Parkinson's Disease (PD) is a progressive neurodegenerative disorder affecting millions of patients worldwide, with significant economic and social implications. The increasing prevalence of PD, coupled with rising healthcare costs, necessitates cost-effective solutions for patient management. Wearable medical devices, such as STAT-ON™, an inertial sensor with AI processing capability, offer an opportunity to enhance symptom monitoring, optimize therapy adjustments, and improve patient quality of life (QoL). However, their cost-effectiveness in routine clinical practice remains insufficiently explored. This study conducts a cost-benefit analysis of integrating STAT-ON™ into European healthcare systems (Spain, Sweden, Germany, Italy, and the UK). Using validated clinical data, we assess the economic impact of early symptom detection facilitated by continuous monitoring. Our findings suggest that improved symptom assessment can lead to optimized medication regimens, reducing hospitalizations and institutional care costs. While medication costs may increase, overall direct healthcare expenses decrease, leading to net savings. As an example, the study estimates potential cost reductions of up to €137.8 million in Germany and €19 million in Sweden when STAT-ON™ is used to detect advanced PD symptoms. Despite these promising results, limitations exist, including variations in healthcare costs, reimbursement policies, and real-world adoption rates across the different countries. Additionally, indirect costs such as caregiver burden were not fully analyzed. Future longitudinal studies are needed to further validate the economic and clinical benefits of wearable monitoring devices in PD management. This study highlights the potential of STAT-ON™ as a valuable tool for reducing healthcare costs and enhancing patient outcomes, supporting its adoption as a complementary solution for objective PD assessment in clinical practice.

The study of human-robot interactions in older persons with dementia is part of worldwide initiatives to respond to one of the major health challenges of what has been described as a global epidemic. As recently summarized by the WHO (2023), the number of dementia cases (over 60

This article presents the development of a database and an initial analysis aimed at detecting potential correlations between mobile phone usage and frailty levels among elderly individuals. The primary objective is to conduct exhaustive monitoring of all information provided by smartphones, focusing on both the use of common applications and sensor data related to mobility during activities of daily living (ADLs), and to contrast these findings with assessed frailty levels. This work forms part of a broader study involving elderly participants aged between 73 and 96 years, based in the Barcelona area. The database constructed for this study is based on two main strategies. First, to gather comprehensive data on smartphone usage, a group of 10 elderly individuals was observed under normal daily living conditions over a period of up to four weeks. For this initial group, key geriatric indices—Barthel Index, Lawton–Brody Instrumental Activities of Daily Living Scale, and Frail-VIG Index—were previously determined through ambulatory medical evaluations. Second, the database was expanded by generating synthetic data using Generative Adversarial Networks (GANs) and Gaussian Copula models, incorporating an additional group of real patients for whom frailty indices were already known. For those patients, we do not have any data from their own smartphones. The combined real and synthetic dataset was used to identify the most significant features and to support feature selection for classification. Generalized Linear Models (GLMs) were subsequently applied to develop decision trees, with the goal of establishing correlations between smartphone usage patterns and different frailty indices. Finally, the model outputs were analysed to extract meaningful insights that could inform future clinical applications.

In assisted ambulation, the user’s psychological comfort has a significant impact not only on acceptability of mobility aids but also on overall gait performance. Specifically, in the case of rollators, negative states such as distress may result in balance loss, inefficient manoeuvres, and an increased risk of falling. This paper presents a pilot study to investigate the effect of distress on rollator assisted navigation. To achieve this goal, a novel test protocol is proposed to assess distress while walking with a rollator, using the Self-Assessment Manikin (SAM) questionnaire. First, the participant completes a standardised visual stress induction test and fills in a SAM questionnaire on the dimensions of arousal and valence, to establish personal benchmarks. Then, they complete a course consisting of four navigation tasks with different levels of difficulty that affect the rollator manoeuvrability, filling in a SAM questionnaire after each task. An experiment including 25 healthy volunteers has been completed. Our preliminary results show that stressors like uneven or sloping surfaces increase perceived stress, whereas the shape of the trajectory does not significantly affect stress. The ultimate purpose of this work is to validate a performance-oriented protocol to investigate the dynamics of stress response in assisted walk and to train automatic stress detection systems.

