A Deep Learning Approach for Voice Disorder Detection for Smart Connected Living Environments

Edge Analytics and Artificial Intelligence are important features of the current smart connected living community. In a society where people, homes, cities, and workplaces are simultaneously connected through various devices, primarily through mobile devices, a considerable amount of data is exchanged, and the processing and storage of these data are laborious and difficult tasks. Edge Analytics allows the collection and analysis of such data on mobile devices, such as smartphones and tablets, without involving any cloud-centred architecture that cannot guarantee real-time responsiveness. Meanwhile, Artificial Intelligence techniques can constitute a valid instrument to process data, limiting the computation time, and optimising decisional processes and predictions in several sectors, such as healthcare. Within this field, in this article, an approach able to evaluate the voice quality condition is proposed. A fully automatic algorithm, based on Deep Learning, classifies a voice as healthy or pathological by analysing spectrogram images extracted by means of the recording of vowel /a/, in compliance with the traditional medical protocol. A light Convolutional Neural Network is embedded in a mobile health application in order to provide an instrument capable of assessing voice disorders in a fast, easy, and portable way. Thus, a straightforward mobile device becomes a screening tool useful for the early diagnosis, monitoring, and treatment of voice disorders. The proposed approach has been tested on a broad set of voice samples, not limited to the most common voice diseases but including all the pathologies present in three different databases achieving F1-scores, over the testing set, equal to 80%, 90%, and 73%. Although the proposed network consists of a reduced number of layers, the results are very competitive compared to those of other “cutting edge” approaches constructed using more complex neural networks, and compared to the classic deep neural networks, for example, VGG-16 and ResNet-50.

Remote Health Monitoring in the Workplace for Early Detection of COVID-19 Cases during the COVID-19 Pandemic Using a Mobile Health Application: COVIDApp.

Background: COVIDApp is a platform created for management of COVID-19 in the workplace. Methods: COVIDApp was designed and implemented for the follow-up of 253 workers from seven companies in Catalonia. The assessment was based on two actions: first, the early detection and management of close contacts and potential cases of COVID-19, and second, the rapid remote activation of protocols. The main objectives of this strategy were to minimize the risk of transmission of COVID-19 infection in the work area through a new real-time communication channel and to avoid unnecessary sick leave. The parameters reported daily by workers were close contact with COVID cases and signs and/or symptoms of COVID-19. Results: Data were recorded between 1 May and 30 November 2020. A total of 765 alerts were activated by 76 workers: 127 green alarms (16.6%), 301 orange alarms (39.3%), and 337 red alarms (44.1%). Of all the red alarms activated, 274 (81.3%) were activated for symptoms potentially associated with COVID-19, and 63 (18.7%) for reporting close contact with COVID-19 cases. Only eight workers (3.1%) presented symptoms associated with COVID-19 infection. All of these workers underwent RT-PCR tests, which yielded negative results for SARS-CoV2. Three workers were considered to have had a risk contact with COVID-19 cases; only 1 (0.4%) asymptomatic worker had a positive RT-PCR test result, requiring the activation of protocols, isolation, and contact tracing. Conclusions: COVIDApp contributes to the early detection and rapid activation of protocols in the workplace, thus limiting the risk of spreading the virus and reducing the economic impact caused by COVID-19 in the productive sector. The platform shows the progression of infection in real time and can help design new strategies.

Effect of Need, Easy, and Trust on the Intensity of Using the Mobile Health Application to Conduct a Laboratoty Examination

This study aims to analyze the influence of need, convenience and trust on the intensity of using the mobile health application to perform laboratory examinations on Pramita Lab Surabaya patients. This research is important because the intensity of the use of the mobile health application is influenced by the needs, convenience and trust of patients in the mobile health application. The sample in this study were all 108patients using the mobile health application at Pramita Lab Surabaya. The research design used is quantitative research with a descriptive approach with an emphasis on theory testing through measurement of research variables through distributing research questionnaires. The distribution of research questionnaires was carried out using probability sampling techniques. The analysis technique in this study is to use multiple linear regression analysis with the help of SPSS 20.0 software. The results showed that the variables of need, convenience and trust had a positive and significant effect simultaneously on the intensity of using the mobile health application in patients at Pramita Lab Surabaya. The result also show that there is a positive and significant influence on the need, convenience and trust on the intensity of using the mobile health application by patients at Pramita Lab Surabaya.

