-
GigaScience Dec 2022To develop a unified framework for analyzing data from 5 large publicly available intensive care unit (ICU) datasets.
OBJECTIVE
To develop a unified framework for analyzing data from 5 large publicly available intensive care unit (ICU) datasets.
FINDINGS
Using 3 American (Medical Information Mart for Intensive Care III, Medical Information Mart for Intensive Care IV, electronic ICU) and 2 European (Amsterdam University Medical Center Database, High Time Resolution ICU Dataset) databases, we constructed a mapping for each database to a set of clinically relevant concepts, which are grounded in the Observational Medical Outcomes Partnership Vocabulary wherever possible. Furthermore, we performed synchronization in the units of measurement and data type representation. On top of this, we built functionality, which allows the user to download, set up, and load data from all of the 5 databases, through a unified Application Programming Interface. The resulting ricu R-package represents the computational infrastructure for handling publicly available ICU datasets, and its latest release allows the user to load 119 existing clinical concepts from the 5 data sources.
CONCLUSION
The ricu R-package (available on GitHub and CRAN) is the first tool that enables users to analyze publicly available ICU datasets simultaneously (datasets are available upon request from respective owners). Such an interface saves researchers time when analyzing ICU data and helps reproducibility. We hope that ricu can become a community-wide effort, so that data harmonization is not repeated by each research group separately. One current limitation is that concepts were added on a case-to-case basis, and therefore the resulting dictionary of concepts is not comprehensive. Further work is needed to make the dictionary comprehensive.
Topics: Humans; Reproducibility of Results; Critical Care; Intensive Care Units; Databases, Factual; Data Management
PubMed: 37318234
DOI: 10.1093/gigascience/giad041 -
Journal of Biomedical Informatics Jun 2023The clinical documentation of cystoscopy includes visual and textual materials. However, the secondary use of visual cystoscopic data for educational and research...
BACKGROUND
The clinical documentation of cystoscopy includes visual and textual materials. However, the secondary use of visual cystoscopic data for educational and research purposes remains limited due to inefficient data management in routine clinical practice.
METHODS
A conceptual framework was designed to document cystoscopy in a standardized manner with three major sections: data management, annotation management, and utilization management. A Swiss-cheese model was proposed for quality control and root cause analyses. We defined the infrastructure required to implement the framework with respect to FAIR (findable, accessible, interoperable, reusable) principles. We applied two scenarios exemplifying data sharing for research and educational projects to ensure compliance with FAIR principles.
RESULTS
The framework was successfully implemented while following FAIR principles. The cystoscopy atlas produced from the framework could be presented in an educational web portal; a total of 68 full-length qualitative videos and corresponding annotation data were sharable for artificial intelligence projects covering frame classification and segmentation problems at case, lesion, and frame levels.
CONCLUSION
Our study shows that the proposed framework facilitates the storage of visual documentation in a standardized manner and enables FAIR data for education and artificial intelligence research.
Topics: Artificial Intelligence; Documentation; Data Management
PubMed: 37088456
DOI: 10.1016/j.jbi.2023.104369 -
Clinical and Translational Science Aug 2023The purpose of this article is to propose and provide a blueprint for a graduate-level curriculum in clinical data science, devoted to the measurement, acquisition,...
The purpose of this article is to propose and provide a blueprint for a graduate-level curriculum in clinical data science, devoted to the measurement, acquisition, care, treatment, and inferencing of clinical research data. The curriculum presented here contains a series of five required core courses, five required research courses, and a list of potential electives. The coursework draws from but does not duplicate content from the foundational areas of biostatistics, clinical medicine, biomedical informatics, and regulatory affairs, and may be reproduced by any institution interested in and capable of offering such a program. This new curriculum in "clinical" data science will prepare students for work in academic, industry, and government research settings as well as offer a unifying knowledge base for the profession.
