Socio-economic Challenges in COVID Detection using Transfer Learning-Based Methods

Abstract

Healthcare systems are at risk of collapsing unless significant structural and transformative measures are taken. Despite the global economy generating an additional 40 million jobs in the health sector by 2030, the World Health Organization projects a shortage of 9.9 million physicians, nurses, and midwives during the same period (WHO, 2016). The core of innovation in the healthcare industry lies in automation systems, particularly in the realm of image detection. As the ratio of healthcare workers to patients decreases, the integration of robotics and artificial intelligence plays a crucial role in bridging the gap. These technologies not only compensate for the declining workforce but also bring a level of accuracy and precision that eliminates the potential for human error in image detection processes. In this paper we focus on the COVID-19 pandemic that presents significant socio-economic challenges, impacting various aspects of daily life, including health, the economy, and social development. The need for chest X-ray (CXR) scans is rising due to pneumonia being a critical and common complication of COVID-19. Early detection and diagnosis are pivotal in curbing the spread of the virus, prompting the utilization of the reverse transcription polymerase chain reaction (RT-PCR) as the predominant screening technology. Nevertheless, the task's complexity, time-consuming nature, and reported insensitivity in this research emphasize the need for alternative approaches. CXR is a widely employed screening tool for lung-related diseases due to its straightforward and cost-effective application. In this paper, we have deployed different transfer learning methods to detect COVID-19 using chest X-ray images such as VGG19, ResNet-50, and InceptionResnetV2. The findings of our results indicate that the fine-tuned model utilizing the transfer learning and data augmentation techniques enhances the efficiency of COVID-19 detection. We performed a comparison of pre-trained networks and identified the InceptionResNetV2 model as having the highest classification performance with an accuracy of 97.33%.