Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: May 13, 2026

A Human-machine-interface Integrating Low-cost Sensors with a Neuromuscular Electrical Stimulation System for Post-stroke Balance Rehabilitation
11:06

A Human-machine-interface Integrating Low-cost Sensors with a Neuromuscular Electrical Stimulation System for Post-stroke Balance Rehabilitation

Published on: April 12, 2016

Forecasting Dropout in Home-Based Movement Rehabilitation After Stroke With Sensors and Machine Learning.

Sangjoon J Kim, George H Collier, Jacob Cartwright

    IEEE Transactions on Neural Systems and Rehabilitation Engineering : a Publication of the IEEE Engineering in Medicine and Biology Society
    |May 11, 2026
    PubMed
    Summary

    Related Concept Videos

    You might also read

    Related Articles

    Articles linked to this work by shared authors, journal, and citation graph.

    Sort by
    Same author

    Robotic Technologies for Hand Recovery After Stroke: A Reflection on Research Paths in Honor of Dr. Steven Wolf.

    Neurorehabilitation and neural repair·2026
    Same author

    FDA-Listed Interactive Devices for Home Movement Rehabilitation After Stroke: A Mixed-Methods Study of Availability, User Needs, Information Gaps, and an Accompanying Dataset.

    Bioengineering (Basel, Switzerland)·2026
    Same author

    Low-Heat and Near-Silent Pneumatic Source Driven by Integrated Endothermic-Exothermic Chemical Reactions for Soft Robots.

    Soft robotics·2026
    Same author

    Signal-Dependent Planning Noise Reduces Task Interference by Assisting in the Formation of Stable Motor Primitives in a Neural Network Model of Muscle Coordination Learning.

    Neural computation·2026
    Same author

    Dynamic thumb localization and its adaptation: quantification with a novel robotic task.

    Experimental brain research·2026
    Same author

    Distribution Analysis for Diagnostics and Therapeutics of Motor Actions.

    IEEE journal of biomedical and health informatics·2025

    Early engagement in home rehabilitation predicts long-term adherence. Key signals like active days and exercise consistency can forecast dropout risk, enabling timely interventions for stroke recovery.

    Area of Science:

    • Rehabilitation Medicine
    • Digital Health
    • Machine Learning in Healthcare

    Background:

    • Home-based rehabilitation is crucial for stroke recovery, but patient adherence often declines early.
    • Limited research exists on predicting long-term perseverance from early behavioral data in large, unsupervised settings.

    Purpose of the Study:

    • To identify early behavioral signals of long-term adherence in home-based stroke rehabilitation.
    • To develop and validate machine learning models for forecasting dropout risk using sensor data.

    Main Methods:

    • Analysis of a large dataset (N=2,747) from a sensorized home rehabilitation system (FitMi).
    • Application of interpretable machine learning models to predict fourth-week persistence based on the first three weeks of exercise behavior.

    More Related Videos

    Home-Based Monitor for Gait and Activity Analysis
    07:24

    Home-Based Monitor for Gait and Activity Analysis

    Published on: August 8, 2019

    Related Experiment Videos

    Last Updated: May 13, 2026

    A Human-machine-interface Integrating Low-cost Sensors with a Neuromuscular Electrical Stimulation System for Post-stroke Balance Rehabilitation
    11:06

    A Human-machine-interface Integrating Low-cost Sensors with a Neuromuscular Electrical Stimulation System for Post-stroke Balance Rehabilitation

    Published on: April 12, 2016

    Home-Based Monitor for Gait and Activity Analysis
    07:24

    Home-Based Monitor for Gait and Activity Analysis

    Published on: August 8, 2019

  • Focus on generalizable features readily available in other home exercise systems.

    • Main Results:

    • The best model achieved an Area Under the Curve (AUC) of 0.810, demonstrating strong predictive accuracy for identifying persisters versus non-persisters.
    • Precision-recall analysis yielded a prAUC of 0.717 and an F1-score of 0.703.
    • Key predictive features included average weekly active days (24.7%), exercise consistency (16.4%), average session length (15.2%), and repetition rate (10.1%).

    Conclusions:

    • Early patterns of engagement in home rehabilitation are strong indicators of long-term adherence.
    • Measurable behavioral signals can be leveraged by sensor-based systems to identify users at risk of disengagement.
    • This approach offers a scalable method for personalized interventions within autonomous rehabilitation systems to improve patient outcomes.