A Novel Preoperative Scoring System to Accurately Predict Cord-Level Intraoperative Neuromonitoring Data Loss During Spinal Deformity Surgery: A Machine-Learning Approach.

IF 4.4 1区医学 Q1 ORTHOPEDICS Journal of Bone and Joint Surgery, American Volume Pub Date : 2024-11-20 DOI:10.2106/JBJS.24.00386

Nathan J Lee, Lawrence G Lenke, Varun Arvind, Ted Shi, Alexandra C Dionne, Chidebelum Nnake, Mitchell Yeary, Michael Fields, Matt Simhon, Anastasia Ferraro, Matthew Cooney, Erik Lewerenz, Justin L Reyes, Steven G Roth, Chun Wai Hung, Justin K Scheer, Thomas Zervos, Earl D Thuet, Joseph M Lombardi, Zeeshan M Sardar, Ronald A Lehman, Benjamin D Roye, Michael G Vitale, Fthimnir M Hassan

{"title":"A Novel Preoperative Scoring System to Accurately Predict Cord-Level Intraoperative Neuromonitoring Data Loss During Spinal Deformity Surgery: A Machine-Learning Approach.","authors":"Nathan J Lee, Lawrence G Lenke, Varun Arvind, Ted Shi, Alexandra C Dionne, Chidebelum Nnake, Mitchell Yeary, Michael Fields, Matt Simhon, Anastasia Ferraro, Matthew Cooney, Erik Lewerenz, Justin L Reyes, Steven G Roth, Chun Wai Hung, Justin K Scheer, Thomas Zervos, Earl D Thuet, Joseph M Lombardi, Zeeshan M Sardar, Ronald A Lehman, Benjamin D Roye, Michael G Vitale, Fthimnir M Hassan","doi":"10.2106/JBJS.24.00386","DOIUrl":null,"url":null,"abstract":"Background: An accurate knowledge of a patient's risk of cord-level intraoperative neuromonitoring (IONM) data loss is important for an informed decision-making process prior to deformity correction, but no prediction tool currently exists.Methods: A total of 1,106 patients with spinal deformity and 205 perioperative variables were included. A stepwise machine-learning (ML) approach using random forest (RF) analysis and multivariable logistic regression was performed. Patients were randomly allocated to training (75% of patients) and testing (25% of patients) groups. Feature score weights were derived by rounding up the regression coefficients from the multivariable logistic regression model. Variables in the final scoring calculator were automatically selected through the ML process to optimize predictive performance.Results: Eight features were included in the scoring system: sagittal deformity angular ratio (sDAR) of ≥15 (score = 2), type-3 spinal cord shape (score = 2), conus level below L2 (score = 2), cervical upper instrumented vertebra (score = 2), preoperative upright largest thoracic Cobb angle of ≥75° (score = 2), preoperative lower-extremity motor deficit (score = 2), preoperative upright largest thoracic kyphosis of ≥80° (score = 1), and total deformity angular ratio (tDAR) of ≥25 (score = 1). Higher cumulative scores were associated with increased rates of cord-level IONM data loss: patients with a cumulative score of ≤2 had a cord-level IONM data loss rate of 0.9%, whereas those with a score of ≥7 had a loss rate of 86%. When evaluated in the testing group, the scoring system achieved an accuracy of 93%, a sensitivity of 75%, a specificity of 94%, and an AUC (area under the receiver operating characteristic curve) of 0.898.Conclusions: This is the first study to provide an ML-derived preoperative scoring system that predicts cord-level IONM data loss during pediatric and adult spinal deformity surgery with >90% accuracy.Level of evidence: Prognostic Level III. See Instructions for Authors for a complete description of levels of evidence.","PeriodicalId":15273,"journal":{"name":"Journal of Bone and Joint Surgery, American Volume","volume":" ","pages":""},"PeriodicalIF":4.4000,"publicationDate":"2024-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Bone and Joint Surgery, American Volume","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.2106/JBJS.24.00386","RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ORTHOPEDICS","Score":null,"Total":0}

引用次数: 0

Abstract

Background: An accurate knowledge of a patient's risk of cord-level intraoperative neuromonitoring (IONM) data loss is important for an informed decision-making process prior to deformity correction, but no prediction tool currently exists.

