-
Frontiers in Health Services 2024The number of mHealth apps has increased rapidly during recent years. Literature suggests a number of problems and barriers to the adoption of mHealth apps, including...
INTRODUCTION
The number of mHealth apps has increased rapidly during recent years. Literature suggests a number of problems and barriers to the adoption of mHealth apps, including issues such as validity, usability, as well as data privacy and security. Continuous quality assessment and assurance systems might help to overcome these barriers. Aim of this scoping review was to collate literature on quality assessment tools and quality assurance systems for mHealth apps, compile the components of the tools, and derive overarching quality dimensions, which are potentially relevant for the continuous quality assessment of mHealth apps.
METHODS
Literature searches were performed in Medline, EMBASE and PsycInfo. Articles in English or German language were included if they contained information on development, application, or validation of generic concepts of quality assessment or quality assurance of mHealth apps. Screening and extraction were carried out by two researchers independently. Identified quality criteria and aspects were extracted and clustered into quality dimensions.
RESULTS
A total of 70 publications met inclusion criteria. Included publications contain information on five quality assurance systems and further 24 quality assessment tools for mHealth apps. Of these 29 systems/tools, 8 were developed for the assessment of mHealth apps for specific diseases, 16 for assessing mHealth apps for all fields of health and another five are not restricted to health apps. Identified quality criteria and aspects were extracted and grouped into a total of 14 quality dimensions, namely "information and transparency", "validity and (added) value", "(medical) safety", "interoperability and compatibility", "actuality", "engagement", "data privacy and data security", "usability and design", "technology", "organizational aspects", "social aspects", "legal aspects", "equity and equality", and "cost(-effectiveness)".
DISCUSSION
This scoping review provides a broad overview of existing quality assessment and assurance systems. Many of the tools included cover only a few dimensions and aspects and therefore do not allow for a comprehensive quality assessment or quality assurance. Our findings can contribute to the development of continuous quality assessment and assurance systems for mHealth apps.
SYSTEMATIC REVIEW REGISTRATION
https://www.researchprotocols.org/2022/7/e36974/, International Registered Report Identifier, IRRID (DERR1-10.2196/36974).
PubMed: 38751854
DOI: 10.3389/frhs.2024.1372871 -
Heliyon May 2024As the number of Internet users grows, the increase in smart devices interconnected through the Internet of Things (IoT) have contributed to improvements in the...
As the number of Internet users grows, the increase in smart devices interconnected through the Internet of Things (IoT) have contributed to improvements in the functionality of everyday products and enhancement of user experience. Yet, they affect user privacy and render personal data more vulnerable. To foster a digital future fully aware of user privacy requirements, a line of design research emerges that focuses on balancing product innovation with user data protection. This matter relates to sociocultural, economic, and technological aspects, and its core is a human-centered design strategy. Still, there is a gap in academic research oriented towards guiding product developers on how to consider personal data privacy concerns when designing honest IoT devices. To define this gap and delve deeper into this relevant topic, this paper presents a systematic literature review of recent academic research using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) method. This review focuses on prevalent research topics such as data privacy, personal data, data surveillance, and user behaviour in IoT. The result is a state-of-the-art compilation of 45 scientific studies mapping the most relevant concepts and approaches for product development in the last ten years of research, aligned with some central research questions. The Discussion and Conclusion sections provide a deep understanding of the complexity of the fast-changing landscape of privacy and personal data management using IoT products. Finally, this study proposes future academic research directions devoted to providing product designer specific, specialised help from different (yet interconnected) scientific approaches.
PubMed: 38737231
DOI: 10.1016/j.heliyon.2024.e30357 -
International Journal of Medical... Jul 2024Human Emotion Recognition (HER) has been a popular field of study in the past years. Despite the great progresses made so far, relatively little attention has been paid... (Review)
Review
BACKGROUND
Human Emotion Recognition (HER) has been a popular field of study in the past years. Despite the great progresses made so far, relatively little attention has been paid to the use of HER in autism. People with autism are known to face problems with daily social communication and the prototypical interpretation of emotional responses, which are most frequently exerted via facial expressions. This poses significant practical challenges to the application of regular HER systems, which are normally developed for and by neurotypical people.
