Artificial intelligence (AI technology) is being used to aid in various aspects of the COVID-19 pandemic, including molecular research, drug development, medical diagnosis, and treatment methods. 

Coronavirus disease (COVID-19) was firstly reported in December 2019. It has caused a large number of deaths and negatively impacted people’s lives worldwide, with more than 200 million positive-confirmed cases and 4.55 million cumulative deaths worldwide as of early September 2021. The rapid increase in the number of new and suspected COVID-19 cases raises a question for every scientist that while AI has great promise to find solutions for many healthcare problems, whether there is a role for artificial intelligence (AI technology) for the detection or characterization of COVID-19? Researchers have been thinking about it and a variety of studies on using machine learning and deep learning to diagnose COVID-19 haven been conducted.  

Deep learning-based diagnostic applications 

The number of studies using AI technology to diagnose COVID-19 rapidly increased in 2020. Most reviews focus on describing diagnosis of COVID-19 from chest CT images using deep learning. Computed tomography (CT) is a test that provides a window into pathophysiology that could shed light on several stages of disease detection and evolution. CT provides a clear and expeditious window into this process, and deep learning of large multinational CT data could provide automated and reproducible biomarkers for classification and quantification of COVID-19 disease. A recent study by a group of researchers showed the conclusion that a CT image method with the support of deep learning model can accurately detect coronavirus 2019 and differentiate it from community-acquired pneumonia and other lung conditions. The result recorded 99.51% accuracy, 100% sensitivity, 99.4% AUC and 99.02% specificity.

Read more: AI in banking: when everything is available online

Machine learning-based diagnostic applications 

The potential applications of ML for COVID-19 have been mentioned in many research reports. The first application of ML was suggested as technical support for early detection and diagnosis of infections. A recent study demonstrated that the more accurate diagnosis could be generated using a computational model trained on large clinical datasets. An association between males and higher serum lymphocyte and neutrophil levels was identified by applying ML to reanalyze COVID-19 data from 151 published studies. The COVID-19 patients could be classified into three clinically relevant subtypes based on serum levels of immune cells, gender, and reported symptoms. A sensitivity of 92.5% and a specificity of 97.9% were achieved to discriminate COVID-19 patients from influenza patients using a computational classification mode.

Deep and machine learning methods have high accuracy in the differentiation of COVID-19 from non-COVID-19 pneumonia. These techniques have facilitated the testing process and produced accurate results given the significant increase in new cases. However, deep learning methods suffer from the absence of transparency and interpretability, as it is not possible to identify the exact imaging feature that has been applied to define the output. If we take as much care in developing AI models as we do with clinical trials, there is no reason why these algorithms won’t become part of routine clinical use and help us all push towards the ideal of more personalized treatment pathways. 

Contact email: business@hekate.ai or Facebook Page Hekate to receive useful advice on AI solutions for your business!