Does Resolution 8430 of 1993 respond to the current needs of ethics in health research with human beings in Colombia?

Prediction of pharmaceutical and non-pharmaceutical expenditures associated with Diabetes Mellitus type II based on clinical risk

OBJECTIVE

To assess the effectiveness of different machine learning models in estimating the pharmaceutical and non-pharmaceutical expenditures associated with Diabetes Mellitus type II diagnosis, based on the clinical risk index determined by the analysis of comorbidities.

MATERIALS AND METHODS

In this cross-sectional study, we have used data from 11,028 anonymized records of patients admitted to a high-complexity hospital in Bogota, Colombia between 2017-2019 with a primary diagnosis of Diabetes. These cases were classified according to Charlson's comorbidity index in several risk categories. The main variables analyzed in this study are hospitalization costs (which include pharmaceutical and non-pharmaceutical expenditures), age, gender, length of stay, medicines and services consumed, and comorbidities assessed by the Charlson's index. The model's dependent variable is expenditure (composed of pharmaceutical and non-pharmaceutical expenditures). Based on these variables, different machine learning models (Multivariate linear regression, Lasso model, and Neural Networks) were used to estimate the pharmaceutical and non-pharmaceutical expenditures associated with the clinical risk classification. To evaluate the performance of these models, different metrics were used: Mean Absolute Percentage Error (MAPE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and Coefficient of Determination (R2).

RESULTS

The results indicate that the Neural Networks model performed better in terms of accuracy in predicting pharmaceutical and non-pharmaceutical expenditures considering the clinical risk based on Charlson's comorbidity index. A deeper understanding and experimentation with Neural Networks can improve these preliminary results, therefore we can also conclude that the main variables used and those that were proposed can be used as predictors for the medical expenditures of patients with diabetes type-II.

CONCLUSIONS

With the increase of technology elements and tools, it is possible to build models that allow decision-makers in hospitals to improve the resource planning process given the accuracy obtained with the different models tested.

Colombian Adolescents’ Perceptions of Violence and Opportunities for Safe Spaces Across Community Settings

During adolescence, access to safe environments is critical for healthy development. This study analyzed adolescents’ perceptions of safety in personal and public spaces in the semi-rural community of Santa Ana, Colombia on the Island of Barú (95.8% of inhabitants live in poverty). We used thematic analysis to explore adolescents’ experiences and reflections to identify the factors influencing their perception of safety across different community spaces. Four gender-segregated focus group discussions were held with 40 adolescents (20 male and 20 female) from ages 13 to 17 ( M = 14.4, SD = 1.2). Most of them self-identified as Black (86%). The more recurrent spaces in the adolescents’ conversations were the streets, the school, the local sports field, individual homes, and commercial sound system parties known as “Picos.” Adolescents perceived the school as the safest space, while the “Picos” were the most unsafe. The other spaces were considered mixed, meaning that their perceived safety shifts and depends on the presence of certain factors. These factors were risky behaviors, group affiliation, designated authority roles and the relevance of time. The authors discuss the importance of addressing the factors that inform adolescents’ safety perception, particularly within low resource settings cross-culturally.

Perfil epidemiológico de la infección por Enterococcus SPP en un hospital regional

Introducción: los enterococos son responsables de múltiples infecciones y por su creciente patrón de resistencia se ha vuelto de interés en el país y en el mundo. Objetivo: caracterizar las infecciones por Enterococcus spp. Metodología: estudio descriptivo, retrospectivo observacional transversal desde enero 2015 hasta enero 2018 en un hospital regional. Resultados: la prevalencia de las infecciones por Enterococcus spp. fue de 0,154%. El E. faecalis fue el más aislado, seguido del E. faecium. La resistencia a ampicilina fue de 19% y a vancomicina de 10%; 32% de los pacientes tuvieron terapia empírica con vancomicina y 22% con piperacilina tazobactam, la mediana de antibioticoterapia fue de 10 días. Discusión: el interés por los Enterococcus spp. se ha incrementado debido a que representan una carga importante en las infecciones asociadas con la atención en salud (IAAS). La mayoría se dan en hombres con una edad mediana de 40 a 60 años, hospitalizados en UCI, con infecciones urinarias y comorbilidades como inmunosupresión y cirugías previas. Conclusión: como ha venido reportándose aumento en las tasas de resistencia a vancomicina y ampicilina, se recomienda el uso responsable de la terapia antibiótica, con la finalidad de erradicar en forma eficaz al patógeno y prevenir nuevas resistencias.