Topics: Humans; Data Management; Data Science; Models, Educational; Biometry; Curriculum
PubMed: 37587756
DOI: 10.1111/cts.13545 -
BMC Medical Informatics and Decision... Jan 2023The growing application of artificial intelligence (AI) in healthcare has brought technological breakthroughs to traditional diagnosis and treatment, but it is...
BACKGROUND
The growing application of artificial intelligence (AI) in healthcare has brought technological breakthroughs to traditional diagnosis and treatment, but it is accompanied by many risks and challenges. These adverse effects are also seen as ethical issues and affect trustworthiness in medical AI and need to be managed through identification, prognosis and monitoring.
METHODS
We adopted a multidisciplinary approach and summarized five subjects that influence the trustworthiness of medical AI: data quality, algorithmic bias, opacity, safety and security, and responsibility attribution, and discussed these factors from the perspectives of technology, law, and healthcare stakeholders and institutions. The ethical framework of ethical values-ethical principles-ethical norms is used to propose corresponding ethical governance countermeasures for trustworthy medical AI from the ethical, legal, and regulatory aspects.
RESULTS
Medical data are primarily unstructured, lacking uniform and standardized annotation, and data quality will directly affect the quality of medical AI algorithm models. Algorithmic bias can affect AI clinical predictions and exacerbate health disparities. The opacity of algorithms affects patients' and doctors' trust in medical AI, and algorithmic errors or security vulnerabilities can pose significant risks and harm to patients. The involvement of medical AI in clinical practices may threaten doctors 'and patients' autonomy and dignity. When accidents occur with medical AI, the responsibility attribution is not clear. All these factors affect people's trust in medical AI.
CONCLUSIONS
In order to make medical AI trustworthy, at the ethical level, the ethical value orientation of promoting human health should first and foremost be considered as the top-level design. At the legal level, current medical AI does not have moral status and humans remain the duty bearers. At the regulatory level, strengthening data quality management, improving algorithm transparency and traceability to reduce algorithm bias, and regulating and reviewing the whole process of the AI industry to control risks are proposed. It is also necessary to encourage multiple parties to discuss and assess AI risks and social impacts, and to strengthen international cooperation and communication.
Topics: Humans; Artificial Intelligence; Algorithms; Delivery of Health Care; Prognosis; Data Management
PubMed: 36639799
DOI: 10.1186/s12911-023-02103-9 -
International Journal of Environmental... May 2020Our study aim is to identify and describe the definitions used for different types of running shoes. In addition, we highlight the existence of gaps in these concepts... (Review)
Review
OBJECTIVE
Our study aim is to identify and describe the definitions used for different types of running shoes. In addition, we highlight the existence of gaps in these concepts and propose possible new approaches. Methods This review was undertaken in line with the guidelines proposed by Green et al., based on a literature search (until December 2019) of the PubMed, Web of Science, Scopus, SPORTDiscus and Google Scholar databases. A total of 23 papers met the inclusion criteria applied to identify the definition of running shoes.
RESULTS
Although there is a certain consensus on the characteristics of minimalist footwear, it is also described by other terms, such as barefoot-style or barefoot-simulating. Diverse terms are also used to describe other types of footwear, and in these cases, there is little or no consensus regarding their characteristics.
CONCLUSIONS
The terms barefoot-simulated footwear, barefoot-style footwear, lightweight shoes and full minimalist shoes are all used to describe minimalist footwear. The expressions partial minimalist, uncushioned minimalist and transition shoes are used to describe footwear with non-consensual characteristics. Finally, labels such as shod shoes, standard cushioned running shoes, modern shoes, neutral protective running shoes, conventional, standardised, stability style or motion control shoes span a large group of footwear styles presenting different properties.
