Impact of the Fourth Industrial Revolution on the Health Sector: A Qualitative Study

Concept of digital health literacy revisited: Using text network and topic model analysis

Background

The rapid integration of ICT into healthcare has elevated the critical role of digital health literacy (DHL). However, the conceptual relationship between DHL and electronic health (eHealth), along with the impact of transformative events such as the Fourth Industrial Revolution and the COVID-19 pandemic, remains inadequately investigated.

Objective

This study seeks to analyze research trends in DHL across four distinct historical periods to uncover key themes and their temporal evolution.

Methods

A comparative analysis of 2645 abstracts from Scopus publications (1977-2022) was conducted, segmented into four periods: (I) emerging era (1977-2006), (II) establishment era (2007-2016), (III) diffusion era (2017-2020), and (IV) post-pandemic era (2021-present). Text network analysis identified core keywords, and Latent Dirichlet Allocation (LDA) extracted dominant topics and their temporal evolution.

Results

Since 2006, DHL research has exhibited consistent growth, underpinned by transformative advancements during the Fourth Industrial Revolution and further amplified by a significant surge in scholarly engagement in the post-pandemic era. Importantly, during the diffusion era (Period III), a divergence in the trajectories of "digital health literacy" and "electronic health literacy" emerged.Text network analysis revealed a progression toward greater uniformity in node sizes over time, coupled with an increase in the complexity and intricacy of connections between nodes. These findings indicate a growing diversity and nuanced understanding of concepts associated with DHL. Moreover, research in the post-pandemic era (Period IV) emphasized the critical role of DHL in addressing health disparities and advancing equitable access to healthcare.

Conclusion

The study reveals the dynamic progression of DHL research, catalyzed by technological advancements and global health crises. Strengthening DHL, particularly among vulnerable populations, is crucial for mitigating health disparities in a rapidly digitalizing world. Future research should prioritize the development of targeted interventions and examine DHL's impact across diverse sociocultural contexts.

Exploring the perspectives of healthcare professionals regarding artificial intelligence; acceptance and challenges

OBJECTIVES

The main objective of the study was to explore the perspectives of healthcare professionals (HCPs) regarding artificial intelligence (AI) and to identify challenges in its incorporation in the healthcare sector of Pakistan.

METHODS

A qualitative exploratory study design was adopted. The study was conducted from January 15th to February 29th, 2024, and HCPs (doctors, pharmacists and nurses) from two tertiary care teaching hospitals in southern Punjab, Pakistan were taken as the study population. The interviews were conducted with the help of a semi structured interview schema. A thematic approach was adopted to analyse the data.

RESULTS

Out of 40 HCPs approached, 25 participated in the study with a response rate of 62%. The participants included in the study were doctors (14), pharmacists (6) and nurses (5). The participants had limited knowledge regarding AI and its basics. However, they showed positive perceptions about its incorporation. They believed that many of the problems faced by the healthcare sector of Pakistan can be minimized by AI incorporation. They believed that AI can boost up the efficiency of healthcare providers, reduce their workload, save time and minimize medical errors. Four main themes with multiple subthemes were identified: (1) Cognizance of AI, (2) Acceptability of AI among HCPs and training requirements for effective incorporation, (3) Merits and Demerits of AI, and (4) Challenges in incorporation of AI with proposed solutions.

CONCLUSION

HCPs showed a willingness to embrace AI incorporation and believed that it may bring numerous benefits to the health system. Policymakers should take necessary steps to ensure AI incorporation in our healthcare sector.

The impact of a mixed reality technology-driven health enhancing physical activity program among community-dwelling older adults: a study protocol

Background

Physical inactivity and a sedentary lifestyle among community-dwelling older adults poses a greater risk for progressive physical and cognitive decline. Mixed reality technology-driven health enhancing physical activities such as the use of virtual coaches provide an emerging and promising solution to support healthy lifestyle, but the impact has not been clearly understood.

Methods and analysis

An observational explanatory sequential mixed-method research design was conceptualized to examine the potential impact of a user-preferred mixed reality technology-driven health enhancing physical activity program directed toward purposively selected community-dwelling older adults in two senior centers in the Philippines. Quantitative components of the study will be done through a discreet choice experiment and a quasi-experimental study. A total of 128, or 64 older adults in each center, will be recruited via posters at community senior centers who will undergo additional screening or health records review by a certified gerontologist to ensure safety and proper fit. Treatments (live coaching with video-based exercise and mixed reality technology-driven exercise) will be assigned to each of the two senior center sites for the quasi-experiment. The participants from the experimental group shall be involved in the discreet choice experiment, modeling, and usability evaluations. Finally, a qualitative sample of participants (n = 6) as key informants shall be obtained from the experimental group using purposive selection.

