-
Journal of Medical Internet Research Jun 2021The influence of social media among adolescent peer groups can be a powerful change agent. (Review)
Review
BACKGROUND
The influence of social media among adolescent peer groups can be a powerful change agent.
OBJECTIVE
Our scoping review aimed to elucidate the ways in which social media use among adolescent peers influences eating behaviors.
METHODS
A scoping review of the literature of articles published from journal inception to 2019 was performed by searching PubMed (ie, MEDLINE), Embase, CINAHL, PsycINFO, Web of Science, and other databases. The review was conducted in three steps: (1) identification of the research question and clarification of criteria using the population, intervention, comparison, and outcome (PICO) framework; (2) selection of articles from the literature using the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines; and (3) charting and summarizing information from selected articles. PubMed's Medical Subject Headings (MeSH) and Embase's Emtree subject headings were reviewed along with specific keywords to construct a comprehensive search strategy. Subject headings and keywords were based on adolescent age groups, social media platforms, and eating behaviors. After screening 1387 peer-reviewed articles, 37 articles were assessed for eligibility. Participant age, gender, study location, social media channels utilized, user volume, and content themes related to findings were extracted from the articles.
RESULTS
Six articles met the final inclusion criteria. A final sample size of 1225 adolescents (aged 10 to 19 years) from the United States, the United Kingdom, Sweden, Norway, Denmark, Portugal, Brazil, and Australia were included in controlled and qualitative studies. Instagram and Facebook were among the most popular social media platforms that influenced healthful eating behaviors (ie, fruit and vegetable intake) as well as unhealthful eating behaviors related to fast food advertising. Online forums served as accessible channels for eating disorder relapse prevention among youth. Social media influence converged around four central themes: (1) visual appeal, (2) content dissemination, (3) socialized digital connections, and (4) adolescent marketer influencers.
CONCLUSIONS
Adolescent peer influence in social media environments spans the spectrum of healthy eating (ie, pathological) to eating disorders (ie, nonpathological). Strategic network-driven approaches should be considered for engaging adolescents in the promotion of positive dietary behaviors.
Topics: Adolescent; Data Management; Diet, Healthy; Feeding Behavior; Humans; Peer Influence; Social Media; United States
PubMed: 34081018
DOI: 10.2196/19697 -
Journal of Medical Internet Research May 2021Machine learning systems are part of the field of artificial intelligence that automatically learn models from data to make better decisions. Natural language processing... (Meta-Analysis)
Meta-Analysis Review
BACKGROUND
Machine learning systems are part of the field of artificial intelligence that automatically learn models from data to make better decisions. Natural language processing (NLP), by using corpora and learning approaches, provides good performance in statistical tasks, such as text classification or sentiment mining.
OBJECTIVE
The primary aim of this systematic review was to summarize and characterize, in methodological and technical terms, studies that used machine learning and NLP techniques for mental health. The secondary aim was to consider the potential use of these methods in mental health clinical practice.
METHODS
This systematic review follows the PRISMA (Preferred Reporting Items for Systematic Review and Meta-analysis) guidelines and is registered with PROSPERO (Prospective Register of Systematic Reviews; number CRD42019107376). The search was conducted using 4 medical databases (PubMed, Scopus, ScienceDirect, and PsycINFO) with the following keywords: machine learning, data mining, psychiatry, mental health, and mental disorder. The exclusion criteria were as follows: languages other than English, anonymization process, case studies, conference papers, and reviews. No limitations on publication dates were imposed.
RESULTS
A total of 327 articles were identified, of which 269 (82.3%) were excluded and 58 (17.7%) were included in the review. The results were organized through a qualitative perspective. Although studies had heterogeneous topics and methods, some themes emerged. Population studies could be grouped into 3 categories: patients included in medical databases, patients who came to the emergency room, and social media users. The main objectives were to extract symptoms, classify severity of illness, compare therapy effectiveness, provide psychopathological clues, and challenge the current nosography. Medical records and social media were the 2 major data sources. With regard to the methods used, preprocessing used the standard methods of NLP and unique identifier extraction dedicated to medical texts. Efficient classifiers were preferred rather than transparent functioning classifiers. Python was the most frequently used platform.
