Artificial Intelligence-Based Prognostic Models for Postoperative Outcomes in Vitreoretinal Surgery: A Systematic Review and Meta-Analysis.
Abdullah Al-Ani, Liam Connors, David Mikhail et al.
✦ AI-curated · Sources linked
In 30 seconds
This systematic review and meta-analysis evaluated the effectiveness of artificial intelligence (AI) models in predicting postoperative outcomes in vitreoretinal surgery, analyzing data from 26 studies involving 18,724 eyes. The AI models demonstrated a pooled sensitivity of 0.89 and specificity of 0.87, indicating their potential to enhance preoperative prognostication compared to traditional methods.
Key findings
- Pooled sensitivity of AI models was 0.89 (95% CI, 0.83-0.93).
- Pooled specificity was 0.87 (95% CI, 0.81-0.91).
- Pooled accuracy of the models was 0.87 (95% CI, 0.83-0.90).
- 69% of studies reported AI outperformance compared to conventional statistical methods.
Why it matters
The integration of AI in predicting surgical outcomes could significantly improve preoperative counseling and surgical planning, potentially leading to better patient management and outcomes in vitreoretinal surgery.
What to keep in mind
Many studies had a high risk of bias, and all outcomes were rated as low certainty evidence.