Dementia can make it difficult for individuals to live independently, impacting their ability to carry out activities of daily living (ADLs). ADL data is frequently screened by clinicians using manual screening tools such as Katz’ Index of Independence in Activities, Lawton Brody, and Barthel Index, to detect a degradation in the ability to complete ADLs. Identifying whether a person living with dementia (PLwD) can carry out an ADL can allow for early support to be provided. This study explores the potential of utility monitoring to identify and monitor ADL achievement in PLwD. By leveraging Internet of Things (IoT) solutions and smart home sensors, including thermal sensors, door contacts, vibration sensors, wearable, motion sensors and smart plugs, utility monitoring is employed to capture ADL data. Through an open-source software framework, these sensors are integrated into a scalable and cost-effective architecture, enabling the real-time monitoring water and electricity usage. By analysing the data collected from these utilities, specific ADLs can be inferred, providing valuable insights into the daily routines and behaviours of PLwD. This research contributes to the growing field of smart home sensor monitoring for ADL identification in dementia care. The results obtained from this study shed light on the feasibility and effectiveness of utility monitoring as a non-intrusive and scalable approach for supporting independent living in PLwD. The findings show potential areas for the development of innovative assistive technologies to enhance the quality of life for individuals with dementia and alleviate caregiver burden.
The growing adoption of healthcare Internet of Things (IoT) devices has led to an exponential increase in the generation and sharing of sensitive patient data. However, ensuring transparency and trustworthiness of healthcare IoT data remains a critical concern. This research paper presents a novel approach to address these challenges by proposing a model that leverages Amazon Web Services (AWS). The model integrates various AWS services to establish secure data storage, encryption, access controls, audit logs, compliance, and data analytics, all while prioritizing data privacy through anonymization techniques. A comprehensive literature review underscores the significance of transparency and trust in healthcare IoT data, highlighting the need for robust mechanisms. The model encompasses AWS S3 and Glacier for encrypted, scalable data storage, AWS KMS for data encryption and key management, AWS IAM for access controls, and AWS CloudTrail and CloudWatch for monitoring and auditing. Additionally, AWS Lambda and Amazon Redshift are employed for data analytics. The paper outlines implementation and deployment considerations, including integration with existing healthcare IoT infrastructure, offering practical steps for implementation. Through case studies and comparative analysis, the advantages of the proposed model are demonstrated. The evaluation metrics and methods outlined enable the assessment of transparency and trustworthiness of healthcare IoT data facilitated by the proposed model. This research contributes a valuable framework for healthcare IoT stakeholders to enhance transparency and trustworthiness in their data management utilizing AWS services, while also identifying future research directions for continuous improvement in healthcare IoT data governance and trust-building mechanisms.
Anxiety state is a transitory condition that afflicts the child population of school age in Mexico City, whose control implies considering therapeutic treatments such as Art Therapy, a psycho therapeutic process that, through different artistic manifestations, offers available alternatives to control this disease. Although art therapies are usually carried out through analogous media and resources, the advances in mobile technology -as part of the implementation of the Internet of Things- and its easy children appropriation, have promoted the use of software applications as APP for mobile devices to optimize the therapeutic process. This requires identifying the contributions and opportunity areas of existing APPs for the Art Therapy process and propose approaches to define the guidelines to develop efficient applications for Art Therapy. This paper presents the justification and development process, based on a documental search and analysis of existing APPs, to propose guidelines to establish the conditions required for the development of an Art Therapy APP to support the therapeutic process in question.
The WODIA project develops Internet of Things (IoT) tools for the screening and long-term monitoring of women suffering from preeclampsia, a non-communicable disease affecting women during pregnancy. This includes performing home monitoring using an internet of thing (IoT) gateway device along with blood pressure and other medico devices as well as activity trackers. It is important that the tools developed are valid and reliable for both clinical and home use. The integration of the devices, the infrastructure, and the server components have not previously been systematically validated and evaluated for reliability during prolonged usage. The aim of this study is to validate the functionality of the WODIA healthcare IoT system, with special focus on the web API. To assess it, a set of tests were defined, and a series of tools were developed to enable testing of the components of the system. With this methodology in place, it was possible to validate several aspects of the system, in an initial development stage.