CONCLUSIONS
Machine learning and NLP models have been highly topical issues in medicine in recent years and may be considered a new paradigm in medical research. However, these processes tend to confirm clinical hypotheses rather than developing entirely new information, and only one major category of the population (ie, social media users) is an imprecise cohort. Moreover, some language-specific features can improve the performance of NLP methods, and their extension to other languages should be more closely investigated. However, machine learning and NLP techniques provide useful information from unexplored data (ie, patients' daily habits that are usually inaccessible to care providers). Before considering It as an additional tool of mental health care, ethical issues remain and should be discussed in a timely manner. Machine learning and NLP methods may offer multiple perspectives in mental health research but should also be considered as tools to support clinical practice.
Topics: Artificial Intelligence; Data Management; Humans; Machine Learning; Mental Health; Natural Language Processing
PubMed: 33944788
DOI: 10.2196/15708 -
Journal of Evidence-based Medicine Feb 2020Data mining technology can search for potentially valuable knowledge from a large amount of data, mainly divided into data preparation and data mining, and expression... (Review)
Review
Data mining technology can search for potentially valuable knowledge from a large amount of data, mainly divided into data preparation and data mining, and expression and analysis of results. It is a mature information processing technology and applies database technology. Database technology is a software science that researches manages, and applies databases. The data in the database are processed and analyzed by studying the underlying theory and implementation methods of the structure, storage, design, management, and application of the database. We have introduced several databases and data mining techniques to help a wide range of clinical researchers better understand and apply database technology.
Topics: Big Data; Data Management; Data Mining; Databases, Factual; Software
PubMed: 32086994
DOI: 10.1111/jebm.12373 -
Indian Journal of Dermatology,... 2021
Topics: Data Management; Dermatology; Humans; Periodicals as Topic
PubMed: 34672477
DOI: 10.25259/IJDVL_989_2021 -
Proceedings of the National Academy of... Mar 2020Machine learning is proving invaluable across disciplines. However, its success is often limited by the quality and quantity of available data, while its adoption is...
Machine learning is proving invaluable across disciplines. However, its success is often limited by the quality and quantity of available data, while its adoption is limited by the level of trust afforded by given models. Human vs. machine performance is commonly compared empirically to decide whether a certain task should be performed by a computer or an expert. In reality, the optimal learning strategy may involve combining the complementary strengths of humans and machines. Here, we present expert-augmented machine learning (EAML), an automated method that guides the extraction of expert knowledge and its integration into machine-learned models. We used a large dataset of intensive-care patient data to derive 126 decision rules that predict hospital mortality. Using an online platform, we asked 15 clinicians to assess the relative risk of the subpopulation defined by each rule compared to the total sample. We compared the clinician-assessed risk to the empirical risk and found that, while clinicians agreed with the data in most cases, there were notable exceptions where they overestimated or underestimated the true risk. Studying the rules with greatest disagreement, we identified problems with the training data, including one miscoded variable and one hidden confounder. Filtering the rules based on the extent of disagreement between clinician-assessed risk and empirical risk, we improved performance on out-of-sample data and were able to train with less data. EAML provides a platform for automated creation of problem-specific priors, which help build robust and dependable machine-learning models in critical applications.
Topics: Data Management; Database Management Systems; Expert Systems; Machine Learning; Medical Informatics
PubMed: 32071251
DOI: 10.1073/pnas.1906831117 -
International Journal of Environmental... Sep 2021The purpose of this study is to establish the absolute reliability between hand-held dynamometers (HHDs) and concurrent validity between HHDs and isokinetic dynamometers... (Meta-Analysis)
Meta-Analysis Review
The purpose of this study is to establish the absolute reliability between hand-held dynamometers (HHDs) and concurrent validity between HHDs and isokinetic dynamometers (IDs) in shoulder rotator strength assessment. The Medline, CINAHL, and Central databases were searched for relevant studies up to July 2020. Absolute reliability was determined by test-retest studies presenting standard error of measurement (SEM%) and/or minimal detectable change (MDC%) expressed as percentage of the mean. Studies considering intra-class correlation coefficient (ICC) between IDs and HHDs were considered for concurrent validity. The risk of bias and the methodological quality were evaluated according to COnsensus-based Standards for the selection of health Measurement INstruments (COSMIN). Thirteen studies were included in the meta-analysis. Shoulder internal rotator strength assessment MDC% was 0.78%, 95% confidence interval (CI) -5.21 to 3.66, while shoulder external rotators MDC% was 3.29%, CI -2.69 to 9.27. ICC between devices was 0.94, CI (0.91 to 0.96) for shoulder internal rotators and 0.92, IC (0.88 to 0.97) for shoulder external rotators. Very high correlation was found for shoulder rotator torque assessment between HHDs and IDs. The COSMIN checklist classified the selected studies as adequate and inadequate.
