1,721,028 research outputs found
The paradox of the artificial intelligence system development process: the use case of corporate wellness programs using smart wearables
Get PDFArtificial intelligence (AI) systems have been widely applied to various contexts, including high-stake decision processes in healthcare, banking, and judicial systems. Some developed AI models fail to offer a fair output for specific minority groups, sparking comprehensive discussions about AI fairness. We argue that the development of AI systems is marked by a central paradox: the less participation one stakeholder has within the AI system's life cycle, the more influence they have over the way the system will function. This means that the impact on the fairness of the system is in the hands of those who are less impacted by it. However, most of the existing works ignore how different aspects of AI fairness are dynamically and adaptively affected by different stages of AI system development. To this end, we present a use case to discuss fairness in the development of corporate wellness programs using smart wearables and AI algorithms to analyze data. The four key stakeholders throughout this type of AI system development process are presented. These stakeholders are called service designer, algorithm designer, system deployer, and end-user. We identify three core aspects of AI fairness, namely, contextual fairness, model fairness, and device fairness. We propose a relative contribution of the four stakeholders to the three aspects of fairness. Furthermore, we propose the boundaries and interactions between the four roles, from which we make our conclusion about the possible unfairness in such an AI developing process
A Home Telemedicine System for Continuous Respiratory Monitoring
Get PDFThis article presents a continuous home telemonitoring system for chronic respiratory patients using 5G connectivity developed in partnership with Vodafone as a part of the 5G Trial in Milan established by the Italian Ministry of Economic Development. The system features a wearable respiratory and activity monitor, an environmental sensor and a pulse oximeter sending the data through a 5G router to a Multi-Edge Computing server, incorporated in the Vodafone 5G infrastructure, where they are stored and accessible for visualization. In particular, activity, respiratory and environmental data are continuously streamed and collected. The solution has been tested on 18 healthy volunteers during non-supervised recordings lasting at least 48 hours. The combination of recognized activities and associated respiratory parameters provided statistically significant variations in breathing patterns between one activity and the other, thus giving more complete information to the clinicians than previously studied telemedicine systems based on spot-checks. In particular, statistically significant differences are found in tidal volume and minute ventilation between horizontal and vertical postures (p < 0.001) and between vertical postures and dynamic activities (p < 0.001); the respiratory rate shows statistically significant differences between horizontal and vertical postures (p < 0.001). Some environmental parameters have different mean values between day and night, such as carbon dioxide (p < 0.001). Trials on patients are needed to further study this telemedicine solution and make it commercially available in the future. The main further technical development suggested is the use of commercial 5G smartphones as routers, in order to make the system usable outside of home settings
A New Wearable System for Personal Air Pollution Exposure Estimation: Pilot Observational Study
Get PDFBackground: Air pollution is a major environmental cause of premature deaths, responsible for around 7 million deaths annually. In this context, personal air pollution exposure (PAPE), the product of pollutant concentration and minute ventilation (V'm), is a crucial measure for understanding individual health risks. Standard exposure techniques do not address the space-time variability of air pollution, both indoor and outdoor, and the intra- and intersubject variability in V'm. Objective: This study evaluates the feasibility of using a wearable body sensor network (BSN) to estimate PAPE in real-life settings, assess its capability to detect spatiotemporal variations in pollution levels, and compare inhaled dose estimates from the BSN with those from fixed monitoring stations and standard V'm values. The study also examines the system's usability. Methods: The system, a BSN capturing physiological (pulse rate [PR] and respiratory rate [RR]) and environmental data, including health-affecting pollutants (particulate matter [PM] 1, PM2.5, PM10, CO2, CO, total volatile organic compounds, and NO2), was tested in a 4.5 km walk in Milan by 20 healthy volunteers. PR and RR collected by the system were used, together with biometric data and forced vital capacity estimations, in a model for V'm estimation to compute PAPE. Pollution levels were compared between morning and afternoon measurements, as well as between indoor and outdoor settings. Results: Variations in RR were found among volunteers and at different locations for the same participant. Significant differences (P<.001) in pollutant concentrations were observed between morning and afternoon for CO2 (higher in the morning) and PM (higher in the afternoon). Spatial variability along the walking path was also detected, highlighting the system's high spatiotemporal resolution. Indoor environments showed high variability in CO2 and total volatile organic compounds, while outdoor settings exhibited elevated and variable PM levels. The mean PAPE to PM2.5 estimated with tabulated V'm and fixed station data was 13.31 (SD 4.16) μg while the one estimated with the BSN was 16.27 (SD 9.78) μg, 2.96 μg higher (22.3%; 95% CI -6.55 to 0.63; P=.05) than the former one, and with a broader IQR. Nevertheless, the 2 estimation methods show a good and strongly significant correlation (r=0.665; P<.001). The system's usability was generally rated as good. Conclusions: The BSN provides high-resolution spatiotemporal data on personal exposure, capturing differences in pollution levels dependent on time, location, and surrounding environment, along with individual physiological variations. It offers a more accurate estimation of inhaled dose in real-life settings, supporting personalized exposure assessments and potential applications in activity planning and complementing epidemiological research
Wearable Tech for Long-Distance Runners
No full textThis chapter illustrates the main parameters that can be detected by means of wearable devices specifically designed for sport activities, with a focus on wearables for long-distance running. Most recent advancements in heart rate monitoring, physiological monitoring, running parameters assessment, and environmental monitoring are discussed and presented. The presented solutions are already on the market or still at the research level. The use of smartphone apps is also briefly illustrated. Some future perspectives are also discussed, especially related to the impact of the external environment on the physiological parameters of the athlete. The outline of the chapter was determined based on an interview of an expert running coach, who provided his insights on the use of wearables during running. Despite the widespread use of wearable devices, not all of them have been validated against a gold standard and some validation studies did not show high accuracy. Furthermore, the technology behind most commercially available solutions is rarely published, thus making it almost impossible for the final users to actually know how reliable their devices are
