Scholarlink

Purpose <p>Vertebral fractures (VFs) are the most common osteoporotic fractures and a hallmark of bone fragility, yet most morphometric VFs remain undiagnosed in routine imaging not focused on the spine. This pilot study evaluated the diagnostic performance of an artificial intelligence (AI) system for opportunistic vertebral fracture detection in chest and abdominal computer tomography (CT) scans compared with human readers in a real-world hospital setting.</p> Methods <p>Over 2&#xa0;months, all thoracic and abdominal CTs performed for any indication in patients aged ≥ 50&#xa0;years at a tertiary hospital were analyzed by the Bone Solution HealthOST AI platform (Nanox AI Ltd.). Routine radiology reports and targeted reviews by endocrinologists were compared to AI outputs using a gold-standard adjudication by an expert panel. Given that all readers assessed the same cases, paired comparisons between AI and human readers were performed using McNemar’s test, with chi-square analyses conducted as secondary comparisons.</p> Results <p>Among 427 eligible CT scans, AI detected vertebral fractures with significantly higher sensitivity (86.3%) than radiologists (50.0%) or endocrinologists (68.8%) (<i>p</i> &lt; 0.001 for both comparisons). Compared with radiologists, AI had 6.3-fold greater odds of correctly identifying true fractures (OR = 6.30; 95% CI: 2.90–13.58), while against targeted review by endocrinologists, AI achieved a 2.85-fold advantage (OR = 2.85; 95% CI: 1.29–6.30). Extrapolated annually, AI integration could uncover around 150 new, otherwise undiagnosed patients eligible for osteoporosis treatment.</p> Conclusion <p>Automated vertebral fracture detection in routine CT scans significantly enhances diagnostic yield versus human interpretation. Its integration into clinical workflows offers a low-cost, high-impact strategy to improve early osteoporosis diagnosis and treatment within the healthcare system.</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

Artificial intelligence vs human opportunistic detection of vertebral fractures in routine CT scans: results of a pilot study

  • 期刊论文

  • 发表日期：

    2026年4月23日

查看全文
  • Polyzois Makras,
  • Eleftherios Chatzellis,
  • Christos Gravvanis,
  • Georgia Kanti,
  • Maria P. Yavropoulou,
  • Konstantinos Papadimitropoulos,
  • Nikolaos Kyriakopoulos,
  • Christos Tekedis,
  • Vasilliki Mparmparousi,
  • Ioannis Liakopoulos,
  • Dimitrios Matsaridis,
  • Emmanouil Skoulikaris,
  • Maria Varela,
  • Harikleia Athanasiou,
  • Stella Koropouli,
  • Nikolaos Gidarakos

摘要

Purpose

Vertebral fractures (VFs) are the most common osteoporotic fractures and a hallmark of bone fragility, yet most morphometric VFs remain undiagnosed in routine imaging not focused on the spine. This pilot study evaluated the diagnostic performance of an artificial intelligence (AI) system for opportunistic vertebral fracture detection in chest and abdominal computer tomography (CT) scans compared with human readers in a real-world hospital setting.

Methods

Over 2 months, all thoracic and abdominal CTs performed for any indication in patients aged ≥ 50 years at a tertiary hospital were analyzed by the Bone Solution HealthOST AI platform (Nanox AI Ltd.). Routine radiology reports and targeted reviews by endocrinologists were compared to AI outputs using a gold-standard adjudication by an expert panel. Given that all readers assessed the same cases, paired comparisons between AI and human readers were performed using McNemar’s test, with chi-square analyses conducted as secondary comparisons.

Results

Among 427 eligible CT scans, AI detected vertebral fractures with significantly higher sensitivity (86.3%) than radiologists (50.0%) or endocrinologists (68.8%) (p < 0.001 for both comparisons). Compared with radiologists, AI had 6.3-fold greater odds of correctly identifying true fractures (OR = 6.30; 95% CI: 2.90–13.58), while against targeted review by endocrinologists, AI achieved a 2.85-fold advantage (OR = 2.85; 95% CI: 1.29–6.30). Extrapolated annually, AI integration could uncover around 150 new, otherwise undiagnosed patients eligible for osteoporosis treatment.

Conclusion

Automated vertebral fracture detection in routine CT scans significantly enhances diagnostic yield versus human interpretation. Its integration into clinical workflows offers a low-cost, high-impact strategy to improve early osteoporosis diagnosis and treatment within the healthcare system.