OBJECTIVE: This paper aims to introduce a GAN technology for the diagnosis of eye disorders, particularly glaucoma. This paper illustrates deep adversarial learning as a potential diagnostic tool and the challenges involved in its implementation. This study describes and analyzes many of the pitfalls and problems that researchers will need to overcome to implement this kind of technology.
METHODS: To organize this review comprehensively, articles and reviews were collected using the following keywords: ("Glaucoma," "optic disc," "blood vessels") and ("receptive field," "loss function," "GAN," "Generative Adversarial Network," "Deep learning," "CNN," "convolutional neural network" OR encoder). The records were identified from 5 highly reputed databases: IEEE Xplore, Web of Science, Scopus, ScienceDirect, and PubMed. These libraries broadly cover the technical and medical literature. Publications within the last 5 years, specifically 2015-2020, were included because the target GAN technique was invented only in 2014 and the publishing date of the collected papers was not earlier than 2016. Duplicate records were removed, and irrelevant titles and abstracts were excluded. In addition, we excluded papers that used optical coherence tomography and visual field images, except for those with 2D images. A large-scale systematic analysis was performed, and then a summarized taxonomy was generated. Furthermore, the results of the collected articles were summarized and a visual representation of the results was presented on a T-shaped matrix diagram. This study was conducted between March 2020 and November 2020.
RESULTS: We found 59 articles after conducting a comprehensive survey of the literature. Among the 59 articles, 30 present actual attempts to synthesize images and provide accurate segmentation/classification using single/multiple landmarks or share certain experiences. The other 29 articles discuss the recent advances in GANs, do practical experiments, and contain analytical studies of retinal disease.
CONCLUSIONS: Recent deep learning techniques, namely GANs, have shown encouraging performance in retinal disease detection. Although this methodology involves an extensive computing budget and optimization process, it saturates the greedy nature of deep learning techniques by synthesizing images and solves major medical issues. This paper contributes to this research field by offering a thorough analysis of existing works, highlighting current limitations, and suggesting alternatives to support other researchers and participants in further improving and strengthening future work. Finally, new directions for this research have been identified.
OBJECTIVE: In an attempt to understand this relationship, this study aimed to carry out an investigation on online intervention features for effective management of Facebook addiction in higher education.
METHODS: This study was conducted quantitatively using surveys and partial least square-structural equational modeling. The study involved 200 postgraduates in a Facebook support group for postgraduates. The Bergen Facebook Addiction test was used to assess postgraduates' Facebook addiction level, whereas online intervention features were used to assess postgraduates' perceptions of online intervention features for Facebook addiction, which are as follows: (1) self-monitoring features, (2) manual control features, (3) notification features, (4) automatic control features, and (5) reward features.
RESULTS: The study discovered six Facebook addiction factors (relapse, conflict, salience, tolerance, withdrawal, and mood modification) and five intervention features (notification, auto-control, reward, manual control, and self-monitoring) that could be used in the management of Facebook addiction in postgraduate education. The study also revealed that relapse is the most important factor and mood modification is the least important factor. Furthermore, findings indicated that notification was the most important intervention feature, whereas self-monitoring was the least important feature.
CONCLUSIONS: The study's findings (addiction factors and intervention features) could assist future developers and educators in the development of online intervention tools for Facebook addiction management in postgraduate education.
OBJECTIVE: This study aims to assess the prevalence of smartphone ownership, the level of comfort in providing the personal information required to use mHealth apps, and interest in using an mHealth app to access harm reduction services among PWID to guide the development of an app.
METHODS: We administered a survey to 115 PWID who were enrolled via respondent-driven sampling from July 2018 to July 2019. We examined the extent to which PWID had access to smartphones; were comfortable in providing personal information such as name, email, and address; and expressed interest in various app-based services. We measured participant characteristics (demographics, health status, and behaviors) and used binary logistic and Poisson regressions to identify independent correlates of mHealth-related variables. The primary regression outcomes included summary scores for access, comfort, and interest. The secondary outcomes included binary survey responses for individual comfort or interest components.
