Risk prediction in spine surgery: a scoping review of traditional models, artificial intelligence, and the challenge of clinical translation
Прогнозирование риска в хирургии позвоночника: обзор традиционных моделей, искусственного интеллекта и проблемы клинической трансляции
2026-04-13
SCID: 54.1/xvx9ckbf
Discuss with AI
artificial intelligenceclinical translationexternal validationperioperative risk predictionspine surgery
Figures from the paper
Abstract (AI)
BACKGROUND: Accurate perioperative risk stratification is essential to patient safety and informed consent in spine surgery. Traditional regression-based risk scores are widely used but have modest predictive performance, while artificial intelligence and machine learning (AI/ML) approaches are increasingly applied to surgical risk prediction. This review synthesizes evidence on spine surgery risk prediction models, compares traditional approaches with AI/ML methods, and identifies key translational barriers. METHODS: A structured literature search was conducted across major biomedical databases using combinations of spine surgery, risk prediction, perioperative outcomes, and AI-related terms, with additional conceptual searches targeting explainability, validation, and clinical translation. Studies were selected for relevance to adult spine surgery risk prediction, model development or validation, and methodological or translational considerations. Given substantial heterogeneity in study design and outcomes, findings were synthesized qualitatively using a narrative approach. RESULTS: Traditional spine-specific risk models demonstrate fair-to-good discrimination for common outcomes, with typical areas under the receiver operating characteristic curve (AUCs) ranging from approximately 0.64 to 0.78. AI/ML models often report modest improvements in discrimination over regression-based approaches, particularly for common outcomes such as intensive care unit (ICU) admission and mortality, but gains are inconsistent and context-dependent. Across both model types, external validation, calibration drift, limited prospective outcome evidence, and challenges related to interpretability and workflow integration remain prominent. CONCLUSIONS: Traditional risk models remain interpretable, trusted, and competitively performant for many spine surgery outcomes. While AI/ML approaches expand data integration and interaction modeling, their clinical impact is constrained by validation, trust, and implementation barriers. Future progress will depend less on incremental performance gains and more on rigorous external validation, prospective outcome studies, and integration into clinical workflows.
Key Findings
1
AI/ML methods enable broader data integration and interaction modeling, but their clinical impact remains constrained by unresolved validation and implementation challenges.
2
AI/ML models often provide modest discrimination improvements over regression models, especially for ICU admission and mortality, but gains are inconsistent and context-dependent.
3
Both traditional and AI/ML models face major translational barriers, including limited external validation, calibration drift, scarce prospective outcome evidence, interpretability concerns, and workflow-integration challenges.
4
Traditional models remain interpretable, trusted, and competitively performant for many spine-surgery outcomes.
5
Traditional spine-surgery risk models show fair-to-good discrimination, with typical AUCs of approximately 0.64–0.78 for common outcomes.
Research Object
adult spine surgery perioperative risk prediction models
Research Subject
comparative predictive performance, validation, calibration, interpretability, and clinical translation of traditional and AI/ML risk models
Publication Details
Publication Date
2026-04-13
Journal
Publisher
ISSN
Cited by
24
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai3
PRISMA Extension for Scoping Reviews (PRISMA-ScR): Checklist and Explanation2018
Explainability for artificial intelligence in healthcare: a multidisciplinary perspective2020
The enlightening role of explainable artificial intelligence in medical & healthcare domains: A systematic literature review2023