SincPD: An Explainable Method based on Sinc Filters to Diagnose Parkinson's Disease Severity by Gait Cycle Analysis

TL;DR

This paper introduces SincPD, an explainable deep learning method using adaptive sinc filters to diagnose Parkinson's Disease and assess its severity from gait cycle data collected via wearable sensors.

Contribution

It presents a novel explainable classifier that models adaptive bandpass filters with sinc layers and reduces complexity through clustering, enabling interpretability in Parkinson's diagnosis.

Findings

Achieved accurate classification of Parkinson's patients and healthy subjects.

Reduced model complexity to 15 key filters per sensor.

Identified important frequency bands associated with Parkinson's gait abnormalities.

Abstract

In this paper, an explainable deep learning-based classifier based on adaptive sinc filters for Parkinson's Disease diagnosis (PD) along with determining its severity, based on analyzing the gait cycle (SincPD) is presented. Considering the effects of PD on the gait cycle of patients, the proposed method utilizes raw data in the form of vertical Ground Reaction Force (vGRF) measured by wearable sensors placed in soles of subjects' shoes. The proposed method consists of Sinc layers that model adaptive bandpass filters to extract important frequency-bands in gait cycle of patients along with healthy subjects. Therefore, by considering these frequencies, the reasons behind the classification a person as a patient or healthy can be explained. In this method, after applying some preprocessing processes, a large model equipped with many filters is first trained. Next, to prune the extra units and reach a more explainable and parsimonious structure, the extracted filters are clusters based on their cut-off frequencies using a centroid-based clustering approach. Afterward, the medoids of the extracted clusters are considered as the final filters. Therefore, only 15 bandpass filters for each sensor are derived to classify patients and healthy subjects. Finally, the most effective filters along with the sensors are determined by comparing the energy of each filter encountering patients and healthy subjects.