Patient characteristics associated with the acceptability of teleconsultation: a retrospective study of osteoporotic patients post-COVID-19
Get PDFBackground: Due to the COVID-19 pandemic, teleconsultations (TCs) have become common practice for many chronic conditions, including osteoporosis. While satisfaction with TCs among patients increases in times of emergency, we have little knowledge of whether the acceptability of TCs persists once in-person visits return to being a feasible and safe option. In this study, we assess the acceptability of TCs across five dimensions for osteoporosis care among patients who started or continued with TCs after the COVID-19 pandemic had waned. We then explore the patient characteristics associated with these perceptions. Methods: Between January and April 2022, 80 osteoporotic patients treated at the Humanitas Hospital in Milan, Italy, were recruited to answer an online questionnaire about the acceptability of TCs for their care. The acceptability of TCs was measured using a modified version of the Service User Technology Acceptability Questionnaire (SUTAQ), which identifies five domains of acceptability: perceived benefits, satisfaction, substitution, privacy and discomfort, and care personnel concerns. Multivariable ordinary least squares (OLS) linear regression analysis was performed to assess which patient characteristics in terms of demographics, socio-economic conditions, digital skills, social support, clinical characteristics and pattern of TC use were correlated with the five domains of acceptability measured through the SUTAQ. Results: The degree of acceptability of TCs was overall good across the 80 respondents and the five domains. Some heterogeneity in perceptions emerged with respect to TCs substituting for in-person visits, negatively impacting continuity of care and reducing the length of consultations. For the most part, acceptability was not affected by patient characteristics with a few exceptions related to treatment time and familiarity with the TC service modality (i.e., length of osteoporosis treatment and number of TCs experienced by the patient). Conclusions: TCs appear to be an acceptable option for osteoporosis care in the aftermath of the COVID-19 pandemic. This study suggests that other characteristics besides age, digital skills and social support, which are traditionally relevant to TC acceptability, should be taken into account in order to better target this care delivery modality
Validation of a Wearable System for Respiratory Rate Monitoring in Dogs
No full textOne of the most relevant physiological parameters in dogs is respiratory rate (RR). The aim of this paper is to present a novel wearable system that allows to accurately estimate RR in dogs, and to compare it to a gold standard in static conditions. Data from 12 dogs were acquired while the animals were anesthetized and attached to a vital signs monitor. The experimental setup consisted of three Inertial Measurement Units (IMUs) applied on the dog, and a video camera filming the RR value shown on the monitor. The range of RR values analyzed in the study is 0 to 29 breaths per minute, read by the vital signs monitor. The mean RMSE for the data acquisitions is 1.68 breaths per minute. The values of the filtering parameters that allow to obtain the best performance depend on the specific acquisition. This result demonstrates that adaptive filtering is a viable method for the application. Future developments include tests on a larger dataset, and trials on dogs in unconstrained environments and during movement
Digital technologies for step counting: between promises of reliability and risks of reductionism
Get PDFStep counting is among the fundamental features of wearable technology, as it grounds several uses of wearables in biomedical research and clinical care, is at the center of emerging public health interventions and recommendations, and is gaining increasing scientific and political importance. This paper provides a perspective of step counting in wearable technology, identifying some limitations to the ways in which wearable technology measures steps and indicating caution in current uses of step counting as a proxy for physical activity. Based on an overview of the current state of the art of technologies and approaches to step counting in digital wearable technologies, we discuss limitations that are methodological as well as epistemic and ethical—limitations to the use of step counting as a basis to build scientific knowledge on physical activity (epistemic limitations) as well as limitations to the accessibility and representativity of these tools (ethical limitations). As such, using step counting as a proxy for physical activity should be considered a form of reductionism. This is not per se problematic, but there is a need for critical appreciation and awareness of the limitations of reductionistic approaches. Perspective research should focus on holistic approaches for better representation of physical activity levels and inclusivity of different user populations
Exploring air pollution awareness: insights from interviews with technology enthusiasts using wearable monitoring devices
Get PDFThis study aims to investigate shifts in awareness regarding air pollution and its correlation with interest in using wearable devices for air quality monitoring. 16 healthy participants, predominantly engineers, residing or studying in Milan, were interviewed to assess their knowledge and interest in air pollution. Participants then walked a predefined route of 4.5 km in Milan while observing real-time air pollution data recorded by a wrist-worn wearable device. Post-walk interviews explored changes in awareness and enthusiasm for personal air quality monitoring. Results indicated widespread recognition of pollution sources, including industries, transportation, and agricultural activities, and health effects. Interestingly, reliance on sensory cues for air quality evaluation was prevalent among participants, underscoring a potential bias toward olfactory indicators. Despite interest in personal air quality monitoring, concerns regarding continuous monitoring leading to feelings of powerlessness and mental stress were noted. Nevertheless, participants expressed interest in actionable information to mitigate these concerns and promote lifestyle choices to decrease exposure to pollutants. Notably, a shift in awareness was observed following interaction with the monitoring device, indicating its potential to enhance public awareness and support for air quality policies. Findings underscore the importance of technological interventions in promoting public awareness and understanding of air pollution dynamics
- …
