Predicting Mortality in Hospitalized COVID-19 Patients in Zambia: An Application of Machine Learning
Clyde Mulenga1,2, Patrick Kaonga1, Raymond Hamoonga3
1Department of Epidemiology and Biostatistics, University of Zambia, Lusaka, Zambia.
Insights
Machine learning models accurately predicted COVID-19 mortality in Zambian patients. Key factors like underlying conditions and hospital stay length can improve pandemic preparedness.
Area of Science:
- Computational epidemiology
- Health informatics
- Machine learning in public health
Background:
- The COVID-19 pandemic caused significant global mortality and strained healthcare systems.
- Predicting mortality in hospitalized patients is crucial for resource allocation and pandemic preparedness.
- Zambia, like many nations, faced challenges in managing COVID-19 patient outcomes.
Purpose of the Study:
- To predict mortality risk in hospitalized COVID-19 patients in Zambia using machine learning (ML).
- To identify key predictive factors for COVID-19 mortality to enhance pandemic preparedness.
- To evaluate the performance of various ML models for mortality prediction in this context.
Main Methods:
- Employed seven machine learning classifiers: decision tree (DT), random forest (RF), support vector machines (SVM), logistic regression (LR), Naïve Bayes (NB), gradient boosting (GB), and XGBoost (XGB).
- Trained models on data from 1,433 hospitalized COVID-19 patients in Zambia.
- Evaluated model performance using metrics including accuracy, recall, F1-Score, ROC_AUC, and PRC_AUC.
Main Results:
- XGBoost achieved the highest performance with 92.3% accuracy, 94.2% recall, 92.4% F1-Score, and 97.5% ROC_AUC.
- Gradient Boosting (91.7% accuracy) and Random Forest (90.8% accuracy) also demonstrated strong predictive capabilities.
- Feature importance analysis identified underlying health conditions, length of stay, white blood cell count, and age as significant predictors of mortality.
Conclusions:
- Machine learning models can effectively predict COVID-19 mortality in hospitalized patients in Zambia.
- Identified factors can guide clinical interventions, improve resource management, and enhance pandemic preparedness.
- The study provides a validated framework for leveraging ML in public health surveillance and response.
Abstract:
The coronavirus disease 2019 (COVID-19) has wreaked havoc globally, resulting in millions of cases and deaths. The objective of this study was to predict mortality in hospitalized COVID-19 patients in Zambia using machine learning (ML) methods based on factors that have been shown to be predictive of mortality and thereby improve pandemic preparedness. This research employed seven powerful ML models that included decision tree (DT), random forest (RF), support vector machines (SVM), logistic regression (LR), Naïve Bayes (NB), gradient boosting (GB), and XGBoost (XGB). These classifiers were trained on 1,433 hospitalized COVID-19 patients from various health facilities in Zambia. The performances achieved by these models were checked using accuracy, recall, F1-Score, area under the receiver operating characteristic curve (ROC_AUC), area under the precision-recall curve (PRC_AUC), and other metrics. The best-performing model was the XGB which had an accuracy of 92.3%, recall of 94.2%, F1-Score of 92.4%, and ROC_AUC of 97.5%. The pairwise Mann-Whitney U-test analysis showed that the second-best model (GB) and the third-best model (RF) did not perform significantly worse than the best model (XGB) and had the following: GB had an accuracy of 91.7%, recall of 94.2%, F1-Score of 91.9%, and ROC_AUC of 97.1%. RF had an accuracy of 90.8%, recall of 93.6%, F1-Score of 91.0%, and ROC_AUC of 96.8%. Other models showed similar results for the same metrics checked. The study successfully derived and validated the selected ML models and predicted mortality effectively with reasonably high performance in the stated metrics. The feature importance analysis found that knowledge of underlying health conditions about patients' hospital length of stay (LOS), white blood cell count, age, and other factors can help healthcare providers offer lifesaving services on time, improve pandemic preparedness, and decongest health facilities in Zambia and other countries with similar settings.
More Related Videos
04:05Author Spotlight: Unveiling Prognostic Indicators in Heart Failure - The Role of Phase Angle and Bioelectrical Impedance Analysis
Published on: June 30, 2023
12:18A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Published on: January 11, 2020
