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.

Purpose: This scoping review examines current evidence supporting multimodal artificial intelligence, continuous monitoring, and digital twin concepts in spine care. Our primary aims were to (1) characterize the state of digital twin development in spine care, (2) identify key technological and conceptual gaps, and (3) evaluate translational barriers to clinical implementation. Methods: A scoping review was conducted following PRISMA-ScR guidelines. PubMed/MEDLINE, Scopus, and Web of Science were searched for studies published between January 2010 and March 2025. Findings were synthesized qualitatively. Results: Twenty-six studies met inclusion criteria. Existing spine prediction models demonstrate modest discrimination and are predominantly static. Imaging-based AI shows weak associations with pain and disability. Wearable sensor monitoring is feasible but lacks consistent evidence for improved outcomes. Spine-specific digital twins remain conceptual, with no prospective validation demonstrating improved decision-making. Conclusion: Multimodal AI-enabled digital twins represent a compelling conceptual framework for personalized spine care, but current evidence does not support clinical superiority or readiness for implementation. Progress will require prospective validation, standardized data integration, and regulatory clarity.

Purpose of Review Osteoporosis affects more than 53 million Americans and contributes to nearly 2 million fragility fractures each year, yet most patients who sustain fractures never receive guideline-recommended pharmacotherapy. Traditional step-therapy typically begins with bisphosphonates and reserves anabolic agents for later-line use, whereas sequential therapy prioritizes anabolic treatment followed by antiresorptive consolidation. This review synthesizes the evidence comparing these treatment paradigms and examines their relevance to orthopedic populations, in whom bone quality directly influences fracture healing, fixation, fusion, and implant-related outcomes. Recent Findings Among 37 studies meeting PRISMA-ScR inclusion criteria, anabolic-first sequential therapy generally produced greater gains in bone mineral density and greater fracture risk reduction than step-therapy or antiresorptive monotherapy. In one representative trial, romosozumab followed by denosumab achieved a 16.8% increase in lumbar spine bone mineral density versus 7.5% with monotherapy, and 92% versus 47% of patients reached treatment targets. In ARCH, anabolic-first therapy was associated with 48% lower vertebral fracture risk and 38% lower hip fracture risk. In orthopedic settings, emerging evidence suggests that sequential protocols may improve postoperative bone mineral density after hip fracture, support spinal fusion, and mitigate periprosthetic bone loss after arthroplasty. Prior antiresorptive exposure appeared to attenuate subsequent anabolic response, particularly at the hip, supporting the rationale for earlier anabolic use. Economic analyses also suggest that, despite higher upfront drug costs, sequential therapy may be cost-effective in patients at high fracture risk. Summary Current evidence supports anabolic-first sequential therapy as a more effective strategy than step-therapy for improving bone mineral density and reducing fracture risk in appropriately selected high-risk patients. For orthopedic populations, the available data suggest meaningful potential benefits in hip fracture care, spinal reconstruction, and arthroplasty, although subspecialty-specific evidence remains more limited than the broader osteoporosis literature. These findings support reconsideration of formulary and treatment policies that delay anabolic therapy in patients most likely to benefit.