An explainable spatial-temporal graphical convolutional network to score freezing of gait in parkinsonian patients

A Hybrid Protection Scheme for the Gait Analysis in Early Dementia Recognition

Human activity recognition (HAR) through gait analysis is a very promising research area for early detection of neurodegenerative diseases because gait abnormalities are typical symptoms of some neurodegenerative diseases, such as early dementia. While working with such biometric data, the performance parameters must be considered along with privacy and security issues. In other words, such biometric data should be processed under specific security and privacy requirements. This work proposes an innovative hybrid protection scheme combining a partially homomorphic encryption scheme and a cancelable biometric technique based on random projection to protect gait features, ensuring patient privacy according to ISO/IEC 24745. The proposed hybrid protection scheme has been implemented along a long short-term memory (LSTM) neural network to realize a secure early dementia diagnosis system. The proposed protection scheme is scalable and implementable with any type of neural network because it is independent of the network's architecture. The conducted experiments demonstrate that the proposed protection scheme enables a high trade-off between safety and performance. The accuracy degradation is at most 1.20% compared with the early dementia recognition system without the protection scheme. Moreover, security and computational analyses of the proposed scheme have been conducted and reported.

Classifying Tremor Dominant and Postural Instability and Gait Difficulty Subtypes of Parkinson's Disease from Full-Body Kinematics

Characterizing motor subtypes of Parkinson's disease (PD) is an important aspect of clinical care that is useful for prognosis and medical management. Although all PD cases involve the loss of dopaminergic neurons in the brain, individual cases may present with different combinations of motor signs, which may indicate differences in underlying pathology and potential response to treatment. However, the conventional method for distinguishing PD motor subtypes involves resource-intensive physical examination by a movement disorders specialist. Moreover, the standardized rating scales for PD rely on subjective observation, which requires specialized training and unavoidable inter-rater variability. In this work, we propose a system that uses machine learning models to automatically and objectively identify some PD motor subtypes, specifically Tremor-Dominant (TD) and Postural Instability and Gait Difficulty (PIGD), from 3D kinematic data recorded during walking tasks for patients with PD (MDS-UPDRS-III Score, 34.7 ± 10.5, average disease duration 7.5 ± 4.5 years). This study demonstrates a machine learning model utilizing kinematic data that identifies PD motor subtypes with a 79.6% F1 score (N = 55 patients with parkinsonism). This significantly outperformed a comparison model using classification based on gait features (19.8% F1 score). Variants of our model trained to individual patients achieved a 95.4% F1 score. This analysis revealed that both temporal, spectral, and statistical features from lower body movements are helpful in distinguishing motor subtypes. Automatically assessing PD motor subtypes simply from walking may reduce the time and resources required from specialists, thereby improving patient care for PD treatments. Furthermore, this system can provide objective assessments to track the changes in PD motor subtypes over time to implement and modify appropriate treatment plans for individual patients as needed.

Neuromelanin-sensitive MRI correlates of cognitive and motor function in Parkinson's disease with freezing of gait

Substantia nigra pars compacta (SNc) and locus coeruleus (LC) are neuromelanin-rich nuclei implicated in diverse cognitive and motor processes in normal brain function and disease. However, their roles in aging and neurodegenerative disease mechanisms have remained unclear due to a lack of tools to study them in vivo. Preclinical and post-mortem human investigations indicate that the relationship between tissue neuromelanin content and neurodegeneration is complex. Neuromelanin exhibits both neuroprotective and cytotoxic characteristics, and tissue neuromelanin content varies across the lifespan, exhibiting an inverted U-shaped relationship with age. Neuromelanin-sensitive MRI (NM-MRI) is an emerging modality that allows measurement of neuromelanin-associated contrast in SNc and LC in humans. NM-MRI robustly detects disease effects in these structures in neurodegenerative and psychiatric conditions, including Parkinson's disease (PD). Previous NM-MRI studies of PD have largely focused on detecting disease group effects, but few studies have reported NM-MRI correlations with phenotype. Because neuromelanin dynamics are complex, we hypothesize that they are best interpreted in the context of both disease stage and aging, with neuromelanin loss correlating with symptoms most clearly in advanced stages where neuromelanin loss and neurodegeneration are coupled. We tested this hypothesis using NM-MRI to measure SNc and LC volumes in healthy older adult control individuals and in PD patients with and without freezing of gait (FOG), a severe and disabling PD symptom. We assessed for group differences and correlations between NM-MRI measures and aging, cognition and motor deficits. SNc volume was significantly decreased in PD with FOG compared to controls. SNc volume correlated significantly with motor symptoms and cognitive measures in PD with FOG, but not in PD without FOG. SNc volume correlated significantly with aging in PD. When PD patients were stratified by disease duration, SNc volume correlated with aging, cognition, and motor deficits only in PD with disease duration >5 years. We conclude that in severe or advanced PD, identified by either FOG or disease duration >5 years, the observed correlations between SNc volume and aging, cognition, and motor function may reflect the coupling of neuromelanin loss with neurodegeneration and the associated emergence of a linear relationship between NM-MRI measures and phenotype.