A new COVID-19 intubation prediction strategy using an intelligent feature selection and K-NN method

Abstract

Background Predicting severe respiratory failure due to COVID-19 can help triage patients to higher levels of care, resource allocation and decrease morbidity and mortality. The need for this research derives from the increasing demand for innovative technologies to overcome complex data analysis and decision-making tasks in critical care units. Hence the aim of our paper is to present a new algorithm for selecting the best features from the dataset and developing Machine Learning(ML) based models to predict the intubation risk of hospitalized COVID-19 patients. Methods In this retrospective single-center study, the data of 1225 COVID-19 patients from February 9, 2020, to July 20, 2021, were analyzed by several ML algorithms which included, Decision Tree(DT), Support Vector Machine (SVM), Multilayer perceptron (MLP), and K-Nearest Neighbors(K-NN). First, the most important predictors were identified using the Horse herd Optimization Algorithm (HOA). Then, by comparing the ML algorithms' performance using some evaluation criteria, the best performing one was identified. Results Predictive models were trained using 12 validated features. Also, it found that proposed DT-based predictive model enables a reasonable level of accuracy (=93%) in predicting the risk of intubation among hospitalized COVID-19 patients. Conclusions The experimental results demonstrate the effectiveness of the proposed meta-heuristic feature selection technique in combining with DT model in predicting intubation risk for hospitalized patients with COVID-19. The proposed model have the potential to inform frontline clinicians with quantitative and non-invasive tool to assess illness severity and identifying high risk patients .

Explainable Artificial Intelligence Approach for the Early Prediction of Ventilator Support and Mortality in COVID-19 Patients

“…Similarly, ref. [15][16][17][18]23] found age as one of the key features for predicting intubation in COVID-19 patients. However, Bae et al [18] used radiomics features and two demographic features (age and gender) to predict mortality and ventilator support.…”

“…However, in the second study, CXR and radiomic data were used and found that the integration of radiomic data improved the early prediction of mortality. Aljouie et al [15] achieved an AUC of 0.83 and a balanced accuracy of 0.80 using RF. Meanwhile, in Bae et al's study [18], the DL model achieved an AUC of 0.83, sensitivity of 0.79, and specificity of 0.74.…”

“…Early prediction of COVID-19 patients who are at risk of deterioration can reduce the risk of mortality and help hospitals to manage their resources. Varzaneh et al [15] proposed an AI-based model for early prediction of intubation in COVID-19-hospitalized patients, using several ML algorithms such as the decision tree (DT), support-vector machine (SVM), k-nearest neighbor (KNN), and multilayer perceptron (MLP) for the classification. However, the feature selection was performed using a bioinspired technique, i.e., the horse herd optimization algorithm (HOA).…”

COVID-19 health data analysis and personal data preserving: A homomorphic privacy enforcement approach

“…Its accuracy mainly focuses on clinical blood samples applying a statistical t-test for filtering unique pandemic diagnosis tools for positive cases. [7] 3D representation empirical mode decomposition techniques for classification and extracting block of backbone components using deep CNN approach. Context-aware attention classifies the main features of pneumonia cases which helps to detect COVID-19.…”

Extracting relevant predictive variables for COVID-19 severity prognosis: An exhaustive comparison of feature selection techniques

“…Specifically, Varzaneh et al . [ 8 ] evaluated various of the classical ML algorithms in terms of their ability to predict patients’ need for intubation due to an adverse progression of COVID-19. In a similar manner, several models have been proposed to predict mortality risk: Caillon et al .…”