Discussion

This study protocol will examine the health impact of a promising mixed reality program in health promotion among older adults. The study utilizes a human-centered mixed method research design in technology development and evaluation in the context of developing nations.Clinical trial registration: ClinicalTrials.gov, identifier NCT06136468.

Deliberative process of health technology reassessment by health technology assessment agency in Korea

In 2019, the National Evidence-based Healthcare Collaborating Agency (NECA) in Korea established a health technology reassessment (HTR) system to manage the life cycle of health technologies and develop operational measures promoting the efficient use of healthcare resources. The purpose of this study is to introduce the detailed implementation process and practical functional methods of the HTR implemented by NECA.The HTR is a structured multidisciplinary method for analyzing health technologies currently used in the healthcare system based on the latest information on parameters, such as clinical safety, effectiveness, and cost-effectiveness of optimizing the use of healthcare resources as well as social and ethical issues. All decision-making stages of the HTR are carefully reviewed and transparently managed. The HTR committee makes significant decisions, and the subcommittee decides the details related to the assessment process.Since the pilot began in 2018, 262 cases have been reassessed, of which, 126 cases (48.1 percent) were health services not covered by the National Health Insurance (NHI). Over the past 5 years, approximately 130 recommendations for the in-use technologies were determined by the HTR committee. In the near future, it will be necessary to officially develop and establish a Korean HTR system and a legal foundation to optimize the NHI system.

Barriers and enablers for implementation of digital-linked diagnostics models at point-of-care in South Africa: stakeholder engagement

The integration of digital technologies holds significant promise in enhancing accessibility to disease diagnosis and treatment at point-of-care (POC) settings. Effective implementation of such interventions necessitates comprehensive stakeholder engagements. This study presents the outcomes of a workshop conducted with key stakeholders, aiming to discern barriers and enablers in implementing digital-connected POC diagnostic models in South Africa. The workshop, a component of the 2022 REASSURED Diagnostics symposium, employed the nominal group technique (NGT) and comprised two phases: Phase 1 focused on identifying barriers, while Phase 2 centered on enablers for the implementation of digital-linked POC diagnostic models. Stakeholders identified limited connectivity, restricted offline functionality, and challenges related to load shedding or rolling electricity blackouts as primary barriers. Conversely, ease of use, subsidies provided by the National Health Insurance, and 24-h assistance emerged as crucial enablers for the implementation of digital-linked POC diagnostic models. The NGT workshop proved to be an effective platform for elucidating key barriers and enablers in implementing digital-linked POC diagnostic models. Subsequent research endeavors should concentrate on identifying optimal strategies for implementing these advanced diagnostic models in underserved populations.

Positive views, attitudes, and acceptability toward mHealth applications in addressing queer sexual and reproductive health: Healthcare providers and the queer individuals

Objective

In the age of digital health, mankind has resources to write over the historical narrative of queer individuals' healthcare exclusions. The main purpose of this study was to explore the perspectives of both healthcare providers (HCPs) and queer individuals regarding the use of web-based tools and mobile health applications (mHealth apps) in the context of addressing queer individuals' sexual and reproductive health services and needs (SRHSN).

Methods

An overall study was conducted as an exploratory sequential mixed method. This article provides findings from the performed qualitative cycle. The selection method was led by purposeful sampling, which targeted 33 HCPs delivering SRHSN within the defined study settings. Additionally, respondent-driven sampling was employed to select 22 queer individuals. Throughout the study, semi-structured one-on-one face-to-face interviews were used to collect data.

Results

Four major themes and related sub-themes emerged from HCPs and queer individuals: (a) aid queer individuals with consultations and treatment improvements, (b) drawing parallels with technology in other sectors, (c) enhancing knowledge and education, and (d) positive perception of technological advancements.

Conclusions

In accordance with our findings, HCPs and queer individuals were all positive and sees mHealth apps as a tool to address SRHSN for homosexual people.

