Search

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. [ABSTRACT FROM AUTHOR]

There is a lack of information on house dust mite (HDM) sensitization and phenotype distribution in patients with severe asthma (SA) living permanently at high-altitude (HA) in tropical regions, which may be different. The aim of this study was to characterize adults with SA in a tropical high altitude city (2,640 m): Bogotá, Colombia. This observational cross-sectional study included severe asthmatic outpatients (n = 129) referred to the ASMAIRE program of the Fundación Neumológica Colombiana in Bogotá (2,640 m). Clinical history, spirometry, total IgE, blood eosinophils, and skin prick test (SPT), including HDM allergens, were performed. Phenotype definitions: Allergic/atopic (AA): IgE ≥100 IU/mL and/or at least one positive SPT; eosinophilic (EOS): blood eosinophils ≥300 cells/µL; type 2-high: AA and/or EOS phenotype; type 2-low: non-AA/non-EOS phenotype (IgE <100 IU/mL, negative SPT, and blood eosinophils <300 cells/µL). A total of 129 adults with SA were included, 79.8% female. Phenotype distribution: AA: 61.2%; EOS: 37.2%; type 2-high: 72.1%; type 2-low: 27.9%. Among AA patients, HDM sensitization was present in 87% and 34.9% were non-eosinophilic. There was a significant overlap between the phenotypes. In contrast to non-tropical high-altitude regions, we found a high frequency of HDM sensitization in patients with AA phenotype living in a tropical high-altitude city. We also found a discrete lower frequency of EOS phenotype with no other significant differences in the phenotypic distribution compared to that described at low altitudes. We propose that tropical location may modify the effect of high altitude on HDM concentrations and allergenicity. [ABSTRACT FROM AUTHOR]

Introduction: Impulse oscillometry (IOS) is used to measure airway impedance. It is an effective tool for diagnosing and treating respiratory diseases, and it has the advantage that it does not require forced respiratory maneuvers. IOS reference values are required for each population group. Objective: This study aimed to determine the IOS reference values and bronchodilator response in healthy preschool children living in Bogotá, Colombia. Methods: We performed a cross-sectional study in preschool children who had no history of respiratory disease; 96 children fit the parameters for testing to determine normal values according to the American Thoracic Society and European Respiratory Society criteria. Results: Values for respiratory resistance (Rrs) and reactance (Xrs) at 5, 10, and 20 Hz, respiratory impedance (Zrs, and resonance frequency (Fres) were established. Height was the most influential independent variable for IOS values; an increase in height led to a reduction in Rrs5 and Rrs20 and an increase in Xrs5. After the administration of 400 mcg of salbutamol the values for Rrs5(−17.48%), Rrs20(−8.63%), Fres (−10.68%), and area of reactance (−35.44%) were reduced, meanwhile Xrs5 (15.35%) was increased. Conclusions: Normal IOS values before and after the administration of 400 mcg of salbutamol were determined for a population of children aged 3–5 years at 2,640 m. Reference IOS equations for these children are presented. A relative change of up to −28% and 36% after the use of salbutamol for respiratory resistance and reactance, respectively, should be considered as an upper limit of the normal range, and possible appropriate cut-off values for defining significant response for evaluating therapeutic interventions. [ABSTRACT FROM AUTHOR]