RESULTS: Most participants were White (74/105, 70.5%), male (78/115, 67.8%), and middle-aged (mean=41.7 years), and 67.9% (74/109) owned a smartphone. Participants reported high levels of comfort in providing personal information to use an mHealth app, including name (96/109, 88.1%), phone number (92/109, 84.4%), email (85/109, 77.9%), physical address (85/109, 77.9%), and linkage to medical records (72/109, 66.1%). Participants also reported strong interest in app-based services, including medication or sterile syringe delivery (100/110, 90.9%), lab or appointment scheduling (90/110, 81.8%), medication reminders (77/110, 70%), educational material (65/110, 59.1%), and group communication forums (64/110, 58.2%). Most participants were comfortable with the idea of home delivery of syringes (93/109, 85.3%). Homeless participants had lower access to smartphones (adjusted odds ratio [AOR] 0.15, 95% CI 0.05-0.46; P=.001), but no other participant characteristics were associated with primary outcomes. Among secondary outcomes, recent SSP use was positively associated with comfort with the home delivery of syringes (AOR 3.29, 95% CI 1.04-10.3 P=.04), and being older than 50 years was associated with an increased interest in educational materials (AOR 4.64, 95% CI 1.31-16.5; P=.02) and group communication forums (AOR 3.69, 95% CI 1.10-12.4; P=.04).
CONCLUSIONS: Our findings suggest that aside from those experiencing homelessness or unstable housing, PWID broadly have access to smartphones, are comfortable with sharing personal information, and express interest in a wide array of services within an app. Given the suboptimal access to and use of SSPs among PWID, an mHealth app has a high potential to address the harm reduction needs of this vulnerable population.
OBJECTIVE: This study examines the sources of information for COVID-19 used by the Malaysian public and identifies those that are associated with building public confidence and positive perceptions toward the Malaysian government.
METHODS: A cross-sectional online survey of 4850 Malaysian residents was conducted. Participant demographics, media use, information sources, and attitudes surrounding COVID-19 were assessed. Descriptive statistics and multiple logistic regression analyses were conducted to gauge the relationship between demographics, information sources, and attitudes toward COVID-19.
RESULTS: Malaysians primarily used television and internet news portals to access information on COVID-19. The Malaysian Ministry of Health was the most preferred source of COVID-19 information. Respondents who referred to the Ministry of Health, television, and the Malaysian National Security Council for information were more likely to believe that the country could win the battle against COVID-19 and that the government was handling the health crisis well compared to those who referred to other information sources. Those who used the World Health Organization, friends, YouTube, family, and radio as sources of information were less likely to harbor confidence and positive belief toward combating COVID-19.
CONCLUSIONS: Managing information and sustaining public confidence is important during a pandemic. Health authorities should pay considerable attention to the use of appropriate media channels and sources to allow for more effective dissemination of critical information to the public.
OBJECTIVE: The aim of this study was to explore public sentiments and emotions toward the LSSR and identify issues, fear, and reluctance to observe this restriction among the Indonesian public.
METHODS: This study adopts a sentiment analysis method with a supervised machine learning approach on COVID-19-related posts on selected media platforms (Twitter, Facebook, Instagram, and YouTube). The analysis was also performed on COVID-19-related news contained in more than 500 online news platforms recognized by the Indonesian Press Council. Social media posts and news originating from Indonesian online media between March 31 and May 31, 2020, were analyzed. Emotion analysis on Twitter platform was also performed to identify collective public emotions toward the LSSR.
RESULTS: The study found that positive sentiment surpasses other sentiment categories by 51.84% (n=1,002,947) of the total data (N=1,934,596) collected via the search engine. Negative sentiment was recorded at 35.51% (686,892/1,934,596) and neutral sentiment at 12.65% (244,757/1,934,596). The analysis of Twitter posts also showed that the majority of public have the emotion of "trust" toward the LSSR.
