Modelo predictivo de enfermedad cardiovascular basado en inteligencia artificial en la atención primaria de salud / A Predictive Model for Cardiovascular Disease based on Artificial Intelligence in Primary Health Care

Introducción: En Cuba y en el resto del mundo, las enfermedades cardiovasculares son reconocidas como un problema de salud pública mayúsculo y creciente, que provoca una alta mortalidad. Objetivo: Diseñar un modelo predictivo para estimar el riesgo de enfermedad cardiovascular basado en técnicas de inteligencia artificial. Métodos: La fuente de datos fue una cohorte prospectiva que incluyó 1633 pacientes, seguidos durante 10 años, fue utilizada la herramienta de minería de datos Weka, se emplearon técnicas de selección de atributos para obtener un subconjunto más reducido de variables significativas, para generar los modelos fueron aplicados: el algoritmo de reglas JRip y el meta algoritmo Attribute Selected Classifier, usando como clasificadores el J48 y el Multilayer Perceptron. Se compararon los modelos obtenidos y se aplicaron las métricas más usadas para clases desbalanceadas. Resultados: El atributo más significativo fue el antecedente de hipertensión arterial, seguido por el colesterol de lipoproteínas de alta densidad y de baja densidad, la proteína c reactiva de alta sensibilidad y la tensión arterial sistólica, de estos atributos se derivaron todas las reglas de predicción, los algoritmos fueron efectivos para generar el modelo, el mejor desempeño fue con el Multilayer Perceptron, con una tasa de verdaderos positivos del 95,2 por ciento un área bajo la curva ROC de 0,987 en la validación cruzada. Conclusiones: Fue diseñado un modelo predictivo mediante técnicas de inteligencia artificial, lo que constituye un valioso recurso orientado a la prevención de las enfermedades cardiovasculares en la atención primaria de salud(AU)

Introduction: In Cuba and in the rest of the world, cardiovascular diseases are recognized as a major and growing public health problem, which causes high mortality. Objective: To design a predictive model to estimate the risk of cardiovascular disease based on artificial intelligence techniques. Methods: The data source was a prospective cohort including 1633 patients, followed for 10 years. The data mining tool Weka was used and attribute selection techniques were employed to obtain a smaller subset of significant variables. To generate the models, the rule algorithm JRip and the meta-algorithm Attribute Selected Classifier were applied, using J48 and Multilayer Perceptron as classifiers. The obtained models were compared and the most used metrics for unbalanced classes were applied. Results: The most significant attribute was history of arterial hypertension, followed by high and low density lipoprotein cholesterol, high sensitivity c-reactive protein and systolic blood pressure; all the prediction rules were derived from these attributes. The algorithms were effective to generate the model. The best performance was obtained using the Multilayer Perceptron, with a true positive rate of 95.2percent and an area under the ROC curve of 0.987 in the cross validation. Conclusions: A predictive model was designed using artificial intelligence techniques; it is a valuable resource oriented to the prevention of cardiovascular diseases in primary health care(AU)

Resilient coping and future expectations in university students in Peru during the pandemic / Afrontamiento resiliente y expectativas de futuro en estudiantes universitarios de Perú durante la pandemia

Objective: To determine the relationship between resilient coping and future expectations. Methods: The approach was exclusively quantitative, observational, prospective, cross-sectional, and correlational in design. The participants were 2202 students from the (UNHEVAL, Perú), and the instruments resilient coping scale and the future expectations scale were used, which were digitized to be applied. A correlation analysis was performed using Spearman's Rho non-parametric statistical test. Results: The level of future expectations where the largest number of students is located was high, with 55.6 percent, and at the same time, 53.4 percent of the students manifested medium-level resilient coping. The main finding is that university students obtained a significant relationship between resilient coping and future expectations (rs=0.39; p=0.000), as in future expectations with the three dimensions of resilient coping, personal resilient coping (rs=0.36; p=0.000), social resilient coping (rs=0.38; p=0.000) and spiritual resilient coping (rs=0.18; p=0.000). Conclusions: There is a statistically significant and positive relationship between resilient coping and future expectations in students (UNHEVAL, Perú) (AU)

Objetivo: Determinar la relación entre el afrontamiento resiliente y las expectativas de futuro. Métodos: El enfoque fue exclusivamente cuantitativo, observacional, prospectivo, transversal y de diseño correlacional. Participaron 2202 estudiantes de la (UNHEVAL, Perú), y se utilizaron los instrumentos Escala de Afrontamiento Resiliente y Escala de Expectativas de Futuro, los cuales fueron digitalizados para su aplicación. Se realizó un análisis de correlación mediante la prueba estadística no paramétrica Rho de Spearman. Resultados: El nivel de expectativas de futuro donde se ubica la mayor cantidad de estudiantes fue alto con un 55,6 percent, y a su vez el 53,4 percent de los estudiantes manifestaron un afrontamiento resiliente de nivel medio. El principal hallazgo es que los estudiantes universitarios obtuvieron una relación significativa entre el afrontamiento resiliente y las expectativas de futuro (rs=0,39; p=0,000), así como en las expectativas de futuro con las tres dimensiones del afrontamiento resiliente, afrontamiento resiliente personal (rs=0,36; p=0,000), afrontamiento resiliente social (rs=0,38; p=0,000) y afrontamiento resiliente espiritual (rs=0,18; p=0,000). Conclusiones: Existe una relación estadísticamente significativa y positiva entre el afrontamiento resiliente y las expectativas de futuro en los estudiantes (UNHEVAL, Perú)(AU)

A Novel Early Warning Model for Hand, Foot and Mouth Disease Prediction Based on a Graph Convolutional Network / 生物医学与环境科学（英文）

Objectives@#Hand, foot and mouth disease (HFMD) is a widespread infectious disease that causes a significant disease burden on society. To achieve early intervention and to prevent outbreaks of disease, we propose a novel warning model that can accurately predict the incidence of HFMD.@*Methods@#We propose a spatial-temporal graph convolutional network (STGCN) that combines spatial factors for surrounding cities with historical incidence over a certain time period to predict the future occurrence of HFMD in Guangdong and Shandong between 2011 and 2019. The 2011-2018 data served as the training and verification set, while data from 2019 served as the prediction set. Six important parameters were selected and verified in this model and the deviation was displayed by the root mean square error and the mean absolute error.@*Results@#As the first application using a STGCN for disease forecasting, we succeeded in accurately predicting the incidence of HFMD over a 12-week period at the prefecture level, especially for cities of significant concern.@*Conclusions@#This model provides a novel approach for infectious disease prediction and may help health administrative departments implement effective control measures up to 3 months in advance, which may significantly reduce the morbidity associated with HFMD in the future.

