Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Jun 13, 2025

Asymmetric Walkway: A Novel Behavioral Assay for Studying Asymmetric Locomotion

Asymmetric Walkway: A Novel Behavioral Assay for Studying Asymmetric Locomotion

Published on: January 15, 2016

Logistic regression analysis and machine learning for predicting post-stroke gait independence: a retrospective

Yuta Miyazaki^1,2,3, Michiyuki Kawakami^4,5, Kunitsugu Kondo^1,2

¹Department of Rehabilitation Medicine, Tokyo Bay Rehabilitation Hospital, Chiba, Japan.

Scientific Reports

|September 11, 2024

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

Sitting-related Sacral Pain in Patients with Sacral Metastases: Retrospective Cross-Sectional Study.

Journal of pain and symptom management·2026

Same author

Focal MRI-guided theta burst TMS in the common marmoset produces bidirectional corticospinal modulation.

Brain stimulation·2026

Same author

Correction: Preoperative risk factors for postoperative pneumonia in patients with esophageal cancer: A systematic review and meta-analysis.

Surgery today·2026

Same author

Predictors of postoperative health-related quality of life in patients with esophageal cancer: a scoping review.

Diseases of the esophagus : official journal of the International Society for Diseases of the Esophagus·2026

Same author

Implementation strategies for cancer rehabilitation in clinical practice: a Delphi study.

Japanese journal of clinical oncology·2026

Same author

Preoperative risk factors for postoperative pneumonia in patients with esophageal cancer: A systematic review and meta-analysis.

Surgery today·2026

Logistic regression analysis (LR) shows comparable predictive accuracy to machine learning (ML) algorithms for predicting gait independence in subacute stroke survivors. LR remains a practical choice due to its simplicity and interpretability.

Area of Science:

Rehabilitation Medicine
Medical Informatics
Biostatistics

Background:

Predicting gait independence is crucial for subacute stroke patients' recovery.
Machine learning (ML) models are increasingly explored for clinical prediction tasks.
Traditional statistical models like logistic regression (LR) are widely used.

Purpose of the Study:

To compare the predictive accuracy of ML algorithms against LR for gait independence in stroke survivors.
To determine if ML offers superior prediction compared to LR in this patient population.

Main Methods:

Developed prediction models using LR and five ML algorithms (Decision Tree, Support Vector Machine, Artificial Neural Network, Ensemble Learning, k-Nearest Neighbor).
Utilized Functional Independence Measure sub-items to assess walking ability.

Keywords:

Gait independence Logistic regression Machine learning Prediction models Stroke

More Related Videos

Motor Dual-Tasks for Gait Analysis and Evaluation in Post-Stroke Patients

Motor Dual-Tasks for Gait Analysis and Evaluation in Post-Stroke Patients

Published on: March 11, 2021

3D Kinematic Gait Analysis for Preclinical Studies in Rodents

3D Kinematic Gait Analysis for Preclinical Studies in Rodents

Published on: August 3, 2019

Related Experiment Videos

Last Updated: Jun 13, 2025

Asymmetric Walkway: A Novel Behavioral Assay for Studying Asymmetric Locomotion

Asymmetric Walkway: A Novel Behavioral Assay for Studying Asymmetric Locomotion

Published on: January 15, 2016

Motor Dual-Tasks for Gait Analysis and Evaluation in Post-Stroke Patients

Motor Dual-Tasks for Gait Analysis and Evaluation in Post-Stroke Patients

Published on: March 11, 2021

3D Kinematic Gait Analysis for Preclinical Studies in Rodents

3D Kinematic Gait Analysis for Preclinical Studies in Rodents

Published on: August 3, 2019

Evaluated model performance using Area Under the Receiver Operating Characteristic Curve (AUC) and other metrics (accuracy, precision, recall, F1 score, specificity).

Main Results:

The Decision Tree algorithm showed significantly lower predictive accuracy (AUC=0.812).
LR (AUC=0.895) demonstrated comparable predictive accuracy to other ML models (AUCs 0.893-0.903).
No substantial differences in other performance metrics were observed between LR and ML algorithms.

Conclusions:

LR provides similar predictive accuracy for gait independence as advanced ML algorithms in subacute stroke patients.
LR's interpretability and computational simplicity make it a viable and practical tool for clinical use.
The Decision Tree algorithm was found to be less accurate for this specific prediction task.