The PANDEMYC Score. An Easily Applicable and Interpretable Model for Predicting Mortality Associated With COVID-19.

Juan Torres-Macho,Mario Pérez-Butragueño,Daniel Velez-Serrano,Pablo Ryan,Marta Alvarado,Eva Jiménez,Salvador Resino,Inés Fernandez-Jimenez,Elena Álvaro-Alonso,Helena Notario,Jorge Valencia,Elsa Izquierdo-García,Alejandro Meca,Andrea Lazaro,Mario Fontán-Vela

doi:10.3390/jcm9103066

Abstract

This study aimed to build an easily applicable prognostic model based on routine clinical, radiological, and laboratory data available at admission, to predict mortality in coronavirus 19 disease (COVID-19) hospitalized patients. Methods: We retrospectively collected clinical information from 1968 patients admitted to a hospital. We built a predictive score based on a logistic regression model in which explicative variables were discretized using classification trees that facilitated the identification of the optimal sections in order to predict inpatient mortality in patients admitted with COVID-19. These sections were translated into a score indicating the probability of a patient’s death, thus making the results easy to interpret. Results. Median age was 67 years, 1104 patients (56.4%) were male, and 325 (16.5%) died during hospitalization. Our final model identified nine key features: age, oxygen saturation, smoking, serum creatinine, lymphocytes, hemoglobin, platelets, C-reactive protein, and sodium at admission. The discrimination of the model was excellent in the training, validation, and test samples (AUC: 0.865, 0.808, and 0.883, respectively). We constructed a prognostic scale to determine the probability of death associated with each score. Conclusions: We designed an easily applicable predictive model for early identification of patients at high risk of death due to COVID-19 during hospitalization.

Highlights

Despite substantial efforts to prevent the spread of coronavirus 19 disease (COVID-19), at the end of June 2020 over 14 million people worldwide had tested positive for SARS-CoV-2, and more than 603,000 had died [1]
The study population comprised all patients admitted to hospital with a confirmed diagnosis of COVID-19 based on a positive result in the SARS-CoV-2 reverse transcriptase-polymerase chain reaction assay between 2nd March and 31st May 2020
Several studies have reported risk factors associated with death in patients with COVID-19, very few propose reliable prediction models, which should be constructed using an adequate sample size and a standardized methodology to avoid significant bias [5,11,12,13,14]

Summary

Introduction

Despite substantial efforts to prevent the spread of coronavirus 19 disease (COVID-19), at the end of June 2020 over 14 million people worldwide had tested positive for SARS-CoV-2, and more than 603,000 had died [1]. During March and April 2020, Spain had one of the highest rates of COVID-19 and had experienced one of the most severe outbreaks of the disease worldwide. The wide variation in the symptoms of COVID-19 makes it difficult to predict the clinical course, complicating triage. Clinical experience has demonstrated significant heterogeneity in the course of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection: while some patients are asymptomatic or progress with mild symptoms, others develop severe acute respiratory distress syndrome with multiorgan failure and death [4]. It is very difficult to accurately predict clinical outcomes in patients with such a myriad of clinical presentations

Objectives

Methods

Conclusion