OBJECTIVE
This study reviews the literature on the use of HER systems in autism, particularly with respect to sensing technologies and machine learning methods, as to identify existing barriers and possible future directions.
METHODS
We conducted a systematic review of articles published between January 2011 and June 2023 according to the 2020 PRISMA guidelines. Manuscripts were identified through searching Web of Science and Scopus databases. Manuscripts were included when related to emotion recognition, used sensors and machine learning techniques, and involved children with autism, young, or adults.
RESULTS
The search yielded 346 articles. A total of 65 publications met the eligibility criteria and were included in the review.
CONCLUSIONS
Studies predominantly used facial expression techniques as the emotion recognition method. Consequently, video cameras were the most widely used devices across studies, although a growing trend in the use of physiological sensors was observed lately. Happiness, sadness, anger, fear, disgust, and surprise were most frequently addressed. Classical supervised machine learning techniques were primarily used at the expense of unsupervised approaches or more recent deep learning models. Studies focused on autism in a broad sense but limited efforts have been directed towards more specific disorders of the spectrum. Privacy or security issues were seldom addressed, and if so, at a rather insufficient level of detail.
Topics: Humans; Machine Learning; Emotions; Autistic Disorder; Facial Expression; Child
PubMed: 38723429
DOI: 10.1016/j.ijmedinf.2024.105469 -
Nursing Research and Practice 2024Bedside nursing handover is a recognized nursing practice that involves conducting shift change communication at the patient's bedside to enhance communication safety....
BACKGROUND
Bedside nursing handover is a recognized nursing practice that involves conducting shift change communication at the patient's bedside to enhance communication safety. Understanding the perceptions of both patients and nurses regarding bedside handover is crucial in identifying the key principles for developing and implementing effective bedside handover protocols. However, there is currently a lack of comprehensive evidence that summarizes and evaluates studies focused on qualitative approaches for gaining insights into the perceptions of both nurses and patients.
PURPOSE
This meta-synthesis review aims to identify, synthesize, and evaluate the quality of primary qualitative studies on the perceptions of patients and nurses about bedside nursing handover.
METHODS
A meta-synthesis review was conducted to identify qualitative studies that reported patients and nurses' perceptions about bedside handover using seven electronic databases, including CINAHL, PsycINFO, Embase, Education Database (ProQuest), Web of Science, The Cochrane Library, and PubMed, from January 2013 to November 2023. The authors independently selected reviews, extracted data, and evaluated the quality of included studies using the 10-item JBI Qualitative Assessment and Review Instrument tool.
RESULTS
A total of 871 articles were retrieved, of which 13 met the inclusion and exclusion criteria. These studies identified three main themes: (1) facilitators of bedside nursing handover, (2) barriers to bedside nursing handover, and (3) strategies to maintain confidentiality during bedside handover.
CONCLUSION
This study systematically reviewed and integrated the perceptions of patients and nurses about bedside handover. Based on nurses' perceptions, the combined findings highlight the facilitators of bedside handover, including developing partnership interaction between nurses and patients, promoting professionalism, and enhancing emotional communication among nurses. From the patients' viewpoint, the synthesized findings emphasize the facilitators of bedside handover, including acknowledging the expertise, professionalism, and humanity of the nursing profession, ensuring a sense of safety, satisfaction, and confidence in the care received, as well as promoting individualized nursing care. In the context of barriers to bedside handover, both nurses and patients perceive breaches of confidentiality and privacy violations as significant barriers. When it comes to maintaining confidentiality during bedside handovers, it is important to consider patients' preferences. Patients often prefer handovers to take place in a private setting. From the nurses' perspective, it is important to inquire with patients about their preference for the presence of caregivers, and to conduct private handovers for sensitive issues away from the bedside. . Clinicians should carefully evaluate the barriers and facilitators in this meta-synthesis prior to implementing bedside handover. . This study is registered in PROSPERO with Protocol registration ID: CRD42024514615.
