Implementation of Chatbot Technology in Health Care: Protocol for a Bibliometric Analysis.

BACKGROUND: Chatbots have the potential to increase people's access to quality health care. However, the implementation of chatbot technology in the health care system is unclear due to the scarce analysis of publications on the adoption of chatbot in health and medical settings. OBJECTIVE: This paper presents a protocol of a bibliometric analysis aimed at offering the public insights into the current state and emerging trends in research related to the use of chatbot technology for promoting health. METHODS: In this bibliometric analysis, we will select published papers from the databases of CINAHL, IEEE Xplore, PubMed, Scopus, and Web of Science that pertain to chatbot technology and its applications in health care. Our search strategy includes keywords such as "chatbot," "virtual agent," "virtual assistant," "conversational agent," "conversational AI," "interactive agent," "health," and "healthcare." Five researchers who are AI engineers and clinicians will independently review the titles and abstracts of selected papers to determine their eligibility for a full-text review. The corresponding author (ZN) will serve as a mediator to address any discrepancies and disputes among the 5 reviewers. Our analysis will encompass various publication patterns of chatbot research, including the number of annual publications, their geographic or institutional distribution, and the number of annual grants supporting chatbot research, and further summarize the methodologies used in the development of health-related chatbots, along with their features and applications in health care settings. Software tool VOSViewer (version 1.6.19; Leiden University) will be used to construct and visualize bibliometric networks. RESULTS: The preparation for the bibliometric analysis began on December 3, 2021, when the research team started the process of familiarizing themselves with the software tools that may be used in this analysis, VOSViewer and CiteSpace, during which they consulted 3 librarians at the Yale University regarding search terms and tentative results. Tentative searches on the aforementioned databases yielded a total of 2340 papers. The official search phase started on July 27, 2023. Our goal is to complete the screening of papers and the analysis by February 15, 2024. CONCLUSIONS: Artificial intelligence chatbots, such as ChatGPT (OpenAI Inc), have sparked numerous discussions within the health care industry regarding their impact on human health. Chatbot technology holds substantial promise for advancing health care systems worldwide. However, developing a sophisticated chatbot capable of precise interaction with health care consumers, delivering personalized care, and providing accurate health-related information and knowledge remain considerable challenges. This bibliometric analysis seeks to fill the knowledge gap in the existing literature on health-related chatbots, entailing their applications, the software used in their development, and their preferred functionalities among users. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): PRR1-10.2196/54349.

Testing the Feasibility and Acceptability of Using an Artificial Intelligence Chatbot to Promote HIV Testing and Pre-Exposure Prophylaxis in Malaysia: Mixed Methods Study.

BACKGROUND: The HIV epidemic continues to grow fastest among men who have sex with men (MSM) in Malaysia in the presence of stigma and discrimination. Engaging MSM on the internet using chatbots supported through artificial intelligence (AI) can potentially help HIV prevention efforts. We previously identified the benefits, limitations, and preferred features of HIV prevention AI chatbots and developed an AI chatbot prototype that is now tested for feasibility and acceptability. OBJECTIVE: This study aims to test the feasibility and acceptability of an AI chatbot in promoting the uptake of HIV testing and pre-exposure prophylaxis (PrEP) in MSM. METHODS: We conducted beta testing with 14 MSM from February to April 2022 using Zoom (Zoom Video Communications, Inc). Beta testing involved 3 steps: a 45-minute human-chatbot interaction using the think-aloud method, a 35-minute semistructured interview, and a 10-minute web-based survey. The first 2 steps were recorded, transcribed verbatim, and analyzed using the Unified Theory of Acceptance and Use of Technology. Emerging themes from the qualitative data were mapped on the 4 domains of the Unified Theory of Acceptance and Use of Technology: performance expectancy, effort expectancy, facilitating conditions, and social influence. RESULTS: Most participants (13/14, 93%) perceived the chatbot to be useful because it provided comprehensive information on HIV testing and PrEP (performance expectancy). All participants indicated that the chatbot was easy to use because of its simple, straightforward design and quick, friendly responses (effort expectancy). Moreover, 93% (13/14) of the participants rated the overall chatbot quality as high, and all participants perceived the chatbot as a helpful tool and would refer it to others. Approximately 79% (11/14) of the participants agreed they would continue using the chatbot. They suggested adding a local language (ie, Bahasa Malaysia) to customize the chatbot to the Malaysian context (facilitating condition) and suggested that the chatbot should also incorporate more information on mental health, HIV risk assessment, and consequences of HIV. In terms of social influence, all participants perceived the chatbot as helpful in avoiding stigma-inducing interactions and thus could increase the frequency of HIV testing and PrEP uptake among MSM. CONCLUSIONS: The current AI chatbot is feasible and acceptable to promote the uptake of HIV testing and PrEP. To ensure the successful implementation and dissemination of AI chatbots in Malaysia, they should be customized to communicate in Bahasa Malaysia and upgraded to provide other HIV-related information to improve usability, such as mental health support, risk assessment for sexually transmitted infections, AIDS treatment, and the consequences of contracting HIV.

