Connected Health System Research Articles

Assessing the sustainable alignment of a sensor-based connected health system with SDGs: an evaluation model and case study

PurposeThe main objective of the study is to address the lack of sustainability assessments of smart connected health systems in the academic literature by presenting an assessment model to determine the alignment of these systems with the 17 Sustainable Development Goals (SDGs) proposed in the 2030 Agenda.Design/methodology/approachAn evaluation model based on decision analysis is proposed that includes three phases: alignment framework, information gathering and assessment. This model measures the alignment of the connected health system with each of the 17 SDGs, identifying the goals and criteria associated with each SDG that the system achieves to satisfy.FindingsThe analysis reveals that the system has achieved more than 24% of the targets among the 17 SDGs. In addition, it identifies four sustainability challenges that the system potentially addresses in relation to the SDGs, providing valuable guidance for researchers and practitioners interested in sustainable health technology development.Practical implicationsThe study's results have significant implications for policymakers and stakeholders in the health and technology sectors.Originality/valueThe originality of this study lies in its comprehensive approach to assessing the sustainability of connected health systems in the context of the SDGs, filling an important gap in the existing literature.

SecuTwin for All: Enhancing Disability-focused Healthcare Through Secure Digital Twin Technology and Connected Health Monitoring

In the evolving domain of disability-focused healthcare, the integration of secure digital twin technology and connected health systems emerges as a pivotal innovation. The “SecuTwin for All” framework represents a novel approach designed to transcend traditional healthcare monitoring barriers, ensuring comprehensive, real-time, and personalized health data management for individuals with disabilities. This enhanced framework is predicated on the seamless amalgamation of wearable computing devices, mobile health (mHealth) applications, and digital twin technology. At its core, SecuTwin for All incorporates dynamic digital representations of patients to facilitate tailored health insights, thereby promoting an inclusive health monitoring ecosystem that is accessible, secure, and efficient. Central to the SecuTwin for All framework is its commitment to data integrity and privacy. Employing state-of-the-art encryption methodologies alongside stringent data privacy protocols, the framework guarantees the safeguarding of sensitive health information. The design ethos of the wearable devices underscores an intuitive user experience, characterized by user-friendly interfaces and seamless integration with mobile applications. These devices are instrumental in capturing and transmitting vital health data in real time, thus enabling continuous monitoring and immediate intervention when necessary. The mHealth application, a critical conduit within the framework, supports robust data processing and incorporates advanced user authentication mechanisms. This ensures both enhanced usability and security, addressing key concerns in digital health platforms. The effectiveness of the SecuTwin for All framework was rigorously evaluated within a simulated healthcare environment tailored to replicate complex real-world scenarios. This simulation was meticulously designed to assess the framework’s proficiency in managing diverse health data types and user interactions, specifically focusing on the unique needs of individuals with disabilities. Simulation results were compelling, demonstrating the framework’s exceptional performance across multiple metrics: a 98% success rate in user experience satisfaction, a 97% compliance rate with data privacy standards, and a 99% effectiveness in thwarting cybersecurity threats.

The role of health system penetration rate in estimating the prevalence of type 1 diabetes in children and adolescents using electronic health records.

