A framework for the automatic description of healthcare processes in natural language: Application in an aortic stenosis integrated care process.

In this paper, we propose a framework for the automatic generation of natural language descriptions of healthcare processes using quantitative and qualitative data and medical expert knowledge. Inspired by the demand of novel ways of conveying process mining analysis results of healthcare processes (Rojas et al., 2016), our framework is based on the most widely used Data-To-Text (D2T) pipeline (Reiter, 2007) and on the usage of process mining techniques. Backed by a general model that handles process data, this framework is able to quantify attributes in time during a process life-span, recall temporal relations and waiting times between events and its possible causes and compare case (patient) attributes between groups, among other features. Through integrating fuzzy quantification techniques, our framework is able to represent relevant quantitative process information with some degree of uncertainty present on it and describe it in natural language involving uncertain terms. A real application over the Aortic Stenosis Integrated Care Process of the University Hospital of Santiago de Compostela is presented, showcasing the potential of our framework for providing natural language descriptions of healthcare processes addressed to medical experts. Following the standards of D2T systems, manual human validation was conducted for the generated natural language descriptions by fifteen medical experts in Cardiology. Validation results are very positive, since a global average of 4.07/5.00 was achieved for questions related to understandability, usefulness and impact of the natural language descriptions on the medical experts work. More precisely, results indicate i) that the modality which conveyed the information most efficiently was natural language ii) a very clear preference of texts over the usual graphic representation of process information as the way for conveying information to experts (4.28/5.00), and iii) natural language descriptions provide relevant and useful information about the process, allowing for its improvement.

Auto-reporte de agresividad escolar y factores asociados en escolares peruanos de educación secundaria / Self-report of bullying aggressive and associated factors in high school Peruvian children

El bullying es un problema de salud pública que no está siendo identificado y afrontado con estrategias claras para reducir la ocurrencia del fenómeno. Objetivo: Estimar la prevalencia de auto-reporte de perpetración de agresividad escolar y determinar qué factores se encuentran asociados a dicho fenómeno. Métodos: Realizamos un análisis secundario de los datos del II Estudio Nacional de Prevención y Consumo de Drogas en Estudiantes de Secundaria de Perú en el año 2007. Se midieron variables sociodemográficas y consumo de sustancias: edad, sexo, región, nivel de pobreza, tipo de colegio, estado de unión de los padres, año de estudio, si trabaja además de estudiar y consumo de drogas legales, ilegales y médicas. Además, determinamos la prevalencia de agresividad, en base al auto-reporte de los escolares en 14 situaciones de violencia. Se hizo en análisis descriptivo, bivariado y multivariado para determinar los factores asociados. Resultados: La prevalencia de auto-reporte de agresividad fue de 37.5% y la frecuencia de agresividad severa fue de 10.3%. Los escolares reportan en mayor frecuencia ser perpetradores de agresión verbal (54.4% de casos), siguen en frecuencia la perpetración de agresión física (35.9%), exclusión social (26.7%) y formas mixtas de violencia (12.8%). El consumo de drogas legales e ilegales fueron los factores más fuertemente asociados con la perpetración de las diferentes formas de violencia analizadas, desde un OR ajustado de 1.56 para la violencia verbal con el consumo de drogas ilegales hasta un OR ajustado de 2.59 para las formas mixtas de violencia con el consumo de drogas ilegales también. Conclusiones: La prevalencia de auto-reporte de agresividad escolar en adolescentes peruanos es elevada, similar a la reportada en otros países sudamericanos y mucho mayor a la reportada en Europa y Estados Unidos. Existen diversas variables asociadas a cada uno de los tipos de agresividad...

Bullying is a public health problem that is not being identified and addressed with clear strategies to reduce its occurrence. Objective: To estimate the prevalence of self-reported perpetration of scholar aggressiveness and to determine associated factors to this phenomenon. Methods: We performed a secondary analysis of data from the II National Study of Prevention and Drug Abuse in Secondary Students of Peru in 2007. We measured socio-demographic variables and substance use: age, sex, region, poverty level, type of school, marriage status of parents, year of study, if the student works and use of legal, illegal and medical drugs. In addition, we determined the prevalence of aggression, based on self-report of school children in 14 situations of violence. Descriptive, bivariate and multivariate analysis were made to determine the associated factors. Results: The prevalence of self-reported aggressiveness was 37.5% and the frequency of severe aggressiveness was 10.3%. The students reported themselves most frequently as perpetrators of verbal aggression (54.4% of cases), followed by the perpetration of physical aggression (35.9%), social exclusion (26.7%) and mixed forms of violence (12.8%). The consumption of licit and illicit drugs were the factors most strongly associated with the perpetration of the various forms of violence analyzed, from an adjusted OR of 1.56 for verbal violence for illegal drug use to an adjusted OR of 2.59 for mixed forms of violence with the use of illegal drugs as well. Conclusions: The prevalence of self-reported scholar aggressiveness among Peruvian adolescents is high, similar to reports in other South American countries, but much higher than reports from Europe and the U.S. There are many variables associated with each of the types of aggression. The profile of the school agresor is a 14 to 16 years boy who has consume legal and illegal drugs during last year...