Understanding Women's Knowledge, Awareness, and Perceptions of STIs/STDs in Asia: A Scoping Review.

OBJECTIVE: This study aimed to conduct a scoping review to collect current literature on the knowledge, awareness, and perception (KAP) of sexually transmitted infections/diseases (STIs/STDs) among women in Asia. METHODOLOGY: The PRISMA-Scoping methodology was used in this study to extract papers from four databases published between 2018 and 2022. Sixty-eight articles were included after screening and elimination. RESULTS: The studies on KAP of STIs/STDs among women were largely undertaken in Southeast Asia (Indonesia, Malaysia, and Vietnam) and South Asia (India, Pakistan, and Bangladesh). Regardless of the specific cohort of women studied, research indicates consistently low levels of knowledge and awareness across Asia. This trend seems to be more prevalent among female commercial sex workers, women with lower educational levels, and those in poorer socioeconomic positions. In South Asia, cultural, sociological, economic, and gender inequalities, particularly male domination, all have a significant impact on KAP levels. CONCLUSION: As education is a major factor that influences health behaviour, this review underscores the need to allocate more resources to educational initiatives, particularly targeting vulnerable groups such as sex workers, transgender women, pregnant women, and rural housewives. This strategic focus may contribute significantly to preventing STIs/STDs, particularly in less developed regions/countries.

A Scoping Review of Knowledge, Awareness, Perceptions, Attitudes, and Risky Behaviors of Sexually Transmitted Infections in Southeast Asia.

This scoping review synthesizes literature to examine the extent of research focusing on knowledge, awareness, perceptions, attitudes, and risky behaviors related to sexually transmitted infections (STIs) in Southeast Asia (SEA). The PRISMA-Scoping approach was adopted targeting articles published from 2018 to 2022, sought from CINALH, PubMed, Web of Science and Scopus. A process of screening and elimination resulted in a total of 70 articles reviewed. Most of the studies were conducted in Indonesia, Thailand, Vietnam, and Malaysia, with the majority focusing on HIV/AIDS. In general, studies examining knowledge, awareness, and risky behaviors related to STIs in SEA reported low levels across various cohorts. However, evidence suggests that these issues are more prominent among individuals with low levels of education or low socioeconomic status, those living in rural areas or those working in the sex/industrial sectors. Engaging in unsafe sex and having multiple partners are the key examples for risky sexual behavior, while fear of being rejected/discriminated/stigmatized and lacking STI awareness were identified as social risky behaviors in SEA. Overall, cultural, societal, economic and gender inequality (male dominance) greatly impact people's knowledge, awareness, perceptions, attitudes, and risky behaviors in SEA. Education is an important factor influencing healthy behavior; therefore, this scoping review calls for increased investment in educating vulnerable populations to prevent STIs, particularly in less-developed countries/regions of SEA.

Machine learning approaches in diagnosing tuberculosis through biomarkers - A systematic review.

Biomarker-based tests may facilitate Tuberculosis (TB) diagnosis, accelerate treatment initiation, and thus improve outcomes. This review synthesizes the literature on biomarker-based detection for TB diagnosis using machine learning. The systematic review approach follows the PRISMA guideline. Articles were sought using relevant keywords from Web of Science, PubMed, and Scopus, resulting in 19 eligible studies after a meticulous screening. All the studies were found to have focused on the supervised learning approach, with Support Vector Machine (SVM) and Random Forest emerging as the top two algorithms, with the highest accuracy, sensitivity and specificity reported to be 97.0%, 99.2%, and 98.0%, respectively. Further, protein-based biomarkers were widely explored, followed by gene-based such as RNA sequence and, Spoligotypes. Publicly available datasets were observed to be popularly used by the studies reviewed whilst studies targeting specific cohorts such as HIV patients or children gathering their own data from healthcare facilities, leading to smaller datasets. Of these, most studies used the leave one out cross validation technique to mitigate overfitting. The review shows that machine learning is increasingly assessed in research to improve TB diagnosis through biomarkers, as promising results were shown in terms of model's detection performance. This provides insights on the possible application of machine learning approaches to diagnose TB using biomarkers as opposed to the traditional methods that can be time consuming. Low-middle income settings, where access to basic biomarkers could be provided as compared to sputum-based tests that are not always available, could be a major application of such models.