Having sufficient population coverage from the electronic health records (EHRs)-connected health system is essential for building a comprehensive EHR-based diabetes surveillance system. This study aimed to establish an EHR-based type 1 diabetes (T1D) surveillance system for children and adolescents across racial and ethnic groups by identifying the minimum population coverage from EHR-connected health systems to accurately estimate T1D prevalence. We conducted a retrospective, cross-sectional analysis involving children and adolescents <20years old identified from the OneFlorida+ Clinical Research Network (2018-2020). T1D cases were identified using a previously validated computable phenotyping algorithm. The T1D prevalence for each ZIP Code Tabulation Area (ZCTA, 5 digits), defined as the number of T1D cases divided by the total number of residents in the corresponding ZCTA, was calculated. Population coverage for each ZCTA was measured using observed health system penetration rates (HSPR), which was calculated as the ratio of residents in the corresponding ZTCA and captured by OneFlorida+ to the overall population in the same ZCTA reported by the Census. We used a recursive partitioning algorithm to identify the minimum required observed HSPR to estimate T1D prevalence and compare our estimate with the reported T1D prevalence from the SEARCH study. Observed HSPRs of 55%, 55%, and 60% were identified as the minimum thresholds for the non-Hispanic White, non-Hispanic Black, and Hispanic populations. The estimated T1D prevalence for non-Hispanic White and non-Hispanic Black were 2.87 and 2.29 per 1000 youth, which are comparable to the reference study's estimation. The estimated prevalence of T1D for Hispanics (2.76 per 1000 youth) was higher than the reference study's estimation (1.48-1.64 per 1000 youth). The standardized T1D prevalence in the overall Florida population was 2.81 per 1000 youth in 2019. Our study provides a method to estimate T1D prevalence in children and adolescents using EHRs and reports the estimated HSPRs and prevalence of T1D for different race and ethnicity groups to facilitate EHR-based diabetes surveillance.

Pathophysiologic Basis of Connected Health Systems.

Since the start of the COVID-19 pandemic, there has been a rapid transition to telehealth across the United States, primarily involving virtual clinic visits. Additionally, the proliferation of consumer technologies related to health reveals that for many people health and care in the contemporary world extends beyond the boundaries of a clinical interaction and includes sensors and devices that facilitate health in personal environments. The ideal connected environment is networked and intelligent, personalized to promote health and prevent disease. The combination of sensors, devices, and intelligence constitutes a connected health system around an individual that is optimized to improve and maintain health, deliver care, and predict and reduce risk of illness. Just as modern medicine uses the pathophysiology of disease as a framework for the basis of pharmacologic therapy, a similar clinically reasoned approach can be taken to organize and architect technological elements into therapeutic systems. In this work, we introduce a systematic methodology for the design of connected health systems grounded in the pathophysiologic basis of disease. As the digital landscape expands with the ubiquity of health devices, it is pivotal to enable technology-agnostic clinical reasoning to guide the integration of technological innovations into systems of health and care delivery that extend beyond the boundaries of a clinical interaction. Applying clinical reasoning in a repeatable and systematic way to organizing technology into therapeutic systems can yield potential benefits including expanding the study of digital therapeutics from individual devices to networked technologies as therapeutic interventions; empowering physicians who are not technological experts to still play a significant role in using clinical reasoning for architecting therapeutic networks of sensors and devices; and developing platforms to catalog and share combinations of technologies that can form therapeutic networks and connected health systems.

Evaluating the Efficacy of Connected Healthcare: An Empirical Examination of Patient Engagement Approaches and Their Impact on Readmission

Connected healthcare is a form of health delivery that connects patients and providers through connected health devices, allowing providers to monitor patient behavior and proactively intervene before an adverse event occurs. Unlike the costs, the benefits of connected healthcare in improving patient behavior and health outcomes are usually difficult to determine. In this study, we examine the efficacy of a connected health system that aimed to reduce readmissions through improved medication adherence. Specifically, we study 975 patients with heart disease who received electronic pill bottles that tracked medication adherence. Patients who were nonadherent received active social support that involved different types of feedback, such as text messages and calls. By integrating data on adherence, intervention, and readmission, we aim to (1) investigate the efficacy of connected healthcare in promoting medication adherence, (2) examine the relationship between medication adherence and readmission, and (3) develop a dynamic readmission risk-scoring model that considers medication adherence and use the model to better target nonadherent patients. Our findings suggest that patients are more likely to become adherent when they or their partners receive high levels of intervention that involve personalized feedback and when the intervention is escalated quickly and consistently. We also find that long-term adherence to three common heart medications is strongly associated with reduced readmission risk. Lastly, using counterfactual simulation, we apply the dynamic readmission risk-scoring model to our setting and find that, when using an intervention strategy that prioritizes high-risk patients, we obtain 10% fewer readmissions while using the same effort level from the patient support team. This paper was accepted by Jayashankar Swaminathan, operations management. Funding: The randomized, controlled trial was funded by the Center for Medicare &amp; Medicaid Innovation [Healthcare Innovation Award 1C1CMS331009]. Supplemental Material: The data files are available at https://doi.org/10.1287/mnsc.2023.4865 .