A Single-Center Experience of Robotic-Assisted Spine Surgery in Korea : Analysis of Screw Accuracy, Potential Risk Factor of Screw Malposition and Learning Curve

OBJECTIVE

Recently, robotic-assisted spine surgery (RASS) has been considered a minimally invasive and relatively accurate method. In total, 495 robotic-assisted pedicle screw fixation (RAPSF) procedures were attempted on 100 patients during a 14-month period. The current study aimed to analyze the accuracy, potential risk factors, and learning curve of RAPSF.

METHODS

This retrospective study evaluated the position of RAPSF using the Gertzbein and Robbins scale (GRS). The accuracy was analyzed using the ratio of the clinically acceptable group (GRS grades A and B), the dissatisfying group (GRS grades C, D, and E), and the Surgical Evaluation Assistant program. The RAPSF was divided into the no-breached group (GRS grade A) and breached group (GRS grades B, C, D, and E), and the potential risk factors of RAPSF were evaluated. The learning curve was analyzed by changes in robot-used time per screw and the occurrence tendency of breached and failed screws according to case accumulation.

RESULTS

The clinically acceptable group in RAPSF was 98.12%. In the analysis using the Surgical Evaluation Assistant program, the tip offset was 2.37±1.89 mm, the tail offset was 3.09±1.90 mm, and the angular offset was 3.72°±2.72°. In the analysis of potential risk factors, the difference in screw fixation level (p=0.009) and segmental distance between the tracker and the instrumented level (p=0.001) between the no-breached and breached group were statistically significant, but not for the other factors. The mean difference between the no-breach and breach groups was statistically significant in terms of pedicle width (p<0.001) and tail offset (p=0.042). In the learning curve analysis, the occurrence of breached and failed screws and the robot-used time per screw screws showed a significant decreasing trend.

CONCLUSION

In the current study, RAPSF was highly accurate and the specific potential risk factors were not identified. However, pedicle width was presumed to be related to breached screw. Meanwhile, the robot-used time per screw and the incidence of breached and failed screws decreased with the learning curve.

Effectiveness of Virtual Reality Simulation Among BSN Students: A Meta-analysis of Randomized Controlled Trials

This study aimed to evaluate the effect of virtual reality simulation in nursing education in five domains: knowledge, skill performance, self-confidence, self-efficacy, and satisfaction. Randomized controlled trials were obtained from the databases SCOPUS, Web of Science, PubMed, and EBSCO from inception until September 2021. The standardized mean differences with 95% confidence intervals were determined for the main variables, and heterogeneity was analyzed using the I2 test. The PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) Checklist was used. Meta-analysis was performed using the Stata 15.0 software. Among the 2074 records identified, 18 trials were included. The meta-analysis of these trials indicated that virtual reality simulation caused a significant improvement in knowledge with a moderate effect, skill performance with a moderate effect, and satisfaction with a moderate effect compared with the control group. However, virtual reality simulation did not significantly influence self-confidence and self-efficiency. The findings of this study suggested that virtual reality simulation might significantly benefit knowledge, skill performance, and satisfaction but not self-confidence and self-efficiency. Further well-designed randomized controlled trials with a larger sample size are recommended to confirm these findings.

Exploring the Intersection of Artificial Intelligence and Clinical Healthcare: A Multidisciplinary Review

Artificial intelligence (AI) plays a more and more important role in our everyday life due to the advantages that it brings when used, such as 24/7 availability, a very low percentage of errors, ability to provide real time insights, or performing a fast analysis. AI is increasingly being used in clinical medical and dental healthcare analyses, with valuable applications, which include disease diagnosis, risk assessment, treatment planning, and drug discovery. This paper presents a narrative literature review of AI use in healthcare from a multi-disciplinary perspective, specifically in the cardiology, allergology, endocrinology, and dental fields. The paper highlights data from recent research and development efforts in AI for healthcare, as well as challenges and limitations associated with AI implementation, such as data privacy and security considerations, along with ethical and legal concerns. The regulation of responsible design, development, and use of AI in healthcare is still in early stages due to the rapid evolution of the field. However, it is our duty to carefully consider the ethical implications of implementing AI and to respond appropriately. With the potential to reshape healthcare delivery and enhance patient outcomes, AI systems continue to reveal their capabilities.