PubMed: 38716049
DOI: 10.1155/2024/3208747 -
MedRxiv : the Preprint Server For... Apr 2024The launch of the Chat Generative Pre-trained Transformer (ChatGPT) in November 2022 has attracted public attention and academic interest to large language models...
BACKGROUND
The launch of the Chat Generative Pre-trained Transformer (ChatGPT) in November 2022 has attracted public attention and academic interest to large language models (LLMs), facilitating the emergence of many other innovative LLMs. These LLMs have been applied in various fields, including healthcare. Numerous studies have since been conducted regarding how to employ state-of-the-art LLMs in health-related scenarios to assist patients, doctors, and public health administrators.
OBJECTIVE
This review aims to summarize the applications and concerns of applying conversational LLMs in healthcare and provide an agenda for future research on LLMs in healthcare.
METHODS
We utilized PubMed, ACM, and IEEE digital libraries as primary sources for this review. We followed the guidance of Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRIMSA) to screen and select peer-reviewed research articles that (1) were related to both healthcare applications and conversational LLMs and (2) were published before September 1, 2023, the date when we started paper collection and screening. We investigated these papers and classified them according to their applications and concerns.
RESULTS
Our search initially identified 820 papers according to targeted keywords, out of which 65 papers met our criteria and were included in the review. The most popular conversational LLM was ChatGPT from OpenAI (60), followed by Bard from Google (1), Large Language Model Meta AI (LLaMA) from Meta (1), and other LLMs (5). These papers were classified into four categories in terms of their applications: 1) summarization, 2) medical knowledge inquiry, 3) prediction, and 4) administration, and four categories of concerns: 1) reliability, 2) bias, 3) privacy, and 4) public acceptability. There are 49 (75%) research papers using LLMs for summarization and/or medical knowledge inquiry, and 58 (89%) research papers expressing concerns about reliability and/or bias. We found that conversational LLMs exhibit promising results in summarization and providing medical knowledge to patients with a relatively high accuracy. However, conversational LLMs like ChatGPT are not able to provide reliable answers to complex health-related tasks that require specialized domain expertise. Additionally, no experiments in our reviewed papers have been conducted to thoughtfully examine how conversational LLMs lead to bias or privacy issues in healthcare research.
CONCLUSIONS
Future studies should focus on improving the reliability of LLM applications in complex health-related tasks, as well as investigating the mechanisms of how LLM applications brought bias and privacy issues. Considering the vast accessibility of LLMs, legal, social, and technical efforts are all needed to address concerns about LLMs to promote, improve, and regularize the application of LLMs in healthcare.
PubMed: 38712148
DOI: 10.1101/2024.04.26.24306390 -
BMC Health Services Research Apr 2024Indigenous adolescents access primary health care services at lower rates, despite their greater health needs and experience of disadvantage. This systematic review... (Meta-Analysis)
Meta-Analysis
Enablers and barriers to primary health care access for Indigenous adolescents: a systematic review and meta-aggregation of studies across Australia, Canada, New Zealand, and USA.
BACKGROUND
Indigenous adolescents access primary health care services at lower rates, despite their greater health needs and experience of disadvantage. This systematic review identifies the enablers and barriers to primary health care access for Indigenous adolescents to inform service and policy improvements.
METHODS
We systematically searched databases for publications reporting enablers or barriers to primary health care access for Indigenous adolescents from the perspective of adolescents, their parents and health care providers, and included studies focused on Indigenous adolescents aged 10-24 years from Australia, Canada, New Zealand, and United States of America. Results were analyzed against the WHO Global standards for quality health-care services for adolescents. An additional ninth standard was added which focused on cultural safety.