Methods: A total of 1,106 patients with spinal deformity and 205 perioperative variables were included. A stepwise machine-learning (ML) approach using random forest (RF) analysis and multivariable logistic regression was performed. Patients were randomly allocated to training (75% of patients) and testing (25% of patients) groups. Feature score weights were derived by rounding up the regression coefficients from the multivariable logistic regression model. Variables in the final scoring calculator were automatically selected through the ML process to optimize predictive performance.

Results: Eight features were included in the scoring system: sagittal deformity angular ratio (sDAR) of ≥15 (score = 2), type-3 spinal cord shape (score = 2), conus level below L2 (score = 2), cervical upper instrumented vertebra (score = 2), preoperative upright largest thoracic Cobb angle of ≥75° (score = 2), preoperative lower-extremity motor deficit (score = 2), preoperative upright largest thoracic kyphosis of ≥80° (score = 1), and total deformity angular ratio (tDAR) of ≥25 (score = 1). Higher cumulative scores were associated with increased rates of cord-level IONM data loss: patients with a cumulative score of ≤2 had a cord-level IONM data loss rate of 0.9%, whereas those with a score of ≥7 had a loss rate of 86%. When evaluated in the testing group, the scoring system achieved an accuracy of 93%, a sensitivity of 75%, a specificity of 94%, and an AUC (area under the receiver operating characteristic curve) of 0.898.

Conclusions: This is the first study to provide an ML-derived preoperative scoring system that predicts cord-level IONM data loss during pediatric and adult spinal deformity surgery with >90% accuracy.

Level of evidence: Prognostic Level III. See Instructions for Authors for a complete description of levels of evidence.

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

一种新的术前评分系统，可以准确预测脊柱畸形手术中脊髓水平的术中神经监测数据丢失：一种机器学习方法。

背景：准确了解患者术中脐带水平神经监测（IONM）数据丢失的风险对于畸形矫正前的知情决策过程非常重要，但目前还没有预测工具。方法：共纳入1106例脊柱畸形患者和205个围手术期变量。采用随机森林（RF）分析和多变量逻辑回归的逐步机器学习（ML）方法。患者随机分配到训练组（75%的患者）和测试组（25%的患者）。通过对多变量logistic回归模型的回归系数进行四舍五入得到特征得分权重。通过ML过程自动选择最终计分计算器中的变量，优化预测性能。结果：评分系统包括八个特征：矢状面畸形角比(sDAR)≥15（评分= 2），3型脊髓形状（评分= 2），L2以下圆锥水平（评分= 2），颈椎上固定椎体（评分= 2），术前直立最大胸椎Cobb角≥75°（评分= 2），术前下肢运动缺陷（评分= 2），术前直立最大胸椎后凸≥80°（评分= 1），总畸形角比(tDAR)≥25（评分= 1）。较高的累积评分与脐带水平IONM数据丢失率增加相关：累积评分≤2的患者脐带水平IONM数据丢失率为0.9%，而评分≥7的患者脐带水平IONM数据丢失率为86%。在测试组中进行评估时，评分系统的准确率为93%，灵敏度为75%，特异性为94%，AUC（受试者工作特征曲线下面积）为0.898。结论：这是第一个提供基于ml的术前评分系统的研究，该系统可以预测儿童和成人脊柱畸形手术中脊髓水平IONM数据丢失，准确率为bbb90 %。证据等级：预后III级。有关证据水平的完整描述，请参见作者说明。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文去求助

来源期刊

Journal of Bone and Joint Surgery, American Volume 医学-外科

CiteScore

8.90

自引率

7.50%

发文量

660

审稿时长

1 months

期刊介绍： The Journal of Bone & Joint Surgery (JBJS) has been the most valued source of information for orthopaedic surgeons and researchers for over 125 years and is the gold standard in peer-reviewed scientific information in the field. A core journal and essential reading for general as well as specialist orthopaedic surgeons worldwide, The Journal publishes evidence-based research to enhance the quality of care for orthopaedic patients. Standards of excellence and high quality are maintained in everything we do, from the science of the content published to the customer service we provide. JBJS is an independent, non-profit journal.