评估和验证机器学习增强的美国脊髓损伤协会损伤等级的入院归因。

IF 2.9 2区 医学 Q2 CLINICAL NEUROLOGY
Ritvik R Jillala, Carlos A Aude, Vikas N Vattipally, Kathleen R Ran, Kelly Jiang, Carly Weber-Levine, A Daniel Davidar, Andrew M Hersh, Jacob Jo, Daniel Lubelski, Ali Bydon, Timothy Witham, Nicholas Theodore, Tej D Azad
{"title":"评估和验证机器学习增强的美国脊髓损伤协会损伤等级的入院归因。","authors":"Ritvik R Jillala, Carlos A Aude, Vikas N Vattipally, Kathleen R Ran, Kelly Jiang, Carly Weber-Levine, A Daniel Davidar, Andrew M Hersh, Jacob Jo, Daniel Lubelski, Ali Bydon, Timothy Witham, Nicholas Theodore, Tej D Azad","doi":"10.3171/2025.1.SPINE241135","DOIUrl":null,"url":null,"abstract":"<p><strong>Objective: </strong>The American Spinal Injury Association Impairment Scale (AIS) assigned at patient admission is an important predictor of outcomes following spinal cord injury (SCI). However, nearly 80% of records in the Spinal Cord Injury Model Systems (SCIMS) database-a multicenter prospective database of patients with SCI-lack admission AIS grades. Accurate imputation of this missing data could enable more robust analyses and insights into SCI recovery. This study aims to develop and validate methods for imputing missing admission AIS data in the SCIMS database.</p><p><strong>Methods: </strong>The study included 16,062 patients with SCI from the publicly available SCIMS database (1988-2020). Five machine learning algorithms-random forest (RF), linear discriminant analysis, K-nearest neighbors, naive Bayes, and support vector machine-were compared using performance metrics (accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and multiclass area under the receiver operating characteristic curve) using five-fold cross-validation on a training subset of 6054 patients with complete AIS admission grades. The model with the highest performance was trained on all 16,062 patients. The imputed AIS grades were validated by predicting discharge functional independence measure (FIM) scores (range 13-91) with simple and multiple linear regression models on a 1:1 propensity score-matched cohort (n = 5828). Model performance was compared using differences in root mean square error (∆RMSE) with bootstrapped 95% confidence intervals (CIs).</p><p><strong>Results: </strong>The full cohort contained a representative distribution of AIS grades (45% grade A, 13% grade B, 18% grade C, and 24% grade D), and the propensity score-matched cohort characteristics were well balanced. The RF algorithm demonstrated the highest validation accuracy (81.7%). Predictive models showed no significant differences between models using true versus imputed AIS grades, with 95% CIs for ∆RMSE of -0.60 to 0.47 for simple regression and -0.63 to 0.46 for multiple regression models. The coefficients of AIS grades also did not significantly differ between models with true versus imputed values.</p><p><strong>Conclusions: </strong>A data-driven approach to imputation resulted in a robust method for imputing admission AIS grades that demonstrated clinical validity in the SCIMS database. This approach extends the utility of this longitudinal database and may provide a framework for other SCI databases.</p>","PeriodicalId":16562,"journal":{"name":"Journal of neurosurgery. Spine","volume":" ","pages":"1-8"},"PeriodicalIF":2.9000,"publicationDate":"2025-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Assessing and validating machine learning-enhanced imputation of admission American Spinal Injury Association Impairment Scale grades for spinal cord injury.\",\"authors\":\"Ritvik R Jillala, Carlos A Aude, Vikas N Vattipally, Kathleen R Ran, Kelly Jiang, Carly Weber-Levine, A Daniel Davidar, Andrew M Hersh, Jacob Jo, Daniel Lubelski, Ali Bydon, Timothy Witham, Nicholas Theodore, Tej D Azad\",\"doi\":\"10.3171/2025.1.SPINE241135\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Objective: </strong>The American Spinal Injury Association Impairment Scale (AIS) assigned at patient admission is an important predictor of outcomes following spinal cord injury (SCI). However, nearly 80% of records in the Spinal Cord Injury Model Systems (SCIMS) database-a multicenter prospective database of patients with SCI-lack admission AIS grades. Accurate imputation of this missing data could enable more robust analyses and insights into SCI recovery. This study aims to develop and validate methods for imputing missing admission AIS data in the SCIMS database.</p><p><strong>Methods: </strong>The study included 16,062 patients with SCI from the publicly available SCIMS database (1988-2020). Five machine learning algorithms-random forest (RF), linear discriminant analysis, K-nearest neighbors, naive Bayes, and support vector machine-were compared using performance metrics (accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and multiclass area under the receiver operating characteristic curve) using five-fold cross-validation on a training subset of 6054 patients with complete AIS admission grades. The model with the highest performance was trained on all 16,062 patients. The imputed AIS grades were validated by predicting discharge functional independence measure (FIM) scores (range 13-91) with simple and multiple linear regression models on a 1:1 propensity score-matched cohort (n = 5828). Model performance was compared using differences in root mean square error (∆RMSE) with bootstrapped 95% confidence intervals (CIs).</p><p><strong>Results: </strong>The full cohort contained a representative distribution of AIS grades (45% grade A, 13% grade B, 18% grade C, and 24% grade D), and the propensity score-matched cohort characteristics were well balanced. The RF algorithm demonstrated the highest validation accuracy (81.7%). Predictive models showed no significant differences between models using true versus imputed AIS grades, with 95% CIs for ∆RMSE of -0.60 to 0.47 for simple regression and -0.63 to 0.46 for multiple regression models. The coefficients of AIS grades also did not significantly differ between models with true versus imputed values.</p><p><strong>Conclusions: </strong>A data-driven approach to imputation resulted in a robust method for imputing admission AIS grades that demonstrated clinical validity in the SCIMS database. This approach extends the utility of this longitudinal database and may provide a framework for other SCI databases.</p>\",\"PeriodicalId\":16562,\"journal\":{\"name\":\"Journal of neurosurgery. Spine\",\"volume\":\" \",\"pages\":\"1-8\"},\"PeriodicalIF\":2.9000,\"publicationDate\":\"2025-05-09\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of neurosurgery. Spine\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.3171/2025.1.SPINE241135\",\"RegionNum\":2,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"CLINICAL NEUROLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of neurosurgery. Spine","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.3171/2025.1.SPINE241135","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"CLINICAL NEUROLOGY","Score":null,"Total":0}
引用次数: 0

