Scholarlink

Objective <p>This narrative review aims to comprehensively explore the integration of artificial intelligence (AI) into POCUS in cardiac arrest and trauma assessment.</p> Background <p>Rapid assessment is of importance in critical situations such as trauma and cardiac arrest where every second counts. The ability to diagnose life-threatening conditions by the bedside helps clinicians to initiate prompt, life-saving treatment. The emergence of point-of-care ultrasound (POCUS) has revolutionised critical and emergency care because of its portability, and non-invasiveness.</p> Methods <p>For the literature used for this narrative review, a structured search was done across the following databases. Search terms included combinations of keywords and Medical Subject Headings (MeSH) such as: “point-of-care ultrasound,” “POCUS,” “artificial intelligence,” “machine learning,” “deep learning,” “trauma,” “cardiac arrest,” “resuscitation,” “FAST,” “eFAST,” and “ultrasound automation.” Boolean operators (AND/OR) were used to modify the search strategy.</p> Result <p>Despite the transformative potential of POCUS in trauma and cardiac arrest assessment, its use still faces significant limitations. With the role of POCUS established in emergency medicine for rapid bedside evaluation of critical patients, AI has changed the scope of medical imaging by providing automated analysis, improving accuracy, and reducing dependence on the operator. As it relates to ultrasound, AI integrates machine learning (ML) and deep learning (DL) techniques for processing complex imaging data.</p> Conclusion <p>Over time, as AI powered POCUS evolved from feasibility studies into outcome-oriented trials, attention has shifted toward its diagnostic performance.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

The Role of Point-of-Care Ultrasound (POCUS) Powered by Artificial Intelligence in Trauma and Cardiac Arrest Assessment: A Narrative Review

  • 期刊论文

  • 发表日期：

    2026年3月31日

查看全文
  • Ajagbe Kamil Adeniran,
  • Emmanuel Oyedeji Oyetola,
  • Habiblah Ayomide Jagunmolu,
  • Rebecca Opeyemi Adeyemo,
  • Saheed Olamide Salami,
  • Olaniyi Taofeek Oyetola,
  • Samuel Oyeponle Oyelude,
  • Precious Adegbosin,
  • Toluwanimi Oladele Idowu,
  • Oluwadamilare Okikijesu Ezekiel,
  • Daniel Ayanleke

摘要

Objective

This narrative review aims to comprehensively explore the integration of artificial intelligence (AI) into POCUS in cardiac arrest and trauma assessment.

Background

Rapid assessment is of importance in critical situations such as trauma and cardiac arrest where every second counts. The ability to diagnose life-threatening conditions by the bedside helps clinicians to initiate prompt, life-saving treatment. The emergence of point-of-care ultrasound (POCUS) has revolutionised critical and emergency care because of its portability, and non-invasiveness.

Methods

For the literature used for this narrative review, a structured search was done across the following databases. Search terms included combinations of keywords and Medical Subject Headings (MeSH) such as: “point-of-care ultrasound,” “POCUS,” “artificial intelligence,” “machine learning,” “deep learning,” “trauma,” “cardiac arrest,” “resuscitation,” “FAST,” “eFAST,” and “ultrasound automation.” Boolean operators (AND/OR) were used to modify the search strategy.

Result

Despite the transformative potential of POCUS in trauma and cardiac arrest assessment, its use still faces significant limitations. With the role of POCUS established in emergency medicine for rapid bedside evaluation of critical patients, AI has changed the scope of medical imaging by providing automated analysis, improving accuracy, and reducing dependence on the operator. As it relates to ultrasound, AI integrates machine learning (ML) and deep learning (DL) techniques for processing complex imaging data.

Conclusion

Over time, as AI powered POCUS evolved from feasibility studies into outcome-oriented trials, attention has shifted toward its diagnostic performance.