso mais eficiente dos recursos disponíveis. No Brasil, recomenda-se que os profissionais de saúde, um dos grupos de risco para a ILTB, realizem triagem periódica para detecção da infecção e aqueles que apresentarem conversão aos testes de diagnóstico, indica-se o tratamento preventivo da tuberculose (TB) ­ TPT uma vez que pessoas com conversão recente apresentam elevada chance de progressão para a doença. Desenvolvemos, no primeiro artigo, um modelo preditivo para identificar profissionais de saúde com maior probabilidade de resultado negativo para dois testes de diagnóstico da ILTB a partir de uma análise secundária de dados publicados anteriormente de 708 profissionais de saúde da atenção primária, de cinco capitais brasileiras, submetidos à prova tuberculínica (PT) e ao Quantiferon®-TB Gold in-tube (QFT-IT®). Construímos um modelo preditivo utilizando árvore de classificação e regressão (CART, classification and regression tree). A avaliação do desempenho foi realizada por meio da análise receiver operating characteristics (ROC) e area under the curve (AUC). Utilizou-se o mesmo banco de dados para validação cruzada do modelo. Entre os 708 profissionais de saúde, 247 (34,9%) apresentaram resultado negativo para os testes. A CART identificou que os médicos e agentes comunitários de saúde apresentaram chances duas vezes maior de testes negativos (probabilidade = 0,60) do que os enfermeiros e técnicos/auxiliares de enfermagem (probabilidade = 0,28) naqueles com menos de 5,5 anos de atuação na atenção primária. Na validação cruzada, a acurácia do modelo preditivo foi de 68% [intervalo de confiança de 95% (IC95%) 65 ­ 71) ], AUC de 62% (IC95% 58 ­ 66), especificidade de 78% (IC95% 74 ­ 81) e sensibilidade de 44% (IC95% 38 ­ 50). Apesar do baixo poder preditivo do modelo, a CART permitiu identificar subgrupos com maior probabilidade de terem ambos os testes negativos. No segundo artigo, analisou-se a razão de custo-efetividade de dois testes de sensibilidade cutânea baseados em antígenos específicos do Mtb -Diaskintest® e C-TST® - e a do QFT-Plus® para o diagnóstico da ILTB comparadas com a estratégia diagnóstica atual (PT) entre profissionais de saúde. Desenvolveu-se um modelo analítico de decisão, representado por coorte hipotética de 100.000 profissionais de saúde, de ambos os sexos, com resultado negativo para a PT no ano anterior, horizonte temporal de cinco anos, na perspectiva do Sistema Único de Saúde. Avaliaram-se três regimes de tratamento para a ILTB: três meses de doses semanais de rifapentina (900 mg) e isoniazida (900 mg) (3HP), seis e nove meses de doses diárias de isoniazida (300 mg) (6H e 9H, respectivamente). Aplicou-se taxa de desconto de 5% na efetividade, medida em casos de TB ativa evitados, e nos custos das estratégias de triagem e de tratamento avaliados, estimados em dólares americanos (US$) com taxa média anual de 2021 de acordo com o Banco Central (US$ 1 = 5,39 reais). Foram realizadas análises de sensibilidade determinística univariada e probabilística. Os testes Diaskintest®, C-TST® e QFT-Plus® apresentam maior especificidade (0,98, 0,98 e 0,97, respectivamente). Os custos com QFT-Plus® foram maiores devido aos equipamentos, mão de obra e ao custo do kit. O Diaskintest® foi o teste mais econômico (US$ 7.042, US$ 5.781 e US$ 18.892 por caso de TB ativa evitado para os regimes de tratamento com 3HP, 6H e 9H, respectivamente), inclusive nas análises de sensibilidade. No cenário nacional, o Diaskintest® foi o teste de melhor custo-efetividade para avaliação anual dos profissionais de saúde.

