Computer Vision and Abnormal Patient Gait Assessment a Comparison of Machine Learning Models

TL;DR

This paper reviews how computer vision combined with various machine learning models can effectively assess abnormal patient gait, aiding in fall risk prediction and clinical decision support.

Contribution

It systematically compares different machine learning algorithms used with computer vision for gait abnormality assessment in patients.

Findings

Computer vision effectively captures patient posture for gait analysis.

Multiple machine learning models like SVM, ANN, Random Forest are used for classification.

The review highlights the benefits and current state of automated gait assessment tools.

Abstract

Abnormal gait, its associated falls and complications have high patient morbidity, mortality. Computer vision detects, predicts patient gait abnormalities, assesses fall risk and serves as clinical decision support tool for physicians. This paper performs a systematic review of how computer vision, machine learning models perform an abnormal patient's gait assessment. Computer vision is beneficial in gait analysis, it helps capture the patient posture. Several literature suggests the use of different machine learning algorithms such as SVM, ANN, K-Star, Random Forest, KNN, among others to perform the classification on the features extracted to study patient gait abnormalities.