Scholarlink

Background <p>Spinal surgery carries substantial perioperative risks. Early identification of high-risk patients is critical for improving outcomes. Machine learning (ML) can enhance predictive accuracy over traditional risk scores by modeling complex clinical data, but many existing models lack large, heterogeneous cohorts.</p> Objective <p>To develop and validate ML models for predicting perioperative complications in spine surgery, and assess fairness across patient subgroups.</p> Methods <p>We conducted a retrospective cohort study of 5,060 adult patients from the SpineReg registry (2015–2023), each with 160 preoperative demographic, clinical, imaging, and patient-reported outcome features. Six ML algorithms—logistic regression (LR), decision tree, k-nearest neighbors, naïve Bayes, random forest (RF), and eXtreme gradient boosting—were trained with 80/20 train-test split, cross-validation, and hyperparameter optimization. Class imbalance was addressed via repeated undersampling. Performance was assessed using area under the ROC curve (AUC), balanced accuracy, positive predictive value (PPV), standardized net benefit (sNB), calibration, and fairness metrics.</p> Results <p>RF achieved the best performance, obtaining an AUC of 0.87, balanced accuracy of 0.80, PPV of 0.71, and sNB of 0.44. RF maintained robust performance across demographic and surgical subgroups. Key predictors of increased complication risk included sagittal imbalance, and multilevel surgery, whereas degenerative pathology and monosegmental fusion were protective. Sensitivity declined for rare complications but exceeded 75% for most categories.</p> Conclusions <p>RF-based models can accurately and equitably predict perioperative complications in diverse spine surgery contexts, supporting personalized counseling, targeted monitoring, and optimized resource allocation. Integration into clinical decision support systems may enhance surgical safety and efficiency.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Machine learning–based prediction of perioperative complications in spine surgery: a large-scale model development and validation study

  • 期刊论文

  • 发表日期：

    2026年7月27日

查看全文
  • Andrea Campagner,
  • Francesco Langella,
  • Pablo Bellosta-López,
  • Francesca Barile,
  • Riccardo Cecchinato,
  • Domenico Compagnone,
  • Marco Damilano,
  • Claudio Lamartina,
  • Andrea Redaelli,
  • Daniele Vanni,
  • Federico Cabitza,
  • Claudia Meroni,
  • Pedro Berjano

摘要

Background

Spinal surgery carries substantial perioperative risks. Early identification of high-risk patients is critical for improving outcomes. Machine learning (ML) can enhance predictive accuracy over traditional risk scores by modeling complex clinical data, but many existing models lack large, heterogeneous cohorts.

Objective

To develop and validate ML models for predicting perioperative complications in spine surgery, and assess fairness across patient subgroups.

Methods

We conducted a retrospective cohort study of 5,060 adult patients from the SpineReg registry (2015–2023), each with 160 preoperative demographic, clinical, imaging, and patient-reported outcome features. Six ML algorithms—logistic regression (LR), decision tree, k-nearest neighbors, naïve Bayes, random forest (RF), and eXtreme gradient boosting—were trained with 80/20 train-test split, cross-validation, and hyperparameter optimization. Class imbalance was addressed via repeated undersampling. Performance was assessed using area under the ROC curve (AUC), balanced accuracy, positive predictive value (PPV), standardized net benefit (sNB), calibration, and fairness metrics.

Results

RF achieved the best performance, obtaining an AUC of 0.87, balanced accuracy of 0.80, PPV of 0.71, and sNB of 0.44. RF maintained robust performance across demographic and surgical subgroups. Key predictors of increased complication risk included sagittal imbalance, and multilevel surgery, whereas degenerative pathology and monosegmental fusion were protective. Sensitivity declined for rare complications but exceeded 75% for most categories.

Conclusions

RF-based models can accurately and equitably predict perioperative complications in diverse spine surgery contexts, supporting personalized counseling, targeted monitoring, and optimized resource allocation. Integration into clinical decision support systems may enhance surgical safety and efficiency.