<?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><Journal><PublisherName>yemenjmed</PublisherName><JournalTitle>Yemen Journal of Medicine</JournalTitle><PISSN>c</PISSN><EISSN>o</EISSN><Volume-Issue>Volume 5 Issue 2</Volume-Issue><IssueTopic>Multidisciplinary</IssueTopic><IssueLanguage>English</IssueLanguage><Season>May-August 2026</Season><SpecialIssue>N</SpecialIssue><SupplementaryIssue>N</SupplementaryIssue><IssueOA>Y</IssueOA><PubDate><Year>2026</Year><Month>08</Month><Day>25</Day></PubDate><ArticleType>Article</ArticleType><ArticleTitle>Role of Artificial Intelligence and Machine Learning in Predicting and Preventing Deep Vein Thrombosis: A Focus on Evolving Paradigms and Global Health Equity</ArticleTitle><SubTitle/><ArticleLanguage>English</ArticleLanguage><ArticleOA>Y</ArticleOA><FirstPage>373</FirstPage><LastPage>380</LastPage><AuthorList><Author><FirstName>Elmukhtar</FirstName><LastName>Habas1</LastName><AuthorLanguage>English</AuthorLanguage><Affiliation/><CorrespondingAuthor>N</CorrespondingAuthor><ORCID/><FirstName>Ala</FirstName><LastName>Habas2</LastName><AuthorLanguage>English</AuthorLanguage><Affiliation/><CorrespondingAuthor>Y</CorrespondingAuthor><ORCID/><FirstName>Amnna</FirstName><LastName>Rayani3</LastName><AuthorLanguage>English</AuthorLanguage><Affiliation/><CorrespondingAuthor>Y</CorrespondingAuthor><ORCID/><FirstName>Aml</FirstName><LastName>Habas4</LastName><AuthorLanguage>English</AuthorLanguage><Affiliation/><CorrespondingAuthor>Y</CorrespondingAuthor><ORCID/><FirstName>Elmehdi</FirstName><LastName>Errayes5</LastName><AuthorLanguage>English</AuthorLanguage><Affiliation/><CorrespondingAuthor>Y</CorrespondingAuthor><ORCID/></Author></AuthorList><DOI>10.63475/yjm.v5i2.0446</DOI><Abstract>Deep vein thrombosis (DVT) and venous thromboembolism (VTE) constitute a considerable global health challenge, leading to a significant increase in morbidity and mortality. The burden falls disproportionately on people in Arab and African countries, who face a distinct risk environment characterized by particular genetic vulnerabilities, a high incidence of comorbidities, such as sickle cell disease, and systemic obstacles in diagnosis and data acquisition. Existing risk assessment models, primarily formulated and validated within Western populations, frequently prove inadequate in diverse contexts, thereby intensifying health disparities. This review argues that artificial intelligence (AI) and machine learning (ML) may rectify the limitations of traditional, static prediction instruments by integrating intricate, high-dimensional data for dynamic and individualized risk classification. We contend that AI is uniquely capable of addressing the healthcare equity gap through the optimization of prophylaxis strategies in resource-limited settings. The realization of this potential relies on the proactive resolution of substantial difficulties, including data bias, the “black box” phenomenon, and the urgent need for varied and representative datasets. A synchronized international effort is crucial for the creation of fair, transparent, and approved AI tools, guaranteeing that the benefits of this technological progress in DVT treatment are universally available and accessible globally.</Abstract><AbstractLanguage>English</AbstractLanguage><Keywords>deep vein thrombosis, DVT, artificial intelligence, machine learning, algorithmic bias, thromboprophylaxis, health equity</Keywords><URLs><Abstract>https://www.yemenjmed.com/admin/abstract?id=456</Abstract></URLs><References><ReferencesarticleTitle>References</ReferencesarticleTitle><ReferencesfirstPage>16</ReferencesfirstPage><ReferenceslastPage>19</ReferenceslastPage><References/></References></Journal></Article></article>
