Feature Selection and Explainability for Machine Learning-Based Outcome Prediction in Robot-Assisted Upper Limb Stroke Rehabilitation

上肢 物理医学与康复 冲程(发动机) 医学 特征(语言学) 特征选择 康复 选择(遗传算法) 人工智能 结果(博弈论) 计算机科学
作者
Anastasios Tzepkenlis,Antonio Frisoli,Cristian Camardella
出处
期刊:IEEE Transactions on Neural Systems and Rehabilitation Engineering [Institute of Electrical and Electronics Engineers]
卷期号:34: 4263-4273
标识
DOI:10.1109/tnsre.2026.3744492
摘要

Accurate and interpretable prediction of rehabilitation outcomes is critical for enabling data-driven clinical decision support in post-stroke robotic therapy. This study systematically investigates feature selection and model explainability to improve the clinical utility of machine learning models that predict post-therapy motor function scores, specifically the Fugl-Meyer Assessment (FMA), Action Research Arm Test (ARAT), and Motricity Index (MI), in stroke patients undergoing upper limb robot-assisted rehabilitation. Building on prior work that identified XGBoost as the top-performing algorithm, we applied Sequential Forward Selection (SFS) with beam search to identify compact, high-performance feature subsets from a 71-feature dataset collected from 40 stroke patients using the MOTORE end-effector robotic platform. Complementary explainability analyses using SHAP values and Permutation Importance (PI) were integrated to identify a consensus feature set of 3–4 variables per outcome. A systematic ablation over the four feature groups shows that clinical variables carry most of the predictive signal, that adding kinematic or time-related variables to the clinical group leaves the error essentially unchanged, and that the benefit of the robotic data emerges only once feature selection is applied. SFS-optimized models reduced prediction error by 26–42% relative to the full 71-feature model and by 20–36% relative to a clinical-only model, with normalized RMSE values of 0.087 (ARAT), 0.046 (FMA), and 0.086 (MI). The compact SHAP+PI feature sets remained usable (nRMSE: 0.130, 0.067, 0.093) while reducing the input space to 3–4 variables. Learning curve analysis shows that error is still decreasing at 40 patients, so the present estimates should be read as an upper bound on the achievable error. Prediction errors were benchmarked against established minimal clinically important difference (MCID) thresholds, demonstrating sufficient precision to distinguish patients likely to achieve meaningful motor recovery. These findings support the development of transparent, clinically deployable decision support systems for robotic rehabilitation.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
任性铅笔完成签到 ,获得积分10
刚刚
大花生小米完成签到,获得积分10
刚刚
不过尔尔完成签到,获得积分10
刚刚
snowinghere完成签到,获得积分10
1秒前
乌乌完成签到,获得积分10
1秒前
橙子完成签到 ,获得积分10
2秒前
arniu2008发布了新的文献求助10
2秒前
null的应助被莫华龙采纳,获得10
2秒前
研友_841dlL发布了新的文献求助10
2秒前
3900完成签到,获得积分10
2秒前
小可爱123456完成签到,获得积分10
2秒前
杨羊完成签到,获得积分10
4秒前
东方诩完成签到,获得积分10
5秒前
5秒前
ne完成签到 ,获得积分10
5秒前
无私的犀牛完成签到,获得积分10
5秒前
咪咪好咪咪的应助被xudaniel采纳,获得10
5秒前
5秒前
花开富贵完成签到 ,获得积分10
6秒前
研友_rLmMYL完成签到,获得积分10
7秒前
nan完成签到,获得积分10
7秒前
8秒前
8秒前
小小小完成签到,获得积分10
8秒前
WSK发布了新的文献求助10
8秒前
万能图书馆的应助被arniu2008采纳,获得10
8秒前
8秒前
无奈狗完成签到,获得积分10
9秒前
piao完成签到,获得积分10
9秒前
MrChew完成签到 ,获得积分10
10秒前
香蕉觅云的应助被sukiii采纳,获得10
10秒前
11秒前
kiana完成签到,获得积分10
11秒前
钢筋炒煤球完成签到,获得积分10
12秒前
XF完成签到,获得积分10
12秒前
yinzhang5完成签到,获得积分10
12秒前
含蓄的之云完成签到,获得积分10
12秒前
全程都v回复v完成签到,获得积分10
12秒前
冷傲太英完成签到,获得积分10
12秒前
殷勤的帽子完成签到,获得积分10
13秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
八旗制度の研究 600
plantTFDB 508
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8173580
求助须知:如何正确求助?哪些是违规求助? 9565737
关于积分的说明 21782083
捐赠科研通 7767775
什么是DOI,文献DOI怎么找? 3431604
关于科研通互助平台的介绍 2555855
邀请新用户注册赠送积分活动 2476870