Non-fungible tokens (NFTs) in healthcare: a thematic analysis and research agenda.

Introduction: In the big data era, where corporations commodify health data, non-fungible tokens (NFTs) present a transformative avenue for patient empowerment and control. NFTs are unique digital assets on the blockchain, representing ownership of digital objects, including health data. By minting their data as NFTs, patients can track access, monetize its use, and build secure, private health information systems. However, research on NFTs in healthcare is in its infancy, warranting a comprehensive review. Methods: This study conducted a systematic literature review and thematic analysis of NFTs in healthcare to identify use cases, design models, and key challenges. Five multidisciplinary research databases (Scopus, Web of Science, Google Scholar, IEEE Explore, Elsevier Science Direct) were searched. The approach involved four stages: paper collection, inclusion/exclusion criteria application, screening, full-text reading, and quality assessment. A classification and coding framework was employed. Thematic analysis followed six steps: data familiarization, initial code generation, theme searching, theme review, theme definition/naming, and report production. Results: Analysis of 19 selected papers revealed three primary use cases: patient-centric data management, supply chain management for data provenance, and digital twin development. Notably, most solutions were prototypes or frameworks without real-world implementations. Four overarching themes emerged: data governance (ownership, tracking, privacy), data monetization (commercialization, incentivization, sharing), data protection, and data storage. The focus lies on user-controlled, private, and secure health data solutions. Additionally, data commodification is explored, with mechanisms proposed to incentivize data maintenance and sharing. NFTs are also suggested for tracking medical products in supply chains, ensuring data integrity and provenance. Ethereum and similar platforms dominate NFT minting, while compact NFT storage options are being explored for faster data access. Conclusion: NFTs offer significant potential for secure, traceable, decentralized healthcare data exchange systems. However, challenges exist, including dependence on blockchain, interoperability issues, and associated costs. The review identified research gaps, such as developing dual ownership models and data pricing strategies. Building an open standard for interoperability and adoption is crucial. The scalability, security, and privacy of NFT-backed healthcare applications require further investigation. Thus, this study proposes a research agenda for adopting NFTs in healthcare, focusing on governance, storage models, and perceptions.

Active transfer learning for audiogram estimation.

Computational audiology (CA) has grown over the last few years with the improvement of computing power and the growth of machine learning (ML) models. There are today several audiogram databases which have been used to improve the accuracy of CA models as well as reduce testing time and diagnostic complexity. However, these CA models have mainly been trained on single populations. This study integrated contextual and prior knowledge from audiogram databases of multiple populations as informative priors to estimate audiograms more precisely using two mechanisms: (1) a mapping function drawn from feature-based homogeneous Transfer Learning (TL) also known as Domain Adaptation (DA) and (2) Active Learning (Uncertainty Sampling) using a stream-based query mechanism. Simulations of the Active Transfer Learning (ATL) model were tested against a traditional adaptive staircase method akin to the Hughson-Westlake (HW) method for the left ear at frequencies ω=0.25,0.5,1,2,4,8 kHz, resulting in accuracy and reliability improvements. ATL improved HW tests from a mean of 41.3 sound stimuli presentations and reliability of ±9.02 dB down to 25.3±1.04 dB. Integrating multiple databases also resulted in classifying the audiograms into 18 phenotypes, which means that with increasing data-driven CA, higher precision is achievable, and a possible re-conceptualisation of the notion of phenotype classifications might be required. The study contributes to CA in identifying an ATL mechanism to leverage existing audiogram databases and CA models across different population groups. Further studies can be done for other psychophysical phenomena using ATL.

Student intentions to continue with distance learning post-COVID: An empirical analysis.

The aftermath of COVID changed how students learn, mainly moving to a distance learning model. The research reported in this paper investigated the organizational and individual factors that influence the preference for continuing with distance / online learning post-COVID. Partial least squares structural equation modeling was applied to a model developed for this research, based on data from 452 students from residential universities in South Africa. The key results reveal an overall reluctance to continue with distance learning. This is despite the technological and faculty support offered to university students and how distance learning fits their learning styles. This is likely due to student living conditions and their perception of low institutional concern. On the other hand, faculty support has a more substantial impact on continuance, compared with a generally negative perception of support from the universities. The research underscores the importance of addressing student reluctance to continue with distance learning by improving institutional support and tailoring learning styles. The research enhances our understanding of crucial factors influencing students' preference for distance/online learning post-COVID. It also underscores the pedagogical shifts brought about by the pandemic, particularly highlighting the changing roles of faculty support and the impact on students' living conditions.

