An Integrated Deep Learning and Belief Rule Base Intelligent System to Predict Survival of COVID-19 Patient under Uncertainty

Tawsin Uddin Ahmed,Raihan Ul Islam,Karl Andersson,Mohammad Shahadat Hossain,Mohammad Newaj Jamil

doi:10.1007/s12559-021-09978-8

Tawsin Uddin Ahmed, Raihan Ul Islam + Show 3 more

Open Access

https://doi.org/10.1007/s12559-021-09978-8

Copy DOI

Abstract

The novel Coronavirus-induced disease COVID-19 is the biggest threat to human health at the present time, and due to the transmission ability of this virus via its conveyor, it is spreading rapidly in almost every corner of the globe. The unification of medical and IT experts is required to bring this outbreak under control. In this research, an integration of both data and knowledge-driven approaches in a single framework is proposed to assess the survival probability of a COVID-19 patient. Several neural networks pre-trained models: Xception, InceptionResNetV2, and VGG Net, are trained on X-ray images of COVID-19 patients to distinguish between critical and non-critical patients. This prediction result, along with eight other significant risk factors associated with COVID-19 patients, is analyzed with a knowledge-driven belief rule-based expert system which forms a probability of survival for that particular patient. The reliability of the proposed integrated system has been tested by using real patient data and compared with expert opinion, where the performance of the system is found promising.

Highlights

The sudden appearance of an unknown member of a large virus family is not a novel experience for humans
Deep learning methods are integrated into numerous medical equipment to diagnose critical diseases
A Graphical User Interface (GUI) is developed by which users can be facilitated with COVID-19 patient status checking system

Summary

Introduction

The sudden appearance of an unknown member of a large virus family is not a novel experience for humans. Almost every century in human history, viruses with novel genome sequences appear and take thousands of lives. Swine Flu, SARS, HIV, Hong Kong Flu, and Asian Flu are the deadliest viruses that caused the death of a large number of. Deep learning approaches are vastly adopted in solving computer vision problems [3, 4]. Deep learning methods are integrated into numerous medical equipment to diagnose critical diseases. X-ray, CT scan, MRI, etc., contain health information of a patient, which are useful input parameters for deep learning models [5]. Automated information extraction from medical images by neural nets makes diagnosis faster for medical professionals.

Objectives

Findings

Discussion

Conclusion