Modelo temporal del comportamiento de pacientes críticos con covid-19 durante su estadía en cuidados intensivos. Lombardía, Italia / Temporal model of the behavior of critically ill patients with COVID-19 during their staying in intensive care. Lombardy, Italy

RESUMEN Introducción: una serie temporal es el producto de la observación de una variable en el tiempo. Es una herramienta matemática que se aplica con frecuencia en la salud. No se han elaborado modelos temporales que predigan el comportamiento de los pacientes durante su ingreso en la Unidad de Cuidados Intensivos. Objetivos: crear una serie temporal que permita predecir el comportamiento, durante su ingreso en la Unidad de Cuidados Intensivos, de pacientes graves producto de la covid-19 en la región de Lombardía, Italia. Materiales y métodos: analítico, longitudinal prospectivo con un grupo de pacientes críticos que ingresaron del 1 de abril al 1 de mayo de 2020, con diagnóstico de covid-19, en el Hospital Mayor de Crema, en la región de Lombardía, Italia. El universo estuvo constituido por 28 pacientes y se trabajó con el total de ellos. Resultados: composición por sexo: 48 % masculino. Media de edad: 83 años. Serie temporal: Modelo 1 que ajusta (Hold) PO2/FiO2 p = 0,251; Modelo 2 (ARIMA) SatO2/FiO2 p = 0,674 (en los dos primeros modelos el resultado se incrementó con los días, siguiendo un comportamiento predecible); Modelo 3 (ARIMA) p = 0,406 (en este caso, el resultado esperado decreció a medida que transcurrió el tiempo). Las funciones obtenidas permiten calcular el valor esperado según el día desde el ingreso. Conclusiones: predecir la evolución del paciente en la Unidad de Cuidados Intensivos permitió detectar tempranamente aquellos con una curva inesperada y dirigir hacia a ellos las terapéuticas más agresivas (AU).

ABSTRACT Introduction: a time series is the product of the observation of a variable in time. It is a mathematical tool frequently applied in health. No temporal models have been developed to predict patients' behavior during their staying in the Intensive Care Unit. Objectives: to create a time series allowing to predict the behavior of seriously-ill patients due to COVID-19, during their staying in the Intensive Care Unit in the region of Lombardy, Italy. Materials and methods: analytic, longitudinal prospective study with a group of critical patients who were admitted from April 1st to May 1st, with COVID-19 diagnosis, to Ospedale Maggiore di Crema, in the Lombardy region, Italy. The universe was formed by 28 patients and all of them were worked on. Results: 48% of patients were male. Average age: 83 years; Time series: Model 1 holding PO2/FiO2 p = 0.251; Model 2 (ARIMA) SatO2/FiO2 p = 0.674 (in the two first models the result increased with the days, following a predictable behavior=; Model 3 (ARIMA) p = 0.406 (in this case the expected result decreased as time passed). The obtained functions allow to calculate the expected value according to the day from the admission. Conclusions: predicting patient's evolution in the Intensive Care Unit allowed early detecting those with unexpected curves and targeting more aggressive therapies toward them (AU).

Aplicación de un modelo cubano predictivo de mortalidad en pacientes graves por covid-19 en Lombardía, Italia / Application of a Cuban mortality-predictive model in seriously-ill patients with Covid-19 in Lombardy, Italy

RESUMEN Introducción: la neumonía por covid-19 es la enfermedad infecciosa que ha revolucionado al mundo en los últimos meses. El diagnóstico pasa por varios momentos: el cuadro clínico, la analítica sanguínea y las imágenes. La estratificación del riesgo de muerte es muy importante para optimizar los recursos. Objetivos: validar un modelo matemático cubano predictivo de mortalidad en pacientes ingresados por covid-19. Materiales y métodos: estudio de cohorte con 191 pacientes, que ingresaron graves en el Hospital Mayor de Crema, en la provincia de Cremona, región de Lombardía (Italia), en el período de abril a mayo de 2020. El universo estuvo constituido por 191 pacientes, y no se tomó muestra alguna. Las variables fueron: edad, estado del paciente, niveles de creatinina plasmática, frecuencia respiratoria, frecuencia cardiaca, presión arterial, niveles de oxígeno y de dióxido de carbono en sangre, valor del sodio y de hemoglobina. Resultados: mortalidad del 22 % en pacientes graves y críticos, con media de la edad (grupo 1: 59 años) (grupo 2: 73 años); t-Student = 0,00. Test de Hosmer-Lemenshow (0,766) con elevado ajuste. Sensibilidad = 93 %. Área bajo la curva = 0,957. Porcentaje de aciertos en la regresión logística de 86,4 % y en la red neuronal de 91,2 %. Media del modelo por grupos (grupo 1: 4 458) (grupo 2: 2 911) t-Student = 0,00. Conclusiones: el modelo demostró ser muy útil en el flujograma de pacientes atendidos con la covid-19. Permitió detectar tempranamente (a los cinco días del ingreso) los pacientes con alto riesgo de muerte y discriminar aquellos que no tendrían este riesgo, de manera que pudieran ser tratados en unidades de cuidados mínimos (AU).