Infodemic and fake news - A comprehensive overview of its global magnitude during the COVID-19 pandemic in 2021: A scoping review.

The spread of fake news increased dramatically during the COVID-19 pandemic worldwide. This study aims to synthesize the extant literature to understand the magnitude of this phenomenon in the wake of the pandemic in 2021, focusing on the motives and sociodemographic profiles, Artificial Intelligence (AI)-based tools developed, and the top trending topics related to fake news. A scoping review was adopted targeting articles published in five academic databases (January 2021-November 2021), resulting in 97 papers. Most of the studies were empirical in nature (N = 69) targeting the general population (N = 26) and social media users (N = 13), followed by AI-based detection tools (N = 27). Top motives for fake news sharing include low awareness, knowledge, and health/media literacy, Entertainment/Pass Time/Socialization, Altruism, and low trust in government/news media, whilst the phenomenon was more prominent among those with low education, males and younger. Machine and deep learning emerged to be the widely explored techniques in detecting fake news, whereas top topics were related to vaccine, virus, cures/remedies, treatment, and prevention. Immediate intervention and prevention efforts are needed to curb this anti-social behavior considering the world is still struggling to contain the spread of the COVID-19 virus.

Mental Health Risk Factors and Coping Strategies among Students in Asia Pacific during COVID-19 Pandemic-A Scoping Review.

The impact of COVID-19 has forced higher education institutes to go into lockdown in order to curb the situation. This sudden change caused students within the institutions to forgo traditional face to face classroom settings and to attend immediate online classes. This review aims to summarize the evidence of the social demographic mental health impacts of the COVID-19 pandemic on students in higher education institutes within the Asia Pacific region and identify the coping mechanisms adopted during these times. A systematic literature search was conducted using three databases (PubMed, Google Scholar, and Scopus), out of which 64 studies met the inclusion/exclusion criteria. The findings revealed that the social demographic groups most at risk were female students, those who were in the final years of their studies (i.e., students who were almost graduating), and postgraduate students as well as students studying medical fields (nursing, dental, medicine, health sciences etc.). The majority of the studies identified that students were relying on mobile devices and extended screen time to cope with the pandemic. Having proper social support, be it through a network of friends or positive family cohesion, can be a good buffer against the mental impacts of COVID-19. Students in higher education institutes are at risk of mental consequences due to COVID-19. By reducing their screen time, finding a healthier coping system, increasing the availability of support within the family and community, as well as actively engaging in beneficial activities students may be able to alleviate general negative emotions, specifically during the pandemic.

COVID-19 mental health prevalence and its risk factors in South East Asia.

With the record surge of positive cases in Southeast Asia, there is a need to examine the adverse mental effects of COVID-19 among the under-researched countries. This study aims to synthesize the extant literature reporting the effects of COVID-19 pandemic on the psychological outcomes of people in Southeast Asia, and its risk factors. A scoping review was adopted targeting articles published in PubMed, Google Scholar and Scopus from January 2020 to March 30, 2021. Articles were screened using predetermined eligibility criteria, resulting in 26 papers. Elevated prevalence of adverse mental effects was noted in most of the countries as the pandemic progressed over time, with Malaysia and Philippines reporting higher prevalence rates. Mental decline was found to be more profound among the general population compared to healthcare workers and students. Dominant risk factors reported were age (younger), sex (females), education (higher), low coping skill and social/family support, and poor reliability in COVID-19 related information. Adverse mental effects were noted among population, healthcare workers and students in most of the Southeast Asian countries. Intervention and prevention efforts should be based at community-level and prioritize young adults, females, and individuals with dire financial constraints.

A deep learning approach in predicting products' sentiment ratings: a comparative analysis.