This thesis aimed to identify screening strategies for tuberculosis infection (TBI) in healthcare workers (HCW) that enable the most efficient use of available resources. Investigation of TBI in HCWs is recommended in Brazil as part of the worker's pre-employment and periodic (annual) health visits. HCWs with a first tuberculin skin test (TST) induration < 10 mm are invited to repeat the test in one to three weeks to assess the booster effect (induration size increment of 10 mm). Those with a persistent TST < 10 mm will undergo a one-step TST every 12 months. TPT is recommended when conversion (10 mm increment over latest induration size) occurs. We developed, in the first manuscript, a predictive model to identify HCWs best targeted for TBI screening. We carried out a secondary analysis of previously published results of 708 HCWs working in primary care services in five Brazilian State capitals who underwent two TBI tests: tuberculin skin test and Quantiferon®-TB Gold in-tube. We used a classification and regression tree (CART) model to predict HCWs with negative results for both tests. The performance of the model was evaluated using the receiver operating characteristics (ROC) curve and the area under the curve (AUC), cross-validated using the same dataset. Among the 708 HCWs, 247 (34.9%) had negative results for both tests. CART allowed us to identify that physicians or a community health agents were twice more likely to be uninfected (probability = 0.60) than registered or aid nurse (probability = 0.28) when working less than 5.5 years in the primary care setting. In cross validation, the predictive accuracy was 68% [95% confidence interval (95%CI): 65 ­ 71], AUC was 62% (95%CI 58 ­ 66), specificity was 78% (95%CI 74 ­ 81), and sensitivity was 44% (95%CI 38 ­ 50). Despite the low predictive power of this model, CART allowed to identify subgroups with higher probability of having both tests negative. In the second manuscript, we analyzed the cost-effectiveness of two TB antigen-based skin tests (TBST) using the recombinant ESAT-6 and CFP-10 immunogens (Diaskintest® and C-TST®) and of QFT-Plus® for TBI diagnosis compared with the current standard of care, TST, among HCWs in Brazil. A state-transition Markov model was created, simulating a cohort of 100,000 HCWs (five annual cycles) for TBI treatment scenarios with 3 months of weekly doses of rifapentine (900 mg) and isoniazid (900 mg) (3HP). We adopted the Brazilian public health system perspective. Effects [tuberculosis disease (TBD) averted) and costs for screening and treating TBI were discounted at 5%. Incremental cost-effectiveness per TBD averted was calculated. Hypothetical cohort of 100,000 HCWs of both sexes with a negative result of TST in the previous year. Diaskintest®, C-TST® and QFT-Plus® tests have higher specificity (0.98, 0.98 and 0.97, respectively). Costs with QFT-Plus® were higher due to equipment, human labor and cost of the kit by test. Diaskintest® was the most cost-effective test (US$ 7,042, US$ 5,781, and US$18,892 per case of TBD averted for the 3HP, 6H, and 9H treatment regimens, respectively), including sensitivity analyses. In the Brazilian scenario, Diaskintest® is the most cost-effective test for sequential testing of HCWs.

Asunto(s)

RESUMEN

ABSTRACT Introduction: With the continuous development of society and the continuous improvement of the economic level, the willingness of Chinese people to participate in sports is also showing an upward trend. However, how to reduce sports damage as much as possible during exercise should be a hot issue of particular concern to athletes in the sports world. Objective: It aimed to discuss the simulation of the relationship between joint motion amplitude (JMA) and motion damage (MD) via a rough set decision-making algorithm to avoid MD. Based on the rough set decision algorithm, JMA and MD models were constructed, and a motion data decision table was established. Methods: Joint change parameters and constraint conditions were set, and joint change parameters were analyzed. Moreover, the changing parameters, feature strength, and algorithm partition accuracy of the simulation model were analyzed. Results: The feature strength and the division accuracy of the rough set decision algorithm all showed good accuracy. The model constructed by such a method can well describe the relationship between JMA and MD. Conclusion: The proposed rough set decision algorithm can describe the relationship between JMA and MD scientifically and effectively, which provided reference value for sports. Level of evidence II; Therapeutic studies - investigation of treatment results.

RESUMO Introdução: Com o desenvolvimento contínuo da sociedade e a melhoria contínua do nível econômico, a disposição do povo chinês para a prática de esportes também apresenta uma tendência ascendente. No entanto, como reduzir os danos ao esporte tanto quanto possível durante o exercício deve ser uma questão importante de particular preocupação para os atletas do mundo dos esportes. Objetivo: o objetivo foi discutir a simulação da relação entre amplitude de movimento articular (JMA) e dano de movimento (MD) por meio de um algoritmo de tomada de decisão de conjunto aproximado, para evitar MD. Com base no algoritmo de decisão de conjunto aproximado, os modelos JMA e MD foram construídos e uma tabela de decisão de dados de movimento foi estabelecida. Métodos: os parâmetros de mudança da junta e as condições de restrição foram definidos, e os parâmetros de mudança da junta foram analisados. Além disso, foram analisados os parâmetros de alteração, a força do recurso e a precisão da partição do algoritmo do modelo de simulação. Resultados: A força do recurso e a precisão da divisão do algoritmo de decisão do conjunto aproximado mostraram boa precisão. O modelo construído por esse método pode descrever bem a relação entre JMA e MD. Conclusão: O algoritmo de decisão de conjunto aproximado proposto pode descrever a relação entre JMA e MD de forma científica e eficaz, o que forneceu valor de referência para a área de esportes. Nível de evidência II; Estudos terapêuticos- investigação dos resultados do tratamento.

