Improving prediction of COVID-19 mortality using machine learning in the Spanish SEMI-COVID-19 registry.

COVID-19 is responsible for high mortality, but robust machine learning-based predictors of mortality are lacking. To generate a model for predicting mortality in patients hospitalized with COVID-19 using Gradient Boosting Decision Trees (GBDT). The Spanish SEMI-COVID-19 registry includes 24,514 pseudo-anonymized cases of patients hospitalized with COVID-19 from 1 February 2020 to 5 December 2021. This registry was used as a GBDT machine learning model, employing the CatBoost and BorutaShap classifier to select the most relevant indicators and generate a mortality prediction model by risk level, ranging from 0 to 1. The model was validated by separating patients according to admission date, using the period 1 February to 31 December 2020 (first and second waves, pre-vaccination period) for training, and 1 January to 30 November 2021 (vaccination period) for the test group. An ensemble of ten models with different random seeds was constructed, separating 80% of the patients for training and 20% from the end of the training period for cross-validation. The area under the receiver operating characteristics curve (AUC) was used as a performance metric. Clinical and laboratory data from 23,983 patients were analyzed. CatBoost mortality prediction models achieved an AUC performance of 84.76 (standard deviation 0.45) for patients in the test group (potentially vaccinated patients not included in model training) using 16 features. The performance of the 16-parameter GBDT model for predicting COVID-19 hospital mortality, although requiring a relatively large number of predictors, shows a high predictive capacity.

Admission hyperglycaemia as a predictor of mortality in patients hospitalized with COVID-19 regardless of diabetes status: data from the Spanish SEMI-COVID-19 Registry.

BACKGROUND: Hyperglycaemia has emerged as an important risk factor for death in coronavirus disease 2019 (COVID-19). The aim of this study was to evaluate the association between blood glucose (BG) levels and in-hospital mortality in non-critically patients hospitalized with COVID-19. METHODS: This is a retrospective multi-centre study involving patients hospitalized in Spain. Patients were categorized into three groups according to admission BG levels: <140 mg/dL, 140-180 mg/dL and >180 mg/dL. The primary endpoint was all-cause in-hospital mortality. RESULTS: Of the 11,312 patients, only 2128 (18.9%) had diabetes and 2289 (20.4%) died during hospitalization. The in-hospital mortality rates were 15.7% (<140 mg/dL), 33.7% (140-180 mg) and 41.1% (>180 mg/dL), p<.001. The cumulative probability of mortality was significantly higher in patients with hyperglycaemia compared to patients with normoglycaemia (log rank, p<.001), independently of pre-existing diabetes. Hyperglycaemia (after adjusting for age, diabetes, hypertension and other confounding factors) was an independent risk factor of mortality (BG >180 mg/dL: HR 1.50; 95% confidence interval (CI): 1.31-1.73) (BG 140-180 mg/dL; HR 1.48; 95%CI: 1.29-1.70). Hyperglycaemia was also associated with requirement for mechanical ventilation, intensive care unit (ICU) admission and mortality. CONCLUSIONS: Admission hyperglycaemia is a strong predictor of all-cause mortality in non-critically hospitalized COVID-19 patients regardless of prior history of diabetes. KEY MESSAGE Admission hyperglycaemia is a stronger and independent risk factor for mortality in COVID-19. Screening for hyperglycaemia, in patients without diabetes, and early treatment of hyperglycaemia should be mandatory in the management of patients hospitalized with COVID-19. Admission hyperglycaemia should not be overlooked in all patients regardless prior history of diabetes.