Towards a Connected Mobile Cataract Screening System: A Future Approach.

Advances in computing and AI technology have promoted the development of connected health systems, indirectly influencing approaches to cataract treatment. In addition, thanks to the development of methods for cataract detection and grading using different imaging modalities, ophthalmologists can make diagnoses with significant objectivity. This paper aims to review the development and limitations of published methods for cataract detection and grading using different imaging modalities. Over the years, the proposed methods have shown significant improvement and reasonable effort towards automated cataract detection and grading systems that utilise various imaging modalities, such as optical coherence tomography (OCT), fundus, and slit-lamp images. However, more robust and fully automated cataract detection and grading systems are still needed. In addition, imaging modalities such as fundus, slit-lamps, and OCT images require medical equipment that is expensive and not portable. Therefore, the use of digital images from a smartphone as the future of cataract screening tools could be a practical and helpful solution for ophthalmologists, especially in rural areas with limited healthcare facilities.

Image Descriptors for Weakly Annotated Histopathological Breast Cancer Data

Introduction: Cancerous Tissue Recognition (CTR) methodologies are continuously integrating advancements at the forefront of machine learning and computer vision, providing a variety of inference schemes for histopathological data. Histopathological data, in most cases, come in the form of high-resolution images, and thus methodologies operating at the patch level are more computationally attractive. Such methodologies capitalize on pixel level annotations (tissue delineations) from expert pathologists, which are then used to derive labels at the patch level. In this work, we envision a digital connected health system that augments the capabilities of the clinicians by providing powerful feature descriptors that may describe malignant regions.Material and Methods: We start with a patch level descriptor, termed Covariance-Kernel Descriptor (CKD), capable of compactly describing tissue architectures associated with carcinomas. To leverage the recognition capability of the CKDs to larger slide regions, we resort to a multiple instance learning framework. In that direction, we derive the Weakly Annotated Image Descriptor (WAID) as the parameters of classifier decision boundaries in a Multiple Instance Learning framework. The WAID is computed on bags of patches corresponding to larger image regions for which binary labels (malignant vs. benign) are provided, thus obviating the necessity for tissue delineations.Results: The CKD was seen to outperform all the considered descriptors, reaching classification accuracy (ACC) of 92.83%. and area under the curve (AUC) of 0.98. The CKD captures higher order correlations between features and was shown to achieve superior performance against a large collection of computer vision features on a private breast cancer dataset. The WAID outperform all other descriptors on the Breast Cancer Histopathological database (BreakHis) where correctly classified malignant (CCM) instances reached 91.27 and 92.00% at the patient and image level, respectively, without resorting to a deep learning scheme achieves state-of-the-art performance.Discussion: Our proposed derivation of the CKD and WAID can help medical experts accomplish their work accurately and faster than the current state-of-the-art.

Role of digital technology in delivering 'healthy futures' and 'healthy cities'.

Digital health technologies and services play a critical role in the delivery of safe and efficient healthcare and better health outcomes. Interoperability of these technologies and services, as well as digital inclusion for communities are important enablers of a modern, connected health system. The ongoing development of these factors is an aspiration of Australia's National Digital Health Strategy (NDHS). The Australian Digital Health Agency co-designed the NDHS with input from healthcare consumers and providers, digital health industry, academic and policy experts and organisations. Approved by all Australian governments in 2017, it provides a forward vision to 2022, with seven pillars that include: Access to health information through My Health record; Secure Messaging; Medicines Safety; Interoperability; Enhanced models of care; Workforce and Education and Driving Innovation. All of these pillars have interdependent features, and many play a role in enabling communities to live healthier and happier lives supported by better connected healthcare services as well as access to information in a timely and efficient manner at the point of care. A 'Communities of Excellence' programme has supported regional communities to connect health services to My Health Record, increase digital health tools use and provide digital health literacy support to consumers. The aims of this programme are to allow the benefits of improved interoperability and better connected care to flow to people and their clinicians, test innovation that could go on to be scaled nationally, and close the health inequity gap experienced by people in rural and remote communities.