RESUMEN Introducción: Con el desarrollo continuo de la sociedad y la mejora continua del nivel económico, la disposición del pueblo chino a participar en deportes también está mostrando una tendencia al alza. Sin embargo, cómo reducir el daño deportivo tanto como sea posible durante el ejercicio debería ser un tema candente de especial preocupación para los atletas en el mundo del deporte. Objetivo: Su objetivo era discutir la simulación de la relación entre la amplitud del movimiento articular (JMA) y el daño por movimiento (MD) a través de un algoritmo de toma de decisiones de conjunto aproximado, para evitar MD. Con base en el algoritmo de decisión de conjunto aproximado, se construyeron modelos JMA y MD, y se estableció una tabla de decisión de datos de movimiento. Métodos: Se establecieron los parámetros de cambio de la articulación y las condiciones de restricción, y se analizaron los parámetros de cambio de la articulación. Además, se analizaron los parámetros cambiantes, la fuerza de la característica y la precisión de la partición del algoritmo del modelo de simulación. Resultados: La fuerza de la característica y la precisión de la división del algoritmo de decisión de conjunto aproximado mostraron una buena precisión. El modelo construido por tal método puede describir bien la relación entre JMA y MD. Conclusión: El algoritmo de decisión de conjunto aproximado propuesto puede describir la relación entre JMA y MD de manera científica y efectiva, lo que proporcionó un valor de referencia para el campo de los deportes. Nivel de evidencia II; Estudios terapéuticos- investigación de los resultados del tratamiento.

Asunto(s)

RESUMEN

Reducing vaccination inequalities is a key goal of the Immunization Agenda 2030. Our main objective was to identify high-risk groups of children who received no vaccines (zero-dose children). A decision tree approach was used for 92 low- and middle-income countries using data from Demographic and Health Surveys and Multiple Indicator Cluster Surveys, allowing the identification of groups of children aged 12-23 months at high risk of being zero dose (no doses of the four basic vaccines-BCG, polio, DPT and measles). Three high-risk groups were identified in the analysis combining all countries. The group with the highest zero-dose prevalence (42%) included 4% of all children, but almost one in every four zero-dose children in the sample. It included children whose mothers did not receive the tetanus vaccine during and before the pregnancy, who had no antenatal care visits and who did not deliver in a health facility. Separate analyses by country presented similar results. Children who have been missed by vaccination services were also left out by other primary health care interventions, especially those related to antenatal and delivery care. There is an opportunity for better integration among services in order to achieve high and equitable immunization coverage.

RESUMEN

This study proposed the development of a protocol for class-II preparations with demineralized gingival margins for the improvement of the longevity of restorations. Evidence sources such as location/color/surface hardness/width of demineralized gingival margin with enamel/demineralized enamel (DE)/dentin/cementum were reviewed based on methodological studies and systematic reviews. A decision tree protocol was developed with criteria (i) lesion location: demineralized gingival margins in enamel must be removed, but if close to cementoenamel-junction, color should be evaluated. (ii) Color: yellow/brown lesions must be removed, but if white/opaque, then the surface hardness should be evaluated. (iii) Surface hardness: soft/demineralized gingival margin must be removed, but if adequately hard, width should be evaluated. (iv) Width: lesions less than half-enamel thickness and impenetrable by an explorer, remineralization is possible and the lesion does not need to be removed. A decision tree protocol was set up with the current available literature. Further continued investigations will be needed for the appropriate protocol updates.