Critical Success Factors for Successful Implementation of Healthcare 4.0: A Literature Review and Future Research Agenda

The digitization of healthcare services is a major shift in the manner in which healthcare services are offered and managed in the modern era. The COVID-19 pandemic has speeded up the use of digital technologies in the healthcare sector. Healthcare 4.0 (H4.0) is much more than the adoption of digital tools, however; going beyond that, it is the digital transformation of healthcare. The successful implementation of H 4.0 presents a challenge as social and technical factors must be considered. This study, through a systematic literature review, expounds ten critical success factors for the successful implementation of H 4.0. Bibliometric analysis of existing articles is also carried out to understand the development of knowledge in this domain. H 4.0 is rapidly gaining prominence, and a comprehensive review of critical success factors in this area has yet to be conducted. Conducting such a review makes a valuable contribution to the body of knowledge in healthcare operations management. Furthermore, this study will also help healthcare practitioners and policymakers to develop strategies to manage the ten critical success factors while implementing H 4.0.

Telemedicine as technoinnovation to tackle COVID-19: A bibliometric analysis☆

Telemedicine has become fundamental for the challenges posed to healthcare. This set of instruments turns pivotal for facing one of the most relevant emergencies in human history: the COVID-19 pandemic. The multisectoral crisis led to a vigorously sustained adoption of innovations, including telemedicine technology. Telehealth was proven, in this context, to be a relevant tool to reduce healthcare costs, reduce not-needed hospitalizations, and improve the results in health care. Some barriers such as the costs of technologies, patient privacy and technical literacy have slowed down telemedicine adoption. Amidst the COVID-19 era, telemedicine calls for a managerial duty to change healthcare's organizational models. The present work aims to explore the growing literature to illuminate the relationships between telemedicine, innovations and healthcare in the COVID-19 framework. A bibliometric analysis of the existing literature based on 285 published works in 2019–2020 is put forward with the aim to detect the relevant literature, themes and approaches on telemedicine and COVID-19. Making use of community detection on the co-occurrence keywords network, we identify the “semantic cores” in the literature representing the relevant results on critical themes. The sorting implications are important for researchers and policymakers by mapping the existing literature and results in evidence-based analysis. We provide the key communities as the “semantic core” of the publications and results for the considered period. This allows for future research to be oriented towards perduring health policies that could lead to the adoption of telemedicine technologies in a post-pandemic scenario.

Evolution and expansion of the One Health approach to promote sustainable and resilient health and well-being: A call to action

One Health is a transdisciplinary approach used to address complex concerns related to human, animal, plant, and ecosystem health. One Health frameworks and operational tools are available to support countries and communities, particularly for the prevention and control of zoonotic diseases and antimicrobial resistance and the protection of food safety. However, One Health has yet to be implemented in a manner that fully considers the complexities and interconnectedness of the diverse influences that have impacts at a larger system level. This lack of consideration can undermine the sustainability of any positive outcomes. To ensure the One Health approach can function effectively within the new global context of converging and escalating health, social, economic, and ecological crises, it must evolve and expand in three overlapping dimensions: (1) Scope: the partners, knowledge, and knowledge systems included, (2) Approach: the techniques, methodologies, and scholarship considered, and (3) Worldview inclusivity: the interweaving of other worldviews together with the mainstream scientific worldview that currently predominates. Diverse partners and knowledge from outside the mainstream health and scientific sectors, including Indigenous peoples and representatives of local communities, and traditionally generated knowledge, must be included. These systems of knowledge can then be braided together with mainstream science to comprise a holistic framework for decision-making. Scholarship and methodologies being applied in other fields and contexts to solve complex challenges and manage uncertainty, such as collaborative governance, social-ecologic systems theory, and complexity science, must be recognized and incorporated. The spectrum of considered worldviews must also expand to authentically integrate the expanded scope and approach into action and sustainable impact. By increasing community and social engagement and by recognizing and entwining different worldviews, the plurality of disciplines, and traditional and scientific ways of knowing to address community concerns in the contexts in which they exist, we can ensure that One Health remains effective and true to its paradigm in our rapidly changing and complex world.

Student perspectives on the integration of artificial intelligence into healthcare services

Background

Healthcare workers are often overworked, underfunded, and face many challenges. Integration of artificial intelligence into healthcare service provision can tackle these challenges by relieving burdens on healthcare workers. Since healthcare students are our future healthcare workers, we assessed the knowledge, attitudes, and perspectives of current healthcare students at Qatar University on the implementation of artificial intelligence into healthcare services.

Methods

This was a cross-sectional study of QU-Health Cluster students via an online survey over a three-week period in November 2021. Chi-squared tests and gamma coefficients were used to compare differences between categorical variables.