This paper presents the initial data analysis and modelling for detecting health changes from data gathered on a low-cost smartphone used during normal daily activities. The work is part of the ENVELLINT project, where one of the main objectives is to explore if it is possible to evaluate the functional aspects of frailty indices automatically using smartphones. The project involves both longitudinal and cross-sectional studies involving elderly participants. In the longitudinal study a comprehensive set of sensor, application and other smartphone data is gathered over lengthy periods for each participant, together with extensive medical assessments. The purpose is to provide a comprehensive data set for investigating frailty and health changes. The larger cross-sectional study, which included only the medical assessments, was necessary to gather more medical related health and frailty data, and to balance project costs. The analysis work to date has involved data and feature engineering to identify, extract and select the most useful features. Insights are given for the potential use of the location and application usage features. A core aspect, given the expense and the limited number of participants in the longitudinal study, is to explore the use of synthetic data generation to leverage the real data from both studies. Generative Adversarial Network and Gaussian Copula models have been investigated to create a larger representative dataset of longitudinal participants. Initial results and insights show generated synthetic data that closely mirrors the real data, especially using Gaussian Copula.

In the past decade, the use of wearable medical devices has been a great breakthrough in clinical practice, trials, and research. In the Parkinson's disease field, clinical evaluation is time limited, and healthcare professionals need to rely on retrospective data collected through patients' self-filled diaries and administered questionnaires. As this often leads to inaccurate evaluations, a more objective system for symptom monitoring in a patient's daily life is claimed. In this regard, the use of wearable medical devices is crucial. This study aims at presenting a review on STAT-ON (TM), a wearable medical device Class IIa, which provides objective information on the distribution and severity of PD motor symptoms in home environments. The sensor analyzes inertial signals, with a set of validated machine learning algorithms running in real time. The device was developed for 12 years, and this review aims at gathering all the results achieved within this time frame. First, a compendium of the complete journey of STAT-ON (TM) since 2009 is presented, encompassing different studies and developments in funded European and Spanish national projects. Subsequently, the methodology of database construction and machine learning algorithms design and development is described. Finally, clinical validation and external studies of STAT-ON (TM) are presented.

Frailty syndrome can be defined as a clinical state in which there is a rise in individual vulnerability, developing an increase in both the dependence of the person and mortality. Frailty is completely related to age. A fundamental factor to apply rehabilitative interventions successfully resides in having a simple and reliable method capable of identifying frailty syndrome. Frailty indexes (FI) have several sources of uncertainty trough the opinion of the patients, white coat effect and external factors. Moreover, in the clinical practice, the experience of the geriatricians led them to determine an approximation of the frailty level only with a simple handshake. Hand grip strength (HGS) has been widely used in tests by investigators and therapists to be able to diagnose sarcopenia and frailty, as it is a reliable indicator of the overall muscle strength, which decreases with age. Most researches focused mainly on peak HGS, which will not give insight on how the patient's strength was distributed over time. In the present work it is proposed to evaluate HGS behavior over a period of time, and to develop a system based on Machine Learning for the identification of frailty levels using physiological features, FI and the classical signal processing based on statistics of the HGS signals. The starting hypothesis is that it can be identified the "way" of performing HGS correlated with the level of frailty. To achieve this goal a clinical study was designed and carried out with a cohort of 70 elderly persons, in two Hospitals.

In the original version of this paper, the affiliations of Gonzalo Joya and Andreu Catala were not correct. This has been now corrected.

This paper concerns the design, analysis, and simulation of a 3D non-stationary channel model fed with inertial measurement unit (IMU) data. The work in this paper provides a framework for simulating the micro-Doppler signatures of indoor channels for human activity recognition by using radio-frequency-based sensing technologies. The major human body segments, such as wrists, ankles, torso, and head, are modelled as a cluster of moving point scatterers. We provide expressions for the time variant (TV) speed and TV angles of motion based on 3D trajectories of the moving person. Moreover, we present mathematical expressions for the TV Doppler shifts and TV path gains associated with each moving point scatterer. Furthermore, a model of the non-stationary time variant channel transfer function (TV-CTF) is provided, which takes into account the effects caused by a moving person as well as fixed objects, such as furniture, walls, and ceiling. The micro-Doppler signatures of the moving person is extracted from the TV-CTF by employing the concept of the spectrogram, whose expression is also provided in closed form. Our model is confirmed by channel state information (CSI) measurements taken during walking, falling, and sitting activities. The proposed channel model is fed with IMU data that has been collected. We evaluate the micro-Doppler signature of the model and CSI measurements. The results show a good agreement between the spectrograms and the TV mean Doppler shifts of our IMU-driven channel model and the measured CSI. The proposed model enables a paradigm shift from traditional experimental-based approaches to future simulation-based approaches for the design of human activity recognition systems.

