<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Publishing DTD v1.2d1 20170631//EN" "JATS-journalpublishing1.dtd">
<article xlink="http://www.w3.org/1999/xlink" dtd-version="1.0" article-type="emergency-medicine-and-critical-care" lang="en">
<front>
<journal-meta>
<journal-id journal-id-type="publisher">JOHS</journal-id>
<journal-id journal-id-type="nlm-ta">Journ of Health Scien</journal-id>
<journal-title-group>
<journal-title>Journal of HealthCare Sciences</journal-title>
<abbrev-journal-title abbrev-type="pubmed">Journ of Health Scien</abbrev-journal-title>
</journal-title-group>
<issn pub-type="ppub">2231-2196</issn>
<issn pub-type="opub">0975-5241</issn>
<publisher>
<publisher-name>Radiance Research Academy</publisher-name>
</publisher>
</journal-meta>
<article-meta>
<article-id pub-id-type="publisher-id">518</article-id>
<article-id pub-id-type="doi">http://dx.doi.org/10.52533/JOHS.2026.60201</article-id>
<article-id pub-id-type="doi-url"/>
<article-categories>
<subj-group subj-group-type="heading">
<subject>Emergency Medicine and Critical Care</subject>
</subj-group>
</article-categories>
<title-group>
<article-title>Artificial Intelligence for COVID-19 Severity Assessment: A Systematic Review and Meta-Analysis
</article-title>
</title-group>
<contrib-group>
<contrib contrib-type="author">
<name>
<surname>Almatrafi</surname>
<given-names>Salma Muteb</given-names>
</name>
</contrib>
<contrib contrib-type="author">
<name>
<surname>Alkhulaif</surname>
<given-names>Norah Mohammed</given-names>
</name>
</contrib>
<contrib contrib-type="author">
<name>
<surname>Altuwaim</surname>
<given-names>Abdulrahman Abdullah</given-names>
</name>
</contrib>
<contrib contrib-type="author">
<name>
<surname>Aljohani</surname>
<given-names>Itidal Mohammed</given-names>
</name>
</contrib>
<contrib contrib-type="author">
<name>
<surname>Alanazi</surname>
<given-names>Almaha Hamdan</given-names>
</name>
</contrib>
<contrib contrib-type="author">
<name>
<surname>Alserhani</surname>
<given-names>Abdulaziz Saeed</given-names>
</name>
</contrib>
<contrib contrib-type="author">
<name>
<surname>Alzaher</surname>
<given-names>Abdulmajeed Zaher</given-names>
</name>
</contrib>
<contrib contrib-type="author">
<name>
<surname>Almuhanna</surname>
<given-names>Meshal Mansour</given-names>
</name>
</contrib>
<contrib contrib-type="author">
<name>
<surname>Alhumaydani</surname>
<given-names>Naif Khalid</given-names>
</name>
</contrib>
<contrib contrib-type="author">
<name>
<surname>Alraddadi</surname>
<given-names>Layan Talal</given-names>
</name>
</contrib>
<contrib contrib-type="author">
<name>
<surname>Kheimi</surname>
<given-names>Rawan Maatouk</given-names>
</name>
</contrib>
<contrib contrib-type="author">
<name>
<surname>Almehmadi</surname>
<given-names>Wajd</given-names>
</name>
</contrib>
<contrib contrib-type="author">
<name>
<surname>Basnawi</surname>
<given-names>Abdullah</given-names>
</name>
</contrib>
</contrib-group>
<pub-date pub-type="ppub">
<day>8</day>
<month>02</month>
<year>2026</year>
</pub-date>
<volume>6</volume>
<issue>2</issue>
<fpage>165</fpage>
<lpage>187</lpage>
<permissions>
<copyright-statement>This article is copyright of Popeye Publishing, 2009</copyright-statement>
<copyright-year>2009</copyright-year>
<license license-type="open-access" href="http://creativecommons.org/licenses/by/4.0/">
<license-p>This is an open-access article distributed under the terms of the Creative Commons Attribution (CC BY 4.0) Licence. You may share and adapt the material, but must give appropriate credit to the source, provide a link to the licence, and indicate if changes were made.</license-p>
</license>
</permissions>
<abstract>
<p>The accurate assessment of coronavirus disease 2019 (COVID-19) severity remains a cornerstone for optimized resource allocation and clinical treatment planning. This systematic review and meta-analysis aimed to evaluate and compare the diagnostic performance of artificial intelligence (AI) models utilizing chest X-ray (CXR) versus lung ultrasound (LUS) modalities for COVID-19 severity stratification. Following the PRISMA 2020 guidelines, we conducted a comprehensive literature search across PubMed, Scopus, Web of Science, and Google Scholar from 2020 through April 2025. Inclusion criteria specifically targeted studies employing AI for severity assessment, while excluding secondary research, case reports, and non-English publications. Our analysis of ten selected studies revealed a progressive evolution in model performance for both binary and multi-class classification tasks. Detailed meta-regression indicated that transformer-based architectures and domain-specific pre-training contributed to higher sensitivity levels, particularly in early-stage stratification. Although CXR was the more prevalent modality in the literature, LUS-based AI models exhibited comparable diagnostic efficacy, offering a portable and radiation-free alternative that enhances clinical workflows in resource-constrained environments and point-of-care settings. Furthermore, the results indicate that the integration of domain knowledge and the application of rigorous external validation significantly enhance model generalizability. The analysis underscores a persistent performance gap in cross-institutional validation, suggesting a need for more diverse training cohorts. We conclude that while AI-driven CXR and LUS tools show high potential for severity assessment, the path to clinical deployment necessitates standardized external validation and the fusion of multi-modal clinical data to ensure robust predictive accuracy in diverse healthcare settings.
</p>
</abstract>
<kwd-group>
<kwd>Artificial intelligence</kwd>
<kwd> COVID-19</kwd>
<kwd> Severity assessment</kwd>
<kwd> Chest radiography</kwd>
<kwd> Lung ultrasound</kwd>
</kwd-group>
</article-meta>
</front>
</article>