Machine Learning Based Clinical Decision Support System for Early COVID-19 Mortality Prediction

Abstract

The coronavirus disease 2019 (COVID-19), caused by the virus SARS-CoV-2, is an acute respiratory disease that has been classified as a pandemic by the World Health Organization (WHO). The sudden spike in the number of infections and high mortality rates have put immense pressure on the public healthcare systems. Hence, it is crucial to identify the key factors for mortality prediction to optimize patient treatment strategy. Different routine blood test results are widely available compared to other forms of data like X-rays, CT-scans, and ultrasounds for mortality prediction. This study proposes machine learning (ML) methods based on blood tests data to predict COVID-19 mortality risk. A powerful combination of five features: neutrophils, lymphocytes, lactate dehydrogenase (LDH), high-sensitivity C-reactive protein (hs-CRP), and age helps to predict mortality with 96% accuracy. Various ML models (neural networks, logistic regression, XGBoost, random forests, SVM, and decision trees) have been trained and performance compared to determine the model that achieves consistently high accuracy across the days that span the disease. The best performing method using XGBoost feature importance and neural network classification, predicts with an accuracy of 90% as early as 16 days before the outcome. Robust testing with three cases based on days to outcome confirms the strong predictive performance and practicality of the proposed model. A detailed analysis and identification of trends was performed using these key biomarkers to provide useful insights for intuitive application. This study provide solutions that would help accelerate the decision-making process in healthcare systems for focused medical treatments in an accurate, early, and reliable manner.

Keywords: biomarkers; coronavirus disease 2019; machine learning; mortality; prognosis.

Figure 1

Distribution of the two classes in the train and test sets after splitting.

Figure 2

Flowchart depicting the model development pipeline used in this study.

Figure 3

Architecture of the neural network implemented for feature selection, where n represents the number of features to be analyzed.

Figure 4

Comparison of the performance of different machine learning algorithms assessed using different metrics. The vertical lines denote the standard deviations. (A) Accuracy. (B) AUC and F1 score.

Figure 5

The performance of neural net on the test data using case 1: Number of days to outcome less than or equal to n. (A) The class-wise distribution of the cumulated data-points (≤ nth day) for all samples in the imputed test set. (B) Accuracy of the model evaluated for different days to outcome. (C) F1-score and AUC of the model evaluated for different days to outcome.

Figure 6

The performance of neural net on the test data using case 2: Number of days to outcome greater than or equal to n. (A) The class-wise distribution of the cumulated data-points (≤ nth day) for all samples in the imputed test set. (B) Accuracy of the model evaluated for different days to outcome. (C) F1-score and AUC of the model evaluated for different days to outcome.

Figure 7

The performance of neural net on the test data using case 3: Number of days to outcome equal to n. (A) The class-wise distribution of the cumulated data-points (≤ nth day) for all samples in the imputed test set. (B) Accuracy of the model evaluated for different days to outcome. (C) F1-score and AUC of the model evaluated for different days to outcome.

Figure 8

Box and whisker plot showing the variations of four selected features with respect to the days to outcome. (A) hs-CRP, (B) neutrophils (%), (C) lymphocyte (%), (D) lactate dehydrogenase.