Successful robot rollators work under the shared control paradigm as the best way to adjust dynamically to users’ needs and preferences in rehabilitation and daily living activities. Deciding how much weight users have in emerging motion commands is necessary to assess their condition and needs, usually from on-board sensors. Unfortunately, some relevant parameters for safe and comfortable gait assistance (i.e. balance or stress) are extremely difficult to measure using only on-board sensors. Therefore, wearable devices that offer real-time physiological data acquisition are meant to be a valuable source of relevant information of users’ psychological states such stress. However, detecting stress in real life with an unobtrusive wearable device is a challenging task. The objective of this study is to develop a method for real-time stress detection based in the wrist band Empatica E4 that can accurately, continuously and unobtrusively monitor psychological stress in real life to feed the system to provide smart gait-assistance. In this preliminary study we explore the feasibility, accuracy and reliability of the wrist-band with machine learning and signal processing techniques applied to electrodermal activity from 6 healthy participants in laboratory conditions. Specifically, the participants’ electrodermal activity (EDA) gathered by the Empatica E4 under a standardized stress induction test (Affective Picture System) is analized to evaluate the sensitivity, validity and robustness of the measure. The present study will be followed by a pilot in the lab with 20 participants fulfilling trajectories of different level of difficulty with the roller, previously to the clinical trials with rehabilitation patients.

One of the most effective ways to improve quality of life in dementia is by exposing people to meaningful activities. The study of engagement is crucial to identify which activities are significant for persons with dementia and customize them. Previous work has mainly focused on developing assessment tools and the only available model of engagement for people with dementia focused on factors influencing engagement or influenced by engagement. This article focuses on the internal functioning of engagement and presents the development and testing of a model specifying the components of engagement, their measures, and the relationships they entertain. We collected behavioral and physiological data while participants with dementia (N = 14) were involved in six sessions of play, three of game-based cognitive stimulation and three of robot-based free play. We tested the concurrent validity of the measures employed to gauge engagement and ran factorial analysis and Structural Equation Modeling to determine whether the components of engagement and their relationships were those hypothesized. The model we constructed, which we call the ENGAGE-DEM, achieved excellent goodness of fit and can be considered a scaffold to the development of affective computing frameworks for measuring engagement online and offline, especially in HCI and HRI.

We conducted an empirical study to answer the research question whether designers could generate richer affective content through mood boards when they are primed by archetypal media content, comparing to non-archetypal media content. Mood board making may stimulate more feedback from target users and help designers discover deeper insights about user needs and aspiration towards products. Today, mood board making has become an essential skill for designers. However, this technique did not gain adequate credits in terms of scientific evidence. It is necessary to assess the validity of mood boards to be an effective tool for studying unconscious emotions in design research. Four professional designers were asked to make mood boards for four different TV commercials (2× without archetypal content; 2× with archetypal content). All 16 mood boards are made online available to a group of 141 raters. In a random order all raters had to click on each mood board to view the full-size and give a rating of ‘attractiveness’ [0–100 score]. The GLM results of all ratings indicate that the attractiveness of the mood boards for archetypal media content and non-archetypal media content are significantly different (F = 15.674, df = 1, p < 0.001). The mood boards primed by archetypal media content (Mean = 54.42, SE = 1.55) are significantly more attractive than the mood boards primed by non-archetypal media content (Mean = 51.37, SE = 1.47). We conclude that mood boards are a enough good tool to investigate and use unconscious emotions what is relevant for addressing design challenges in different contexts.

This paper demonstrates the time-variant (TV) Doppler power characteristics of human activities using measured channel state information (CSI). We model the measured CSI as a complex channel transfer function corresponding to a 3D non-stationary multipath fading channel consisting of a fixed transmitter, a fixed receiver, fixed scatterers representing fixed objects, and a cluster of moving scatterers representing a moving person performing some human activities. We demonstrate the relationship between the TV Doppler frequency caused by each moving scatterer and the rate of change of its corresponding TV propagation delay. Furthermore, we express the TV mean Doppler shift in terms of the path gains of the fixed scatterers, the TV path gains, and the TV Doppler frequencies of the moving scatterers. To provide an insight into the TV Doppler power characteristics of the measured calibrated CSI, we employ the spectrogram from which we derive the TV mean Doppler shift. Finally, we present the spectrograms and the TV mean Doppler shifts of the measured calibrated CSI for different human activities. The results show the possibility of designing human activity recognition systems using commercial Wi-Fi devices by employing deep learning or machine learning algorithms.