ABSTRACT Introduction: COVID-19 pneumonia is an infectious disease that has revolutionized the world in the last months. The diagnosis goes thought several moments: clinical features, blood analytic and images. Death risk stratification is very important to optimize resources. Objective: to validate the Cuban mathematic predictive model of mortality in patients admitted due to COVID-19. Materials and methods: cohort study with 191 seriously-ill patients who were admitted to Maggiore di Crema Hospital, Cremona, Lombardy region, Italy, in the period April-May 2020. The universe were 191 patients and no sample was chosen. The variables were: age; patient's status; plasma creatinine levels; respiratory rate; heart rate; arterial pressure; blood oxygen and carbon dioxide levels; values of sodium and hemoglobin. Results: 22 % of mortality in seriously-ill and critical patients, with average age in Group 1: 59 years, in Group 2: 73 years; t-Student = 0.00. Hosmer-Lemenshow test (0.766) with high adjustment. Sensitivity= 93 %. Area below the curve=0.957. Success percentage in logistic regression of 86.4 % and 91.2 % in the neuronal net. Model media per groups: Group 1= 4 458; Group 2= 2 911, t-Student = 0.00. Conclusions: the model showed to be very useful in the flow chart of patients attended with COVID-19. It allowed to early detect the patients at high death risk five days from admission and discriminating those who were not at risk, in a way that they could be treated in minimal care units (AU).

Sistema IOTA ADNEX: ¿Confiable como predictor en pacientes con blastoma anexial? / ADNEX IOTA SYSTEM: Reliable as a predictor in patients with adnexal blastoma?

Objetivos: Evaluar el valor predictivo del sistema IOTA ADNEX®, en pacientes con diagnóstico de blastoma anexial. Objetivo secundario: Evaluar otras características sugestivas de malignidad no incluidas en el sistema IOTA ADNEX®. Materiales y métodos: Estudio observacional, retrospectivo, descriptivo. Se incluyeron 42 pacientes con diagnóstico ecográfico inicial de blastoma anexial que se atendieron y fueron operadas en nuestro servicio en el periodo 2013 - 2018, divididas en 2 grupos: Grupo A (21 pacientes con diagnóstico posterior de cáncer de ovario) y Grupo B (Pacientes con diagnóstico benigno postoperatorio). Se evaluó el valor predictivo del sistema IOTA ADNEX®, para dichas pacientes y se comparó los resultados del Grupo A vs Grupo B. Resultados: El aumento de Ca125, se encontró fuertemente asociado al cáncer de ovario. La diferencia entre Grupo A y B fue estadísticamente significativo p<0,0001. Encontramos una asociación entre el GRUPO A, con la predicción de cáncer de ovario, siendo esta diferencia estadísticamente significativa p<0,0001. Conclusión: De acuerdo a nuestros resultados el sistema ADNEX®, podría predecir tanto el riesgo de malignidad como de benignidad de un blastoma anexial de manera fidedigna. Dicho sistema presenta como ventaja el objetivar la interpretación de los estudios y su fácil implementación en todos los ámbitos. La adecuada caracterización e intervención pre quirúrgica permite la planificación del tratamiento mejorando el pronóstico de las pacientes (AU)

ABSTRACT: AIM: To assess the predictive value of the IOTA ADNEX® system, in patients diagnosed with adnexal blastoma. Secondary aim: To evaluate other characteristics suggestive of malignancy not included in the IOTA ADNEX® system. Materials and methods: Observational, retrospective, descriptive study. We included 42 patients with initial ultrasound diagnosis of adnexal blastoma, who were treated and operated in our service 2013-2018 period, divided into 2 groups: Group A (21 patients with subsequent diagnosis of ovarían cancer) and Group B (Patients with benign postoperative diagnosis). The predictive value of the IOTA ADNEX® system was evaluated for these patients and the results of Group A vs Group B were compared. Results: Ca125 was found to be strongly associated with ovarian cancer. The difference between Group A and B was statistically significant p <0.0001. We found an association between GROUP A, with the prediction of ovarian cancer, this difference being statistically significant p <0.0001. Conclusion: According to our results, the ADNEX® system could predict both the risk of malignancy and benignity of an adnexal blastoma reliably. This system has the advantage of objectifying the interpretation of the studies and their easy implementation in all areas. Proper characterization and presurgical intervention allows treatment planning to improve the prognosis of patients (AU)

A pandemia da COVID-19 no Brasil: a série de projeções do Institute for Health Metrics and Evaluation e a evolução observada, maio a agosto de 2020 / La Pandemia de COVID-19 en Brasil: Serie de Proyecciones del Institute for Health Metrics and Evaluation y la Evolución Observada, desde mayo hasta agosto, 2020 / The COVID-19 Pandemic in Brazil: Institute for Health Metrics and Evaluation projections and observed evolution, May-August, 2020

Objetivo: Descrever as projeções do Institute for Health Metrics and Evaluation (IHME) para a COVID-19 no Brasil e seus estados, apresentar sua acurácia e discutir suas implicações. Métodos: As previsões do IHME de maio a agosto de 2020, para o Brasil e alguns estados, foram comparadas ao número de mortes cumulativas observadas. Resultados: A projeção prevê 182.809 mortes causadas pela pandemia até 1º de dezembro de 2020 no Brasil. O aumento no uso de máscara poderia poupar ~17 mil óbitos. O erro médio no número acumulado de óbitos em duas, quatro e seis semanas das projeções foi de 13%, 18% e 22% respectivamente. Conclusão: Projeções de curto e médio prazo dispõem dados importantes e acurácia suficiente para informar os gestores de saúde, autoridades eleitas e sociedade geral. Após trajeto difícil até agosto, a pandemia, conforme as projeções, terá declínio sustentado, embora demorado, causando em média 400 óbitos/dia no início de dezembro.

Objetivo: Describir las proyecciones del Institute for Health Metrics and Evaluation para COVID-19 en Brasil y sus estados, presentar su precisión y discutir sus implicaciones. Métodos Las previsiones del IHME de mayo a agosto de 2020 para Brasil y algunos estados, se compararon con las muertes acumuladas observadas. Resultados La proyección prevé 182.809 muertes por la pandemia hasta el 1º de diciembre de 2020 en Brasil. Un aumento en el uso de mascarillas podría evitar ~17.000 muertes. El error medio en el número acumulado de muertes en 2, 4 y 6 semanas de las proyecciones fue de 13%, 18% y 22%. Conclusión: Las proyecciones de corto y medio plazo proporcionan datos importantes y con suficiente precisión para informar a los administradores de salud, autoridades electas y a la sociedad. Después de un camino difícil hasta agosto, la pandemia, según las proyecciones, tendrá una disminución sostenida, pero lenta, y seguirá causando alrededor de 400 muertes/día a principios de diciembre.

