机器学习在卒中后72小时内预测上肢结局的准确性
本研究基于4项荷兰前瞻性队列研究共296例首次缺血性卒中患者,开发并内部验证机器学习模型,用卒中后3天内的简易床旁临床测试预测6个月Action Research Arm Test评分。模型采用肩外展Motricity指数、主动手指伸展、Fugl-Meyer上肢和NIHSS总分,在测试集(n=32)中位绝对误差为5.9分(IQR 2.9-12.9),低于6分的MCID。
要点
- 卒中后3天内床旁测试可预测6个月上肢功能。
- 最小预测集为肩外展、手指伸展、Fugl-Meyer上肢和NIHSS。
- 中位绝对误差5.9分,低于MCID 6分。
核心结论
- 模型用卒中后3天内最小床旁测试集预测6个月ARAT评分,中位绝对误差5.9分,低于MCID 6分。
研究设计与样本
- 汇总4项荷兰前瞻性队列研究,44个中心,2000-2019年,296例首次缺血性卒中患者。
- 比较多个XGBoost模型,交叉验证预测性能,选出最小预测集,并在同队列测试集(n=32)中验证。
主要发现
- 最佳模型纳入肩外展Motricity指数、主动手指伸展、Fugl-Meyer上肢和NIHSS总分。
- 测试集中位绝对误差5.9分(0-57分ARAT量表;IQR 2.9-12.9)。
关键数值与推荐
- ARAT评分范围0-57分,MCID为6分。
- 中位绝对误差5.9分(IQR 2.9-12.9),低于MCID。
临床怎么用
- 卒中单元可在发病72小时内用简易床旁测试评估上肢预后,辅助康复规划。
局限性
- 测试集样本量小(n=32),仅内部验证,需外部验证。
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: Timely and accurate prediction of poststroke motor outcome is important for efficient rehabilitation planning and resource allocation. Existing bedside models for predicting upper-limb outcome after stroke require further refinement to be effectively implemented in stroke units within the first 72 hours. This study aimed to develop and internally validate a machine learning model to predict the 6-month Action Research Arm Test score using simple clinical tests commonly assessed within the first 3 days poststroke. METHODS: In 296 first-ever ischemic stroke patients pooled from 4 prospective Dutch cohort studies across 44 centers (2000-2019), we compared the cross-validated prediction performance of multiple eXtreme Gradient Boosting models using different sets of bedside clinical tests to predict the 6-month Action Research Arm Test outcome (0-57). We then selected the model with the minimal predictor set that best balanced bedside feasibility and accuracy and validated it within 72 hours poststroke on a test data set (n=32) from the same cohort using median absolute error as the evaluation metric. RESULTS: A model incorporating Shoulder Abduction from the Motricity Index, voluntary finger extension, Fugl-Meyer Upper Extremity, and total National Institutes of Health Stroke Scale score as bedside tests, showed the best tradeoff between model simplicity and predictive accuracy (median absolute error, 5.9 on the 0-57 score; interquartile range, 2.9-12.9). CONCLUSIONS: Our model predicts the 6-month Action Research Arm Test score using a minimal set of bedside clinical tests collected within the first 3 days after stroke, achieving a median absolute error below the Action Research Arm Test minimal clinically important difference of 6 points.
引用
- van der Gun GJ, Selles RW, Meskers CGM, et al. Accuracy of Machine Learning to Predict Upper-Limb Outcome Within the First 72 Hours Poststroke. Stroke. 2026. PMID: 42267434. doi:10.1161/STROKEAHA.125.054989
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。