Robust and accurate human activity recognition (HAR) systems are essential to many human-centric services within active assisted living and healthcare facilities. Traditional HAR systems mostly leverage a single sensing modality (e.g., either wearable, vision, or radio frequency sensing) combined with machine learning techniques to recognize human activities. Such unimodal HAR systems do not cope well with real-time changes in the environment. To overcome this limitation, new HAR systems that incorporate multiple sensing modalities are needed. Multiple diverse sensors can provide more accurate and complete information resulting in better recognition of the performed activities. This article presents WiWeHAR-a multimodal HAR system that uses combined Wi-Fi and wearable sensing modalities to simultaneously sense the performed activities. WiWeHAR makes use of standard Wi-Fi network interface cards to collect the channel state information (CSI) and a wearable inertial measurement unit (IMU) consisting of accelerometer, gyroscope, magnetometer sensors to collect the user's local body movements. We compute the time-variant mean Doppler shift (MDS) from the processed CSI data and magnitude from the inertial data for each sensor of the IMU. Thereafter, we separately extract various time- and frequency-domain features from the magnitude data and the MDS. We apply feature-level fusion to combine the extracted features, and finally supervised learning techniques are used to recognize the performed activities. We evaluate the performance of WiWeHAR by using a multimodal human activity data set, which was obtained from 9 participants. Each participant carried out four activities, such as walking, falling, sitting, and picking up an object from the floor. Our results indicate that the proposed multimodal WiWeHAR system outperforms the unimodal CSI, accelerometer, gyroscope, and magnetometer HAR systems and achieves an overall recognition accuracy of 99.6%-100%.

We present a multi-subject first-person vision dataset of office activities. The dataset contains the highest number of subjects and activities compared to existing office activity datasets. Office activities include person-to-person interactions, such as chatting and handshaking, person-to-object interactions, such as using a computer or a whiteboard, as well as generic activities such as walking. The videos in the dataset present a number of challenges that, in addition to intra-class differences and inter-class similarities, include frames with illumination changes, motion blur, and lack of texture. Moreover, we present and discuss state-of-the-art features extracted from the dataset and baseline activity recognition results with a number of existing methods. The dataset is provided along with its annotation and the extracted features.

Engagement in activities is crucial to improve quality of life in dementia. Yet, its measurement relies exclusively on behavior observation and the influence that behavioral and psychological symptoms of dementia (BPSD) have on it is overlooked. This study investigated whether quantity of movement, gauged with a wrist-worn accelerometer, could be a sound measure of engagement and whether apathy and depression negatively affected engagement. Fourteen participants with dementia took part in 6 sessions of activities: 3 of cognitive games (eg, jigsaw puzzles) and 3 of robot play (Pleo). Results highlighted significant correlations between quantity of movement and observational scales of engagement and a strong negative influence of apathy and depression on engagement. Overall, these findings suggest that quantity of movement could be used as an ancillary measure of engagement and underline the need to profile people with dementia according to their concurrent BPSD to better understand their engagement in activities.

Engagement in activities is of crucial importance for people with dementia. State of the art assessment techniques rely exclusively on behavior observation to measure engagement in dementia. These techniques are either too general to grasp how engagement is naturally expressed through behavior or too complex to be traced back to an overall engagement state. We carried out a longitudinal study to develop a coding system of engagement-related behavior that could tackle these issues and to create an evidence-based model of engagement to make meaning of such a coding system. Fourteen elderlies with mild to moderate dementia took part in the study. They were involved in two activities: a game-based cognitive stimulation and a robot-based free play. The coding system was developed with a mixed approach: ethographic and Laban-inspired. First, we developed two ethograms to describe the behavior of participants in the two activities in detail. Then, we used Laban Movement Analysis (LMA) to identify a common structure to the behaviors in the two ethograms and unify them in a unique coding system. The inter-rater reliability (IRR) of the coding system proved to be excellent for cognitive games (kappa = 0.78) and very good for robot play (kappa = 0.74). From the scoring of the videos, we developed an evidence-based model of engagement. This was based on the most frequent patterns of body part organization (i.e., the way body parts are connected in movement) observed during activities. Each pattern was given a meaning in terms of engagement by making reference to the literature. The model was tested using structural equation modeling (SEM). It achieved an excellent goodness of fit and all the hypothesized relations between variables were significant. We called the coding system that we developed the Ethographic and Laban-Inspired Coding System of Engagement (ELICSE) and the model the Evidence-based Model of Engagement-related Behavior (EMODEB). To the best of our knowledge, the ELICSE and the EMODEB constitute the first formalization of engagement-related behavior for dementia that describes how behavior unfolds over time and what it means in terms of engagement.

• A submitted manuscript is the author's version of the article upon submission and before peer-review. There can be important differences between the submitted version and the official published version of record. People interested in the research are advised to contact the author for the final version of the publication, or visit the DOI to the publisher's website. • The final author version and the galley proof are versions of the publication after peer review. • The final published version features the final layout of the paper including the volume, issue and page numbers.