%0 Journal Article
%A Revuelta, Ignacio 
%A Santos Arteaga, Francisco Javier
%A Diekmann, Fritz 
%T A hybrid data envelopment analysis—artificial neural network prediction model for COVID-19 severity in transplant recipients
%D 2021
%@ 0269-2821
%@ 1573-7462
%U https://hdl.handle.net/20.500.14352/114135
%X In an overwhelming demand scenario, such as the SARS-CoV-2 pandemic, pressure overhealth systems may outburst their predicted capacity to deal with such extreme situations.Therefore, in order to successfully face a health emergency, scientifc evidence and validated models are needed to provide real-time information that could be applied by anyhealth center, especially for high-risk populations, such as transplant recipients. We havedeveloped a hybrid prediction model whose accuracy relative to several alternative confgurations has been validated through a battery of clustering techniques. Using hospitaladmission data from a cohort of hospitalized transplant patients, our hybrid Data Envelopment Analysis (DEA)—Artifcial Neural Network (ANN) model extrapolates the progression towards severe COVID-19 disease with an accuracy of 96.3%, outperformingany competing model, such as logistic regression (65.5%) and random forest (44.8%). Inthis regard, DEA-ANN allows us to categorize the evolution of patients through the valuesof the analyses performed at hospital admission. Our prediction model may help guidingCOVID-19 management through the identifcation of key predictors that permit a sustainable management of resources in a patient-centered model.
%~