Predicting critical illness on initial diagnosis of COVID-19 based on easily-obtained clinical variables: development and validation of the PRIORITY model

Martinez-Lacalzada, Miguel; Viteri-Noël, Adrián; Manzano, Luis; Fabregate, Martin; Rubio-Rivas, Manuel; Garcia, Sara Luis; Fernández, Francisco Arnalich; Beato Pérez, José Luis; Vargas Núñez, Juan Antonio; Manuel, Elpidio Calvo; Espiño Álvarez, Alexia Constanza; Freire Castro, Santiago J.; Loureiro-Amigo, Jose; Pesqueira Fontan, Paula Maria; Pina, Adela; Álvarez Suárez, Ana María; Asiain, Andrea Silva; López, Beatriz García; Luque del Pino, Jairo; Cánovas, Jaime Sanz; Pérez, Paloma Chazarra; García García, Gema María; Núñez-Cortés, Jesús Millán; Casas Rojo, José Manuel; Huelgas, Ricardo Gómez

OBJECTIVES: We aimed to develop and validate a prediction model, based on clinical history and examination findings on initial diagnosis of COVID-19, to identify patients at risk of critical outcomes. METHODS: We used data from the SEMI-COVID-19 Registry, a cohort of consecutive patients hospitalized for COVID-19 from 132 centers in Spain (23 March to 21 May, 2020). For the development cohort tertiary referral hospitals were selected, while the validation cohort included smaller hospitals. The primary outcome was a composite of in-hospital death, mechanical ventilation or admission to intensive care unit. Clinical signs and symptoms, demographics, and medical history ascertained at presentation were screened using least absolute shrinkage and selection operator, and logistic regression was used to construct the predictive model. RESULTS: : There were 10,433 patients, 7,850 in the development cohort (primary outcome 25.1%, 1,967/7,850) and 2,583 in the validation cohort (outcome 27.0%, 698/2,583). The PRIORITY model included: age, cardiovascular disease, chronic kidney disease, dyspnea, tachypnea, confusion, systolic blood pressure, and SpO(2)≤93% or oxygen requirement. The model showed high discrimination for critical illness in both the development (C-statistic 0.823; 95% confidence interval [CI] 0.813, 0.834) and validation (C-statistic 0.794; 95% CI 0.775, 0.813) cohorts. A freely available web-based calculator was developed based on this model (https://www.evidencio.com/models/show/2344). CONCLUSIONS: The PRIORITY model, based on easily-obtained clinical information, had good discrimination and generalizability for identifying COVID-19 patients at risk of critical outcomes.