CONCLUSIONS: Public sentiment toward the LSSR appeared to be positive despite doubts on government consistency in executing the LSSR. The emotion analysis also concluded that the majority of people believe in LSSR as the best method to break the chain of COVID-19 transmission. Overall, Indonesians showed trust and expressed hope toward the government's ability to manage this current global health crisis and win against COVID-19.
OBJECTIVE: In this study, we investigated whether and how artificial intelligence chatbots facilitate the expression of user emotions, specifically sadness and depression. We also examined cultural differences in the expression of depressive moods among users in Western and Eastern countries.
METHODS: This study used SimSimi, a global open-domain social chatbot, to analyze 152,783 conversation utterances containing the terms "depress" and "sad" in 3 Western countries (Canada, the United Kingdom, and the United States) and 5 Eastern countries (Indonesia, India, Malaysia, the Philippines, and Thailand). Study 1 reports new findings on the cultural differences in how people talk about depression and sadness to chatbots based on Linguistic Inquiry and Word Count and n-gram analyses. In study 2, we classified chat conversations into predefined topics using semisupervised classification techniques to better understand the types of depressive moods prevalent in chats. We then identified the distinguishing features of chat-based depressive discourse data and the disparity between Eastern and Western users.
RESULTS: Our data revealed intriguing cultural differences. Chatbot users in Eastern countries indicated stronger emotions about depression than users in Western countries (positive: P
OBJECTIVE: This study examined the COVID-19 pandemic-related topics online users discussed with a commercially available social chatbot and compared the sentiment expressed by users from 5 culturally different countries.
METHODS: We analyzed 19,782 conversation utterances related to COVID-19 covering 5 countries (the United States, the United Kingdom, Canada, Malaysia, and the Philippines) between 2020 and 2021, from SimSimi, one of the world's largest open-domain social chatbots. We identified chat topics using natural language processing methods and analyzed their emotional sentiments. Additionally, we compared the topic and sentiment variations in the COVID-19-related chats across countries.
RESULTS: Our analysis identified 18 emerging topics, which could be categorized into the following 5 overarching themes: "Questions on COVID-19 asked to the chatbot" (30.6%), "Preventive behaviors" (25.3%), "Outbreak of COVID-19" (16.4%), "Physical and psychological impact of COVID-19" (16.0%), and "People and life in the pandemic" (11.7%). Our data indicated that people considered chatbots as a source of information about the pandemic, for example, by asking health-related questions. Users turned to SimSimi for conversation and emotional messages when offline social interactions became limited during the lockdown period. Users were more likely to express negative sentiments when conversing about topics related to masks, lockdowns, case counts, and their worries about the pandemic. In contrast, small talk with the chatbot was largely accompanied by positive sentiment. We also found cultural differences, with negative words being used more often by users in the United States than by those in Asia when talking about COVID-19.
CONCLUSIONS: Based on the analysis of user-chatbot interactions on a live platform, this work provides insights into people's informational and emotional needs during a global health crisis. Users sought health-related information and shared emotional messages with the chatbot, indicating the potential use of chatbots to provide accurate health information and emotional support. Future research can look into different support strategies that align with the direction of public health policy.
OBJECTIVE: This scientometric investigation aims to examine collaborative research networks, dominant research themes and disciplines, and seminal research studies that have contributed most to the field of telemedicine. This information is vital for scientists, institutions, and policy stakeholders to evaluate research areas where more infrastructural or scholarly contributions are required.
METHODS: For analyses, we used CiteSpace (version 4.0 R5; Drexel University), which is a Java-based software that allows scientometric analysis, especially visualization of collaborative networks and research themes in a specific field.