RESULTS
A total of 41 studies were included. More barriers were identified than enablers, and against the WHO Global standards most enablers and barriers related to supply factors - providers' competencies, appropriate package of services, and cultural safety. Providers who built trust, respect, and relationships; appropriate package of service; and culturally safe environments and care were enablers to care reported by adolescents, and health care providers and parents. Embarrassment, shame, or fear; a lack of culturally appropriate services; and privacy and confidentiality were common barriers identified by both adolescent and health care providers and parents. Cultural safety was identified as a key issue among Indigenous adolescents. Enablers and barriers related to cultural safety included culturally appropriate services, culturally safe environment and care, traditional and cultural practices, cultural protocols, Indigenous health care providers, cultural training for health care providers, and colonization, intergenerational trauma, and racism. Nine recommendations were identified which aim to address the enablers and barriers associated with primary health care access for Indigenous adolescents.
CONCLUSION
This review provides important evidence to inform how services, organizations and governments can create accessible primary health care services that specifically meet the needs of Indigenous adolescents. We identify nine recommendations for improving the accessibility of primary health care services for Indigenous adolescents.
Topics: Adolescent; Humans; Australia; Canada; Health Services Accessibility; Health Services, Indigenous; New Zealand; Primary Health Care; United States; Indigenous Peoples
PubMed: 38693527
DOI: 10.1186/s12913-024-10796-5 -
MHealth 2024The virtual care model can be used in all aspects of healthcare, such as prevention, diagnosis, treatment, and follow-up of most medical and surgical conditions. The... (Review)
Review
BACKGROUND
The virtual care model can be used in all aspects of healthcare, such as prevention, diagnosis, treatment, and follow-up of most medical and surgical conditions. The objective of this study was to identify the current barriers to implementing and consolidating the virtual healthcare model, of "telemedicine", in Latin American countries.
METHODS
A systematic review was conducted through four databases: PubMed, Scopus, Web of Science, and Virtual Health, including articles in Spanish, Portuguese, and English. A combination of Boolean operators was used with the terms "telemedicine", "telehealth", "telecare", "home care services", "remote care" and the name of each Latin American country. Articles published from January 2020 to January 2023 that reported on the barriers and challenges of using the virtual care model were included.
RESULTS
Nineteen articles were included. Brazil (n=5) and Argentina (n=4) were the countries where there was the greatest interest to explore barriers to virtual care. The barriers identified were categorized into five main themes: (I) technological and technical issues; (II) absence of a physical examination; (III) patient's negative perceptions; (IV) negative perceptions among healthcare professionals; and (V) structural obstacles and those associated with the healthcare system. The main obstacles reported were connectivity problems, lack of a complete physical examination, issues of privacy, high risk of medical malpractice, and absence of local regulation.
CONCLUSIONS
The virtual care model is a safe and cost-effective alternative for the delivery of health services, with multiple benefits for patients and their families. The indication for the use of virtual care should be based on a risk model for patient prioritization. Likewise, the analysis of the main barriers and benefits is fundamental to consolidating this model of care and ensuring its expansion in the region.
PubMed: 38689618
DOI: 10.21037/mhealth-23-47 -
Diagnostic and Interventional Imaging 2024The purpose of this study was to systematically review the reported performances of ChatGPT, identify potential limitations, and explore future directions for its... (Review)
Review
PURPOSE
The purpose of this study was to systematically review the reported performances of ChatGPT, identify potential limitations, and explore future directions for its integration, optimization, and ethical considerations in radiology applications.
MATERIALS AND METHODS
After a comprehensive review of PubMed, Web of Science, Embase, and Google Scholar databases, a cohort of published studies was identified up to January 1, 2024, utilizing ChatGPT for clinical radiology applications.
RESULTS
Out of 861 studies derived, 44 studies evaluated the performance of ChatGPT; among these, 37 (37/44; 84.1%) demonstrated high performance, and seven (7/44; 15.9%) indicated it had a lower performance in providing information on diagnosis and clinical decision support (6/44; 13.6%) and patient communication and educational content (1/44; 2.3%). Twenty-four (24/44; 54.5%) studies reported the proportion of ChatGPT's performance. Among these, 19 (19/24; 79.2%) studies recorded a median accuracy of 70.5%, and in five (5/24; 20.8%) studies, there was a median agreement of 83.6% between ChatGPT outcomes and reference standards [radiologists' decision or guidelines], generally confirming ChatGPT's high accuracy in these studies. Eleven studies compared two recent ChatGPT versions, and in ten (10/11; 90.9%), ChatGPTv4 outperformed v3.5, showing notable enhancements in addressing higher-order thinking questions, better comprehension of radiology terms, and improved accuracy in describing images. Risks and concerns about using ChatGPT included biased responses, limited originality, and the potential for inaccurate information leading to misinformation, hallucinations, improper citations and fake references, cybersecurity vulnerabilities, and patient privacy risks.
