Related Experiment Video
Updated: Sep 3, 2025
Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
Published on: October 11, 2018
A Hybrid Feature Selection Approach to Screen a Novel Set of Blood Biomarkers for Early COVID-19 Mortality Prediction
Asif Hassan Syed1, Tabrej Khan2, Nashwan Alromema1
1Department of Computer Science, Faculty of Computing and Information Technology Rabigh (FCITR), King Abdulaziz University, Jeddah 22254, Saudi Arabia.
Insights
This study identifies three key blood biomarkers—International Normalized Ratio (INR), platelet large cell ratio (P-LCR), and D-dimer—that predict COVID-19 mortality. A Random Forest model using these biomarkers achieved high accuracy in predicting patient outcomes.
Area of Science:
- Biomedical Science
- Data Science
- Medical Informatics
Background:
- The COVID-19 pandemic has strained global healthcare systems.
- Accurate prediction of COVID-19 severity and mortality is crucial for optimizing patient treatment strategies.
Purpose of the Study:
- To identify critical blood biomarkers for predicting COVID-19 mortality.
- To develop a machine learning model for accurate in-hospital mortality prediction in COVID-19 patients.
Main Methods:
- A hybrid feature selection approach (mRMR, t-test, WOA) was used to identify informative blood biomarkers from a dataset of 485 COVID-19 patients.
- Machine learning algorithms, including Random Forest (RF), were trained and evaluated for their predictive performance.
- The study compared the performance of the developed RF model against existing models using established blood biomarkers.
Main Results:
- International Normalized Ratio (INR), platelet large cell ratio (P-LCR), and D-dimer were identified as the most informative blood biomarkers.
- The RF-based model achieved high predictive performance with an accuracy of 0.96 ± 0.062, F1 score of 0.96 ± 0.099, and AUC of 0.98 ± 0.024.
- The proposed RF model demonstrated superior performance compared to existing machine learning models utilizing different blood biomarkers.
Conclusions:
- A novel hybrid approach effectively screens informative blood biomarkers for COVID-19 mortality prediction.
- The developed RF-based model provides an accurate and reliable tool for predicting in-hospital mortality in COVID-19 patients.
- An application based on the model was successfully developed and deployed, facilitating clinical decision-making during surge periods.
Abstract:
The increase in coronavirus disease 2019 (COVID-19) infection caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has placed pressure on healthcare services worldwide. Therefore, it is crucial to identify critical factors for the assessment of the severity of COVID-19 infection and the optimization of an individual treatment strategy. In this regard, the present study leverages a dataset of blood samples from 485 COVID-19 individuals in the region of Wuhan, China to identify essential blood biomarkers that predict the mortality of COVID-19 individuals. For this purpose, a hybrid of filter, statistical, and heuristic-based feature selection approach was used to select the best subset of informative features. As a result, minimum redundancy maximum relevance (mRMR), a two-tailed unpaired t-test, and whale optimization algorithm (WOA) were eventually selected as the three most informative blood biomarkers: International normalized ratio (INR), platelet large cell ratio (P-LCR), and D-dimer. In addition, various machine learning (ML) algorithms (random forest (RF), support vector machine (SVM), extreme gradient boosting (EGB), naïve Bayes (NB), logistic regression (LR), and k-nearest neighbor (KNN)) were trained. The performance of the trained models was compared to determine the model that assist in predicting the mortality of COVID-19 individuals with higher accuracy, F1 score, and area under the curve (AUC) values. In this paper, the best performing RF-based model built using the three most informative blood parameters predicts the mortality of COVID-19 individuals with an accuracy of 0.96 ± 0.062, F1 score of 0.96 ± 0.099, and AUC value of 0.98 ± 0.024, respectively on the independent test data. Furthermore, the performance of our proposed RF-based model in terms of accuracy, F1 score, and AUC was significantly better than the known blood biomarkers-based ML models built using the Pre_Surv_COVID_19 data. Therefore, the present study provides a novel hybrid approach to screen the most informative blood biomarkers to develop an RF-based model, which accurately and reliably predicts in-hospital mortality of confirmed COVID-19 individuals, during surge periods. An application based on our proposed model was implemented and deployed at Heroku.