RESULTS: We found that scholarly activity has experienced a significant increase in the last decade. Most important works were conducted by institutions located in high-income countries. A discipline-specific shift from radiology to telestroke, teledermatology, telepsychiatry, and primary care was observed. The most important innovations that yielded a collaborative influence were reported in the following medical disciplines, in descending order: public environmental and occupational health, psychiatry, pediatrics, health policy and services, nursing, rehabilitation, radiology, pharmacology, surgery, respiratory medicine, neurosciences, obstetrics, and geriatrics.
CONCLUSIONS: Despite a continuous rise in scholarly activity in telemedicine, we noticed several gaps in the literature. For instance, all the primary and secondary research central to telemedicine was conducted in the context of high-income countries, including the evidence synthesis approaches that pertained to implementation aspects of telemedicine. Furthermore, the research landscape and implementation of telemedicine infrastructure are expected to see exponential progress during and after the COVID-19 era.
OBJECTIVE: The primary objective of this study was to test the mediation influence of the Unified Theory of Acceptance and Use of Technology (UTAUT) on the relationship between internal HLOC and the behavioral intention to use mHealth.
METHODS: A total of 374 responses were collected from Malaysian adult users of mHealth, using convenience and snowball sampling methods. Partial least squares structural equation modeling was used to analyze the data. Data were collected for variables, including demographics, internal HLOC, and modified UTAUT constructs (ie, performance expectancy, effort expectancy, and social influence).
RESULTS: The results showed that there was no direct relationship between internal HLOC and the behavioral intention to use mHealth (β=-0.039, P=.32). The indirect relationship between internal HLOC and the intent to adopt mHealth was supported, indicating that the UTAUT constructs performance expectancy (β=0.104, P
OBJECTIVE: The aim of this study was to determine the efficacy of social media as an educational medium to effectively translate emerging research evidence into clinical practice.
METHODS: The study used a mixed-methods approach. Evidence-based practice points were delivered via social media platforms. The primary outcomes of attitude, knowledge, and behavior change were assessed using a preintervention/postintervention evaluation, with qualitative data gathered to contextualize the findings.
RESULTS: Data were obtained from 317 clinicians from multiple health disciplines, predominantly from the United Kingdom, Australia, the United States, India, and Malaysia. The participants reported an overall improvement in attitudes toward social media for professional development (P
OBJECTIVE: Our objective was to create a framework that can guide future implementation and research on the use of eHealth tools to support patients with growth disorders who require growth hormone therapy.
METHODS: A total of 12 pediatric endocrinologists with experience in eHealth, from a wide geographical distribution, participated in a series of online discussions. We summarized the discussions of 3 workshops, conducted during 2020, on the use of eHealth in the management of growth disorders, which were structured to provide insights on existing challenges, opportunities, and solutions for the implementation of eHealth tools across the patient journey, from referral to the end of pediatric therapy.
RESULTS: A total of 815 responses were collected from 2 questionnaire-based activities covering referral and diagnosis of growth disorders, and subsequent growth hormone therapy stages of the patient pathway, relating to physicians, nurses, and patients, parents, or caregivers. We mapped the feedback from those discussions into a framework that we developed as a guide to integration of eHealth tools across the patient journey. Responses focused on improved clinical management, such as growth monitoring and automation of referral for early detection of growth disorders, which could trigger rapid evaluation and diagnosis. Patient support included the use of eHealth for enhanced patient and caregiver communication, better access to educational opportunities, and enhanced medical and psychological support during growth hormone therapy management. Given the potential availability of patient data from connected devices, artificial intelligence can be used to predict adherence and personalize patient support. Providing evidence to demonstrate the value and utility of eHealth tools will ensure that these tools are widely accepted, trusted, and used in clinical practice, but implementation issues (eg, adaptation to specific clinical settings) must be addressed.
CONCLUSIONS: The use of eHealth in growth hormone therapy has major potential to improve the management of growth disorders along the patient journey. Combining objective clinical information and patient adherence data is vital in supporting decision-making and the development of new eHealth tools. Involvement of clinicians and patients in the process of integrating such technologies into clinical practice is essential for implementation and developing evidence that eHealth tools can provide value across the patient pathway.