Objective: To describe the Institute for Health Metrics and Evaluation (IHME) projections for the COVID-19 pandemic in Brazil and the Brazilian states, present their accuracy and discuss their implications. Methods: The IHME projections from May to August 2020 for Brazil and selected states were compared with the ensuing reported number of cumulative deaths. Results: The pandemic was projected to cause 182,809 deaths by December 1, 2020 in Brazil. An increase in mask use could reduce the projected death toll by ~17,000. The mean error in the cumulative number of deaths at 2, 4 and 6 weeks after the projections were made was 13%, 18% and 22%, respectively. Conclusion: Short and medium-term projections provide important and sufficiently accurate data to inform health managers, elected officials, and society at large. After following an arduous course up until August, the pandemic is projected to decline steadily although slowly, with ~400 deaths/day still occurring in early December.

Validación externa del modelo predictivo de mortalidad en ancianos con neumonía adquirida en la comunidad / External validation of the predictive model of mortality in elder people with community-acquired pneumonia

RESUMEN Introducción: la neumonía adquirida en la comunidad es la enfermedad infecciosa que conlleva una mayor mortalidad en los países desarrollados. El diagnóstico pasa por varios momentos, el cuadro clínico, la analítica y las imágenes. Objetivos: realizar la validación externa de un modelo matemático predictivo de mortalidad en pacientes ingresados por neumonía grave adquirida en la comunidad. Material y métodos: estudio longitudinal prospectivo (cohorte) con un grupo, con todos los pacientes que ingresaron en la Unidad de Cuidados intensivos emergentes con el diagnóstico de neumonía adquirida en la comunidad en el Hospital Militar Dr. Carlos J. Finlay, de febrero de 2018 hasta marzo del 2019. El universo estuvo constituido por 160 pacientes y no se tomó muestra alguna. Resultados: índice de Kappa K=1. Test Hosmer Lemenshow 0,650 con elevado ajuste. Resultados del modelo con sensibilidad= 79%. Especificidad: 91% con (VPP): 80 y (VPN)= 91. RR: 9,1. Área bajo la Curva = 0997. Porcentaje de aciertos en la regresión logística de 88,4 %. Conclusiones: el modelo propuesto constituyo una herramienta útil en la detección temprana de pacientes con riesgo de muerte a corto plazo. Permitió unificar en una sola variable el resultado de otras que aparentemente no tienen relación entre ellas; con lo que se hace más fácil la interpretación de los resultados, toda vez que este refleja, el conjunto y no la individualidad (AU).

SUMMARY Introduction: community-acquired pneumonia is the infectious disease leading to higher mortality in developed countries. The diagnosis goes through several moments, clinical symptoms, analytics, and images. Objective: to perform the external validation of a predictive mathematical model of mortality in patients admitted by serious community-acquired pneumonia. Methods: longitudinal prospective (cohort) study with a group formed with all patients who were admitted to the Emergent Intensive Care Unit in the Military Hospital ¨Dr. Carlos Juan Finlay¨ with the diagnosis of community-acquired pneumonia, from February 2018 to March 2019. The universe was formed by 160 patients and no sample was chosen. Results: Kappa index K= 1. Hosmer Lemenshow test= 0.650 with a high adjustment. Result of the model with sensibility= 79 %. Specificity= 91 % with (APV) = 80 and (NPV) = 91. RR= 9.1. Area under the curve= 0997. Percentage of correctness in logistic regression of 88.4 %. Conclusions: The proposed model was a useful tool in the early detection of patients at near-term death risk. It allowed to unite in an only variant the result of others that apparently are not related one to another, making it easier the interpretation of the results, since it reflects the whole and not the individuality (AU).

Estimación de casos de COVID-19 en países de Suramérica empleando modelos ARIMA (Autorregresivo Integrado de Promedio Móvil) / Estimation of COVID-19 cases in South American countries using ARIMA models

El objetivo principal de este trabajo es emplear modelos ARIMA para la estimación de nuevos contagios usando datos públicos disponibles para Venezuela y la región suramericana, actualmente foco principal de un segundo brote de la COVID-19. Se realiza la predicción a 30 días del número de casos de Covid-19 en países suramericanos usando los datos públicos disponibles. Se emplearon modelos ARIMA para estimar el impacto de nuevos contagios en las dinámicas de infección para Suramérica. Desde la aparición del primer caso de la nueva neumonía Covid-19 en China, esta enfermedad se ha convertido en un problema de salud pública global y representa un gran reto el control de la infección para los países de Suramérica. Al 24 de junio de 2020 un total de 1.866.090 casos han sido detectados en la región y en el caso particular de Venezuela un total de 4.365 casos. El rápido incremento en el número de casos y la alta tasa de contagios asociado con el virus han llevado al desarrollo de distintas aproximaciones matemáticas, tales como: modelos SIR, SEIR, redes neuronales y regresiones lineales que permitan predecir la probable evolución de la epidemia. Los modelos ARIMA han sido empleados con éxito en otras infecciones como influenza, malaria, SARS, entre otras. Los resultados de las estimaciones realizadas empleando estos modelos muestran que aún en la región hacen falta mayores esfuerzos que conlleven al control de la epidemia(AU)

The main objective of this work is to use ARIMA models for the estimation of new contagions using public data available for Venezuela and the South American region, currently the main focus of a second COVID19 outbreak. A 30-day prediction is made for the num-ber of Covid-19 cases in South American countries using available public data. ARIMA models were used to estimate the impact of new contagions on infection dynamics for South America Since the appearance of the first case of the new Covid-19 pneumonia in China, which has become a global public health problem and the great challenge that the infection has represented for the countries of South America to June 24, 2020, a total of 1,866,090 cases have been detected and in the particular case of Venezuela a total of 4,365 cases have been detected for the same date. The rapid increase in the number of cases and the high rate of contagion associated with the virus have led to the development of different mathematical approaches, such as: SIR, SEIR models, neural networks and linear regressions that allow predicting the probable evolution of the epidemic. The ARIMA model has been successfully used in other infections such as influenza, malaria, SARS, among others. In the following work, the 30 - day prediction of the number of Covid-19 cases in South American countries is made using public data available. The results of the estimates made using these models show that even in the region, greater efforts are needed to control the epidemic(AU)

