RESUMEN
Patients with COVID-19 may experience multiple conditions (e.g., fever, hyperventilation, anorexia, gastroenteritis, acid-base disorder) that may cause electrolyte imbalances. Hypokalemia is a concerning electrolyte disorder that may increase the susceptibility to various kinds of arrhythmia. This study aimed to estimate prevalence, risk factors and outcome of hypokalemia in a cohort of non-critically ill patients. A retrospective analysis was conducted on 290 hospitalized patients with confirmed COVID-19 infection at the tertiary teaching hospital of Modena, Italy. Hypokalemia (<3.5 mEq/L) was detected in 119 patients (41%). The decrease of serum potassium level was of mild entity (3-3.4 mEq/L) and occurred in association with hypocalcemia (P=0.001) and lower level of serum magnesium (P=0.028) compared to normokaliemic patients. Urine K: creatinine ratio, measured in a small subset of patients (n=45; 36.1%), showed an increase of urinary potassium excretion in the majority of the cases (95.5%). Causes of kaliuria were diuretic therapy (53.4%) and corticosteroids (23.3%). In the remaining patients, urinary potassium loss was associated with normal serum magnesium, low sodium excretion (FENa< 1%) and metabolic alkalosis. Risk factors for hypokalemia were female gender (P=0.002; HR 0.41, 95%CI 0.23-0.73) and diuretic therapy (P=0.027; HR 1.94, 95%CI 1.08-3.48). Hypokalemia, adjusted for sex, age and SOFA score, resulted not associated with ICU admission (P=0.131, 95% CI 0.228-1.212) and in-hospital mortality (P=0.474; 95% CI 0,170-1,324) in our cohort of patients. Hypokalemia is a frequent disorder in COVID-19 patients and urinary potassium loss may be the main cause of hypokalemia. The disorder was mild in the majority of the patients and was unrelated to poor outcomes. Nevertheless, hypokalemic patients required potassium supplements to dampen the risk of arrhythmias.
RESUMEN
AimsThe aim of this study was to estimate a 48 hour prediction of moderate to severe respiratory failure, requiring mechanical ventilation, in hospitalized patients with COVID-19 pneumonia. MethodsThis was an observational study that comprised consecutive patients with COVID-19 pneumonia admitted to hospital from 21 February to 6 April 2020. The patients medical history, demographic, epidemiologic and clinical data were collected in an electronic patient chart. The dataset was used to train predictive models using an established machine learning framework leveraging a hybrid approach where clinical expertise is applied alongside a data-driven analysis. The study outcome was the onset of moderate to severe respiratory failure defined as PaO2/FiO2 ratio <150 mmHg in at least one of two consecutive arterial blood gas analyses in the following 48 hours. Shapley Additive exPlanations values were used to quantify the positive or negative impact of each variable included in each model on the predicted outcome. ResultsA total of 198 patients contributed to generate 1068 usable observations which allowed to build 3 predictive models based respectively on 31-variables signs and symptoms, 39-variables laboratory biomarkers and 91-variables as a composition of the two. A fourth "boosted mixed model" included 20 variables was selected from the model 3, achieved the best predictive performance (AUC=0.84) without worsening the FN rate. Its clinical performance was applied in a narrative case report as an example. ConclusionThis study developed a machine model with 84% prediction accuracy, which is able to assist clinicians in decision making process and contribute to develop new analytics to improve care at high technology readiness levels.