摘要

目的:在患者入院时分配的美国脊髓损伤协会损伤量表(AIS)是脊髓损伤(SCI)后预后的重要预测指标。然而,在脊髓损伤模型系统(SCIMS)数据库(一个多中心前瞻性sci患者数据库)中,近80%的记录缺乏入院AIS分级。对这些缺失数据的准确输入可以对SCI恢复进行更可靠的分析和洞察。本研究旨在开发并验证SCIMS数据库中缺失入院AIS数据的输入方法。方法:该研究纳入了来自公开可用的SCIMS数据库(1988-2020)的16,062例SCI患者。在6054例AIS完整住院分级患者的训练子集上,使用五倍交叉验证,比较了随机森林(RF)、线性判别分析、k近邻、朴素贝叶斯和支持向量机这五种机器学习算法的性能指标(准确性、灵敏度、特异性、阳性预测值、阴性预测值和接受者工作特征曲线下的多类别面积)。在所有16062名患者身上训练了表现最好的模型。在1:1倾向评分匹配的队列(n = 5828)中,通过简单和多元线性回归模型预测出院功能独立测量(FIM)评分(范围13-91),验证了输入的AIS评分。采用自举95%置信区间(ci)的均方根误差(∆RMSE)差异比较模型性能。结果:整个队列包含具有代表性的AIS等级分布(45%为a级,13%为B级,18%为C级,24%为D级),并且倾向评分匹配的队列特征得到了很好的平衡。RF算法的验证准确率最高(81.7%)。预测模型显示,使用真实AIS评分的模型与输入AIS评分的模型之间没有显著差异,简单回归模型的∆RMSE的95% ci为-0.60至0.47,多元回归模型的ci为-0.63至0.46。AIS等级的系数在真实值和输入值的模型之间也没有显著差异。结论:数据驱动的归算方法产生了一种可靠的归算入院AIS评分的方法,该方法在SCIMS数据库中证明了临床有效性。这种方法扩展了该纵向数据库的实用性,并可能为其他SCI数据库提供一个框架。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Assessing and validating machine learning-enhanced imputation of admission American Spinal Injury Association Impairment Scale grades for spinal cord injury.

Objective: The American Spinal Injury Association Impairment Scale (AIS) assigned at patient admission is an important predictor of outcomes following spinal cord injury (SCI). However, nearly 80% of records in the Spinal Cord Injury Model Systems (SCIMS) database-a multicenter prospective database of patients with SCI-lack admission AIS grades. Accurate imputation of this missing data could enable more robust analyses and insights into SCI recovery. This study aims to develop and validate methods for imputing missing admission AIS data in the SCIMS database.

Methods: The study included 16,062 patients with SCI from the publicly available SCIMS database (1988-2020). Five machine learning algorithms-random forest (RF), linear discriminant analysis, K-nearest neighbors, naive Bayes, and support vector machine-were compared using performance metrics (accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and multiclass area under the receiver operating characteristic curve) using five-fold cross-validation on a training subset of 6054 patients with complete AIS admission grades. The model with the highest performance was trained on all 16,062 patients. The imputed AIS grades were validated by predicting discharge functional independence measure (FIM) scores (range 13-91) with simple and multiple linear regression models on a 1:1 propensity score-matched cohort (n = 5828). Model performance was compared using differences in root mean square error (∆RMSE) with bootstrapped 95% confidence intervals (CIs).

Results: The full cohort contained a representative distribution of AIS grades (45% grade A, 13% grade B, 18% grade C, and 24% grade D), and the propensity score-matched cohort characteristics were well balanced. The RF algorithm demonstrated the highest validation accuracy (81.7%). Predictive models showed no significant differences between models using true versus imputed AIS grades, with 95% CIs for ∆RMSE of -0.60 to 0.47 for simple regression and -0.63 to 0.46 for multiple regression models. The coefficients of AIS grades also did not significantly differ between models with true versus imputed values.

Conclusions: A data-driven approach to imputation resulted in a robust method for imputing admission AIS grades that demonstrated clinical validity in the SCIMS database. This approach extends the utility of this longitudinal database and may provide a framework for other SCI databases.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Journal of neurosurgery. Spine
Journal of neurosurgery. Spine 医学-临床神经学
CiteScore
5.10
自引率
10.70%
发文量
396
审稿时长
6 months
期刊介绍: Primarily publish original works in neurosurgery but also include studies in clinical neurophysiology, organic neurology, ophthalmology, radiology, pathology, and molecular biology.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信