Topics: Biomechanical Phenomena; Consensus; Data Management; Running; Shoes; Terminology as Topic
PubMed: 32438717
DOI: 10.3390/ijerph17103562 -
Human Resources For Health Dec 2019Healthcare providers (HCPs) are recognized as one of the cornerstones and drivers of health interventions. Roles such as documentation of patient care, data management,... (Review)
Review
BACKGROUND
Healthcare providers (HCPs) are recognized as one of the cornerstones and drivers of health interventions. Roles such as documentation of patient care, data management, analysing, interpreting and appropriate use of data are key to ending vaccine-preventable diseases (VPDs). However, there is a great deal of uncertainty and concerns about HCPs' skills and competencies regarding immunization data handling and the importance of data use for improving service delivery in low- and middle-income countries (LMICs). Questions about the suitability and relevance of the contents of training curriculum, appropriateness of platforms through which training is delivered and the impact of such training on immunization data handling competencies and service delivery remain a source of concern. This review identified and assessed published studies that report on pre- and in-service training with a focus on HCPs' competencies and skills to manage immunization data in LMICs.
METHODS
An electronic search of six online databases was performed, in addition to websites of the WHO, Global Alliance for Vaccines and Immunization (GAVI), Oxfam International, Save the Children, Community Health Workers Central (CHW Central), UNAIDS and UNICEF. Using appropriate keywords, MeSH terms and selection procedure, 12 articles published between January 1980 and May 2019 on pre- and in-service training of HCPs, interventions geared towards standardized data collection procedures, data documentation and management of immunization data in LMICs, including curriculum reviews, were considered for analysis.
RESULTS
Of the 2705 identified references, only 12 studies met the inclusion criteria. The review provides evidence that shows that combined and multifaceted training interventions could help improve HCPs' knowledge, skills and competency on immunization data management. It further suggests that offering the right training to HCPs and sustaining standard immunization data management is hampered in LMICs by limited or/lack of training resources.
CONCLUSION
Pre-service training is fundamental in the skills' acquisition of HCPs; however, they require additional in-service training and supportive supervision to function effectively in managing immunization data tasks. Continuous capacity development in immunization data-management competencies such as data collection, analysis, interpretation, synthesis and data use should be strengthened at all levels of the health system. Furthermore, there is a need for periodic review of the immunization-training curriculum in health training institutions, capacity development and retraining tutors on the current trends in immunization data management.
Topics: Community Health Workers; Curriculum; Data Management; Developing Countries; Humans; Immunization; Inservice Training; Poverty
PubMed: 31791352
DOI: 10.1186/s12960-019-0437-6 -
Computational Intelligence and... 2022In order to further understand the economic data management system and technology, in-depth research was conducted in the state of people's nervous system feeling. The...
In order to further understand the economic data management system and technology, in-depth research was conducted in the state of people's nervous system feeling. The method of building open platform algorithm to optimize and modify weight rule 2BP grid construction was used to study. According to the basic principle, the BP neural network which is more suitable for economic data management system was constructed. At the same time, to construct economic database resources, neural network system was mainly to simplify and abstract or simulate the human brain nervous system, which is not completely the same, but can also map the basic characteristics of many functions of the human brain. Through the analysis of the economic data of the neural network, the neural network is widely used in the economic data management, which not only improves the management level of enterprises, but also improves the benefits and profits of enterprises. Besides, it has application effect in predicting economic early warning risk analysis cost control strategy management enterprise credit evaluation and enterprise competitiveness evaluation.
Topics: Algorithms; Data Management; Humans; Neural Networks, Computer
PubMed: 35845916
DOI: 10.1155/2022/9036917 -
BMJ Open Jan 2022Awareness of patients' innovative capabilities is increasing, but there is limited knowledge regarding the extent and nature of patient-driven innovations in the... (Review)
Review
BACKGROUND
Awareness of patients' innovative capabilities is increasing, but there is limited knowledge regarding the extent and nature of patient-driven innovations in the peer-reviewed literature.
OBJECTIVES
The objective of the review was to answer the question: what is the nature and extent of patient-driven innovations published in peer-reviewed scientific journals?
ELIGIBILITY CRITERIA
We used a broad definition of innovation to allow for a comprehensive review of different types of innovations and a narrow definition of 'patient driven' to focus on the role of patients and/or family caregivers. The search was limited to years 2008-2020.
