Smartphones dependency risk analysis using machine-learning predictive models.

Recent technological advances have changed how people interact, run businesses, learn, and use their free time. The advantages and facilities provided by electronic devices have played a major role. On the other hand, extensive use of such technology also has adverse effects on several aspects of human life (e.g., the development of societal sedentary lifestyles and new addictions). Smartphone dependency is new addiction that primarily affects the young population. The consequences may negatively impact mental and physical health (e.g., lack of attention or local pain). Health professionals rely on self-reported subjective information to assess the dependency level, requiring specialists' opinions to diagnose such a dependency. This study proposes a data-driven prediction model for smartphone dependency based on machine learning techniques using an analytical retrospective case-control approach. Different classification methods were applied, including classical and modern machine learning models. Students from a private university in Cali-Colombia (n = 1228) were tested for (i) smartphone dependency, (ii) musculoskeletal symptoms, and (iii) the Risk Factors Questionnaire. Random forest, logistic regression, and support vector machine-based classifiers exhibited the highest prediction accuracy, 76-77%, for smartphone dependency, estimated through the stratified-k-fold cross-validation technique. Results showed that self-reported information provides insight into predicting smartphone dependency correctly. Such an approach opens doors for future research aiming to include objective measures to increase accuracy and help to reduce the negative consequences of this new addiction form.

Estimación de riesgo cardiovascular por mediciones corporales como punto a favor de la atención primaria / Estimation of Cardiovascular Risk Based on Body Measu8rements: A Score Ahead in Primary Care

Introducción: El riesgo cardiovascular es considerado actualmente como uno de los más peligrosos desencadenantes de enfermedades crónicas, ya que es el causante de miles de muertes a nivel mundial. Objetivo: Generar un modelo de regresión logística para una aplicación de escritorio que estime el riesgo cardiovascular por medidas antropométricas y diferentes fórmulas, y así identificar la prevalencia del riesgo cardiovascular en la población objeto de estudio. Métodos: Estudio observacional descriptivo de corte transversal realizado en 169 trabajadores de una institución universitaria del suroccidente colombiano, a los cuales se les tomaron medidas antropométricas de peso, talla y circunferencia de cintura aplicando el protocolo de la Sociedad Internacional de Avances para la Cineantropometría. Además, se aplicó una encuesta estructurada para recolectar datos sociodemográficos. Los datos se analizaron con un paquete estadístico minitab con una descripción univariada para variables cualitativas como frecuencias absolutas y relativas; media y desviación estándar para las cuantitativas. La aplicación de escritorio resultado se realizó con la plataforma JAVA. Resultados: En una población de 93 mujeres y 76 hombres se halló un modelo de regresión logística con las variables cuantitativas predictoras peso y circunferencia de cintura con relación significativa a la variable respuesta riesgo cardiovascular, al igual que la variable cualitativa género. Aplicando el modelo se halló prevalencia de riesgo cardiovascular de 53,85 por ciento en la población laboralmente activa de la institución universitaria. Conclusiones: El riesgo cardiovascular es un fenómeno que cada vez gana más fuerza, y la toma de peso y circunferencia de cintura generan una determinación de este riesgo, hecho que facilitará la prevención y el control de enfermedades cardiovasculares en la atención primaria(AU)

Introduction: Cardiovascular risk is currently considered one of the most dangerous triggers of chronic diseases, as it is the cause of thousands of deaths worldwide. Objective: To create a logistic regression model for a desktop application that estimates cardiovascular risk using anthropometric measures and different formulas, and thus identify the prevalence of cardiovascular risk in the study population. Methods: A descriptive, observational and cross-sectional study was carried out with 169 workers from a university in southwestern Colombia, to whom anthropometric measurements such as weight, height and waist circumference were taken, applying the protocol of the International Society for the Advancement of Kinanthropometry. In addition, a structured survey was applied to collect sociodemographic data. The data were analyzed with a Minitab statistical package, using univariate description for qualitative variables as absolute and relative frequencies, as well as mean and standard deviation for quantitative variables. The resulting desktop application was made with the JAVA platform. Results: In a population of 93 women and 76 men, a logistic regression model was found, using the quantitative predictor variables of weight and waist circumference, significantly related to the cardiovascular risk response variable, as well as the qualitative variable of gender. Applying the model, prevalence of cardiovascular risk was found to be 53.85 percent in the working population of the university institution. Conclusions: Cardiovascular risk is a phenomenon that is gaining more and more strength, while measuring weight and waist circumference is a way for determining such risk, a fact that will facilitate the prevention and control of cardiovascular diseases in the primary care level(AU)