Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 May:179:1-9.
doi: 10.1016/j.pbiomolbio.2023.02.003. Epub 2023 Feb 19.

A systematic review of artificial intelligence-based COVID-19 modeling on multimodal genetic information

Karthik Sekaran  1 , R Gnanasambandan  2 , Ramkumar Thirunavukarasu  3 , Ramya Iyyadurai  4 , G Karthik  5 , C George Priya Doss  6
Affiliations

A systematic review of artificial intelligence-based COVID-19 modeling on multimodal genetic information

Karthik Sekaran et al. Prog Biophys Mol Biol. 2023 May.

Abstract

This study systematically reviews the Artificial Intelligence (AI) methods developed to resolve the critical process of COVID-19 gene data analysis, including diagnosis, prognosis, biomarker discovery, drug responsiveness, and vaccine efficacy. This systematic review follows the guidelines of Preferred Reporting for Systematic Reviews and Meta-Analyses (PRISMA). We searched PubMed, Embase, Web of Science, and Scopus databases to identify the relevant articles from January 2020 to June 2022. It includes the published studies of AI-based COVID-19 gene modeling extracted through relevant keyword searches in academic databases. This study included 48 articles discussing AI-based genetic studies for several objectives. Ten articles confer about the COVID-19 gene modeling with computational tools, and five articles evaluated ML-based diagnosis with observed accuracy of 97% on SARS-CoV-2 classification. Gene-based prognosis study reviewed three articles and found host biomarkers detecting COVID-19 progression with 90% accuracy. Twelve manuscripts reviewed the prediction models with various genome analysis studies, nine articles examined the gene-based in silico drug discovery, and another nine investigated the AI-based vaccine development models. This study compiled the novel coronavirus gene biomarkers and targeted drugs identified through ML approaches from published clinical studies. This review provided sufficient evidence to delineate the potential of AI in analyzing complex gene information for COVID-19 modeling on multiple aspects like diagnosis, drug discovery, and disease dynamics. AI models entrenched a substantial positive impact by enhancing the efficiency of the healthcare system during the COVID-19 pandemic.

Keywords: COVID-19; Explainable artificial intelligence; Genomics; Machine learning; Systematic review.

PubMed Disclaimer

Figures

Fig. 1
Fig. 1
Bioinformatics processes.
Fig. 2
Fig. 2
Article Selection process through PRISMA guidelines.
Fig. 3
Fig. 3
AI generic framework.
See this image and copyright information in PMC

References

    1. Adadi A., Berrada M. 2020. Explainable AI for Healthcare: from Black Box to Interpretable Models. Embedded Systems and Artificial Intelligence; pp. 327–337.
    1. Ahmed I., Jeon G. Enabling artificial intelligence for genome sequence analysis of COVID-19 and alike viruses. Interdiscipl. Sci. Comput. Life Sci. 2022;14:504–519. - PMC - PubMed
    1. Amrute J., Perry A., Anand G., Cruchaga C., Hock K., Farnsworth C., Randolph G., Lavine K., Steed A. Cell specific peripheral immune responses predict survival in critical COVID-19 patients. Nat. Commun. 2022;13:1–11. - PMC - PubMed
    1. Auwul M., Rahman M., Gov E., Shahjaman M., Moni M. Bioinformatics and machine learning approach identifies potential drug targets and pathways in COVID-19. Briefings Bioinf. 2021;22:bbab120. - PMC - PubMed
    1. Bengio Y., Lecun Y., Hinton G. Deep learning for AI. Commun. ACM. 2021;64:58–65.