Estruturas fetais e suas correlações com a predição do dia antes do parto em raças de cães miniaturas / Fetal structures and their correlations with a prediction of the parturition date in the miniature canine breeds

Avaliou-se a correlação entre estruturas fetais e extrafetais com a predição do dia antes do parto (DAP) em raças de cães miniaturas. Para isso, realizou-se um experimento, utilizando-se 12 cadelas, com peso corporal entre 3,0kg e 5,0kg, sendo seis da raça Chihuahua, duas da raça Shih-Tzu, duas da raça Spitz Alemão e duas da raça Yorkshire. Foram mensurados, por meio da ultrassonografia, diâmetro biparietal (DBP), diâmetro torácico (DTX), diâmetro abdominal (DAB), comprimento craniocaudal (CCC), diâmetro da cavidade coriônica interna (DCI) e espessura da placenta (EP), a partir do 15º dia após a última monta. Foram estudadas as correlações simples e a significância dos coeficientes de regressão linear simples e o coeficiente de determinação (R), com nível de significância estabelecido em P<0,05. Entre os parâmetros avaliados, DBP, DTX, DAB e CCC foram os mais correlacionados com tempo gestacional, podendo ser utilizados para prever dia antes do parto em cadelas de raças miniaturas.(AU)

The correlation between fetal and extra-fetal structures with the pre-delivery prediction (DAP) in miniature dog breeds was evaluated. For this, an experiment was carried out using 12 bitches, with body weight between 3.0kg and 5.0kg, being 6 Chihuahua, 2 Shih-Tzu, 2 German Spitz and 2 Yorkshire breed. The Biparietal Diameter (BD), Thoracic Diameter (TD), Abdominal Diameter (AD), Crown-rump length (CRL), Internal Chorionic Cavity Diameter (ICD) and Placenta Thickness (PT) were measured by ultrasonography from the 15th day after the last mating. The simple correlations and significance of simple linear regression coefficients and the coefficient of determination (R) were studied, with a significance level of P<0.05. BD, T, AD and CRL were the most correlated with gestational time, and can be used to predict day before delivery in miniature breed bitches.(AU)

Avaliação do modelo NRC para predição do consumo de matéria seca por vacas leiteiras manejadas em pastos tropicais / NCR Model Evaluation for prediction of dry matter intake by dairy cows managed in tropical pastures

Objetivou-se avaliar o poder preditivo do modelo do National Research Council (NRC) para gado leiteiro em estimar o consumo de matéria seca (CMS) por vacas mestiças, em pastagens tropicais. Foi efetuada uma análise conjunta de cinco estudos, contemplando três forrageiras. Foram avaliadas 132 estimativas individuais do CMS observado (CMSObs), obtidas por meio do indicador externo Cr2O3. O CMS também foi predito por meio do software do NRC (CMSPred), que, por sua vez, foi abastecido com inputs referentes aos animais e ao ambiente de criação. Os valores de CMSPred (12,7±1,6kg/d) foram semelhantes aos de CMSObs (12,3±3,3kg/d). Foram obtidas as seguintes estimativas da avaliação do poder preditivo do modelo: viés médio (-0,419kg/d), coeficiente de determinação (0,029), coeficiente de correlação (0,17; P=,051), quadrado médio do erro de predição (11,844±20,034), fator de eficiência do modelo (-0,081), coeficiente de determinação do modelo (4,1032) e fator de correção do viés (0,767). A comparação entre CMSObs e CMSPred permitiu identificar a tendência de superestimação das predições se considerado o ajuste por meio de regressão robusta para o modelo linear simples sem intercepto. Nas condições avaliadas, o modelo produz predições de CMS com satisfatória exatidão, porém com baixa precisão.(AU)

The aim of the present study was to evaluate the predictive power of estimating the dry matter intake (DMI) of crossbred cows on tropical pastures by the National Research Council (NRC) equation for dairy cattle. A joint analysis of five studies covering three forages was performed in which 132 individual estimates of observed DMI obtained through Cr2O3 as a marker. DMI was also predicted from the NRC (DMIPred) software with inputs concerning animals and breeding environment of the studies used. Predicted DMIPred average values (12.7±1.6kg/d) were similar to the observed DMIObs ones (12.3±3.3kg/d). We obtained the following estimates of the evaluation of the predictive power of the model: average bias (- 0.419kg/d), coefficient of determination (0.029), Person's correlation coefficient (0.17, P= 0.051), mean square error of prediction (11,844±20,034), model efficiency factor (- 0.081), coefficient of determination (4.1032), and bias correction factor (0.767). The comparison between DMIObs and DMIPred values allowed the identification of the overestimating tendency of the predictions demonstrated by the robust regression fit of the simple linear no intercept model. Nevertheless, the model yields predictions with satisfactory accuracy, but with low precision.(AU)

Una vía para la predicción de una laringoscopia anatómicamente difícil / A way to predict an anatomically difficult laryngoscopy / Uma maneira de prever uma laringoscopia anatomicamente difícil

RESUMEN Introducción: En la valoración de dificultad para realizar la laringoscopia convencional no se realza la integración necesaria de aspectos clínicos esenciales relacionados con el control respiratorio. Objetivo: Validar un modelo de predicción de una laringoscopia anatómicamente difícil en el paciente que requiere de intubación orotraqueal. Método: Se realizó un estudio analítico en una población de 17 966 pacientes con necesidad de laringoscopia directa para una intubación orotraqueal con fines quirúrgicos en el Hospital General Docente "Dr. Agostinho Neto" de Guantánamo entre el 2015 y el 2018. Se determinó por muestreo aleatorizado una muestra de 17 068 pacientes. Se estudiaron las siguientes variables: estigma periférico para laringoscopia difícil, laringoscopia difícil pos-inducción anestésico, evaluación laringoscópica según Cormack-Lehane, valor diagnóstico del modelo de evaluación predictiva para laringoscopia. Resultados: Los altos grados en la clasificación de aspectos clínicos predictivos y la coexistencia con la alteración morfológica de la epiglotis fueron los marcadores más asociados con la probabilidad de laringoscopia anatómicamente difícil. Con la integración de cuatros aspectos clínicos esenciales se identificó el grado de dificultad probable para visualizar las cuerdas vocales. Conclusiones: Se diseñó un modelo que posibilitó la predicción de una laringoscopia anatómicamente difícil, cuya validación certificó su viabilidad para aplicarlo en la práctica médica.