RESUMEN

Diabetes incidence has been a problem, because according with the World Health Organization and the International Diabetes Federation, the number of people with this disease is increasing very fast all over the world. Diabetic treatment is important to prevent the development of several complications, also lipid profile monitoring is important. For that reason the aim of this work is the implementation of machine learning algorithms that are able to classify cases, that corresponds to patients diagnosed with diabetes that have diabetes treatment, and controls that refers to subjects who do not have diabetes treatment but some of them have diabetes, bases on lipids profile levels. Logistic regression, K-nearest neighbor, decision trees and random forest were implemented, all of them were evaluated with accuracy, sensitivity, specificity and AUC-ROC curve metrics. Artificial neural network obtain an acurracy of 0.685 and an AUC value of 0.750, logistic regression achieve an accuracy of 0.729 and an AUC value of 0.795, K-nearest neighbor gets an accuracy of 0.669 and an AUC value of 0.709, on the other hand, decision tree reached an accuracy pg 0.691 and a AUC value of 0.683, finally random forest achieve an accuracy of 0.704 and an AUC curve of 0.776. The performance of all models was statistically significant, but the best performance model for this problem corresponds to logistic regression.

RESUMEN

This paper presents new approaches to fit regression models for symbolic internal-valued variables, which are shown to improve and extend the center method suggested by Billard and Diday and the center and range method proposed by Lima-Neto, E.A.and De Carvalho, F.A.T. Like the previously mentioned methods, the proposed regression models consider the midpoints and half of the length of the intervals as additional variables. We considered various methods to fit the regression models, including tree-based models, K-nearest neighbors, support vector machines, and neural networks. The approaches proposed in this paper were applied to a real dataset and to synthetic datasets generated with linear and nonlinear relations. For an evaluation of the methods, the root-mean-squared error and the correlation coefficient were used. The methods presented herein are available in the the RSDA package written in the R language, which can be installed from CRAN.

RESUMEN

ABSTRACT: Objectives: Healthcare workers (HCWs) have a high risk of acquiring tuberculosis infection (TBI). However, annual testing is resource-consuming. We aimed to develop a predictive model to identify HCWs best targeted for TBI screening. Methodology: We conducted a secondary analysis of previously published results of 708 HCWs working in primary care services in five Brazilian State capitals who underwent two TBI tests: tuberculin skin test and Quantiferon®-TB Gold in-tube. We used a classification and regression tree (CART) model to predict HCWs with negative results for both tests. The performance of the model was evaluated using the receiver operating characteristics (ROC) curve and the area under the curve (AUC), cross-validated using the same dataset. Results: Among the 708 HCWs, 247 (34.9%) had negative results for both tests. CART identified that physician or a community health agent were twice more likely to be uninfected (probability = 0.60) than registered or aid nurse (probability = 0.28) when working less than 5.5 years in the primary care setting. In cross validation, the predictive accuracy was 68% [95% confidence interval (95%CI): 65 - 71], AUC was 62% (95%CI 58 - 66), specificity was 78% (95%CI 74 - 81), and sensitivity was 44% (95%CI 38 - 50). Conclusion: Despite the low predictive power of this model, CART allowed to identify subgroups with higher probability of having both tests negative. The inclusion of new information related to TBI risk may contribute to the construction of a model with greater predictive power using the same CART technique.

RESUMO: Objetivos: Desenvolver um modelo preditivo para identificar profissionais de saúde com maior probabilidade de resultado negativo para dois testes de diagnóstico da infecção latente por Mycobacterium tuberculosis (ILTB). Métodos: Foi realizada uma análise secundária dos resultados publicados anteriormente de 708 profissionais de saúde da atenção primária, de cinco capitais brasileiras, submetidos à prova tuberculínica e ao Quantiferon®-TB Gold in-tube. Um modelo preditivo com árvore de classificação e regressão (CART, Classification and regression tree) foi construído. A avaliação do desempenho foi realizada por meio da análise receiver operating characteristics (ROC) e area under the curve (AUC). Utilizamos o mesmo banco de dados para validação cruzada do modelo. Resultados: Entre os 708 profissionais de saúde, 247 (34,9%) apresentaram resultado negativo para os testes. A CART identificou que os médicos e agentes comunitários de saúde apresentaram duas vezes mais chances de não estarem infectados (probabilidade = 0,60) que os enfermeiros e técnicos/auxiliares de enfermagem (probabilidade = 0,28) nos casos com menos de 5,5 anos de atuação na atenção primária. Na validação cruzada, a acurácia do modelo preditivo foi de 68% [intervalo de confiança de 95% (IC95%) 65 - 71)], AUC de 62% (IC95% 58 - 66), especificidade de 78% (IC95% 74 - 81) e sensibilidade de 44% (IC95% 38 - 50). Conclusão: Apesar do baixo poder preditivo do modelo, a CART permitiu identificar subgrupos com maior probabilidade de terem ambos os testes negativos. A inclusão de novas informações relacionadas ao risco de ILTB pode contribuir para a construção de um modelo com maior poder preditivo utilizando a mesma técnica.