SOURCES OF EVIDENCE
Four electronic databases (Medline (Ovid), Web of Science Core Collection, PsycINFO (Ovid) and Cinahl (Ebsco)) were searched in December 2020 for publications describing patient-driven innovations and complemented with snowball strategies.
CHARTING METHODS
Data from the included articles were extracted and categorised inductively.
RESULTS
A total of 96 articles on 20 patient-driven innovations were included. The number of publications increased over time, with 69% of the articles published between 2016 and 2020. Author affiliations were exclusively in high income countries with 56% of first authors in North America and 36% in European countries. Among the 20 innovations reported, 'Do-It-Yourself Artificial Pancreas System' and the online health network 'PatientsLikeMe', were the subject of half of the articles.
CONCLUSIONS
Peer-reviewed publications on patient-driven innovations are increasing and we see an important opportunity for researchers and clinicians to support patient innovators' research while being mindful of taking over the work of the innovators themselves.
Topics: Data Management; Humans; MEDLINE; North America; Peer Review; Periodicals as Topic
PubMed: 35074818
DOI: 10.1136/bmjopen-2021-053735 -
Journal of Biosciences 2021Efficient analysis of Single Nucleotide Polymorphisms (SNPs) across genomic samples enable in deciphering the relationship between genotype and phenotype. The core...
Efficient analysis of Single Nucleotide Polymorphisms (SNPs) across genomic samples enable in deciphering the relationship between genotype and phenotype. The core principle behind SNP comparison is to arrive at a probable list of variants that can differentiate two sets of data (populations). Such SNPs have direct applications in array design, genotype imputation and in cataloging of variants in regions of interest. We have developed GAMUT (Genomics bigdAta Management Tool), a big data-based solution for efficient run-time comparison of SNPs across large datasets based on partition of samples belonging to different populations taking into account user-defined splits. The tool is based on client-server architecture with MongoDB at the back-end and JSF with PrimeFaces as the front-end. It is readily deployable on wild-fly server as well as a docker container. Spark-based parallel data uploader enables optimal loading times. GAMUT enables dynamic querying of the large datasets consisting of multiple samples using text-based, chromosome position-based as well as gene-name based options. Various charting options like bar and pie charts along with tabular formats are available to ease the analysis of the queried data. The resultant data pertaining to comparison of genomewide SNPs can also be downloaded in different formats like text, html, json for further stand-alone analysis. GAMUT is available for download at: https://github.com/bioinformatics-cdac/gamut.
Topics: Big Data; Data Management; Databases, Factual; Genomics; Genotype; Humans; Polymorphism, Single Nucleotide; Software
PubMed: 34544908
DOI: No ID Found -
International Journal of Environmental... Mar 2021In soccer, the assessment of the load imposed by training and a match is recognized as a fundamental task at any competitive level. The objective of this study is to... (Review)
Review
In soccer, the assessment of the load imposed by training and a match is recognized as a fundamental task at any competitive level. The objective of this study is to carry out a systematic review on internal and external load monitoring during training and/or a match, identifying the measures used. In addition, we wish to make recommendations that make it possible to standardize the classification and use of the different measures. The systematic review was carried out according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. The search was conducted through the electronic database Web of Science, using the keywords "soccer" and "football", each one with the terms "internal load", "external load", and "workload". Of the 1223 studies initially identified, 82 were thoroughly analyzed and are part of this systematic review. Of these, 25 articles only report internal load data, 20 report only external load data, and 37 studies report both internal and external load measures. There is a huge number of load measures, which requires that soccer coaches select and focus their attention on the most useful and specific measures. Standardizing the classification of the different measures is vital in the organization of this task, as well as when it is intended to compare the results obtained in different investigations.
Topics: Data Management; Databases, Factual; Soccer; Workload
PubMed: 33800275
DOI: 10.3390/ijerph18052721