Related Experiment Video
Updated: Nov 15, 2025
07:15
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
Published on: August 16, 2020
7.1K
Unsupervised and scalable low train pathology detection system based on neural networks.
Jorge Sanchez-Casanova1, Judith Liu-Jimenez1, Paloma Tirado-Martin1
1University Group for ID technologies (GUTI), University Carlos III of Madrid, Spain.
Heliyon
|March 4, 2021
Summary
This study introduces a novel Neural Network (NN) system for detecting lower body pathologies through gait analysis. The system achieves 92% accuracy in classifying walking abnormalities without retraining for new users.
Area of Science:
- Biomedical Engineering
- Artificial Intelligence in Medicine
- Gait Analysis
Background:
- Existing medical technologies often overlook lower body pathologies.
- Gait analysis offers a non-invasive method for assessing lower body health.
Purpose of the Study:
- To develop a Neural Network (NN)-based system for classifying lower body pathologies using gait.
- To enable the system to adapt to new users without complete retraining.
Main Methods:
- Filtering and processing signals to extract Gait Cycles (GCs).
- Utilizing GCs as input for the NN.
- Employing random search optimization for network tuning.
Main Results:
- The system achieved 92% accuracy in classifying lower body pathologies.
- Effective classification was obtained using 60% of the training data.
- The system demonstrated adaptability to new users.
Conclusions:
- The developed NN system provides a promising first-stage detection method for lower body pathologies.
- This approach allows for pathology detection in uncontrolled environments without requiring specialized facilities.
