Parkinson's Disease Freezing of Gait (FoG) Symptom Detection Using Machine Learning from Wearable Sensor Data

TL;DR

This paper presents a novel Transformer Encoder-Bi-LSTM model that accurately detects freezing of gait episodes in Parkinson's patients using wearable sensor data, potentially improving diagnosis and treatment.

Contribution

It introduces a new deep learning fusion model combining Transformer Encoder and Bi-LSTM for real-time FoG detection from accelerometer data.

Findings

Achieved 92.6% accuracy in FoG detection

Attained 80.9% F1 score, indicating balanced precision and recall

Reached 52.06% mean average precision on the dataset

Abstract

Freezing of gait (FoG) is a special symptom found in patients with Parkinson's disease (PD). Patients who have FoG abruptly lose the capacity to walk as they normally would. Accelerometers worn by patients can record movement data during these episodes, and machine learning algorithms can be useful to categorize this information. Thus, the combination may be able to identify FoG in real time. In order to identify FoG events in accelerometer data, we introduce the Transformer Encoder-Bi-LSTM fusion model in this paper. The model's capability to differentiate between FoG episodes and normal movement was used to evaluate its performance, and on the Kaggle Parkinson's Freezing of Gait dataset, the proposed Transformer Encoder-Bi-LSTM fusion model produced 92.6% accuracy, 80.9% F1 score, and 52.06% in terms of mean average precision. The findings highlight how Deep Learning-based approaches may progress the field of FoG identification and help PD patients receive better treatments and management plans.