Risk prediction in spine surgery: a scoping review of traditional models, artificial intelligence, and the challenge of clinical translation

Key Points

• This review aims to evaluate the effectiveness of traditional and AI risk prediction models in spine surgery.
• Performed a scoping review of existing literature on risk prediction models for spine surgery.
• Assessed traditional models and AI/machine learning approaches for their performance and usability.
• Analyzed challenges related to validation and integration in clinical settings.
• Traditional risk models are still seen as reliable and interpretable for spine surgery outcomes.
• AI/ML approaches improve data handling but face challenges in clinical validation and trust.
• Future success requires rigorous testing and seamless integration into clinical workflows.

Abstract