文献速递关节外科

机器学习基于术前可穿戴传感器计时起立-行走测试对全膝关节置换患者早期功能改善可能性进行分组

Machine Learning Groups Patients by Early Functional Improvement Likelihood Based on Wearable Sensor Instrumented Preoperative Timed-Up-and-Go Tests.
PubMed 文献 · J Arthroplasty · 2019-06-05

本研究纳入68例初次单侧全膝关节置换患者,术前及术后2、6、12周完成可穿戴传感器仪器的计时起立-行走测试,提取55项指标,采用K-means算法将患者分为2个功能组(n=46和n=22),两组测试完成时间分别为12.6秒和21.6秒(P<.001)。追踪至12周随访,一组64%患者功能改善,另一组63%维持术前功能;改善较高组测试时间缩短4.94秒(P=.005),另一组未超过最小重要临床差异(0.87秒,P=.07)。

要点

  • 术前可穿戴传感器计时起立-行走测试可区分全膝关节置换患者的功能组别。
  • 两组术前测试完成时间分别为12.6秒和21.6秒,差异有统计学意义(P<.001)。
  • 12周随访时一组64%功能改善,另一组63%维持术前功能。

核心结论

  • 本研究支持在临床随访中使用可穿戴传感器进行功能测试,并利用机器学习解析复杂模式以揭示临床相关参数。

研究设计与样本

  • 纳入68例初次单侧全膝关节置换患者,术前及术后2、6、12周完成可穿戴传感器仪器的计时起立-行走测试,提取55项指标,采用K-means算法将患者分为功能不同的组别。

主要发现

  • 患者被分为2个集群(n=46和n=22),两组测试完成时间分别为12.6秒和21.6秒,差异有统计学意义(P<.001)。
  • 追踪两组至12周随访,一组64%的患者功能改善,另一组63%维持术前功能。
  • 改善较高组测试时间缩短4.94秒(P=.005),显示恢复更快;另一组未改善超过最小重要临床差异(0.87秒,P=.07)。
  • 组间效应量最大的特征被认定为重要的功能参数。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

BACKGROUND: Wearable sensors permit efficient data collection and unobtrusive systems can be used for instrumenting knee patients for objective assessment. Machine learning can be leveraged to parse the abundant information these systems provide and segment patients into relevant groups without specifying group membership criteria. The objective of this study is to examine functional parameters influencing favorable recovery outcomes by separating patients into functional groups and tracking them through clinical follow-ups. METHODS: Patients undergoing primary unilateral total knee arthroplasty (n = 68) completed instrumented timed-up-and-go tests preoperatively and at their 2-, 6-, and 12-week follow-up appointments. A custom wearable system extracted 55 metrics for analysis and a K-means algorithm separated patients into functionally distinguished groups based on the derived features. These groups were analyzed to determine which metrics differentiated most and how each cluster improved during early recovery. RESULTS: Patients separated into 2 clusters (n = 46 and n = 22) with significantly different test completion times (12.6 s vs 21.6 s, P < .001). Tracking the recovery of both groups to their 12-week follow-ups revealed 64% of one group improved their function while 63% of the other maintained preoperative function. The higher improvement group shortened their test times by 4.94 s, (P = .005) showing faster recovery while the other group did not improve above a minimally important clinical difference (0.87 s, P = .07). Features with the largest effect size between groups were distinguished as important functional parameters. CONCLUSION: This work supports using wearable sensors to instrument functional tests during clinical visits and using machine learning to parse complex patterns to reveal clinically relevant parameters.

来源:J Arthroplasty,查看原文。版权归原作者所有。

引用

  1. Bloomfield RA, Williams HA, Broberg JS, et al. Machine Learning Groups Patients by Early Functional Improvement Likelihood Based on Wearable Sensor Instrumented Preoperative Timed-Up-and-Go Tests. J Arthroplasty. 2019. PMID: 31255408. doi:10.1016/j.arth.2019.05.061

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。