Multivariable mortality risk prediction using machine learning for COVID-19 patients at admission (AICOVID)

Abstract

In Coronavirus disease 2019 (COVID-19), early identification of patients with a high risk of mortality can significantly improve triage, bed allocation, timely management, and possibly, outcome. The study objective is to develop and validate individualized mortality risk scores based on the anonymized clinical and laboratory data at admission and determine the probability of Deaths at 7 and 28 days. Data of 1393 admitted patients (Expired—8.54%) was collected from six Apollo Hospital centers (from April to July 2020) using a standardized template and electronic medical records. 63 Clinical and Laboratory parameters were studied based on the patient’s initial clinical state at admission and laboratory parameters within the first 24 h. The Machine Learning (ML) modelling was performed using eXtreme Gradient Boosting (XGB) Algorithm. ‘Time to event’ using Cox Proportional Hazard Model was used and combined with XGB Algorithm. The prospective validation cohort was selected of 977 patients (Expired—8.3%) from six centers from July to October 2020. The Clinical API for the Algorithm is http://20.44.39.47/covid19v2/page1.php being used prospectively. Out of the 63 clinical and laboratory parameters, Age [adjusted hazard ratio (HR) 2.31; 95% CI 1.52–3.53], Male Gender (HR 1.72, 95% CI 1.06–2.85), Respiratory Distress (HR 1.79, 95% CI 1.32–2.53), Diabetes Mellitus (HR 1.21, 95% CI 0.83–1.77), Chronic Kidney Disease (HR 3.04, 95% CI 1.72–5.38), Coronary Artery Disease (HR 1.56, 95% CI − 0.91 to 2.69), respiratory rate > 24/min (HR 1.54, 95% CI 1.03–2.3), oxygen saturation below 90% (HR 2.84, 95% CI 1.87–4.3), Lymphocyte% in DLC (HR 1.99, 95% CI 1.23–2.32), INR (HR 1.71, 95% CI 1.31–2.13), LDH (HR 4.02, 95% CI 2.66–6.07) and Ferritin (HR 2.48, 95% CI 1.32–4.74) were found to be significant. The performance parameters of the current model is at AUC ROC Score of 0.8685 and Accuracy Score of 96.89. The validation cohort had the AUC of 0.782 and Accuracy of 0.93. The model for Mortality Risk Prediction provides insight into the COVID Clinical and Laboratory Parameters at admission. It is one of the early studies, reflecting on ‘time to event’ at the admission, accurately predicting patient outcomes.

Iron metabolism in infections: Focus on COVID-19

“…In this MLA-based study the discriminant cut-off for ferritin was >450 µg/L, which performed better than well-established clinical risk factors (i.e. age and cardiovascular comorbidities) and other inflammatory parameters like C-Reactive Protein ( 50 ).…”

“…In particular, Ramiro and colleagues showed that patients with ferritin levels higher that the median value of 1,419 µg/L had the better benefit from tocilizumab plus corticosteroids ( 46 ). Despite such robust evidence, ferritin has been rarely incorporated in COVID-19 simple multiparameter prognostic scores ( 48 ), with notable exceptions represented by complex algorithms obtained through machine learning approaches (MLA) ( 49 , 50 ). For example, Kar and colleagues applied MLA to 1,393 hospitalized patients, obtaining a multivariable mortality risk score that was prospectively validated in further 977 patients ( 50 ).…”

“…Despite such robust evidence, ferritin has been rarely incorporated in COVID-19 simple multiparameter prognostic scores ( 48 ), with notable exceptions represented by complex algorithms obtained through machine learning approaches (MLA) ( 49 , 50 ). For example, Kar and colleagues applied MLA to 1,393 hospitalized patients, obtaining a multivariable mortality risk score that was prospectively validated in further 977 patients ( 50 ). Of note, of the 23 parameters that entered the final score (available at http://20.44.39.47/covid19v2/page1.php ), ferritin ranked in the fourth position in terms of adjusted hazard ratio (HR 2.48, 95% CI 1.32-4.74; P <0.005), only preceded by lactate dehydrogenase (HR 4.02, 95% CI 2.66-6.07; P <0.005) and certain comorbidities like chronic liver disease (3.95, 95% CI 1.16-13.42; P =0.02), and chronic kidney disease (HR 3.04, 95% CI 1.72-5.38; P <0.005).…”

Machine Learning Based Prediction of COVID-19 Mortality Suggests Repositioning of Anticancer Drug for Treating Severe Cases

“…Several studies have revealed general risk factors for a poor disease outcome, such as age, male gender, and low platelet count [ 20 , 42 , 46 , 65 ]. In addition, machine learning (ML) models have been published to predict mortality risk for individual patients, primarily based on data from Intensive Care Units and electronic health records from the US and UK [ 3 , 6 , 19 , 31 , 48 , 53 , 57 ] as well as a few other countries [ 33 , 39 ]. Notably the 4C mortality score developed by Ali et al., based on data from the UK has recently been validated within an intendent study in Canada [31] .…”

Independent Risk Factors for the Dynamic Development of COVID-19: A Retrospective Study

“…Previous studies have indicated that deep learning and the resultant risk score have the potential to provide frontline physicians with quantitative tools to stratify patients more effectively in time-sensitive and resource-constrained circumstances. [50][51][52] In the present study, a risk score system was constructed using the statistically significant clinical variables to predict progression and mortality. The progression and mortality rates increased with increasing risk scores, which is consistent with recent research.…”