The area of diagnostic decision assistance in radiology is going through a rapid shift with the availability of a lot of patient information and the advancement of new AI (Artificial Intelligence) techniques of ML (Machine Learning), like DL (Deep Learning). They have the potential to offer imaging professionals tools that will increase the precision and effectiveness of diagnosis and therapy. This paper will discuss the development of the area of radiology and general trends emphasizing advancements in diagnostic decision assistance from the earliest rule-based expert systems to contemporary cognitive assistants utilizing I4.0 technology. The accuracy, dependability, and productivity of electronic equipment in the healthcare industry must be improved with the use of the IoMT (Internet of Medical Things). Researchers are building a digital healthcare system by connecting the already available medical resources and healthcare services. Although IoT is converging across many disciplines, our attention is on the scientific contributions of IoT in the healthcare domain. In terms of medical services in healthcare, this article discusses IoT applications, user contributions, and upcoming problems specifically in medical imaging hence the name Internet of Medical Imaging Things. It also gives a complete overview of the latest developments of ML approaches broadly utilized for Medical Imaging Diagnostic using I4.0 by classifying the study as per the ML methods, equipment, and machinery used and a foundation for future research.
Diabetes, a chronic ailment requiring ongoing care and monitoring, has undergone a healthcare shift thanks to the Internet of Things (IoT). Real-time monitoring, individualized treatment plans, and improved patient-provider communication are all features of IoT-based mobile health solutions. This study explores the components, functionalities, benefits, and disadvantages of IoT-based mobile health systems for the management of diabetes. It investigates wearable sensors, smartphone apps, and linked devices like glucose meter and monitors, placing a focus on their precision, dependability, and usability. The study explores data analytics techniques that allow for customized advice and actions. Patients can effectively control their diabetes with the use of individualized treatments and real-time monitoring. The research also looks into the data analytical methods used in IoT-based mobile health systems for the treatment of diabetes. IoT-based mobile health system issues and implications are also covered. These include issues with data security and privacy, platform and device compatibility, standardization of data formats, and ensuring that all people with diabetes have equal access to technology. Healthcare workers, academics, and policymakers may learn more about the potential of IoT-based mobile health systems to revolutionize diabetes treatment through this thorough assessment.
The widespread use of ubiquitous computing has led to people spending more time in front of screens, causing poor posture. The COVID-19 pandemic and the shift towards remote work have only worsened the situation, as many people are now working from home with inadequate ergonomics. Maintaining a healthy posture is crucial for both physical and mental health, and poor posture can result in spinal problems. Wearable systems have been developed to monitor posture and provide instant feedback. Their goal is to improve posture over time by using these devices. This article will review commercially available, and research-based wearable devices used to analyse posture. The potential of these devices in the healthcare industry, particularly in preventing, monitoring, and treating spinal and musculoskeletal conditions, will also be discussed. The findings indicate that current devices can accurately assess posture in clinical settings, but further research is needed to validate the long-term effectiveness of these technologies and to improve their practicality for commercial use.
This article discusses the revolution of medical education through immersive learning experiences in Virtual Reality (VR). It highlights the advantages, challenges, and future advancements of VR in medical education. The benefits of VR include immersive and interactive scenarios that help students understand complex medical concepts and empower personalized and self-directed learning. However, implementing VR in medical education is difficult due to technical challenges and potential physiological side effects. Despite these challenges, the growth of the VR industry offers hope for transforming medical education by closing gaps, increasing accessibility, and encouraging collaboration. The article emphasizes the need for collaboration among educators, researchers, and institutions to fully harness the transformative potential of VR in medical education. It concludes by stating that VR not only transforms medical education technologically but also changes how medical knowledge is acquired, internalized, and applied, creating a dynamic and immersive learning experience for future healthcare professionals.
This study presents a low-latency, real-time breathing cycle tracking system utilizing a conditional Generative Adversarial Network (GAN) with Wasserstein loss, with a low-powered, low sample rate Photoplethysmography (PPG) sensor. The aim is to provide a clinically accurate respiratory tool capable of tracking and visualizing the breathing cycle and rate in real-time for at-home and general ambulatory applications. To detect breathing activity in real-time, we used a wearable headband with a 25 Hz PPG sensor and an inductive respiratory sensor as ground truth. To meet the real-time and low latency constraints, the inputs were processed in 1-s windows. Signal processing and machine learning techniques were explored, and the proposed GAN-based method with Wasserstein loss and gradient penalty, outperformed others in accurately tracking the ground-truth breathing curve. Leveraging the GAN-generated breathing curve, a peak-detection algorithm calculated the respiratory rate (RR) with an average mean absolute error (MAE) of 1.47 breaths per minute (bpm) across 10 test subjects, comparable to high-sampling rate PPG literature (1 bpm), but with the advantage of 5 times faster real-time monitoring. The GAN-generated respiratory signal from a low-sampling rate wearable PPG sensor demonstrates potential as a viable alternative to traditional respiratory monitoring systems. This system offers valuable breathing monitoring, useful in various applications such as pain management.
