Brigato Paolo, Vadalà Gianluca, De Salvatore Sergio, Oggiano Leonardo, Papalia Giuseppe Francesco, Russo Fabrizio, Papalia Rocco, Costici Pier Francesco, Denaro Vincenzo
Research Unit of Orthopaedic and Trauma Surgery, Department of Medicine and Surgery, Università Campus Bio-Medico di Roma, Via Alvaro del Portillo, Roma, 21 - 00128, Italy.
Fondazione Campus Bio-Medico di Roma, Via Alvaro del Portillo 200, Roma 00128, Italy.
Brain Spine. 2025 May 5;5:104273. doi: 10.1016/j.bas.2025.104273. eCollection 2025.
Adult spinal deformity (ASD) surgery involves high costs and risks, with Proximal Junctional Kyphosis (PJK) and Proximal Junctional Failure (PJF) being major concerns. Artificial intelligence (AI) and machine learning (ML) offer potential in predicting and preventing these complications. This review examines the role of AI in predicting PJK/PJF, its effectiveness, and future research needs.
Can AI-based models accurately predict PJK/PJF after ASD surgery, and what factors affect their performance?
A systematic review was conducted following PRISMA guidelines, analyzing Medline, Scopus, Embase, and Cochrane Library databases up to December 2024. Keywords included "Adult Spinal Deformity," "PJK," "PJF," "AI," and "ML." Data extracted included study characteristics, patient demographics, surgical details, AI model parameters, and performance metrics. Bias risk was assessed using the MINORS score.
Among 164 studies, 7 met inclusion criteria (n = 2179 patients). Mean age was 63.2 ± 3.7 years, BMI 26.1 ± 2.4 kg/m, and fusion levels 9.82 ± 1.8. PJK/PJF occurred in 41.1 %. AI models (Random Forest, supervised learning) had accuracy from 72.5 % to 100 % (AUC up to 1.0). Key predictors included age, BMD, spinal alignment, and implant type.
AI and ML models show promise in predicting PJK/PJF after ASD surgery. However, larger multicenter studies with standardized definitions, BMD assessments, and preoperative MRI integration are needed for broader clinical application and validation.
成人脊柱畸形（ASD）手术成本高、风险大，近端交界性后凸（PJK）和近端交界性失败（PJF）是主要关注点。人工智能（AI）和机器学习（ML）在预测和预防这些并发症方面具有潜力。本综述探讨了AI在预测PJK/PJF中的作用、其有效性以及未来的研究需求。
基于AI的模型能否准确预测ASD手术后的PJK/PJF，哪些因素会影响其性能？
按照PRISMA指南进行系统综述，分析截至2024年12月的Medline、Scopus、Embase和Cochrane图书馆数据库。关键词包括“成人脊柱畸形”、“PJK”、“PJF”、“AI”和“ML”。提取的数据包括研究特征、患者人口统计学、手术细节、AI模型参数和性能指标。使用MINORS评分评估偏倚风险。
在164项研究中，7项符合纳入标准（n = 2179例患者）。平均年龄为63.2±3.7岁，体重指数为26.1±2.4kg/m，融合节段数为9.82±1.8。PJK/PJF发生率为41.1%。AI模型（随机森林，监督学习）的准确率为72.5%至100%（AUC高达1.0）。关键预测因素包括年龄、骨密度、脊柱排列和植入物类型。
AI和ML模型在预测ASD手术后的PJK/PJF方面显示出前景。然而，需要进行更大规模的多中心研究，采用标准化定义、骨密度评估和术前MRI整合，以实现更广泛的临床应用和验证。
