InSEption: A Robust Mechanism for Predicting FoG Episodes in PD Patients

Abstract

The integration of IoT and deep learning provides the opportunity for continuous monitoring and evaluation of patients’ health status, leading to more personalized treatment and improved quality of life. This study explores the potential of deep learning to predict episodes of freezing of gait (FoG) in Parkinson’s disease (PD) patients. Initially, a literature review was conducted to determine the state of the art; then, two inception-based models, namely LN-Inception and InSEption, were introduced and tested using the Daphnet dataset and an additional novel medium-sized dataset collected from an IMU (inertial measuring unit) sensor. The results show that both models performed very well, outperforming or achieving performance comparable to the state-of-the-art. In particular, the InSEption network showed exceptional performance, achieving a 6% increase in macro F1 score compared to the inception-only-based counterpart on the Daphnet dataset. In a newly introduced IMU dataset, InSEption scored 97.2% and 98.6% in terms of F1 and AUC, respectively. This can be attributed to the added squeeze and excitation blocks and the domain-specific oversampling methods used for training. The benefits of using the Inception mechanism for signal data and its potential for integration into wearable IoT are validated.

Insights into Parkinson’s Disease-Related Freezing of Gait Detection and Prediction Approaches: A Meta Analysis

“…It is often cited by researchers, making it appropriate for machine learning model evaluation and training. The extensive use of the Daphnet dataset in research enables insightful comparisons and promotes improvements in FOG prediction techniques [ 40 , 60 , 80 , 82 , 94 , 106 , 123 ]. Even though the Daphnet dataset is widely used, it is important to recognize its limitations.…”

Comparison of state-of-the-art deep learning architectures for detection of freezing of gait in Parkinson’s disease

“…A further expansion of the iSPLInception network has been conducted in which the inSEption and LN-Inception networks were proposed ( 19 ). Here, inSEption utilizes the inception module but also includes squeeze and excitation blocks.…”

“…A public dataset was added to the DaphNet dataset, containing the IMU data of 38 people with PD who were turning on the spot ( 34 ). The data contained 173 FOG episodes ( 19 , 34 ). They found remarkable detection of FOG for both models; the LN-Inception had a sensitivity of 97% and specificity of 99%, whereas the inSEption model resulted in a sensitivity of 98% and specificity of 99% ( 19 ).…”

“…The data contained 173 FOG episodes ( 19 , 34 ). They found remarkable detection of FOG for both models; the LN-Inception had a sensitivity of 97% and specificity of 99%, whereas the inSEption model resulted in a sensitivity of 98% and specificity of 99% ( 19 ). This clearly illustrates the potential of an Inception-based model for the detection of FOG.…”

“…Rocket is further succeeded by the MiniRocket, which is a fast data mining classifier ( 16 ). InceptionTime is an ensemble of deep CNN models ( 17 ), and while Inception-based networks have previously been used to detect FOG with high accuracy (93.5%) ( 18 ), high sensitivity (98%), and high specificity (99%) ( 19 ), the InceptionTime model specifically has not been tested yet for FOG detection. The MiniRocket has also not been tested to detect FOG on IMU data ( 7 , 15 ).…”