ABSTRACT Introduction: In assessing the difficulty of performing conventional laryngoscopy, the necessary integration of essential clinical aspects related to respiratory control is not enhanced. Objective: To validate a prediction model of an anatomically difficult laryngoscopy in the patient that requires orotracheal intubation. Method: An analytical study was carried out in a population of 17,966 patients in need of direct laryngoscopy for an orotracheal intubation for surgical purposes at the General Teaching Hospital "Dr. Agostinho Neto" from Guantanamo between 2015 and 2018. A sample of 17,068 patients was determined by randomized sampling. The following variables were studied: peripheral stigma for difficult laryngoscopy, difficult laryngoscopy after anesthetic induction, laryngoscopic evaluation according to Cormack-Lehane, diagnostic value of the predictive evaluation model for laryngoscopy. Results: The high degrees in the classification of predictive clinical aspects and the coexistence with the morphological alteration of the epiglottis were the markers most associated with the probability of anatomically difficult laryngoscopy. With the integration of four essential clinical aspects, the degree of probable difficulty in visualizing the vocal cords was identified. Conclusions: A model was designed that allowed the prediction of an anatomically difficult laryngoscopy, whose validation certified its feasibility to apply it in medical practice.

RESUMO Introdução: Na avaliação da dificuldade na realização da laringoscopia convencional, a integração necessária dos aspectos clínicos essenciais relacionados ao controle respiratório não é aprimorada. Objetivo: Validar um modelo de previsão de uma laringoscopia anatomicamente difícil no paciente que necessita de intubação orotraqueal. Método: Foi realizado um estudo analítico em uma população de 17.966 pacientes com necessidade de laringoscopia direta para intubação orotraqueal para fins cirúrgicos no Hospital Geral de Ensino "Dr. Agostinho Neto" de Guantánamo entre 2015 e 2018. Uma amostra de 17.068 pacientes foi determinada por amostragem aleatória. Foram estudadas as seguintes variáveis: estigma periférico para laringoscopia difícil, laringoscopia difícil após indução anestésica, avaliação laringoscópica segundo Cormack-Lehane, valor diagnóstico do modelo de avaliação preditiva para laringoscopia. Resultados: Os altos graus na classificação dos aspectos clínicos preditivos e a coexistência com a alteração morfológica da epiglote foram os marcadores mais associados à probabilidade de laringoscopia anatomicamente difícil. Com a integração de quatro aspectos clínicos essenciais, foi identificado o grau de provável dificuldade na visualização das cordas vocais. Conclusões: Foi elaborado um modelo que permitia prever uma laringoscopia anatomicamente difícil, cuja validação atestava sua viabilidade de aplicá-la na prática médica.

Projeção de internações em terapia intensiva pela COVID-19 no Distrito Federal, Brasil: uma análise do impacto das medidas de distanciamento social / Proyección de hospitalizaciones en cuidados intensivos por COVID-19 en el Distrito Federal, Brasil: un análisis del impacto de las medidas de distanciamiento social / Projection of COVID-19 intensive care hospitalizations in the Federal District, Brazil: an analysis of the impact of social distancing measures

Objetivo: Construir cenários e analisar o impacto das políticas de distanciamento social na propagação da COVID-19 e a necessidade de leitos de unidades de terapia intensiva (UTI). Métodos: Sobre modelo compartimental de transição dinâmica e simulações de Monte Carlo, construíram-se três cenários de propagação conforme o nível de adesão às medidas de distanciamento social no Distrito Federal, Brasil. Os valores dos parâmetros do modelo fundamentaram-se em fontes oficiais, bases com indexação bibliográfica e repositórios públicos de dados. Resultados: O cenário favorável, com manutenção constante de 58% de adesão ao distanciamento social, estimou pico de 189 (intervalo interquartil [IIQ]: 57 a 394) internações-UTI em 7/3/2021. A ausência do distanciamento implicaria grave cenário, com pico de 6.214 (IIQ: 4.618 a 8.415) internações-UTI já na data provável de 14/7/2020. Conclusão: as projeções indicam alto impacto das medidas de distanciamento social e reforçam a aplicabilidade de indicadores públicos no monitoramento da COVID-19.

Objetivo: Construir escenarios y analizar el impacto de las políticas de distanciamiento social en la propagación de Covid-19 y la necesidad de camas en unidades de cuidados intensivos (UCI). Métodos: Con un modelo compartimental de transición dinámica y simulaciones de Monte Carlo, los escenarios de propagación se construyeron de acuerdo al nivel de adhesión de las medidas de distanciamiento social en el Distrito Federal, Brasil. Los parámetros se basaron en fuentes oficiales, bases de datos indexadas y repositorios de datos. Resultados: La adhesión al nivel de distanciamiento social con manutención constante de 58% fue el único escenario favorable, con un pico de 189 (intervalo intercuartil IIC: 57 a 394) admisiones en la UCI el 7/3/2021. La ausencia de distanciamiento implicaría en grave escenario, con un pico de 6.214 (IIC: 4.618 a 8.415) admisiones en UCI ya en la fecha probable de 14/7/2020. Conclusión: Las proyecciones muestran el alto impacto de las medidas de distanciamiento social y la aplicabilidad de indicadores públicos en el monitoreo.

Objective: To build scenarios and analyze the impact of social distancing policies on the spread of COVID-19 and the need for intensive care unit beds. Methods: Three dissemination scenarios were built according to level of adherence to social distancing measures in the context of Brazil's Federal District, based on a dynamic transition compartmental model and Monte Carlo simulations. The model's parameter values were based on official sources, indexed bibliographic databases and public data repositories. Results: The favorable scenario, with constant 58% adherence to social distancing, estimated a peak of 189 (interquartile range [IQR]: 57 - 394) ICU hospitalizations on March 3rd2021. Absence of social distancing would result in an unfavorable scenario with a peak of 6,214 (IQR: 4,618 - 8,415) ICU hospitalizations probably as soon as July 14th2020. Conclusion: The projections indicate the high impact of social distancing measures and emphasize the applicability of public indicators for COVID-19 monitoring.