OBJECTIVE: This study aims to examine the phenomenon of health information avoidance among Generation Z, a representative cohort of active web users in this era.
METHODS: Drawing on the planned risk information avoidance model, we adopted a qualitative approach to explore the factors related to information avoidance within the context of health and risk communication. The researchers recruited 38 participants aged 16 to 25 years for the focus group discussion sessions.
RESULTS: In this study, we sought to perform a deductive qualitative analysis of the focus group interview content with open, focused, and theoretical coding. Our findings support several key components of the planned risk information avoidance model while highlighting the underlying influence of cognition on emotions. Specifically, socioculturally, group identity and social norms among peers lead some to avoid health information. Cognitively, mixed levels of risk perception, conflicting values, information overload, and low credibility of information sources elicited their information avoidance behaviors. Affectively, negative emotions such as anxiety, frustration, and the desire to stay positive contributed to avoidance.
CONCLUSIONS: This study has implications for understanding young users' information avoidance behaviors in both academia and practice.
OBJECTIVE: This scoping review aims to identify (1) strategies used to implement web-based apps for health screening, (2) frameworks used for implementing web-based apps for health screening, (3) outcome measures of implementation strategies, and (4) effective implementation strategies.
METHODS: This scoping review was conducted based on Arksey and O'Malley's framework. After identifying the review question, two researchers independently screened and selected relevant literature from PubMed, Embase, Cochrane, Cumulative Index of Nursing and Allied Health Literature, PsycINFO, International Standard Randomised Controlled Trial Number Registry, OpenGrey, ClinicalTrials.gov, World Health Organization International Clinical Trials Registry Platform, and Web of Science. This was followed by charting the data using a standardized form. Finally, we collated, summarized, and reported the results quantitatively and qualitatively based on the review objectives.
RESULTS: A total of 16,476 studies were retrieved, of which 5669 were duplicates. From a total of 10,807 studies, 10,784 studies were excluded based on their titles and abstracts. There were 23 full-text articles reviewed, and 4 articles were included in the final analysis. Many studies were excluded because they focused on the effectiveness and not on the implementation of web-based apps. Facilitation was the most cited implementation strategy used, followed by reminders, clinical champions, and educational meetings and materials. Only 2 studies used implementation frameworks to guide the evaluation of their studies. Common outcome measures for implementation strategies were feasibility, fidelity, and penetration. Implementation strategies reported to be effective were quality improvement meetings, facilitation, educational meetings, and clinical champions.
CONCLUSIONS: There is a dearth of literature on the implementation of web-based apps for health screening. Implementation strategies were developed without any reported use of implementation theories or frameworks in most studies. More research on the development and evaluation of web-based screening app implementations is needed.
OBJECTIVE: This study aims to develop, implement, and evaluate the effectiveness of Stop and Play, a digital parental health education intervention to reduce excessive screen time among preschoolers from low socioeconomic families in Malaysia.
METHODS: A single-blind, 2-arm cluster randomized controlled trial was conducted among 360 mother-child dyads attending government preschools in the Petaling district, who were randomly allocated into the intervention and waitlist control groups between March 2021 and December 2021. This 4-week intervention, developed using whiteboard animation videos, infographics, and a problem-solving session, was delivered via WhatsApp (WhatsApp Inc). Primary outcome was the child's screen time, whereas secondary outcomes included mother's screen time knowledge, perception about the influence of screen time on the child's well-being, self-efficacy to reduce the child's screen time and increase physical activity, mother's screen time, and presence of screen device in the child's bedroom. Validated self-administered questionnaires were administered at baseline, immediately after the intervention, and 3 months after the intervention. The intervention's effectiveness was evaluated using generalized linear mixed models.
RESULTS: A total of 352 dyads completed the study, giving an attrition rate of 2.2% (8/360). At 3 months after the intervention, the intervention group showed significantly reduced child's screen time compared with the control group (β=-202.29, 95% CI -224.48 to -180.10; P