Prediction and Classification of COVID-19 Admissions to Intensive Care Units (ICU) Using Weighted Radial Kernel SVM Coupled with Recursive Feature Elimination (RFE)

Abstract

Healthcare systems have been under immense pressure since the beginning of the COVID-19 pandemic; hence, studies on using machine learning (ML) methods for classifying ICU admissions and resource allocation are urgently needed. We investigated whether ML can propose a useful classification model for predicting the ICU admissions of COVID-19 patients. In this retrospective study, the clinical characteristics and laboratory findings of 100 patients with laboratory-confirmed COVID-19 tests were retrieved between May 2020 and January 2021. Based on patients’ demographic and clinical data, we analyzed the capability of the proposed weighted radial kernel support vector machine (SVM), coupled with (RFE). The proposed method is compared with other reference methods such as linear discriminant analysis (LDA) and kernel-based SVM variants including the linear, polynomial, and radial kernels coupled with REF for predicting ICU admissions of COVID-19 patients. An initial performance assessment indicated that the SVM with weighted radial kernels coupled with REF outperformed the other classification methods in discriminating between ICU and non-ICU admissions in COVID-19 patients. Furthermore, applying the Recursive Feature Elimination (RFE) with weighted radial kernel SVM identified a significant set of variables that can predict and statistically distinguish ICU from non-ICU COVID-19 patients. The patients’ weight, PCR Ct Value, CCL19, INF-β, BLC, INR, PT, PTT, CKMB, HB, platelets, RBC, urea, creatinine and albumin results were found to be the significant predicting features. We believe that weighted radial kernel SVM can be used as an assisting ML approach to guide hospital decision makers in resource allocation and mobilization between intensive care and isolation units. We model the data retrospectively on a selected subset of patient-derived variables based on previous knowledge of ICU admission and this needs to be trained in order to forecast prospectively.

Determining important features for dengue diagnosis using feature selection methods

“…recursive feature elimination (RFE) [30,31], correlation matrix from Pearson's correlation coefficient (PCC) [2,28] and KBest [27].…”

“…In this study, feature selection methods used to determine important features are feature importance [29], recursive feature elimination (RFE) [30,31], correlation matrix from Pearson’s correlation coefficient (PCC) [2,28] and KBest [27].…”

Tourism demand forecasting using PCA-BPNN

“…Artificial intelligence models, by training and learning from a large amount of data, can provide more accurate predictions of future tourism demand. Common artificial intelligence models include the BP neural network model (BPNN) [9], support vector machine model (SVM) [10], long short-term memory model (LSTM) [11], gated recurrent unit model (GRU) [12], and convolutional neural network model (CNN) [13]. The BP neural network model is one of the most classic artificial neural network models, capable of learning and predicting through the connections between multiple neurons.…”

Deep self-supervised machine learning algorithms with a novel feature elimination and selection approaches for blood test-based multi-dimensional health risks classification

“…For the best of the authors' knowledge, they have not been yet considered for the blood test-based analyses, but widely implemented in various medical problems. Alshanbari et al enriched the weighted radial kernel support vector machine with a recursive feature elimination algorithm to estimate and classify the COVID-19 admissions into intensive care units [7]. Similarly, Yu et al designed a risk prediction model based on a backward feature elimination algorithm to estimate acute on chronic liver failure in hepatitis B patients with severe exacerbation [8].…”