Short-term forecasting of daily COVID-19 cases in Brazil by using the Holts model

Abstract: INTRODUCTION: We evaluated the performance of the Holt's model to forecast the daily COVID-19 reported cases in Brazil and three Brazilian states. METHODS: We chose the date of the first COVID-19 case to April 25, 2020, as the training period, and April 26 to May 3, 2020, as the test period. RESULTS: The Holt's model performed well in forecasting the cases in Brazil and in São Paulo and Minas Gerais states, but the forecasts were underestimated in Rio de Janeiro state. Conclusions: The Holt's model can be an adequate short-term forecasting method if their assumptions are adequately verified and validated by experts.

Criação de questionário e modelo de rastreamento de lipedema / Development of a questionnaire and screening model for lipedema

Resumo Contexto O lipedema é muito subdiagnosticado e faltam ferramentas auxiliares diagnósticas de baixo custo. Baseado em um questionário de avaliação sintomática, criamos e validamos um questionário de rastreamento do lipedema. Objetivos Os objetivos do trabalho foram a identificação de perguntas clínicas relevantes, a elaboração de questionário de rastreamento e a criação de modelo de predição do lipedema. Métodos Um questionário simplificado foi criado e aplicado em um grupo de pacientes com e sem lipedema, sendo avaliada a probabilidade de acerto no diagnóstico. Resultados Os 109 pacientes que responderam ao questionário eram do sexo feminino e as questões foram compreendidas. O modelo preditivo com perguntas individuais mostrou excelente probabilidade de acerto, de 91,2%, e o modelo preditivo com somatória de pontos também teve boa probabilidade de acerto, de 86,15%. Conclusões O questionário de rastreamento do lipedema é um instrumento prático, de fácil e rápida aplicação, que pode ser utilizado em nossa população para a identificação de possíveis pacientes com lipedema, aumentando o nível de suspeição no momento da anamnese e exame físico.

Abstract Background Lipedema is greatly underdiagnosed and there is a lack of low-cost tools to facilitate diagnostic. We created a lipedema screening questionnaire based on a questionnaire for assessing symptoms. Objectives The study objectives were to identify relevant clinical questions, develop a screening questionnaire, and construct a model for predicting lipedema. Method A simplified questionnaire was constructed and administered to a sample of patients with and without lipedema and then the probability of correct diagnosis was analyzed. Results All 109 patients who answered the questionnaire were female and all of them understood the questions. A predictive model using individual question scores achieved an excellent probability of correct diagnosis, at 91.2%, and a predictive model based on total score also achieved a good probability of correct diagnosis, at 86.15%. Conclusions The lipedema screening questionnaire is a practical instrument that is quick and easy to administer and can be used with our population for identification of possible lipedema patients, raising the level of suspicion when taking a patient's history and conducting a physical examination.

The future is coming: promising perspectives regarding the use of machine learning in renal transplantation / O futuro está chegando: perspectivas promissoras sobre o uso de machine learning no transplante renal

Abstract Introduction: The prediction of post transplantation outcomes is clinically important and involves several problems. The current prediction models based on standard statistics are very complex, difficult to validate and do not provide accurate prediction. Machine learning, a statistical technique that allows the computer to make future predictions using previous experiences, is beginning to be used in order to solve these issues. In the field of kidney transplantation, computational forecasting use has been reported in prediction of chronic allograft rejection, delayed graft function, and graft survival. This paper describes machine learning principles and steps to make a prediction and performs a brief analysis of the most recent applications of its application in literature. Discussion: There is compelling evidence that machine learning approaches based on donor and recipient data are better in providing improved prognosis of graft outcomes than traditional analysis. The immediate expectations that emerge from this new prediction modelling technique are that it will generate better clinical decisions based on dynamic and local practice data and optimize organ allocation as well as post transplantation care management. Despite the promising results, there is no substantial number of studies yet to determine feasibility of its application in a clinical setting. Conclusion: The way we deal with storage data in electronic health records will radically change in the coming years and machine learning will be part of clinical daily routine, whether to predict clinical outcomes or suggest diagnosis based on institutional experience.

Resumo Introdução: A predição de resultados pós-transplante é clinicamente importante e envolve vários problemas. Os atuais modelos de previsão baseados em padrões estatísticos são muito complexos, difíceis de validar e não fornecem previsões precisas. Machine Learning, é uma técnica estatística que permite que o computador faça previsões futuras usando experiências anteriores, está começando a ser usada para resolver essas questões. No campo do transplante renal, o uso da previsão computacional foi relatado na predição de rejeição crônica de aloenxerto, função tardia do enxerto e sobrevida do enxerto. Este artigo descreve os princípios e etapas de machine learning para fazer uma previsão e realiza uma breve análise das aplicações mais recentes de seu uso na literatura. Discussão: Existem evidências convincentes de que as abordagens de machine learning baseadas nos dados do doador e do receptor são melhores para proporcionar melhor prognóstico dos resultados do enxerto do que a análise tradicional. As expectativas imediatas que emergem dessa nova técnica de modelagem de previsão são que ela gerará melhores decisões clínicas baseadas em dados de práticas dinâmicas e locais e aperfeiçoará a alocação de órgãos, bem como o gerenciamento de cuidados pós-transplante. Apesar dos resultados promissores, ainda não há um número substancial de estudos para determinar a viabilidade de sua aplicação em um cenário clínico. Conclusão: A forma como lidamos com dados de armazenamento em prontuários eletrônicos de saúde mudará radicalmente nos próximos anos e a machine learning fará parte da rotina clínica diária, seja para prever resultados clínicos ou sugerir um diagnóstico baseado na experiência institucional.