Network modeling and Internet of things for smart and connected health systems—a case study for smart heart health monitoring and management

Heart disease is a leading cause of death in the US. Recent advances in the Internet of Things (IoT) provide a great opportunity to realize smart and connected health systems through IoT monitoring and sensor-based data analytics of cardiac disorders. However, big data arising from the large-scale IoT system pose a significant challenge for efficient and effective sensory information processing and decision making. Very little has been done to glean pertinent information about the disease-altered cardiac activity in the context of large-scale IoT network. In this study, we propose a parallel computing framework for multi-level network modeling and monitoring of cardiac dynamics to realize the potential of IoT-enabled smart health management. Specifically, dissimilarities among cardiac signals are firstly characterized among heartbeats for an individual patient, as well as among representative heartbeats for different patients. Then, a stochastic learning approach is developed to optimize the embedding of cardiac signals into a beat-to-beat network model, as well as a patient-to-patient network model. Further, we develop a parallel computing algorithm to improve the computational efficiency. Finally, a statistical process monitoring scheme is designed to harness network features for real-time monitoring and anomaly detection of cardiac activities. Experimental results show the proposed methodology has strong potential to realize a smart and interconnected system for cardiac health management in the context of large-scale IoT network.

Distributed Security Architecture Based on Blockchain for Connected Health: Architecture, Challenges, and Approaches

The ubiquitous nature of a connected health system imposes challenges with regard to the design of system architecture, security, and privacy. Different from traditional centralized systems, a distributed blockchain-based security protection architecture is proposed. In particular, smart contracts, as an intelligent protocol in the blockchain technology, are exploited to automatically achieve system confidentiality, integrity, and authenticity. Research challenges related to security and privacy issues in our proposed architecture are then analyzed, followed by potential solutions. Finally, security performance simulations and analyses are conducted to validate and evaluate the effectiveness of the proposed security architecture.

Software mediators as first-class entities of systems-of-systems software architectures

ContextIn contrast to traditional software systems that are mostly created from scratch, current software systems are engineered as a junction of systems already in operation. Examples can be found in domains, such as smart cities, crisis and emergency, IoT, big data, industry 4.0, and connected health systems. Most of them can be considered systems-of-systems (SoS), since they refer to alliances of operational and managerial independent software-intensive systems, which are sometimes distributed over different environments. Therefore, SoS software architectures must be dynamic, evolve over time, and support the execution of emergent behaviors to accomplish SoS missions. They must be also designed to enable the connection of heterogeneous systems, making possible their interoperation, communication, coordination, cooperation, and collaboration, most of the times, in a seamless way. Similar challenges have been addressed by using software mediators as architectural entities. However, the application of mediators in SoS has not been properly explored.GoalThis article introduces MediArch, a layered architecture that considers mediators as first-class software entities to be used in the construction of SoS architectures. Our objective is to present evidence about how MediArch’s can support the construction of SoS architectures.MethodsThe following four steps were conducted to define MediArch: (1) identification of mediation requirements to allow SoS properties; (2) establishment and categorization of twelve types of mediators, for enabling capabilities of communication and control of constituent systems interactions and conversion of heterogeneous messages exchanged through a mediation infrastructure; (3) specification of duties, behaviors, assumptions, and guarantees of mediators; and (4) organization of MediArch in three layers, namely, the constituents & consumer systems layer; the communication, conversion, & coordination layer; and the control layer. This architecture was used as the backbone for the software architectures of two SoS in different domains, namely, flood monitoring system-of-systems (FMSoS), and health-care supportive home system-of-systems (HSH-SoS), for providing evidence on how MediArch supports the architecting process of SoS.ResultsMediArch (1) supports the integration of independent constituent systems, (2) provides strategies to manage emergent behaviors, (3) defines different schemes of control authorities, (4) offers elements to support SoS evolution, and (5) promotes the resilience and adaptability of SoS architectures.ConclusionsAlthough MediArch contributes to the establishment of SoS architectures, some challenges related to performance, resource consumption, security, safety, and non-disruptive reconfigurations must still be overcome.