We present a benchmark comparison of several deep learning models including Convolutional Neural Networks, Recurrent Neural Network and Bi-directional Long Short Term Memory, assessed based on various word embedding approaches, including the Bi-directional Encoder Representations from Transformers (BERT) and its variants, FastText and Word2Vec. Data augmentation was administered using the Easy Data Augmentation approach resulting in two datasets (original versus augmented). All the models were assessed in two setups, namely 5-class versus 3-class (i.e., compressed version). Findings show the best prediction models were Neural Network-based using Word2Vec, with CNN-RNN-Bi-LSTM producing the highest accuracy (96%) and F-score (91.1%). Individually, RNN was the best model with an accuracy of 87.5% and F-score of 83.5%, while RoBERTa had the best F-score of 73.1%. The study shows that deep learning is better for analyzing the sentiments within the text compared to supervised machine learning and provides a direction for future work and research.

COVID-19 depression and its risk factors in Asia Pacific - A systematic review and meta-analysis.

BACKGROUND: This systematic review and meta-analysis aim to synthesize the extant literature reporting the effects of COVID-19 pandemic based on the pooled prevalence of depression among affected populations in Asia Pacific, as well as its risk factors. METHOD: A systematic review and meta-analysis approach was adopted as per the PRISMA guidelines, targeting articles published in PubMed, Google Scholar and Scopus from January 2021 to March 30, 2021. The screening resulted in 82 papers. RESULTS: The overall pooled depression prevalence among 201,953 respondents was 34% (95%CI, 29-38, 99.7%), with no significant differences observed between the cohorts, timelines, and regions (p > 0.05). Dominant risk factors found were fear of COVID-19 infection (13%), gender (i.e., females; 12%) and deterioration of underlying medical conditions (8.3%), regardless of the sub-groups. Specifically, fear of COVID-19 infection was the most reported risk factor among general population (k = 14) and healthcare workers (k = 8). Gender (k = 7) and increased workload (k = 7) were reported among healthcare workers whereas education disruption among students (k = 7). LIMITATION: The review is limited to articles published in three electronic databases. Conclusion The pandemic has caused depression among the populations across Asia Pacific, specifically among the general population, healthcare workers and students. Immediate attention and interventions from the concerned authorities are needed in addressing this issue.

The Relationship between Dark Triad Personality Traits and Sexting Behaviors among Adolescents and Young Adults across 11 Countries.

BACKGROUND: Sexting is an increasingly common phenomenon among adolescents and young adults. Some studies have investigated the role of personality traits in different sexting behaviors within mainstream personality taxonomies like Big Five and HEXACO. However, very few studies have investigated the role of maladaptive personality factors in sexting. Therefore, the present study investigated the relationship between Dark Triad Personality Traits and experimental (i.e., sharing own sexts), risky (i.e., sexting under substance use and with strangers), and aggravated sexting (i.e., non-consensual sexting and sexting under pressure) across 11 countries. METHODS: An online survey was completed by 6093 participants (Mage = 20.35; SDage = 3.63) from 11 different countries which covered four continents (Europe, Asia, Africa, and America). Participants completed the Sexting Behaviors Questionnaire and the 12-item Dark Triad Dirty Dozen scale. RESULTS: Hierarchical regression analyses showed that sharing own sexts was positively predicted by Machiavellianism and Narcissism. Both risky and aggravated sexting were positively predicted by Machiavellianism and Psychopathy. CONCLUSIONS: The present study provided empirical evidence that different sexting behaviors were predicted by Dark Triad Personality Traits, showing a relevant role of Machiavellianism in all kinds of investigated sexting behaviors. Research, clinical, and education implications for prevention programs are discussed.

To share or not to share - The underlying motives of sharing fake news amidst the COVID-19 pandemic in Malaysia.

This study investigates the underlying motives for online fake news sharing during the COVID-19 pandemic, an unprecedented time that witnessed a spike in the spread of false content. Motives were identified based on a fake news sharing model developed using the SocioCultural-Psychological-Technology (SCulPT) model, Uses and Gratification (U&G) theory and Self-Determination Theory (SDT), and further extended using fake news predictors/gratifications from past studies. A self-administered survey resulted in 869 online Malaysian respondents aged between 18 and 59 years old (Mean = 22.6, Standard deviation = 6.13). Structured equation modelling revealed the fake news sharing model to collectively account for 49.2 % of the variance, with Altruism (ß = 0.333; p < 0.001), Ignorance (ß = 0.165; p < 0.001) and Entertainment (ß = 0.139; p < 0.001) significantly predicting the behaviour. Conversely, Availability/Effort, Pass Time and Fear of Missing Out were found to be insignificant. Our findings indicate that fake news sharing behavior is determined by different motives, hence these need to be understood in order to develop better solutions to mitigate this problem.