Sistema para medición y predicción de la intensión de movimiento / System for measurement and prediction of motion intention

En la actualidad, los dispositivos de asistencia para el movimiento humano como exoesqueletos se utilizan ampliamente para resolver problemas ergonómicos en tareas como el trabajo repetitivo, la rehabilitación, etc., esto permite mantener o mejorar el nivel de calidad de vida del usuario lo que permite nuevos movimientos o reduce la fatiga al final de un día de trabajo. El estudio y desarrollo de estos exoesqueletos requiere en gran medida parámetros externos (condiciones de operación y propósito) y parámetros internos del movimiento. Estos requisitos y características son aspectos fundamentales para detectar qué tipo de acción desea realizar en el proceso de movimiento del cuerpo. El control de los exoesqueletos que se utilizan en la actualidad se suele realizar manualmente o la reacción al movimiento detectado, causando problemas de demoras en la realización del movimiento o la incomodidad de llevar a cabo el mismo, por lo que hoy por hoy se realizan estudios para identifique de manera fiel la acción que el usuario intenta realizar y apoye el movimiento desde antes de que comenzara. El objetivo del proyecto es identificar de la intensión de movimiento de personas mediante señales de electroencefalografía y electromiografía de superficie como punto de partida para futuros métodos de control de exoesqueletos. Como resultado del estudio, se obtuvo el diseño y la implementación de un sistema para obtener, procesar e identificar señales electrofisiológicas para predecir la intención de movimiento de los miembros inferiores con porcentajes de aciertos superiores a 86,66 por ciento(AU)

At present, assistive devices for human movement such as exoskeletons are widely used to solve ergonomic problems in tasks such as repetitive work, rehabilitation, etc., this allows maintaining or improving the level of quality of life of the user which allows new movements or reduces fatigue at the end of a work day. The study and development of these exoskeletons largely requires external parameters (operating conditions and purpose) and internal movement parameters. These requirements and characteristics are fundamental aspects to detect what kind of action you want to perform in the process of body movement. The control of the exoskeletons that are currently used is usually done manually or the reaction to the movement detected, causing problems of delays in the realization of the movement or the discomfort of carrying out the movement, so studies are currently carried out to faithfully identify the action that the user tries to perform and support the movement from before it began. The objective of the project is to identify the intention of movement of people by means of electroencephalography and surface electromyography signals as a starting point for future exoskeleton control methods. As a result of the study, the design and implementation of a system was obtained to obtain, process and identify electrophysiological signals to predict the intention of movement of the lower limbs with success rates greater than 86.66 percent(AU)

Actualización del modelo predictivo SEGRAV 23, intervenciones diagnósticas terapéuticas de mayor riesgo / Updating the predictive model SEGRAV 23, higher risk diagnostic and therapeutic interventions

Introducción: los modelos predictivos constituyen herramienta importante en cuidados intensivos. La escala SEGRAV 23 ha mostrado su validez para establecer pronóstico en pacientes pediátricos. Objetivo: determinar intervenciones de mayor riesgo del SEGRAV 23. Métodos: estudio observacional, analítico, de cohorte retrospectivo, en el cual se aplicó el modelo SEGRAV 23 en pacientes con neumonía adquirida en la comunidad, en la Unidad de Cuidados Intensivos Pediátricos del Hospital Militar Central Dr. Luis Díaz Soto , durante cinco años (2007-2008, 2012-2014). La muestra fue de 356 pacientes. Se calculó chi cuadrado de ajuste, se comprobó independencia a través de chi cuadrado de Pearson y prueba exacta de Fisher, con nivel de significación estadística p< 0,05. Se descartaron variables no puntuables y las de menor influencia en categoría fallecidos (p> 0,05). Se calculó odds ratio (OR) con intervalo de confianza (IC) de 95 por ciento para determinar riesgo. Resultados: la mortalidad fue 2,53 por ciento (356 ingresos/9 fallecidos), los pacientes no graves predominaron (222/62,4 por ciento; p< 0,05). Entre los muy graves (12/3,4 por ciento) y críticos (9/2,5 por ciento) estuvieron todos los fallecidos. Una vía venosa central (71/19,9 por ciento y tratamiento de trastornos hidroelectrolíticos severos (63/17,7 por ciento) fueron más frecuentes. El doppler transcraneal, la nutrición parenteral total y el tratamiento de la coagulación intravascular diseminada, no puntuaron. Realización de tomografía, una vía venosa central, intervención quirúrgica y pleurotomía mostraron relación poco significativa con mortalidad (p> 0,05). La realización de reanimación cardiopulmonar (OR= 1 380; IC 95 por ciento [113,198-16 823,63]) y uso de FiO2≥ de 60 por ciento (OR= 454,67; IC 95 por ciento [48,89-4 228,57]) presentaron mayor riesgo. Conclusiones: de las 23 intervenciones diagnósticas y terapéuticas del SEGRAV 23, se determinaron 15 asociadas a mayor riesgo de mortalidad(AU)

Introduction: predictive models are an important tool in intensive care. The SEGRAV 23 scale has proven to be useful to establish a prognosis in pediatric patients. Objective: determine SEGRAV 23 higher risk interventions. Methods: an observational analytical retrospective cohort study based on application of the SEGRAV 23 model was conducted with community-acquired pneumonia patients at the Pediatric Intensive Care Unit of Dr. Luis Díaz Soto Central Military Hospital during five years (2007-2008, 2012-2014). The sample consisted of 356 patients. Adjustment chi square was estimated, and independence verified by Pearson's chi-squared test and Fisher's exact test, with a statistical significance level of p< 0.05. Nonpoint variables and those with a lesser influence on the deceased category (p> 0.05) were discarded. Odds ratio (OR) was estimated with a confidence interval (CI) of 95 percent to determine risk. Results: mortality was 2.53 percent (356 admissions/9 deaths), with a predominance of non-critical patients (222/62.4 percent; p< 0.05). All the deaths were among very critical (12/3.4 percent) and critical (9/2.5 percent) patients. The most frequent procedures were one central venous route (71/19.9 percent) and treatment for severe hydroelectrolitic disorders (63/17.7 percent). Transcranial Doppler, total parenteral nutrition, and the treatment for disseminated intravascular coagulation did not score. Tomography, one central venous route, surgery and pleurotomy exhibited a not very significant relationship to mortality (p> 0.05). Cardiopulmonary resuscitation (OR= 1 380; CI 95 percent [113.198-16 823.63]) and the use of FiO2≥ 60 percent (OR= 454.67; IC 95 percent [48.89-4 228.57]) displayed higher risk. Conclusions: of the 23 SEGRAV 23 diagnostic and therapeutic interventions, 15 were found to be associated with a higher risk of mortality(AU)