Artificial intelligence demonstrates comparable diagnostic accuracy to radiologists for anterior cruciate ligament tears on MRI: A systematic review and meta-analysis.
Knee Surg Sports Traumatol ArthroscJun 30, 2026 (epub)
Gabriel Moraes de Oliveira, Serafina Zotter, Brian Tao et al.
✦ AI-curated · Sources linked
In 30 seconds
This systematic review and meta-analysis evaluated the diagnostic accuracy of artificial intelligence (AI) in detecting anterior cruciate ligament (ACL) tears on MRI, comparing it to radiologists' performance. The analysis included 31 studies with 1192 cases. AI achieved a pooled sensitivity of 0.90 and specificity of 0.91, while radiologists had a sensitivity of 0.85 and specificity of 0.90, indicating comparable diagnostic accuracy.
Key findings
- AI demonstrated a pooled sensitivity of 0.90 and specificity of 0.91 in detecting ACL tears.
- Radiologists showed a sensitivity of 0.85 and specificity of 0.90 for the same task.
- No significant difference in diagnostic accuracy was found between AI and radiologists (p = 0.782).
- AI's overall sensitivity was 0.94 and specificity was 0.93 in the pooled analysis.
Why it matters
The findings highlight the potential of AI as a reliable diagnostic tool for ACL tears, which could enhance efficiency in imaging practices and reduce the workload on radiologists, ultimately improving patient care.