Asunto(s)

RESUMEN

ABSTRACT Objective To explore an artificial intelligence approach based on gradient-boosted decision trees for prediction of all-cause mortality at an intensive care unit, comparing its performance to a recent logistic regression system in the literature, and a logistic regression model built on the same platform. Methods A gradient-boosted decision trees model and a logistic regression model were trained and tested with the Medical Information Mart for Intensive Care database. The 1-hour resolution physiological measurements of adult patients, collected during 5 hours in the intensive care unit, consisted of eight routine clinical parameters. The study addressed how the models learn to categorize patients to predict intensive care unit mortality or survival within 12 hours. The performance was evaluated with accuracy statistics and the area under the Receiver Operating Characteristic curve. Results The gradient-boosted trees yielded an area under the Receiver Operating Characteristic curve of 0.89, compared to 0.806 for the logistic regression. The accuracy was 0.814 for the gradient-boosted trees, compared to 0.782 for the logistic regression. The diagnostic odds ratio was 17.823 for the gradient-boosted trees, compared to 9.254 for the logistic regression. The Cohen's kappa, F-measure, Matthews correlation coefficient, and markedness were higher for the gradient-boosted trees. Conclusion The discriminatory power of the gradient-boosted trees was excellent. The gradient-boosted trees outperformed the logistic regression regarding intensive care unit mortality prediction. The high diagnostic odds ratio and markedness values for the gradient-boosted trees are important in the context of the studied unbalanced dataset.

RESUMO Objetivo Explorar uma abordagem de inteligência artificial baseada em árvores de decisão impulsionadas por gradiente para previsão de mortalidade por todas as causas em unidade de terapia intensiva, comparando seu desempenho com um sistema de regressão logística recente na literatura e um modelo de regressão logística construído na mesma plataforma. Métodos Foram desenvolvidos um modelo de árvores impulsionadas por gradiente e um modelo de regressão logística, treinados e testados com o banco de dados Medical Information Mart for Intensive Care. As medidas fisiológicas de pacientes adultos com resolução de 1 hora, coletadas durante 5 horas na unidade de terapia intensiva, consistiram em oito parâmetros clínicos de rotina. Estudou-se como os modelos aprendem a categorizar os pacientes para prever a mortalidade ou a sobrevida, em unidades de terapia intensiva, em 12 horas. O desempenho foi avaliado por meio de estatísticas de acurácia e pela área sob a curva Característica de Operação do Receptor. Resultados As árvores impulsionadas por gradiente produziram área sob a curva Característica de Operação do Receptor de 0,89, em comparação com 0,806 para a regressão logística. A acurácia foi de 0,814 para as árvores impulsionadas por gradiente, em comparação com 0,782 para a regressão logística. A razão de chances de diagnóstico foi de 17,823 para as árvores impulsionadas por gradiente, em comparação a 9,254 para a regressão logística. O kappa de Cohen, a medida F, o coeficiente de correlação de Matthews e a marcação foram maiores para as árvores impulsionadas por gradiente. Conclusão O poder discriminatório das árvores impulsionadas por gradiente foi excelente. As árvores impulsionadas por gradiente superaram a regressão logística em relação à previsão de mortalidade em unidade de terapia intensiva. A alta razão de chances de diagnóstico e os valores de marcação para as árvores impulsionadas por gradiente são importantes no contexto do conjunto de dados não balanceados estudado.