This study delves into the landscape of health applications within online markets. These applications, offering health-related functionalities, have become integral to the lives of European citizens. The transformation of healthcare delivery, accelerated by the pace of modern life and accentuated by the COVID-19 pandemic, has elevated health applications from conveniences to essential tools capable of optimising diagnoses, self-awareness, and doctor-patient collaborations. As European societies undergo demographic shifts, with an ageing population, the significance of health applications grows. The elderly population has implications for healthcare demand as longer lifespans necessitate sustained medical interventions. These technologies, though often perceived as youth-oriented, offer substantial benefits for older individuals, a significant portion of whom grapple with chronic ailments, particularly in rural areas with limited access. The article highlights the challenge of obtaining valid user consent for health data processing, which is a cornerstone of health data protection. Issues such as granularity of consent, transparency, and power imbalances are explored in the context of health applications. The study emphasises the need for informed, unambiguous, and freely given consent, noting the discrepancies between legal requirements and actual practices. Concluding, the research suggests that despite existing legal safeguards, there are gaps in implementing robust data protection practices in health applications. The study proposes empowering users with knowledge about their rights and encouraging best practices among application manufacturers to bridge the divide between legal provisions and actual data protection. This approach aims to ensure the integrity and security of users‘ health data in the realm of health applications.
In the last years, the integration of handicapped individuals in society has gained significant attention and is being strongly stimulated by several activities. In this context, technology has major importance. Several technological solutions that help handicapped people in their daily routine, allowing their integration into society, have emerged. However, besides all efforts that have been made, still exist some challenges related to specific basic tasks in blind people’s daily routines. Namely, the management and identification of personal garments could become a complex and time-consuming task. For this specific task, these people depend on their relatives for choosing the exact clothes desired. In this way, and based on the problems presented, this paper proposes the development of an automatic wardrobe capable to assist blind people. This proposal is integrated in a work under development of a prototype of a mechatronic system for the choice and management of garments. The proposed solution seeks to provide an improvement in the quality of life of blind people.
A fall of an elderly person often leads to serious injuries, even death. Many falls occur in the home environment, and hence, a reliable fall detection system that can raise alarms immediately is a necessity. Wrist-worn accelerometer-based fall detection systems have been developed, and there are various data sets available, but the accuracy and precision have not been standardized or compared; even where comparison does exist, it has been run on GPUs. No analysis of the workability of the models and the data sets on SoCs has been previously attempted. Though over the last few years, ML and DL algorithms have been increasingly used in fall detection, and there have also been some suggestions for the use of compressed modelling, there are no concrete statistics available to form this conclusion. In this paper, we attempt to understand why ML algorithms cannot run as-is on existing SoCs; We are using Snapdragon 410c to do our analytics as it is primarily used in Biomedical and IoT applications, has low power consumption and small form factor making it ideal for wearables. In this paper, we have used KNN to prove that ML cannot be used directly on SoCs. We are using KNN as it does not have any pre-training period, and it is a very simple algorithm that gives good accuracy. In this paper, we establish the need for model and data compression for fall detection if we must use ML or DL algorithms on SOCs. We have done this with statistical analysis across different data sets.
According to the World Health Organization (WHO), about 17.9 millions people per year die from cardiovascular diseases (CVDs), representing more than 32
In this paper, an overview of the smartphone measurement methods for Heart Rate (HR) and Heart Rate Variability (HRV) is presented. HR and HRV are important vital signs to be evaluated and monitored especially in a sudden heart crisis and in the case of COVID-19. Unlike other specific medical devices, the smartphone can always be present with a person, and it is equipped with sensors that can be used to estimate or acquire such vital signs. Furthermore, their computation and connection capabilities make them suitable for Internet of Things applications. Although in the literature many interesting solutions for evaluating HR and HRV are proposed, often a lack in the analysis of the measurement uncertainty, the description of the measurement procedure for their validation, and the use of a common gold standard for testing all of them is highlighted. The lack of standardization in experimental protocol, processing methodology, and validation procedures, impacts the comparability of results and their general validity. To stimulate the research activities to fill this gap, the paper gives an analysis of the most recent literature together with a logical classification of the measurement methods by highlighting their main advantages and disadvantages from a metrological point of view together with the description of the measurement methods and instruments proposed by authors for their validation.
A fall in third age triggers a domino effect of consequences that are recognized by specialists as leading causes of further falls. After the first event, the post-fall syndrome onsets: a pathological fear of falling that affects quality of life. It leads to loss of self-efficacy, sedentarism, musculoskeletal weakening, reduced mobility, postural insufficiency, gait disorders, isolation and depression—all acknowledged as fall risk factors. Specialists agreed that the most effective approach to prevent new episodes is to restore confident postures and good alignments. This paper presents the first design stages of a soft-actuated re-educational garment for remote post-fall rehabilitation in female users. The objective is to i) restore postural control by providing a gentle pressure stimulus, suggesting corrections when poor body alignments are detected; ii) restore the perceived self-efficacy; iii) promote physical activity by motion monitoring and providing daily reports through a patient-therapist smartphone app. To date, we have tested a soft body-postures detection system by cross-checking data from a network of e-textile stretch sensors, along with a pneumatic actuator system around the user’s torso providing a targeted pressure stimulus to correct bad habits. Tests have been run on a limited number of users due to the Covid-19 emergency. Data are not yet statistically conclusive but suggest the way to a new dimensional approach, both for rehabilitation and prevention.
