Scholarlink

<p>There are no prospective clinical studies evaluating artificial intelligence implementation for glaucoma detection in real-world settings. We developed an automated retinal photography and AI-based screening system and prospectively assessed its accuracy, feasibility, and acceptability in Australian general practice (GP) clinics. Adults aged 50 years or older were recruited during routine GP visits, with retinal images captured using an automated fundus camera and analysed by the AI system for glaucoma risk classification. Of 414 participants, 277 (66.9%) had analysable images, with a total of 483 eyes included. The AI system achieved an AUROC of 0.80, sensitivity of 65.0%, and specificity of 94.6%. Among 161 previously undiagnosed patients, 18 (11.2%) were identified as referable glaucoma. Patient feedback was positive, and clinic staff supported AI-assisted screening to enhance glaucoma care. Despite challenges such as lower sensitivity and image acquisition limitations, the system shows promise for opportunistic screening in primary care settings.</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

Prospective pragmatic trial of automated retinal photography and AI glaucoma screening in Australian primary care

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年7月1日

查看全文
  • Catherine L. Jan,
  • Sanil Joseph,
  • Algis J. Vingrys,
  • Jacqueline Henwood,
  • Zongyuan Ge,
  • Randall S. Stafford,
  • Mingguang He

摘要

There are no prospective clinical studies evaluating artificial intelligence implementation for glaucoma detection in real-world settings. We developed an automated retinal photography and AI-based screening system and prospectively assessed its accuracy, feasibility, and acceptability in Australian general practice (GP) clinics. Adults aged 50 years or older were recruited during routine GP visits, with retinal images captured using an automated fundus camera and analysed by the AI system for glaucoma risk classification. Of 414 participants, 277 (66.9%) had analysable images, with a total of 483 eyes included. The AI system achieved an AUROC of 0.80, sensitivity of 65.0%, and specificity of 94.6%. Among 161 previously undiagnosed patients, 18 (11.2%) were identified as referable glaucoma. Patient feedback was positive, and clinic staff supported AI-assisted screening to enhance glaucoma care. Despite challenges such as lower sensitivity and image acquisition limitations, the system shows promise for opportunistic screening in primary care settings.