A Rainbow-Based Authentical Scheme for Securing Smart Connected Health Systems.

Smart Connected Health Systems (SCHSs) belong to health systems that provide services of health care remotely. They provide the doctors with access to electronic medical records with the aid of medical sensors, smart wearable devices and smart medical instruments. Although SCHSs have many applications in the area of health care, securing massive amount of valuable and sensitive data of the patients and preserving the privacy are challenging. User authentication based on public key cryptographic techniques is playing a crucial role in SCHSs for protecting the privacy of patients. However, quantum computers will break such techniques. Rainbow signature is one of the candidates of the next generation of cryptographic algorithms which can resist attacks on quantum computers. However, it is vulnerable to Differential Power Analysis (DPA) attacks, which is based on information gained from the cryptographic implementations. We present techniques to exploit the countermeasures to protect Rainbow against DPA attacks. We propose a variant of Rainbow with resistance to DPA attacks. First, we take a random vector to randomize the power consumption of private keys during computing the first affine transformation; Second, random variables are adopted during computing central map transformation; Third, we take two random vectors during computing the second affine transformation to randomize the power consumption of private keys. We analyze the efficiency and implement the scheme on hardware. Compared with the related implementations, our scheme is efficient and suitable for signature generations on hardware. Besides, we propose a secure authentical scheme based on the implementation for protecting record of patients in SCHSs.

Sharing information safely and securely: the foundation of a modern health care system.

Sharing information safely and securely: the foundation of a modern health care system.

Halalopathy: A science of trust in medicine

The human body is well organized, regulated and connected. One of the greatest scientific challenges today is to integrate mind, behaviour and health. Enormous advances in health care have been achieved. However, diseases like cancer still require treatment options beyond therapeutic drugs, namely surgery and radiation. Human being is not only made of cells, tissues and organs, but also feelings and sensations. Linking mental state with physical health is essential to include all elements of disease. For this purpose, halalopathy has been introduced as a new model to integrate mind, behaviour and health, where psychology, spirituality and rationality can be integrated together to generate a well-organized, regulated and connected health system. Halalopathic approaches are based on mind-trust-drug and mind-trust-belief. If the drug and human’s belief are compatible, trust in the rationally designed drug will be synergized and placebo effects will be activated to initiate the healing process. Such an organized health system will lower the body’s entropy and increase potential energy, which is an important aspect to promote the healing process, with a therapeutic drug toward complete recovery. This study enlightens laws of compatibility to initiate a domino chain effect to activate placebo effects and lower the body’s entropy. The healing power of each effect will contribute to the healing process and enhance the total drug effects.

Barriers to care in a West Bank refugee camp: a qualitative study

BackgroundHealth-care delivery is fragmented owing to poorly connected health systems in the occupied Palestinian territory. Palestinian refugees are particularly vulnerable. Aida Camp in Bethlehem (with a population of approximately 6000 people) hosts refugees from 27 villages in what is now Israel. There is no clinic within Aida Camp, and health-care access is a longstanding community concern. This study aimed to elucidate refugees' perceptions of the following topics in focus group discussions, with the goal of developing interventions in a spirit of community-based praxis: (1) community health burdens; (2) access to health facilities; (3) barriers to care; and (4) engagement of community health workers as a means of addressing gaps in care. MethodsFocus group interviews with male and female refugees living in Aida Camp were conducted from December, 2016, to February, 2017. Participants were targeted using flyers and internet advertisements. Only Palestinian refugees currently living in Aida Camp and aged 18–75 years were included, and a total of 54 participants were interviewed. Sessions lasted 90–120 min, with 12 to 16 open-ended questions and facilitated discussion among eight to ten participants. Six focus groups were required to reach thematic saturation. Translated transcripts of discussions were coded and analysed. Institutional review board approval was not required for this work. Informed verbal consent was obtained for all participants. FindingsThe health issues considered to be most burdensome among Aida Camp inhabitants were diabetes, hypertension, cancer, and depression, with additional focus on physical and mental trauma owing to incursions from Israeli forces. Regarding barriers to health, five principle themes were identified: military occupation, poverty, health system and provider distrust, trauma and psychological impact, and lack of a sense of agency. A community conceptual framework and flow chart were developed from the results. InterpretationAida Camp residents have strong opinions on and novel ideas for addressing common illnesses and barriers to healthcare. A community health worker programme is appealing to adult residents of the camp. A focus on social accompaniment may be an innovative intervention to improve management of non-communicable diseases, implement trauma-informed mental health care, and address social and political determinants of health. Funding1for3 and Lajee Center.

