基于机器学习的表面肌电图地形图评估在慢性下腰痛功能恢复康复中的预后预测。

A Machine Learning-based Surface Electromyography Topography Evaluation for Prognostic Prediction of Functional Restoration Rehabilitation in Chronic Low Back Pain.

机构信息

Department of Orthopaedics and Traumatology, Li Ka Shing Faculty of Medicine, The University of Hong Kong, Pokfulam, Hong Kong.

Department of Orthopaedics and Traumatology, Shenzhen Key Laboratory for Innovative Technology in Orthopaedic Trauma, The University of Hong Kong-Shenzhen Hospital, Shenzhen, 518053, China.

出版信息

Spine (Phila Pa 1976). 2017 Nov 1;42(21):1635-1642. doi: 10.1097/BRS.0000000000002159.

DOI:10.1097/BRS.0000000000002159

PMID:28338573

Abstract

STUDY DESIGN

A retrospective study.

OBJECTIVE

The aim of this study was to investigate the feasibility and applicability of support vector machine (SVM) algorithm in classifying patients with LBP who would obtain satisfactory or unsatisfactory progress after the functional restoration rehabilitation program.

SUMMARY OF BACKGROUND DATA

Dynamic surface electromyography (SEMG) topography has demonstrated the potential use in predicting the prognosis of functional restoration rehabilitation for patients with low back pain (LBP). However, processing from raw SEMG topography to make prediction is not easy to clinicians.

METHODS

A total of 30 patients with nonspecific LBP were recruited and divided into "responding" and "non-responding" group according to the change of Visual analog pain rating scale and Oswestry Disability Index. Each patient received a 12-week functional restoration rehabilitation program. A normal database was calculated from a control group from 48 healthy participants. Root-mean-square difference (RMSD) was extracted from the recorded dynamic SEMG topography during symmetrical and asymmetrical trunk-movement. SVM and cross-validation were applied to the prediction based on the optimized features selected by the sequential floating forward selection (SFFS) algorithm.

RESULTS

RMSD feature parameters following rehabilitation in the "responding" group showed a significant difference (P < 0.05) with the one in the "nonresponding" group. The SVM classifier with Quadratic kernel based on SFFS-selected features showed the best prediction performance (accuracy: 96.67%, sensitivity: 100%, specificity: 93.75%, average area under curve [AUC]: 0.8925) comparing with linear kernel (accuracy: 80.00%, sensitivity: 85.71%, specificity: 75.00%, average AUC: 0.7825), polynomial kernel (accuracy: 93.33%, sensitivity: 92.86%, specificity: 93.75%, average AUC: 0.9675), and radial basis function (RBF) kernel (accuracy: 86.67%, sensitivity: 85.71%, specificity: 87.50%, average AUC: 0.7900).

CONCLUSION

The use of SVM-based classifier of SEMG topography can be applied to identify the patient responding to functional restoration rehabilitation, which will help the healthcare worker to improve the efficiency of LBP rehabilitation.

LEVEL OF EVIDENCE

摘要

研究设计

回顾性研究。

目的

本研究旨在探讨支持向量机（SVM）算法在分类接受功能恢复康复后疗效满意或不满意的下腰痛（LBP）患者中的可行性和适用性。

背景资料概要

动态表面肌电图（SEMG）地形图已证明在预测 LBP 患者功能恢复康复预后方面具有潜在的应用价值。然而，从原始 SEMG 地形图进行处理以进行预测对临床医生来说并不容易。

方法

共招募了 30 名非特异性 LBP 患者，根据视觉模拟疼痛评分和 Oswestry 残疾指数的变化，将其分为“有反应”和“无反应”组。每位患者接受 12 周的功能恢复康复计划。从 48 名健康参与者的对照组中计算出正常数据库。从对称和不对称躯干运动过程中记录的动态 SEMG 地形图中提取均方根差（RMSD）。基于顺序浮动前向选择（SFFS）算法选择的优化特征，应用 SVM 和交叉验证进行预测。

结果

康复后“有反应”组的 RMSD 特征参数与“无反应”组相比有显著差异（P<0.05）。基于 SFFS 选择特征的二次核 SVM 分类器显示出最佳的预测性能（准确率：96.67%，灵敏度：100%，特异性：93.75%，平均 AUC：0.8925），与线性核（准确率：80.00%，灵敏度：85.71%，特异性：75.00%，平均 AUC：0.7825）、多项式核（准确率：93.33%，灵敏度：92.86%，特异性：93.75%，平均 AUC：0.9675）和径向基函数（RBF）核（准确率：86.67%，灵敏度：85.71%，特异性：87.50%，平均 AUC：0.7900）相比。