Results

One hundred and ninety-three QU-Health students responded. Most participants had a positive attitude towards artificial intelligence, finding it useful and reliable. The most popular perceived advantage of artificial intelligence was its ability to speed up work processes. Around 40% expressed concern about a threat to job security from artificial intelligence, and a majority believed that artificial intelligence cannot provide sympathetic care (57.9%). Participants who felt that artificial intelligence can better make diagnoses than humans also agreed that artificial intelligence could replace their job (p  =  0.005). Male students had more knowledge (p  =  0.005) and received more training (p  =  0.005) about healthcare artificial intelligence. Participants cited a lack of expert mentorship as a barrier to obtaining knowledge about artificial intelligence, followed by lack of dedicated courses and funding.

Conclusions

More resources are required for students to develop a good understanding about artificial intelligence. Education needs to be supported by expert mentorship. Further work is needed on how best to integrate artificial intelligence teaching into university curricula.

Nursing and human-computer interaction in healthcare robots for older people: An integrative review

Objectives

This study examined the published works related to healthcare robotics for older people using the attributes of health, nursing, and the human-computer interaction framework.

Design

An integrative literature review.

Methods

A search strategy captured 55 eligible articles from databases (CINAHL, Embase, IEEE Xplore, and PubMed) and hand-searching approaches. Bibliometric and content analyses grounded on the health and nursing attributes and human-computer interaction framework were performed using MAXQDA. Finally, results were verified using critical friend feedback by a second reviewer.

Results

Most articles were from multiple authorship, published in non-nursing journals, and originating from developed economies. They primarily focused on applying healthcare robots in practice settings, physical health, and communication tasks. Using the human-computer interaction framework, it was found that older adults frequently served as the primary users while nurses, healthcare providers, and researchers functioned as secondary users and operators. Research articles focused on the usability, functionality, and acceptability of robotic systems. At the same time, theoretical papers explored the frameworks and the value of empathy and emotion in robots, human-computer interaction and nursing models and theories supporting healthcare practice, and gerontechnology. Current robotic systems are less anthropomorphic, operated through real-time direct and supervisory inputs, and mainly equipped with visual and auditory sensors and actuators with limited capability in performing health assessments.

Conclusion

Results communicate the need for technological competency among nurses, advancements in increasing healthcare robot humanness, and the importance of conscientious efforts from an interdisciplinary research team in improving robotic system usability and utility for the care of older adults.

Nursing informatics skills relevance and competence for final year nursing students

BACKGROUND

 The increasing use of technology in nursing practice requires nursing students to be competent in nursing informatics with an attitude of acceptance of technology in the healthcare environment.

OBJECTIVES

 The objectives of the study were to determine final year nursing students' perceptions and skills in nursing informatics and their attitudes towards computerisation in nursing practice.

METHOD

 The study population were 198 final year nursing students from a selected university in the Western Cape, South Africa. All-inclusive sampling was used. A descriptive survey was conducted using a self-administered questionnaire which included two validated scales, namely the validated Nursing Informatics Competency Assessment Tool (NICAT) and the Nurses' Attitudes towards Computerisation scale. Means and 95% confidence intervals (CI) of the ratings of the perceived relevance of nursing informatics skills in nursing practice, perceived levels of competence in nursing informatics skills and attitudes towards computers were calculated.

RESULTS

 A total of 91 undergraduate respondents completed the survey. Computer literacy skills were rated overall as most relevant (4.23, 95% confidence interval [95% CI]: 4.06-4.40) and the skills perceived most competent (4.16, 95% CI: 3.81-4.22). The respondents had an overall positive score for attitudes towards computerisation in healthcare (67.34, s.d. = 10.40, 95% CI: 65.18-69.51).

CONCLUSION

 The study concluded that computer literacy skills, informatics literacy skills and information management skills were relevant to nursing practice, despite varying levels of competence in these skills among nurses.Contribution: What key insights into the research results and its future function are revealed? How do these insights link to the focus and scope of the journal? It should be a concise statement of the primary contribution of the manuscript; and how it fits within the scope of the journal.

Update on Stroke Rehabilitation in Motor Impairment

Motor impairment due to stroke limits patients' mobility, activities of daily living, and negatively affects their return to the workplace. It also reduces patients' quality of life and increases the socioeconomic burden of stroke. Therefore, optimizing the recovery of motor impairment after stroke is a very important goal for both individuals and society as a whole. The emergence and improvement of various technologies in the Fourth Industrial Revolution have exerted a major influence on the development of new rehabilitation methods and efficiency enhancements for existing methods. This review categorizes rehabilitation methods that promote the recovery of motor function into upper limb function and lower limb function and summarizes recent advances in stroke rehabilitation. Although debate continues regarding the effects of some rehabilitation therapies, it is hoped that the evidence will be improved through ongoing research so that clinicians can treat patients with a higher level of evidence.