Asunto(s)

RESUMEN

Abstract Objectives This study aimed to investigate patterns and risk factors related to the feasibility of achieving technical quality and periapical healing in root canal non-surgical retreatment, using regression and data mining methods. Methodology This retrospective observational study included 321 consecutive patients presenting for root canal retreatment. Patients were treated by graduate students, following standard protocols. Data on medical history, diagnosis, treatment, and follow-up visits variables were collected from physical records and periapical radiographs and transferred to an electronic chart database. Basic statistics were tabulated, and univariate and multivariate analytical methods were used to identify risk factors for technical quality and periapical healing. Decision trees were generated to predict technical quality and periapical healing patterns using the J48 algorithm in the Weka software. Results Technical outcome was satisfactory in 65.20%, and we observed periapical healing in 80.50% of the cases. Several factors were related to technical quality, including severity of root curvature and altered root canal morphology (p<0.05). Follow-up periods had a mean of 4.05 years. Periapical lesion area, tooth type, and apical resorption proved to be significantly associated with retreatment failure (p<0.05). Data mining analysis suggested that apical root resorption might prevent satisfactory technical outcomes even in teeth with straight root canals. Also, large periapical lesions and poor root filling quality in primary endodontic treatment might be related to healing failure. Conclusion Frequent patterns and factors affecting technical outcomes of endodontic retreatment included root canal morphological features and its alterations resulting from primary endodontic treatment. Healing outcomes were mainly associated with the extent of apical periodontitis pathological damages in dental and periapical tissues. To determine treatment predictability, we suggest patterns including clinical and radiographic features of apical periodontitis and technical quality of primary endodontic treatment.

Asunto(s)

RESUMEN

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.

Asunto(s)

RESUMEN

A leptospirose se relaciona a problemas de saneamento ambiental, com incremento de casos em períodos de inundações. Levando-se em consideração as questões relacionadas a mudanças climáticas, as inundações tendem a um aumento. As inundações não atingem as populações de maneira homogênea, em geral os menos favorecidos em termos socioeconômicos são os mais acometidos. Para saber se o número de inundações aumentaria a incidência de leptospirose e sua relação com as variáveis contextuais, utilizou-se dados socioeconômicos, ambientais e de ocorrência da doença no nível municipal. Os municípios que tinham problemas no esgotamento sanitário apresentaram maior risco para a ocorrência da leptospirose. O total de inundações adquirida a partir da decretação pela autoridade municipal constituiu um importante marcador de risco para a ocorrência de leptospirose. A modelagem de árvore de regressão mostrou-se útil para estimar a ocorrência de leptospirose no Brasil.

Leptospirosis is related to problems with environmental sanitation, and the incidence tends to increase during flood periods. Considering issues related to climate change, floods can be expected to increase. Floods do not affect populations homogeneously, and communities with worse socioeconomic conditions tend to be impacted more heavily. In order to determine whether the number of floods increases the incidence of leptospirosis and its relationship to contextual variables, the study used socioeconomic, environmental, and disease occurrence data at the municipal (county) level. Municipalities suffering problems with sewage disposal showed a higher risk of leptospirosis incidence. Total flooding since the municipality's declaration of flood emergency was an important risk marker for leptospirosis incidence. Regression tree modeling proved useful for estimating leptospirosis incidence in Brazil.

La leptospirosis se relaciona con problemas de saneamiento ambiental, así como con el incremento de casos en períodos de inundaciones. Teniendo en consideración las cuestiones relacionadas con el cambio climático, las inundaciones tienden a aumentar. Las inundaciones no afectan a las poblaciones de manera homogénea, en general, los menos favorecidos en términos socioeconómicos son los más afectados. Para saber si el número de inundaciones aumentaría la incidencia de leptospirosis, y su relación con variables contextuales, se utilizaron datos socioeconómicos, ambientales y de ocurrencia de la enfermedad en el nivel municipal. Los municipios que poseían problemas en el alcantarillado sanitario presentaron un mayor riesgo para la ocurrencia de leptospirosis. El total de inundaciones sufridas a partir de su reconocimiento oficial por parte de la autoridad municipal constituyó un importante marcador de riesgo para la ocurrencia de leptospirosis. El modelo de árbol de regresión se mostró útil para estimar la ocurrencia de leptospirosis en Brasil.

Asunto(s)

RESUMEN

The growth of older adults in new regions poses challenges for public health. We know that these seniors live increasingly alone, and this impairs their health and general wellbeing. Studies suggest that social networking sites (SNS) can reduce isolation, improve social participation, and increase autonomy. However, there is a lack of knowledge about the characteristics of older adult users of SNS in these new territories. Without this information, it is not possible to improve the adoption of SNS in this population. Based on decision trees, this study analyzes how the elderly users of various SNS in Chile are like. For this purpose, a segmentation of the different groups of elderly users of social networks was constructed, and the most discriminating variables concerning the use of these applications were classified. The results highlight the existence of considerable differences between the various social networks analyzed in their use and characterization. Educational level is the most discriminating variable, and gender influences the types of SNS use. In general, it is observed that the higher the educational level, the more the different social networking sites are used.

