Bertsimas, DimitrisLukin, GalitMingardi, LucaNohadani, OmidOrfanoudaki, AgniStellato, BartolomeoWiberg, HollyGonzalez-Garcia, SaraParra-Calderón, Carlos LuisRobinson, KennethSchneider, MichelleStein, BarryEstirado, AlbertoA Beccara, LiaCanino, RosarioDal Bello, MartinaPezzetti, FedericaPan, Angelo2021-12-282021-12-282020-12-09Bertsimas D, Lukin G, Mingardi L, Nohadani O, Orfanoudaki A, Stellato B, et al. COVID-19 mortality risk assessment: An international multi-center study. PLoS One. 2020 Dec 9;15(12):e0243262.http://hdl.handle.net/10668/3440Timely identification of COVID-19 patients at high risk of mortality can significantly improve patient management and resource allocation within hospitals. This study seeks to develop and validate a data-driven personalized mortality risk calculator for hospitalized COVID-19 patients. De-identified data was obtained for 3,927 COVID-19 positive patients from six independent centers, comprising 33 different hospitals. Demographic, clinical, and laboratory variables were collected at hospital admission. The COVID-19 Mortality Risk (CMR) tool was developed using the XGBoost algorithm to predict mortality. Its discrimination performance was subsequently evaluated on three validation cohorts. The derivation cohort of 3,062 patients has an observed mortality rate of 26.84%. Increased age, decreased oxygen saturation (≤ 93%), elevated levels of C-reactive protein (≥ 130 mg/L), blood urea nitrogen (≥ 18 mg/dL), and blood creatinine (≥ 1.2 mg/dL) were identified as primary risk factors, validating clinical findings. The model obtains out-of-sample AUCs of 0.90 (95% CI, 0.87-0.94) on the derivation cohort. In the validation cohorts, the model obtains AUCs of 0.92 (95% CI, 0.88-0.95) on Seville patients, 0.87 (95% CI, 0.84-0.91) on Hellenic COVID-19 Study Group patients, and 0.81 (95% CI, 0.76-0.85) on Hartford Hospital patients. The CMR tool is available as an online application at covidanalytics.io/mortality_calculator and is currently in clinical use. The CMR model leverages machine learning to generate accurate mortality predictions using commonly available clinical features. This is the first risk score trained and validated on a cohort of COVID-19 patients from Europe and the United States.enAtribución 4.0 InternacionalAtribución 4.0 Internacionalhttp://creativecommons.org/licenses/by/4.0/http://creativecommons.org/licenses/by/4.0/COVID-19Hospital mortalityAged, 80 and overAgedEuropeUnited StatesMortalidad hospitalariaAnciano de 80 o más añosAncianosFactores de riesgoEstados UnidosEuropaMedical Subject Headings::Persons::Persons::Age Groups::Adult::AgedMedical Subject Headings::Persons::Persons::Age Groups::Adult::Aged::Aged, 80 and overMedical Subject Headings::Diseases::Virus Diseases::RNA Virus Infections::Nidovirales Infections::Coronaviridae Infections::Coronavirus InfectionsMedical Subject Headings::Geographical Locations::Geographic Locations::EuropeMedical Subject Headings::Check Tags::MaleMedical Subject Headings::Persons::Persons::Age Groups::Adult::Middle AgedMedical Subject Headings::Health Care::Environment and Public Health::Public Health::Epidemiologic Measurements::Risk AssessmentMedical Subject Headings::Health Care::Environment and Public Health::Public Health::Epidemiologic Factors::Causality::Risk FactorsMedical Subject Headings::Geographical Locations::Geographic Locations::Americas::North America::United StatesMedical Subject Headings::Phenomena and Processes::Mathematical Concepts::AlgorithmsMedical Subject Headings::Health Care::Population Characteristics::Demography::Vital Statistics::Mortality::Hospital MortalityMedical Subject Headings::Analytical, Diagnostic and Therapeutic Techniques and Equipment::Investigative Techniques::Models, Theoretical::Models, Biologicalresearch article33296405Acceso abierto10.1371/journal.pone.02432621932-6203PMC7725386