A comparison of two clinical scores for bronchiolitis. A multicentre and prospective study conducted in hospitalised infants.

BACKGROUND: There are a number of clinical scores for bronchiolitis but none of them are firmly recommended in the guidelines. METHOD: We designed a study to compare two scales of bronchiolitis (ESBA and Wood Downes Ferres) and determine which of them better predicts the severity. A multicentre prospective study with patients <12 months with acute bronchiolitis was conducted. Each patient was assessed with the two scales when admission was decided. We created a new variable "severe condition" to determine whether one scale afforded better discrimination of severity. A diagnostic test analysis of sensitivity and specificity was made, with a comparison of the AUC. Based on the optimum cut-off points of the ROC curves for classifying bronchiolitis as severe we calculated new Se, Sp, LR+ and LR- for each scale in our sample. RESULTS: 201 patients were included, 66.7% males and median age 2.3 months (IQR=1.3-4.4). Thirteen patients suffered bronchiolitis considered to be severe, according to the variable severe condition. ESBA showed a Se=3.6%, Sp=98.1%, and WDF showed Se=46.2% and Sp=91.5%. The difference between the two AUC for each scale was 0.02 (95%CI: 0.01-0.15), p=0.72. With new cut-off points we could increase Se and Sp for ESBA: Se=84.6%, Sp=78.7%, and WDF showed Se=92.3% and Sp=54.8%; with higher LR. CONCLUSIONS: None of the scales studied was considered optimum for assessing our patients. With new cut-off points, the scales increased the ability to classify severe infants. New validation studies are needed to prove these new cut-off points.

Mortality predictors in patients with COVID-19 pneumonia: a machine learning approach using eXtreme Gradient Boosting model.

Recently, global health has seen an increase in demand for assistance as a result of the COVID-19 pandemic. This has prompted many researchers to conduct different studies looking for variables that are associated with increased clinical risk, and find effective and safe treatments. Many of these studies have been limited by presenting small samples and a large data set. Using machine learning (ML) techniques we can detect parameters that help us to improve clinical diagnosis, since they are a system for the detection, prediction and treatment of complex data. ML techniques can be valuable for the study of COVID-19, especially because they can uncover complex patterns in large data sets. This retrospective study of 150 hospitalized adult COVID-19 patients, of which we established two groups, those who died were called Case group (n = 53) while the survivors were Control group (n = 98). For analysis, a supervised learning algorithm eXtreme Gradient Boosting (XGBoost) has been used due to its good response compared to other methods because it is highly efficient, flexible and portable. In this study, the response to different treatments has been evaluated and has made it possible to accurately predict which patients have higher mortality using artificial intelligence, obtaining better results compared to other ML methods.

Incidence and Severity of Community- and Hospital-Acquired Hyponatremia in Pediatrics.

Hyponatremia is the most common electrolyte disturbance in hospitalized children, with a reported incidence of 15-30%, but its overall incidence and severity are not well known. The objective of our study was to determine the incidence, severity, and associated risk factors of community- and hospital-acquired hyponatremia on a general pediatric ward. Data of 5550 children admitted from June 2012 to December 2019 on plasma sodium and discharge diagnosis were analyzed by logistic regression model. Clinically relevant diagnostic groups were created. Hyponatremia was classified as mild, moderate, and severe. The incidence of community- and hospital-acquired hyponatremia was 15.8% and 1.4%, respectively. Most of the cases were mild (90.8%) to moderate (8.6%), with only two cases of severe community-acquired hyponatremia. There were no clinical complications in any of the hyponatremic children. Age and diagnosis at discharge were principal factors significantly correlated with hyponatremia. Community-acquired hyponatremia is more common than hospital-acquired hyponatremia in clinical practice. Severe cases of both types are rare. Children from 2 to 11 years of age presenting with infections, cardiovascular disorders, and gastrointestinal disorders are at risk of developing hyponatremia.