Parkinson’s disease (PD) is the second most common movement disorder in the world. It is characterized by motor and non-motor symptoms that have a profound impact on the independence and quality of life of people affected by the disease, which increases caregivers’ burdens. The use of the quantitative gait data of people with PD and deep learning (DL) approaches based on gait are emerging as increasingly promising methods to support and aid clinical decision making, with the aim of providing a quantitative and objective diagnosis, as well as an additional tool for disease monitoring. This will allow for the early detection of the disease, assessment of progression, and implementation of therapeutic interventions. In this paper, the authors provide a systematic review of emerging DL techniques recently proposed for the analysis of PD by using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. The Scopus, PubMed, and Web of Science databases were searched across an interval of six years (between 2018, when the first article was published, and 2023). A total of 25 articles were included in this review, which reports studies on the movement analysis of PD patients using both wearable and non-wearable sensors. Additionally, these studies employed DL networks for classification, diagnosis, and monitoring purposes. The authors demonstrate that there is a wide employment in the field of PD of convolutional neural networks for analyzing signals from wearable sensors and pose estimation networks for motion analysis from videos. In addition, the authors discuss current difficulties and highlight future solutions for PD monitoring and disease progression.

The aim of this study was to determine a gait pattern, i.e., a subset of spatial and temporal parameters, through a supervised machine learning (ML) approach, which could be used to reliably distinguish Parkinson’s Disease (PD) patients with and without mild cognitive impairment (MCI). Thus, 80 PD patients underwent gait analysis and spatial–temporal parameters were acquired in three different conditions (normal gait, motor dual task and cognitive dual task). Statistical analysis was performed to investigate the data and, then, five ML algorithms and the wrapper method were implemented: Decision Tree (DT), Random Forest (RF), Naïve Bayes (NB), Support Vector Machine (SVM) and K-Nearest Neighbour (KNN). First, the algorithms for classifying PD patients with MCI were trained and validated on an internal dataset (sixty patients) and, then, the performance was tested by using an external dataset (twenty patients). Specificity, sensitivity, precision, accuracy and area under the receiver operating characteristic curve were calculated. SVM and RF showed the best performance and detected MCI with an accuracy of over 80.0%. The key features emerging from this study are stance phase, mean velocity, step length and cycle length; moreover, the major number of features selected by the wrapper belonged to the cognitive dual task, thus, supporting the close relationship between gait dysfunction and MCI in PD.

Parkinson’s disease (PD) is characterized by a slow, short-stepping, shuffling gait pattern caused by a combination of motor control limitations due to a reduction in dopaminergic neurons. Gait disorders are indicators of global health, cognitive status, and risk of falls and increase with disease progression. Therefore, the use of quantitative information on the gait mechanisms of PD patients is a promising approach, particularly for monitoring gait disorders and potentially informing therapeutic interventions, though it is not yet a well-established tool for early diagnosis or direct assessment of disease progression. Over the years, many studies have investigated the spatiotemporal parameters that are altered in the PD gait pattern, while kinematic and kinetic gait parameters are more limited. A scoping review was performed according to the PRISMA guidelines. The Scopus and PubMed databases were searched between 1999 and 2023. A total of 29 articles were included that reported gait changes in PD patients under different gait conditions: single free walking, sequential motor task, and dual task. The main findings of our review highlighted the use of optoelectronic systems for recording kinematic parameters and force plates for measuring kinetic parameters, due to their high accuracy. Most gait analyses in PD patients have been conducted at self-selected walking speeds to capture natural movement, although studies have also examined gait under various conditions. The results of our review indicated that PD patients experience alterations in the range of motion of the hip, knee, and ankle joints, as well as a reduction in the power generated/absorbed and the extensor/flexor moments. These findings suggest that the PD gait pattern may be more effectively understood using kinematic and kinetic parameters.

