Assessment and Biomechanical Analysis of Sit-to-Stand Proficiency in Stroke Survivors Using Wearable Inertial Sensors for Targeted Rehabilitation

Project Abstract

This study investigates sit-to-stand (STS) proficiency in stroke survivors through a biomechanical lens using wearable inertial sensors to enable targeted rehabilitation strategies. A cross-sectional design was employed to capture kinematic and kinetic-related STS performance metrics in a representative cohort of chronic stroke patients (n = 60) and age-matched controls (n = 30). Participants completed a standardized STS protocol while wearing wireless inertial measurement units (IMUs) positioned on the trunk, thigh, and shank to quantify temporal-spatial features, joint accelerations, trunk lean, center of mass displacement, and integrated angular velocity throughout the movement. Ground reaction forces were estimated using synchronized force plate data in a subset (n = 20) to validate sensor-derived estimates of peak knee extension moment and hip-knee-ankle coordination patterns. Key outcomes include reaction time to initiate the stand, seat-off transition duration, vertical acceleration peak, peak anterior-posterior velocity, and STS duration. Biomechanical analysis focused on (i) synergy patterns between hip and knee joints during ascent, (ii) compensatory strategies such as forward trunk flexion and increased sway, (iii) asymmetries between paretic and non-paretic sides, and (iv) correlation of IMU-derived metrics with clinical scales such as the Berg Balance Scale, Timed Up and Go, and the Five Times Sit-to-Stand Test. Machine learning models (random forest and support vector machines) were trained to classify STS performance quality and predict fall risk based on IMU features, with model interpretability explored via SHAP values to identify the most influential sensors and movement phases. The results reveal that stroke survivors exhibit significantly longer STS initiation times, reduced peak knee extension moments, and greater trunk flexion range compared to controls. A key finding is that compensatory trunk forward lean and reduced ankle dorsiflexion contribute to diminished STS efficiency and increased variability across repetitions. IMU-based features demonstrated strong discriminative power in distinguishing stroke versus control groups (AUC > 0.90) and predicting falls risk (accuracy ~82%). The study identifies actionable targets for rehabilitation, including strategies to enhance knee extension strength, improve ankle dorsiflexion control, and promote upright trunk alignment through task-specific training and biofeedback. Clinical implications emphasize the feasibility of deploying wearable IMUs in routine neurorehabilitation to monitor progression, tailor interventions, and provide real-time feedback for optimizing STS performance. The findings support the development of personalized rehabilitation protocols that leverage sensor-driven metrics to track recovery trajectories, reduce compensatory strategies, and mitigate fall risk in stroke survivors. Limitations include the cross-sectional design and a subset with force-plate validation, suggesting longitudinal studies to evaluate responsiveness to targeted interventions. Future work will integrate surface electromyography to elucidate neuromuscular activation patterns and assess portability for home-based rehabilitation settings.

Project Overview

What This Project Is About

---

A plain-language overview of the topic and what the project investigates.

---

---

The Problem It Addresses

---

Stroke survivors often struggle with sit-to-stand movements, which are essential for daily activities. Traditional assessments may miss subtle motor issues, and targeted rehabilitation can be difficult to customize. This project explores how wearable sensors can help measure and understand sit-to-stand performance to guide better therapy.

---

---

Objectives of the Project

---

1. Explain what sit-to-stand proficiency means in simple terms.
2. Identify key factors that affect performance after a stroke.
3. Show how wearable sensors can capture useful data during the movement.
4. Develop a basic framework to classify movement quality for rehabilitation planning.
5. Provide practical guidelines for therapists based on findings.

---

---

What You Will Do Step by Step

---

1) Learn the basics of sit-to-stand movements and common post-stroke challenges. 2) Get familiar with wearable sensors and how they collect data. 3) Design a simple protocol to record movements from volunteers. 4) Process data to extract easy-to-understand metrics (like speed and range of motion). 5) Analyze patterns to see which factors influence performance. 6) Interpret results into practical rehab tips. 7) Write a clear summary of findings and limitations.

---

---

---

---

Expected Outcome

Clear, easy-to-use insights on how to improve sit-to-stand in stroke survivors, with practical sensor-based measures that therapists can use to tailor exercises and track progress over time.