Asunto(s)

RESUMEN

Abstract The aim of this study was to construct a predictive model that uses classification tree statistical analysis to predict the occurrence of temporomandibular disorder, by dividing the sample into groups of high and low risk for the development of the disease. The use of predictive statistical approaches that facilitate the process of recognizing and/or predicting the occurrence of temporomandibular disorder is of interest to the scientific community, for the purpose of providing patients with more adequate solutions in each case. This was a cross-sectional analytical population-based study that involved a sample of 776 individuals who had sought medical or dental attendance at the Family Health Units in Recife, PE, Brazil. The sample was submitted to anamnesis using the instrument Research Diagnostic Criteria for Temporomandibular Disorders. The data were inserted into the software Statistical Package for the Social Sciences 20.0 and analyzed by the Pearson Chi-square test for bivariate analysis, and by the classification tree method for the multivariate analysis. Temporomandibular disorder could be predicted by orofacial pain, age and depression. The high-risk group was composed of individuals with orofacial pain, those between the ages of 25 and 59 years and those who presented depression. The low risk group was composed of individuals without orofacial pain. The authors were able to conclude that the best predictor for temporomandibular disorder was orofacial pain, and that the predictive model proposed by the classification tree could be applied as a tool for simplifying decision making relative to the occurrence of temporomandibular disorder.

Resumo O objetivo deste estudo foi construir um modelo preditivo que utiliza a análise estatística de árvore de classificação para predizer a ocorrência de disfunção temporomandibular, dividindo a amostra em grupos de alto e baixo risco para o desenvolvimento da doença. A utilização de abordagens estatísticas preditivas que facilitem o processo de reconhecimento e / ou previsão da ocorrência de disfunção temporomandibular é de interesse da comunidade científica, com o objetivo de fornecer aos pacientes soluções mais adequadas a cada caso. Trata-se de um estudo transversal analítico de base populacional que envolveu uma amostra de 776 indivíduos que procuraram atendimento médico ou odontológico nas Unidades de Saúde da Família de Recife, PE, Brasil. A amostra foi submetida à anamnese por meio do instrumento Research Diagnostic Criteria for Temporomandibular Disorders. Os dados foram inseridos no software Statistical Package for the Social Sciences 20.0 e analisados pelo teste Qui-quadrado de Pearson para análise bivariada e pelo método de árvore de classificação para análise multivariada. A desordem temporomandibular pode ser prevista pela presença da dor orofacial, idade e depressão. O grupo de alto risco foi composto por indivíduos com dor orofacial, entre 25 e 59 anos e que apresentavam depressão. O grupo de baixo risco foi composto por indivíduos sem dor orofacial. Os autores puderam concluir que o melhor preditor para a disfunção temporomandibular foi a dor orofacial e que o modelo preditivo proposto pela árvore de classificação pode ser aplicado como ferramenta para simplificar a tomada de decisão em relação à ocorrência de disfunção temporomandibular.

Asunto(s)

RESUMEN

ABSTRACT Objectives: Describe a predictive model of hospitalization frequency for children and adolescents with chronic disease. Methods: A decision tree-based model was built using a database of 141 children and adolescents with chronic disease admitted to a federal public hospital; 18 variables were included and the frequency of hospitalization was defined as the outcome. Results: The decision tree obtained in this study could properly classify 80.85% of the participants. Model reading provided an understanding that situations of greater vulnerability such as unemployment, low income, and limited or lack of family involvement in care were predictors of a higher frequency of hospitalization. Conclusions: The model suggests that nursing professionals should adopt prevention actions for modifiable factors and authorities should make investments in health promotion for non-modifiable factors. It also enhances the debate about differentiated care to these patients.