An electrocardiogram (ECG) is a simple test that checks the heart's rhythm and electrical activity and can be used by specialists to detect anomalies that could be linked to diseases. This paper intends to describe the results of several artificial intelligence methods created to automate identifying and classifying potential cardiovascular diseases through electrocardiogram signals. The ECG data utilized was collected from a total of 46 individuals (24 females, aged 26 to 90, and 22 males, aged 19 to 88) using a BITalino (r)evolution device and the OpenSignals (r)evolution software. Each ECG recording contains around 60 s, where, during 30 s, the individuals were in a standing position and seated down during the remaining 30 s. The best performance in identifying cardiovascular diseases with ECG data was achieved with the Naive Bays classifier, reporting an accuracy of 81.36%, a precision of 26.48%, a recall of 28.16%, and an F1-Score of 27.29%.
Skin Conductance (SC) variations, or, alternatively, changes of the human skin resistance known as Galvanic Skin Response (GSR), allow to detect the physiological reactions of a subject to different stimuli, either physical, or emotional and cognitive. This paper presents the analysis of SC variations under acoustic stimulation, performed by using a low-cost portable device designed for experimental use, able to acquire the human skin resistance values, which can be easily converted into SC ones. Preliminary findings, despite not generalizable because of the small set of participants involved in experiments, suggest that the reaction to sounds perceived as not pleasant is quite clear to identify, while further investigations are needed for acoustic stimuli classified as pleasant.
The essential criterion for developing an intelligent age-friendly environment is evaluating and monitoring the provision of services. Our research aims to allow the deployment of a broad range of digital healthcare solutions interconnected in an IoT network ecosystem. Through their interoperability, we will be able to cultivate age-friendly smart homes for older adults. Thus, we will enable interpreted living and wellbeing. The intelligent integrations of digital solutions will allow the acquisition and evaluation of health-related data. Standardization, interoperability and scalability of the integration will increase efficiency in healthcare, improving older adults' Quality of Life (QoL). Also, interpreting their needs will allow key stakeholders to optimize the Quality of Service (QoS). The proposed Internet of Health (IoH) framework will encapsulate sustainable and affordable innovative solutions and their benefits for a comfortable, meaningful, and independent life in an intelligent environment. Therefore, the frame mediated by edge computing, in-home and community settings will be able to interact with healthcare networks contributing to hospitalizations and institutional care.
In the area of smartphone-based hearing screening, the number of speech-in-noise tests available is growing rapidly. However, the available tests are typically based on a univariate classification approach, for example using the speech recognition threshold (SRT) or the number of correct responses. There is still lack of multivariate approaches to screen for hearing loss (HL). Moreover, all the screening methods developed so far do not assess the degree of HL, despite the potential importance of this information in terms of patient education and clinical follow-up. The aim of this study was to characterize multivariate approaches to identify mild and moderate HL using a recently developed, validated speech-in-noise test for hearing screening at a distance, namely the WHISPER (Widespread Hearing Impairment Screening and PrEvention of Risk) test. The WHISPER test is automated, minimally dependent on the listeners’ native language, it is based on an optimized, efficient adaptive procedure, and it uses a multivariate approach. The results showed that age and SRT were the features with highest performance in identifying mild and moderate HL, respectively. Multivariate classifiers using all the WHISPER features achieved better performance than univariate classifiers, reaching an accuracy equal to 0.82 and 0.87 for mild and moderate HL, respectively. Overall, this study suggested that mild and moderate HL may be discriminated with high accuracy using a set of features extracted from the WHISPER test, laying the ground for the development of future self-administered speech-in-noise tests able to provide specific recommendations based on the degree of HL.
Human activity classification is assuming great relevance in many fields, including the well-being of the elderly. Many methodologies to improve the prediction of human activities, such as falls or unexpected behaviors, have been proposed over the years, exploiting different technologies, but the complexity of the algorithms requires the use of processors with high computational capabilities. In this paper different deep learning techniques are compared in order to evaluate the best compromise between recognition performance and computational effort with the aim to define a solution that can be executed by an IoT device, with a limited computational load. The comparison has been developed considering a dataset containing different types of activities related to human walking obtained from an automotive Radar. The procedure requires a pre-processing of the raw data and then the feature extraction from range-Doppler maps. To obtain reliable results different deep learning architectures and different optimizers are compared, showing that an accuracy of more than 97% is achieved with an appropriate selection of the network parameters.