Developing attention deficits/hyperactivity disorder-virtual reality diagnostic tool with machine learning for children and adolescents

The traditional diagnosis of Attention Deficits/Hyperactivity Disorder (ADHD) is through parent-child interviews and observations; therefore, innovative ADHD diagnostic tools that represent this digital era are needed. Virtual reality (VR) is a significant technology that can present a virtual immersive environment; it can provide an illusion of participation in an artificial milieu for children with ADHD. This study aimed to develop an ADHD-VR diagnostic tool construct (Research Domain Construct/RDC) based on the DSM5 ADHD diagnostic criteria, and using the RDC to develop a diagnostic tool with a machine learning (ML) application that can produce an intelligent model to receive some complex and multifaceted clinical data (ADHD clinical symptoms). We aimed to expand a model algorithm from the data, and finally make predictions by providing new data (output data) that have more accurate diagnostic value. This was an exploratory qualitative study and consisted of two stages. The first stage of the study applied the Delphi technique, and the goal was to translate ADHD symptoms based on DSM 5 diagnostic criteria into concrete behavior that can be observed among children in a classroom setting. This stage aimed to gather information, perceptions, consensus, and confirmation from experts. In this study, three rounds of Delphi were conducted. The second stage was to finalize the RDC of the ADHD-VR diagnostic tool with ML, based on the first-stage results. The results were transformed into concrete activities that could be applied in the programming of the ADHD-VR diagnostic tool, followed by starting to input data that were required to build the diagnostic tool. The second stage consisted of more than ten focus-group discussions (FGDs) before it could be transformed into the ADHD-VR diagnostic tool with the ML prototype. First-stage data analysis was performed using Microsoft Excel for Mac. Qualitative data were analyzed using conceptual content analysis with a manifest/latent analysis approach. From the first stage of the study, there were 13 examples of student behaviors that received more than 75% totally agreed or agreed from the experts. The RDC of the ADHD-VR diagnostic tool with machine learning application consisted of three domains and was divided into six sub-domains: reward-related processing, emotional lability, inhibitory, sustained attention, specific timing of playing in order, and arousal. In conclusion, the results of this study can be used as a reference for future studies in a similar context and content, that is, the ADHD-VR diagnostic tool with machine learning based on the constructed RDC.

Nursing Students' Acceptance Intention of a Smart Device, Information Literacy, and Problem-Solving Confidence

The purpose of this study was to investigate the relationship between nursing students’ acceptance intention of a smart device, information literacy, and problem-solving confidence to explore the factors that may improve nursing students’ problem-solving confidence. Data were collected from 450 nursing students between July and August 2019 in two cities in Korea. The results showed that there is a positive correlation between problem-solving confidence and acceptance intention (r = 0.353, p < 0.001) and between problem-solving confidence and information literacy (r = 0.501, p < 0.001). Further, participants with high acceptance intention of a smart device and information literacy scores had significantly higher problem-solving confidence (t = 5.447, p < 0.001; t = 10.072, p < 0.001) than participants with low acceptance intention. In addition, in the logistic regression the odds ratio between the acceptance intention of a smart device, information literacy, and problem-solving confidence groups was odds ratio 2.071 (p < 0.001, CI: 1.412–3.037) and odd ratio 4.966 (p < 0.001, CI: 3.298–7.477). To improve nursing students’ problem-solving confidence, educational strategies should be developed to build information experience and information utilization capabilities.

Filtered BERT: Similarity Filter-Based Augmentation with Bidirectional Transfer Learning for Protected Health Information Prediction in Clinical Documents

For the secondary use of clinical documents, it is necessary to de-identify protected health information (PHI) in documents. However, the difficulty lies in the fact that there are few publicly annotated PHI documents. To solve this problem, in this study, we propose a filtered bidirectional encoder representation from transformers (BERT)-based method that predicts a masked word and validates the word again through a similarity filter to construct augmented sentences. The proposed method effectively performs data augmentation. The results show that the augmentation method based on filtered BERT improved the performance of the model. This suggests that our method can effectively improve the performance of the model in the limited data environment.