Baroncini Alice, Larrieu Daniel, Bourghli Anouar, Pizones Javier, Pellisé Ferran, Kleinstueck Frank S, Alanay Ahmet, Boissiere Louis, Obeid Ibrahim
IRCCS Ospedale Galeazzi - Sant'Ambrogio, Milan, Italy.
ELSAN, Polyclinique Jean Villar, Brugge, France.
Eur Spine J. 2025 Jan 11. doi: 10.1007/s00586-025-08653-y.
The choice of the best management for Adult Spine Deformity (ASD) is challenging. Health-related quality of life (HRQoL), comorbidities, symptoms and spine geometry, along with surgical risk and potential residual disability play a role, and a definite algorithm for patient management is lacking. Machine learning allows to analyse complex settings more efficiently than other available statistical tools. Aim of this study was to develop a machine-learning algorithm that, based on baseline data, would be able to predict whether an ASD patient would undergo surgery or not.
Retrospective evaluation of prospectively collected data. Demographic data, HRQoL and radiographic parameters were collected. Two clustering methods were performed to differentiate groups of patients with similar characteristics. Three models were then used to identify the most relevant variables for management prediction.
Data from 1319 patients were available. Three clusters were identified: older subjects with sagittal imbalance and high PI, younger patients with greater coronal deformity and no sagittal imbalance, older patients with moderate sagittal imbalance and lower PI. The group of younger patients showed the highest error rate for the prediction (37%), which was lower for the other two groups (20-27%). For all groups, quality of life parameters such as the ODI and the SRS 22 and the Cobb angle of the major curve were the strongest predictors of surgical indication, albeit with different odds ratios in each group.
Three clusters could be identified along with the variables that, in each, are most likely to drive the choice of management.
为成人脊柱畸形（ASD）选择最佳治疗方案具有挑战性。与健康相关的生活质量（HRQoL）、合并症、症状和脊柱形态，以及手术风险和潜在的残余残疾都起着作用，目前缺乏明确的患者管理算法。与其他可用的统计工具相比，机器学习能够更有效地分析复杂情况。本研究的目的是开发一种基于基线数据能够预测ASD患者是否会接受手术的机器学习算法。
对前瞻性收集的数据进行回顾性评估。收集人口统计学数据、HRQoL和影像学参数。采用两种聚类方法区分具有相似特征的患者组。然后使用三种模型来识别管理预测中最相关的变量。
有1319例患者的数据可用。识别出三个聚类：矢状面失衡且PI值高的老年患者；冠状面畸形较大且无矢状面失衡的年轻患者；矢状面失衡程度中等且PI值较低的老年患者。年轻患者组的预测错误率最高（37%），其他两组较低（20%-27%）。对于所有组，诸如ODI、SRS 22等生活质量参数以及主弯的Cobb角是手术指征的最强预测因素，尽管每组的优势比不同。
可以识别出三个聚类以及每个聚类中最有可能驱动治疗选择的变量。
