Predicting Three Types of Freezing of Gait Events Using Deep Learning Models

TL;DR

This paper develops deep learning models combining transformer encoders and Bidirectional LSTM layers to predict three types of freezing of gait events in Parkinson's Disease patients, achieving competitive accuracy.

Contribution

It introduces a novel deep learning approach specifically designed to classify different freezing of gait event types using time-series data.

Findings

Best model scores 0.427 on test data

Model ranks top 5 in Kaggle competition

Overfitting observed, potential improvements identified

Abstract

Freezing of gait is a Parkinson's Disease symptom that episodically inflicts a patient with the inability to step or turn while walking. While medical experts have discovered various triggers and alleviating actions for freezing of gait, the underlying causes and prediction models are still being explored today. Current freezing of gait prediction models that utilize machine learning achieve high sensitivity and specificity in freezing of gait predictions based on time-series data; however, these models lack specifications on the type of freezing of gait events. We develop various deep learning models using the transformer encoder architecture plus Bidirectional LSTM layers and different feature sets to predict the three different types of freezing of gait events. The best performing model achieves a score of 0.427 on testing data, which would rank top 5 in Kaggle's Freezing of Gait prediction competition, hosted by THE MICHAEL J. FOX FOUNDATION. However, we also recognize overfitting in training data that could be potentially improved through pseudo labelling on additional data and model architecture simplification.