Topics: Data Management; Humans; Muscle Strength Dynamometer; Reproducibility of Results; Shoulder; Torque
PubMed: 34501883
DOI: 10.3390/ijerph18179293 -
Sensors (Basel, Switzerland) Jul 2022Over the last couple of years, Blockchain technology has emerged as a game-changer for various industry domains, ranging from FinTech and the supply chain to healthcare... (Review)
Review
Over the last couple of years, Blockchain technology has emerged as a game-changer for various industry domains, ranging from FinTech and the supply chain to healthcare and education, thereby enabling them to meet the competitive market demands and end-user requirements. Blockchain technology gained its popularity after the massive success of Bitcoin, of which it constitutes the backbone technology. While blockchain is still emerging and finding its foothold across domains, Cloud computing is comparatively well defined and established. Organizations such as Amazon, IBM, Google, and Microsoft have extensively invested in Cloud and continue to provide a plethora of related services to a wide range of customers. The pay-per-use policy and easy access to resources are some of the biggest advantages of Cloud, but it continues to face challenges like data security, compliance, interoperability, and data management. In this article, we present the advantages of integrating Cloud and blockchain technology along with applications of Blockchain-as-a-Service. The article presents itself with a detailed survey illustrating recent works combining the amalgamation of both technologies. The survey also talks about blockchain-cloud services being offered by existing Cloud Service providers.
Topics: Blockchain; Cloud Computing; Computer Security; Data Management; Technology
PubMed: 35890918
DOI: 10.3390/s22145238 -
Anesthesiology Mar 2019
Topics: Acetaminophen; Administration, Intravenous; Analgesics, Opioid; Colectomy; Data Management
PubMed: 30762645
DOI: 10.1097/ALN.0000000000002570 -
Studies in Health Technology and... May 2021Intraoperative neurophysiological monitoring (IOM) enables a function-preserving surgical strategy for surgeries of brain or spinal cord pathologies by...
Intraoperative neurophysiological monitoring (IOM) enables a function-preserving surgical strategy for surgeries of brain or spinal cord pathologies by neurophysiological measurements. However, the IOM data management at neurosurgical institutions are often either not digitized or inefficient in terms of collecting, storing and processing of IOM data. Here, we describe the development of a web application, called IOM-Manager, as a first step towards the complete digitization of the IOM workflow. The web application is used for structured protocoling based on standardized protocol entry catalog, data archiving, and data analysis. These functionalities are based on the results of the requirement engineering of a process analysis, a survey with potential users and a market analysis. A usability test with one IOM team indicated the IOM-Manager and its other components can in fact solve many problems of existing solutions.
Topics: Data Management; Evoked Potentials, Somatosensory; Intraoperative Neurophysiological Monitoring; Neurophysiology; Neurosurgical Procedures
PubMed: 34042896
DOI: 10.3233/SHTI210071 -
NanoImpact Jul 2022Publishing research data using a findable, accessible, interoperable, and reusable (FAIR) approach is paramount to further innovation in many areas of research. In... (Review)
Review
Publishing research data using a findable, accessible, interoperable, and reusable (FAIR) approach is paramount to further innovation in many areas of research. In particular in developing innovative approaches to predict (eco)toxicological risks in (nano or advanced) material design where efficient use of existing data is essential. The use of tools assessing the FAIRness of data helps the future improvement of data FAIRness and therefore their re-use. This paper reviews ten FAIR assessment tools that have been evaluated and characterized using two datasets from the nanomaterials and microplastics risk assessment domain. The tools were grouped into four categories: online and offline self-assessment survey based, online (semi-) automated and other tools. We found that the online self-assessment tools can be used for a quick scan of a user's dataset due to their ease of use, little need for experience and short time investment. When a user is looking to assess full databases, and not just datasets, for their FAIRness, (semi-)automated tools are more practical. The offline assessment tools were found to be limited and unreliable due to a lack of guidance and an under-developed state. To further characterize the usability, two datasets were run through all tools to check the similarity in the tools' results. As most of the tools differ in their implementation of the FAIR principles, a large variety in outcomes was obtained. Furthermore, it was observed that only one tool gives recommendations to the user on how to improve the FAIRness of the evaluated dataset. This paper gives clear recommendations for both the user and the developer of FAIR assessment tools.
Topics: Data Management; Databases, Factual; Plastics; Risk Assessment; Self-Assessment
PubMed: 35717894
DOI: 10.1016/j.impact.2022.100402