Comparison of machine learning algorithms for clinical event prediction (risk of coronary heart disease).

AIM: The aim of this study is to compare the utility of several supervised machine learning (ML) algorithms for predicting clinical events in terms of their internal validity and accuracy. The results, which were obtained using two statistical software platforms, were also compared. MATERIALS AND METHODS: The data used in this research come from the open database of the Framingham Heart Study, which originated in 1948 in Framingham, Massachusetts as a prospective study of risk factors for cardiovascular disease. Through data mining processes, three data models were elaborated and a comparative methodological study between the different ML algorithms - decision tree, random forest, support vector machines, neural networks, and logistic regression - was carried out. The global selection criterium for choosing the right set of hyperparameters and the type of data manipulation was the area under a curve (AUC). The software tools used to analyze the data were R-Studio® and RapidMiner®. RESULTS: The Framingham study open database contains 4240 observations. The algorithm that yielded the greatest AUC when analyzing the data in R-Studio was neural network applied to a model that excluded all observations in which there was at least one missing value (AUC = 0.71); when analyzing the data in RapidMiner and applying the same model, the best algorithm was support vector machines (AUC = 0.75). CONCLUSIONS: ML algorithms can reinforce the diagnostic and prognostic capacity of traditional regression techniques. Differences between the applicability of those algorithms and the results obtained with them were a function of the software platforms used in the data analysis.

Escuchando la voz de las personas que escuchan voces / Listening to the voice of people who hear voices

El presente estudio pretende explorar los aportes percibidos por los miembros de un grupo de escucha de voces (GEV) que acuden a un Centro de Día para personas con trastorno mental grave. Se ha utilizado una metodología cualitativa realizando entrevistas en profundidad a los participantes. Las experiencias previas que estas personas tuvieron cuando intentaron hablar sobre sus voces fueron generalmente negativas. Los resultados muestran que la participación en el GEV tiene un impacto positivo en la vivencia subjetiva de la persona, refiriendo un mayor control sobre la experiencia, una visión menos negativa de la misma y un menor temor ante la presencia de las voces. El hecho de compartir la experiencia con «iguales» fomenta la esperanza, disminuye el aislamiento y mejora la relación de la persona con sus voces. Los resultados plantean la necesidad de reflexionar sobre el tipo de prácticas que se llevan a cabo en los dispositivos de atención en salud mental y servicios sociales y la filosofía que subyace a las mismas (AU)

This study aims to explore the experiences of a group of participants in a Hearing Voices Group (HVG) who attend a day center for people with severe mental disorder. In-depth, semi-structured interviews were conducted with seven participants. Previous experiences of these people when trying to talk about their voices had generally been negative. The results show that participation in the HVG has had a positive impact on the subjective experience of the person, conferring more control over the experience, a less negative view of it and less fear in the presence of voices. Sharing the experience with «equals» fosters hope, reduces isolation and improves the relationship of the person with their voices. The results suggest the need to reflect on the kind of practices carried out in mental health care and social services centers along with their underlying philosophy (AU)