Evaluating the Efficacy of Connected Healthcare: An Empirical Examination of Patient Engagement Systems and Their Impact on Readmission

Connected healthcare is a form of health delivery that connects patients and providers through connected health devices, allowing providers to monitor patient behavior and proactively intervene before an adverse event occurs. Unlike the costs, the benefits of connected healthcare in improving patient behavior and health outcomes are usually difficult to determine. In this study, we examine the efficacy of a connected health system that aimed to reduce readmissions through improved medication adherence. Specifically, we study 1,000 patients with heart disease who received electronic pill bottles that tracked medication adherence. Patients who were non-adherent received active social support that involved different types of feedback such as text messages and calls. By integrating data on adherence, intervention, and readmission, we aim to (1) investigate the efficacy of connected healthcare in promoting medication adherence, (2) examine the relationship between medication adherence and readmission, and (3) develop a dynamic readmission risk-scoring model that considers medication adherence and use the model to better target non-adherent patients. Our findings suggest that patients are more likely to become adherent when they or their partners receive high levels of intervention that involve personalized feedback and when the intervention is escalated quickly and consistently. We also find that long-term adherence to two crucial heart medications, statins and beta-blockers, is strongly associated with reduced readmission risk. Lastly, using counterfactual simulation, we apply the dynamic readmission risk-scoring model to our setting and find that, when using an intervention strategy that prioritizes high-risk patients, we obtain 10% fewer readmissions than we would obtain without considering readmission risk while using the same effort level from the patient support team.

Does culture affect usability? A trans-European usability and user experience assessment of a falls-risk connected health system following a user-centred design methodology carried out in a single European country

BackgroundUser-centred design (UCD) is a process whereby the end-user is placed at the centre of the design process. The WIISEL (Wireless Insole for Independent and Safe Elderly Living) system is designed to monitor fall risk and to detect falls, and consists of a pair of instrumented insoles and a smartphone app. The system was designed using a three-phase UCD process carried out in Ireland, which incorporated the input of Irish end-users and multidisciplinary experts throughout. ObjectiveIn this paper we report the results of a usability and user experience (UX) assessment of the WIISEL system in multiple countries and thus establish whether the UCD process carried out in Ireland produced positive usability and UX results outside of Ireland. Methods15 older adults across three centres (Ireland, Italy and Israel) were recruited for a three-day trial of the system in their home. Usability and UX data were captured using observations, interviews and usability questionnaires. ResultsThe system was satisfactory in terms of the usability and UX feedback from the participants in all three countries. There was no statistically significant difference in the usability scores for the three countries tested, with the exception of comfort. ConclusionsA connected health system designed using a UCD process in a single country resulted in positive usability and UX for users in other European countries.

Enhancing Home Health Mobile Phone App Usability Through General Smartphone Training: Usability and Learnability Case Study.