RESUMEN Objetivos: Describir un modelo predictor de frecuencia de internación hospitalaria para niños y adolescentes con enfermedades crónicas. Métodos: Se construyó un modelo basado en árboles de decisión, utilizando un banco de datos de 141 niños y adolescentes con enfermedades crónicas internados en hospital público federal. Para elaborar el modelo fueron consideradas 18 variables, la frecuencia de internación fue definida como desenlace. Resultados: Se obtuvo un árbol de decisiones capaz de clasificar correctamente al 80,85% de los participantes. La lectura del modelo permitió entender que las situaciones de mayor vulnerabilidad, como desempleo, bajos ingresos, restricciones y ausencia de compromiso familiar para el cuidado, actuaron como predictoras de mayor frecuencia de internación hospitalaria. Conclusiones: El modelo sugiere a la enfermería y equipo acciones preventivas para aquellos factores modificables, e inversión en promoción de salud para los factores no modificables; fortaleciendo también el debate sobre el cuidado diferenciado para esta población.

RESUMO Objetivos: Descrever um modelo preditor de frequência de internação hospitalar para crianças e adolescentes com doença crônica. Métodos: Foi construído um modelo baseado em árvore de decisão, a partir do banco de dados de 141 crianças e adolescentes, com doença crônica, internados em um hospital público federal. Para construção do modelo, foram incluídas 18 variáveis e a frequência de internação foi definida como desfecho. Resultados: Obteve-se uma árvore de decisão capaz de classificar corretamente 80,85% dos participantes. A leitura do modelo proporcionou o entendimento de que as situações de maior vulnerabilidade, como desemprego, baixa renda, restrições e ausência de envolvimento da família no cuidado, foram preditoras da maior frequência de internação hospitalar. Conclusões: O modelo sugere à enfermagem e equipe ações de prevenção para os fatores modificáveis e investimentos em promoção à saúde para os fatores não modificáveis e fortalece o debate sobre o cuidado diferenciado para esse público.

RESUMEN

ABSTRACT Objectives: Describe a predictive model of hospitalization frequency for children and adolescents with chronic disease. Methods: A decision tree-based model was built using a database of 141 children and adolescents with chronic disease admitted to a federal public hospital; 18 variables were included and the frequency of hospitalization was defined as the outcome. Results: The decision tree obtained in this study could properly classify 80.85% of the participants. Model reading provided an understanding that situations of greater vulnerability such as unemployment, low income, and limited or lack of family involvement in care were predictors of a higher frequency of hospitalization. Conclusions: The model suggests that nursing professionals should adopt prevention actions for modifiable factors and authorities should make investments in health promotion for non-modifiable factors. It also enhances the debate about differentiated care to these patients.

RESUMEN Objetivos: Describir un modelo predictor de frecuencia de internación hospitalaria para niños y adolescentes con enfermedades crónicas. Métodos: Se construyó un modelo basado en árboles de decisión, utilizando un banco de datos de 141 niños y adolescentes con enfermedades crónicas internados en hospital público federal. Para elaborar el modelo fueron consideradas 18 variables, la frecuencia de internación fue definida como desenlace. Resultados: Se obtuvo un árbol de decisiones capaz de clasificar correctamente al 80,85% de los participantes. La lectura del modelo permitió entender que las situaciones de mayor vulnerabilidad, como desempleo, bajos ingresos, restricciones y ausencia de compromiso familiar para el cuidado, actuaron como predictoras de mayor frecuencia de internación hospitalaria. Conclusiones: El modelo sugiere a la enfermería y equipo acciones preventivas para aquellos factores modificables, e inversión en promoción de salud para los factores no modificables; fortaleciendo también el debate sobre el cuidado diferenciado para esta población.

RESUMO Objetivos: Descrever um modelo preditor de frequência de internação hospitalar para crianças e adolescentes com doença crônica. Métodos: Foi construído um modelo baseado em árvore de decisão, a partir do banco de dados de 141 crianças e adolescentes, com doença crônica, internados em um hospital público federal. Para construção do modelo, foram incluídas 18 variáveis e a frequência de internação foi definida como desfecho. Resultados: Obteve-se uma árvore de decisão capaz de classificar corretamente 80,85% dos participantes. A leitura do modelo proporcionou o entendimento de que as situações de maior vulnerabilidade, como desemprego, baixa renda, restrições e ausência de envolvimento da família no cuidado, foram preditoras da maior frequência de internação hospitalar. Conclusões: O modelo sugere à enfermagem e equipe ações de prevenção para os fatores modificáveis e investimentos em promoção à saúde para os fatores não modificáveis e fortalece o debate sobre o cuidado diferenciado para esse público.