Big Data and Infectious Disease Epidemiology: Bibliometric Analysis and Research Agenda.

BACKGROUND: Infectious diseases represent a major challenge for health systems worldwide. With the recent global pandemic of COVID-19, the need to research strategies to treat these health problems has become even more pressing. Although the literature on big data and data science in health has grown rapidly, few studies have synthesized these individual studies, and none has identified the utility of big data in infectious disease surveillance and modeling. OBJECTIVE: The aim of this study was to synthesize research and identify hotspots of big data in infectious disease epidemiology. METHODS: Bibliometric data from 3054 documents that satisfied the inclusion criteria retrieved from the Web of Science database over 22 years (2000-2022) were analyzed and reviewed. The search retrieval occurred on October 17, 2022. Bibliometric analysis was performed to illustrate the relationships between research constituents, topics, and key terms in the retrieved documents. RESULTS: The bibliometric analysis revealed internet searches and social media as the most utilized big data sources for infectious disease surveillance or modeling. The analysis also placed US and Chinese institutions as leaders in this research area. Disease monitoring and surveillance, utility of electronic health (or medical) records, methodology framework for infodemiology tools, and machine/deep learning were identified as the core research themes. CONCLUSIONS: Proposals for future studies are made based on these findings. This study will provide health care informatics scholars with a comprehensive understanding of big data research in infectious disease epidemiology.

Modeling COVID-19 incidence with Google Trends.

Infodemiologic methods could be used to enhance modeling infectious diseases. It is of interest to verify the utility of these methods using a Nigerian case study. We used Google Trends data to track COVID-19 incidences and assessed whether they could complement traditional data based solely on reported case numbers. Data on the Nigerian weekly COVID-19 cases spanning through March 1, 2020, to May 31, 2021, were matched with internet search data from Google Trends. The reported weekly incidence numbers and the GT data were split into training and testing sets. ARIMA models were fitted to describe reported weekly COVID cases using the training set. Several COVID-related search terms were theoretically and empirically assessed for initial screening. The utilized Google Trends (GT) variable was added to the ARIMA model as a regressor. Model forecasts, both with and without GTD, were compared with weekly cases in the test set over 13 weeks. Forecast accuracies were compared visually and using RMSE (root mean square error) and MAE (mean average error). Statistical significance of the difference in predictions was determined with the two-sided Diebold-Mariano test. Preliminary results of contemporaneous correlations between COVID-related search terms and weekly COVID cases reveal "loss of smell," "loss of taste," "fever" (in order of magnitude) as significantly associated with the official cases. Predictions of the ARIMA model using solely reported case numbers resulted in an RMSE (root mean squared error) of 411.4 and mean absolute error (MAE) of 354.9. The GT expanded model achieved better forecasting accuracy (RMSE: 388.7 and MAE = 340.1). Corrected Akaike Information Criteria also favored the GT expanded model (869.4 vs. 872.2). The difference in predictive performances was significant when using a two-sided Diebold-Mariano test (DM = 6.75, p < 0.001) for the 13 weeks. Google trends data enhanced the predictive ability of a traditionally based model and should be considered a suitable method to enhance infectious disease modeling.

COVID-Bot, an Intelligent System for COVID-19 Vaccination Screening: Design and Development.

BACKGROUND: Coronavirus continues to spread worldwide, causing various health and economic disruptions. One of the most important approaches to controlling the spread of this disease is to use an artificial intelligence (AI)-based technological intervention, such as a chatbot system. Chatbots can aid in the fight against the spread of COVID-19. OBJECTIVE: This paper introduces COVID-Bot, an intelligent interactive system that can help screen students and confirm their COVID-19 vaccination status. METHODS: The design and development of COVID-Bot followed the principles of the design science research (DSR) process, which is a research method for creating a new scientific artifact. COVID-Bot was developed and implemented using the SnatchBot chatbot application programming interface (API) and its predefined tools, which are driven by various natural language processing algorithms. RESULTS: An evaluation was carried out through a survey that involved 106 university students in determining the functionality, compatibility, reliability, and usability of COVID-Bot. The findings indicated that 92 (86.8%) of the participants agreed that the chatbot functions well, 85 (80.2%) agreed that it fits well with their mobile devices and their lifestyle, 86 (81.1%) agreed that it has the potential to produce accurate and consistent responses, and 85 (80.2%) agreed that it is easy to use. The average obtained α was .87, indicating satisfactory reliability. CONCLUSIONS: This study demonstrates that incorporating chatbot technology into the educational system can combat the spread of COVID-19 among university students. The intelligent system does this by interacting with students to determine their vaccination status.