BackgroundEach year, millions of older adults fall, with more than 1 out of 4 older people experiencing a fall annually, thereby causing a major social and economic impact. Falling once doubles one’s chances of falling again, making fall prediction an important aspect of preventative strategies. In this study, 22 older adults aged between 65 and 85 years were trained in the use of a smartphone-based fall prediction system. The system is designed to continuously assess fall risk by measuring various gait and balance parameters using a smart insole and smartphone, and is also designed to detect falls. The use case of the fall prediction system in question required the users to interact with the smartphone via an app for device syncing, data uploads, and checking system status.ObjectiveThe objective of this study was to observe the effect that basic smartphone training could have on the user experience of a group that is not technically proficient with smartphones when using a new connected health system. It was expected that even short rudimentary training could have a large effect on user experience and therefore increase the chances of the group accepting the new technology.MethodsAll participants received training on how to use the system smartphone app; half of the participants (training group) also received extra training on how to use basic functions of the smartphone, such as making calls and sending text messages, whereas the other half did not receive this extra training (no extra training group). Comparison of training group and no extra training group was carried out using metrics such as satisfaction rating, time taken to complete tasks, cues required to complete tasks, and errors made during tasks.ResultsThe training group fared better in the first 3 days of using the system. There were significant recorded differences in number of cues required and errors committed between the two groups. By the fourth and fifth day of use, both groups were performing at the same level when using the system.ConclusionsSupplementary basic smartphone training may be critical in trials where a smartphone app–based system for health intervention purposes is being introduced to a population that is not proficient with technology. This training could prevent early technology rejection and increase the engagement of older participants and their overall user experience with the system.

Big Sensed Data Meets Deep Learning for Smarter Health Care in Smart Cities

With the advent of the Internet of Things (IoT) concept and its integration with the smart city sensing, smart connected health systems have appeared as integral components of the smart city services. Hard sensing-based data acquisition through wearables or invasive probes, coupled with soft sensing-based acquisition such as crowd-sensing results in hidden patterns in the aggregated sensor data. Recent research aims to address this challenge through many hidden perceptron layers in the conventional artificial neural networks, namely by deep learning. In this article, we review deep learning techniques that can be applied to sensed data to improve prediction and decision making in smart health services. Furthermore, we present a comparison and taxonomy of these methodologies based on types of sensors and sensed data. We further provide thorough discussions on the open issues and research challenges in each category.

A Human-Centered Design Methodology to Enhance the Usability, Human Factors, and User Experience of Connected Health Systems: A Three-Phase Methodology.

BackgroundDesign processes such as human-centered design, which involve the end user throughout the product development and testing process, can be crucial in ensuring that the product meets the needs and capabilities of the user, particularly in terms of safety and user experience. The structured and iterative nature of human-centered design can often present a challenge when design teams are faced with the necessary, rapid, product development life cycles associated with the competitive connected health industry.ObjectiveWe wanted to derive a structured methodology that followed the principles of human-centered design that would allow designers and developers to ensure that the needs of the user are taken into account throughout the design process, while maintaining a rapid pace of development. In this paper, we present the methodology and its rationale before outlining how it was applied to assess and enhance the usability, human factors, and user experience of a connected health system known as the Wireless Insole for Independent and Safe Elderly Living (WIISEL) system, a system designed to continuously assess fall risk by measuring gait and balance parameters associated with fall risk.MethodsWe derived a three-phase methodology. In Phase 1 we emphasized the construction of a use case document. This document can be used to detail the context of use of the system by utilizing storyboarding, paper prototypes, and mock-ups in conjunction with user interviews to gather insightful user feedback on different proposed concepts. In Phase 2 we emphasized the use of expert usability inspections such as heuristic evaluations and cognitive walkthroughs with small multidisciplinary groups to review the prototypes born out of the Phase 1 feedback. Finally, in Phase 3 we emphasized classical user testing with target end users, using various metrics to measure the user experience and improve the final prototypes.ResultsWe report a successful implementation of the methodology for the design and development of a system for detecting and predicting falls in older adults. We describe in detail what testing and evaluation activities we carried out to effectively test the system and overcome usability and human factors problems.ConclusionsWe feel this methodology can be applied to a wide variety of connected health devices and systems. We consider this a methodology that can be scaled to different-sized projects accordingly.