Mild cognitive impairment (MCI) and gait deficits are commonly associated with Parkinson’s disease (PD). Early detection of MCI associated with Parkinson’s disease (PD-MCI) and its biomarkers is critical to managing disability in PD patients, reducing caregiver burden and healthcare costs. Gait is considered a surrogate marker for cognitive decline in PD. However, gait kinematic and kinetic features in PD-MCI patients remain unknown. This study was designed to explore the difference in gait kinematics and kinetics during single-task and dual-task walking between PD patients with and without MCI. Kinematic and kinetic data of 90 PD patients were collected using 3D motion capture system. Differences in gait kinematic and kinetic gait features between groups were identified by using: first, univariate statistical analysis and then a supervised machine learning analysis. The findings of this study showed that the presence of MCI in PD patients is coupled with kinematic and kinetic deviations of gait cycle which may eventually identify two different phenotypes of the disease. Indeed, as shown by the demographical and clinical comparison between the two groups, PD-MCI patients were older and more impaired. Moreover, PD-MCI kinematic results showed that cognitive dysfunction coexists with more severe axial symptoms and an increase postural flexion. A lack of physiological distal-to-proximal shift in joint kinetics was evidenced in the PD phenotype associated with cognitive impairments.

Parkinson’s Disease (PD) is a neurodegenerative disease which involves both motor and non-motor symptoms. Non-motor mental symptoms are very common among patients with PD since the earliest stage. In this context, gait analysis allows to detect quantitative gait variables to distinguish patients affected by non-motor mental symptoms from patients without these symptoms. A cohort of 68 PD subjects (divided in two groups) was acquired through gait analysis (single and double task) and spatial temporal parameters were analysed; first with a statistical analysis and then with a machine learning (ML) approach. Single-task variables showed that 9 out of 16 spatial temporal features were statistically significant for the univariate statistical analysis (p-value< 0.05). Indeed, a statistically significant difference was found in stance phase (p-value=0.032), swing phase (p-value=0.042) and cycle length (p-value=0.03) of the dual task. The ML results confirmed the statistical analysis, in particular, the Decision Tree classifier showed the highest accuracy (80.9%) and also the highest scores in terms of specificity and precision. Our findings indicate that patients with non-motor mental symptoms display a worse gait pattern, mainly dominated by increased slowness and dynamic instability.

Background: Respiratory rate (RR) is a key vital sign and one of the most sensitive indicators of physiological conditions, playing a crucial role in the early identification of clinical deterioration. The monitoring of RR using electrocardiography (ECG) and photoplethysmography (PPG) aims to overcome limitations of traditional methods in clinical settings. Methods: The proposed approach extracts RR from ECG and PPG signals using different morphological and temporal features from publicly available datasets (iAMwell and Capnobase). The algorithm was used to develop and test with a selection of relevant ECG (e.g., R-peak, QRS area, and QRS slope) and PPG (amplitude and frequency modulation) characteristics. Results: The results show promising performance, with the ECG-derived signal using the R-peak–based method yielding the lowest error, with a mean absolute error of 0.99 breaths/min in the iAMwell dataset and 3.07 breaths/min in the Capnobase dataset. In comparison, the RR PPG-derived signal showed higher errors of 5.10 breaths/min in the iAMwell dataset and 10.66 breaths/min in the Capnobase dataset, for the FM and AM method, respectively. Bland–Altman analysis revealed a small negative bias, approximately −0.97 breaths/min for the iAMwell dataset (with limits of agreement from −2.62 to 0.95) and −1.16 breaths/min for the Capnobase dataset (limits of agreement from −3.37 to 1.10) in the intra-subject analysis. In the inter-subject analysis, the bias was −0.84 breaths/min (limits of agreement from −1.76 to 0.20) for iAMwell and −1.22 breaths/min (limits of agreement from −7.91 to 5.35) for Capnobase, indicating a slight underestimation. Conversely, the PPG-derived signal tended to overestimate RR, resulting in higher variability and reduced accuracy. These findings highlight the higher reliability of ECG-derived features for RR estimation in the analyzed datasets. Conclusion: This study suggests that the proposed approach could guide the design of cost-effective, non-invasive methods for continuous respiration monitoring, offering a reliable tool for detecting conditions like stress, anxiety, and sleep disorders.