Indirect effect of management support on users' compliance behaviour towards information security policies.

BACKGROUND: Health information systems are innovative products designed to improve the delivery of effective healthcare, but they are also vulnerable to breaches of information security, including unauthorised access, use, disclosure, disruption, modification or destruction, and duplication of passwords. Greater openness and multi-connectedness between heterogeneous stakeholders within health networks increase the security risk. OBJECTIVE: The focus of this research was on the indirect effects of management support (MS) on user compliance behaviour (UCB) towards information security policies (ISPs) among health professionals in selected Malaysian public hospitals. The aim was to identify significant factors and provide a clearer understanding of the nature of compliance behaviour in the health sector environment. METHOD: Using a survey design and stratified random sampling method, self-administered questionnaires were distributed to 454 healthcare professionals in three hospitals. Drawing on theories of planned behaviour, perceived behavioural control (self-efficacy (SE) and MS components) and the trust factor, an information system security policies compliance model was developed to test three related constructs (MS, SE and perceived trust (PT)) and their relationship to UCB towards ISPs. RESULTS: Results showed a 52.8% variation in UCB through significant factors. Partial least squares structural equation modelling demonstrated that all factors were significant and that MS had an indirect effect on UCB through both PT and SE among respondents to this study. CONCLUSION: The research model based on the theory of planned behaviour in combination with other human and organisational factors has made a useful contribution towards explaining compliance behaviour in relation to organisational ISPs, with trust being the most significant factor. In adopting a multidimensional approach to management-user interactions via multidisciplinary concepts and theories to evaluate the association between the integrated management-user values and the nature of compliance towards ISPs among selected health professionals, this study has made a unique contribution to the literature.

Ringed Seal Search for Global Optimization via a Sensitive Search Model.

The efficiency of a metaheuristic algorithm for global optimization is based on its ability to search and find the global optimum. However, a good search often requires to be balanced between exploration and exploitation of the search space. In this paper, a new metaheuristic algorithm called Ringed Seal Search (RSS) is introduced. It is inspired by the natural behavior of the seal pup. This algorithm mimics the seal pup movement behavior and its ability to search and choose the best lair to escape predators. The scenario starts once the seal mother gives birth to a new pup in a birthing lair that is constructed for this purpose. The seal pup strategy consists of searching and selecting the best lair by performing a random walk to find a new lair. Affected by the sensitive nature of seals against external noise emitted by predators, the random walk of the seal pup takes two different search states, normal state and urgent state. In the normal state, the pup performs an intensive search between closely adjacent lairs; this movement is modeled via a Brownian walk. In an urgent state, the pup leaves the proximity area and performs an extensive search to find a new lair from sparse targets; this movement is modeled via a Levy walk. The switch between these two states is realized by the random noise emitted by predators. The algorithm keeps switching between normal and urgent states until the global optimum is reached. Tests and validations were performed using fifteen benchmark test functions to compare the performance of RSS with other baseline algorithms. The results show that RSS is more efficient than Genetic Algorithm, Particles Swarm Optimization and Cuckoo Search in terms of convergence rate to the global optimum. The RSS shows an improvement in terms of balance between exploration (extensive) and exploitation (intensive) of the search space. The RSS can efficiently mimic seal pups behavior to find best lair and provide a new algorithm to be used in global optimization problems.

Critical product features' identification using an opinion analyzer.

The increasing use and ubiquity of the Internet facilitate dissemination of word-of-mouth through blogs, online forums, newsgroups, and consumer's reviews. Online consumer's reviews present tremendous opportunities and challenges for consumers and marketers. One of the challenges is to develop interactive marketing practices for making connections with target consumers that capitalize consumer-to-consumer communications for generating product adoption. Opinion mining is employed in marketing to help consumers and enterprises in the analysis of online consumers' reviews by highlighting the strengths and weaknesses of the products. This paper describes an opinion mining system based on novel review and feature ranking methods to empower consumers and enterprises for identifying critical product features from enormous consumers' reviews. Consumers and business analysts are the main target group for the proposed system who want to explore consumers' feedback for determining purchase decisions and enterprise strategies. We evaluate the proposed system on real dataset. Results show that integration of review and feature-ranking methods improves the decision making processes significantly.