CONCLUSION
Although ChatGPT's effectiveness has been shown in 84.1% of radiology studies, there are still multiple pitfalls and limitations to address. It is too soon to confirm its complete proficiency and accuracy, and more extensive multicenter studies utilizing diverse datasets and pre-training techniques are required to verify ChatGPT's role in radiology.
Topics: Humans; Radiology; Forecasting
PubMed: 38679540
DOI: 10.1016/j.diii.2024.04.003 -
Journal of Clinical Medicine Apr 2024: Several studies have shown a relation between obesity and cognitive decline, highlighting a significant global health challenge. In recent years, artificial... (Review)
Review
: Several studies have shown a relation between obesity and cognitive decline, highlighting a significant global health challenge. In recent years, artificial intelligence (AI) and machine learning (ML) have been integrated into clinical practice for analyzing datasets to identify new risk factors, build predictive models, and develop personalized interventions, thereby providing useful information to healthcare professionals. This systematic review aims to evaluate the potential of AI and ML techniques in addressing the relationship between obesity, its associated health consequences, and cognitive decline. : Systematic searches were performed in PubMed, Cochrane, Web of Science, Scopus, Embase, and PsycInfo databases, which yielded eight studies. After reading the full text of the selected studies and applying predefined inclusion criteria, eight studies were included based on pertinence and relevance to the topic. : The findings underscore the utility of AI and ML in assessing risk and predicting cognitive decline in obese patients. Furthermore, these new technology models identified key risk factors and predictive biomarkers, paving the way for tailored prevention strategies and treatment plans. : The early detection, prevention, and personalized interventions facilitated by these technologies can significantly reduce costs and time. Future research should assess ethical considerations, data privacy, and equitable access for all.
PubMed: 38673581
DOI: 10.3390/jcm13082307 -
Saudi Journal of Anaesthesia 2024This review article examines the utility of artificial intelligence (AI) in anesthesia, with a focus on recent developments and future directions in the field. A total... (Review)
Review
This review article examines the utility of artificial intelligence (AI) in anesthesia, with a focus on recent developments and future directions in the field. A total of 19,300 articles were available on the given topic after searching in the above mentioned databases, and after choosing the custom range of years from 2015 to 2023 as an inclusion component, only 12,100 remained. 5,720 articles remained after eliminating non-full text. Eighteen papers were identified to meet the inclusion criteria for the review after applying the inclusion and exclusion criteria. The applications of AI in anesthesia after studying the articles were in favor of the use of AI as it enhanced or equaled human judgment in drug dose decision and reduced mortality by early detection. Two studies tried to formulate prediction models, current techniques, and limitations of AI; ten studies are mainly focused on pain and complications such as hypotension, with a P value of <0.05; three studies tried to formulate patient outcomes with the help of AI; and three studies are mainly focusing on how drug dose delivery is calculated (median: 1.1% ± 0.5) safely and given to the patients with applications of AI. In conclusion, the use of AI in anesthesia has the potential to revolutionize the field and improve patient outcomes. AI algorithms can accurately predict patient outcomes and anesthesia dosing, as well as monitor patients during surgery in real time. These technologies can help anesthesiologists make more informed decisions, increase efficiency, and reduce costs. However, the implementation of AI in anesthesia also presents challenges, such as the need to address issues of bias and privacy. As the field continues to evolve, it will be important to carefully consider the ethical implications of AI in anesthesia and ensure that these technologies are used in a responsible and transparent manner.
PubMed: 38654854
DOI: 10.4103/sja.sja_955_23