Machine Learning Approach to Predicting COVID-19 Disease Severity Based on Clinical Blood Test Data: Statistical Analysis and Model Development.

Sakifa Aktar,Md Rashed-Al-Mahfuz,Ping-I Lin,Ahm Kamal,Sheikh Mohammed Shariful Islam,Valsamma Eapen,Julian Mw Quinn,Mohammad Ali Moni,Salem A Alyami,Md Martuza Ahamad,Akm Azad,Shahadat Uddin

doi:10.2196/25884

Abstract

BackgroundAccurate prediction of the disease severity of patients with COVID-19 would greatly improve care delivery and resource allocation and thereby reduce mortality risks, especially in less developed countries. Many patient-related factors, such as pre-existing comorbidities, affect disease severity and can be used to aid this prediction.ObjectiveBecause rapid automated profiling of peripheral blood samples is widely available, we aimed to investigate how data from the peripheral blood of patients with COVID-19 can be used to predict clinical outcomes.MethodsWe investigated clinical data sets of patients with COVID-19 with known outcomes by combining statistical comparison and correlation methods with machine learning algorithms; the latter included decision tree, random forest, variants of gradient boosting machine, support vector machine, k-nearest neighbor, and deep learning methods.ResultsOur work revealed that several clinical parameters that are measurable in blood samples are factors that can discriminate between healthy people and COVID-19–positive patients, and we showed the value of these parameters in predicting later severity of COVID-19 symptoms. We developed a number of analytical methods that showed accuracy and precision scores >90% for disease severity prediction.ConclusionsWe developed methodologies to analyze routine patient clinical data that enable more accurate prediction of COVID-19 patient outcomes. With this approach, data from standard hospital laboratory analyses of patient blood could be used to identify patients with COVID-19 who are at high risk of mortality, thus enabling optimization of hospital facilities for COVID-19 treatment.

Highlights

SARS-CoV-2 has caused the current pandemic of COVID-19, a disease that first emerged as an outbreak in December 2019 in the Chinese province of Hubei [1]
Data from standard hospital laboratory analyses of patient blood could be used to identify patients with COVID-19 who are at high risk of mortality, enabling optimization of hospital facilities for COVID-19 treatment
COVID-19; blood samples; machine learning; statistical analysis; prediction; severity; mortality; morbidity; risk; blood; testing; outcome; data set SARS-CoV-2 has caused the current pandemic of COVID-19, a disease that first emerged as an outbreak in December 2019 in the Chinese province of Hubei [1]

Summary

Introduction

SARS-CoV-2 has caused the current pandemic of COVID-19, a disease that first emerged as an outbreak in December 2019 in the Chinese province of Hubei [1]. An infected patient can rapidly develop additional and more severe symptoms that can be life-threatening and require intensive care intervention; these include pneumonia, severe shortness of breath, diarrhea, dispersed thrombosis, and vascular inflammation [3,4]. An additional issue in caring for patients with COVID-19 is the presence of comorbidities that interact with COVID-19, pulmonary and vascular conditions, which can greatly worsen the patient’s prognosis [5]. This is an important consideration given the current lack of effective therapy for COVID-19. Accurate prediction of the disease severity of patients with COVID-19 would greatly improve care delivery and resource allocation and thereby reduce mortality risks, especially in less developed countries. Many patient-related factors, such as pre-existing comorbidities, affect disease severity and can be used to aid this prediction

Methods

Results

Discussion

Conclusion