ACCU3RATE: A mobile health application rating scale based on user reviews

Background Over the last decade, mobile health applications (mHealth App) have evolved exponentially to assess and support our health and well-being. Objective This paper presents an Artificial Intelligence (AI)-enabled mHealth app rating tool, called ACCU3RATE, which takes multidimensional measures such as user star rating, user review and features declared by the developer to generate the rating of an app. However, currently, there is very little conceptual understanding on how user reviews affect app rating from a multi-dimensional perspective. This study applies AI-based text mining technique to develop more comprehensive understanding of user feedback based on several important factors, determining the mHealth app ratings. Method Based on the literature, six variables were identified that influence the mHealth app rating scale. These factors are user star rating, user text review, user interface (UI) design, functionality, security and privacy, and clinical approval. Natural Language Toolkit package is used for interpreting text and to identify the App users’ sentiment. Additional considerations were accessibility, protection and privacy, UI design for people living with physical disability. Moreover, the details of clinical approval, if exists, were taken from the developer’s statement. Finally, we fused all the inputs using fuzzy logic to calculate the new app rating score. Results and conclusions ACCU3RATE concentrates on heart related Apps found in the play store and App gallery. The findings indicate the efficacy of the proposed method as opposed to the current device scale. This study has implications for both App developers and consumers who are using mHealth Apps to monitor and track their health. The performance evaluation shows that the proposed mHealth scale has shown excellent reliability as well as internal consistency of the scale, and high inter-rater reliability index. It has also been noticed that the fuzzy based rating scale, as in ACCU3RATE, matches more closely to the rating performed by experts.

Security Mechanisms of a Mobile Health Application for Promoting Physical Activity among Older Adults

Physical activity contributes to the maintenance of health conditions and functioning. However, the percentage of older adults who comply with the recommendations for physical activity levels is low when compared to the same percentages on younger groups. The SmartWalk system aims to encourage older adults to perform physical activity (i.e., walking in the city), which is monitored and adjusted by healthcare providers for best results. The study reported in this article focused on the implementation of SmartWalk security services to keep personal data safe during communications and while at rest, which were validated considering a comprehensive use case. The security framework offers various mechanisms, including an authentication system that was designed to complement the pairs of usernames and passwords with trusted execution environments and token-based features, authorization with different access levels, symmetric and asymmetric key cryptography, critical transactions review, and logging supported by blockchain technology. The resulting implementation contributes for a common understanding of the security features of trustful smart cities’ applications, which conforms with existing legislation and regulations.

Development of a concept for a mobile application to support orofacial myofunctional therapy

This study aimed to develop a concept for a mobile health application, an app-based exercise tool, to support the treatment of orofacial myofunctional disorders by speech-language therapists (SLTs). Method:A sequential mixed research design combining qualitative research and user-centered software development was applied. Qualitative interviews and focus groups were conducted with eight SLTs, one patient and three relatives to gather ideas for an app to support orofacial myofunctional therapy. On the basis of the findings, a paper-based prototype was developed, which was then evaluated by seven end users, to refine the concept of the app. Results: Qualitative data on desirable functionalities were clustered into topics and related subcategories containing general ideas for the app – a control mechanism, a reward system, the visualization of exercises, and pop-up messages for reminders and recommendations. The paper prototype was developed that addressed these functionalities. Discussion: An app-based exercise tool is considered to have added value for orofacial myofunctional therapy. A prototype for a mobile application is ready for programming and subsequent testing in the treatment of orofacial myofunctional disorders by conducting additional interviews to ascertain patients’ perceptions.

Using virtual representations in mHealth application interventions for health-related behaviour change: A systematic review (Preprint)

UNSTRUCTURED Many mobile health application interventions include virtual representations of the self in varying forms, such as agents, or avatars to initiate behaviour change. This review aimed to determine: (i) which virtual representations and digital features are effective in mHealth application interventions, and (ii) whether if any studies implemented specific mechanisms (the psychological causes of change) and BCTs implemented to influence positive behaviour change were identified. Following PRISMA guidelines, a narrative systematic review of empirical studies from ten different databases (ranging from MEDLINE to Cochrane Library) from inception to October 2021, published from any time point, which included a virtual representation mHealth app intervention that addressed and reported a variety of outcome health behaviours. Out of the 2,579 original hits, five eligible studies (total participants = 509), with low to moderate quality were included. It was found that customisable avatar or agent-based interventions that included mechanisms such as motivation, feedback, self-image, and BCTs such as goal setting, and self-monitoring were effective in encouraging behaviour change and app adherence. However, there is limited evidence available to determine to which these influences are a result of the virtual representations, or the intervention design.

Rút bài vì sử dụng dữ liệu trái phép

SSHPA (30-09-2021) — Tạp chí International Journal of Older People Nursing đã ra quyết định rút bài báo “Co-designing technology with people with dementia and their carers: Exploring user perspectives when co-creating a mobile health application” vì lý do khá đặc biệt: Tác giả duy nhất của bài sử dụng dữ liệu không được phép, và không ghi nhận vai trò của các nhà nghiên cứu và nguồn tài trợ khác [1,2].