Información de la Revista

Journal of Biomedical Informatics (JBI)

Por favor Iniciar sesión para ver el sitio web de la revista
Cuenta gratuita: consulta los sitios oficiales, sigue las fechas límite y recibe recordatorios por correo.
Registrarse Iniciar sesión
Obtener estos datos por API
Las búsquedas y las listas de rankings no necesitan credenciales; el detalle completo de esta página requiere una clave de API gratuita. Consulta la guía para desarrolladores.
Factor de Impacto:
5.9
Editor:
Elsevier
ISSN:
1532-0464
Vistas:
29559
Seguidores:
18

Solicitud de Artículos

Journal of Biomedical Informatics (JBI) is an academic journal published by Elsevier. (ISSN 1532-0464, impact factor 5.9, CCF C).

Aims & Scope Endorsed by the American Medical Informatics Association The Journal of Biomedical Informatics (JBI) is the premier methodology journal in the field of biomedical informatics. JBI publishes research on new methodologies and techniques that have general applicability and form the basis for the evolving science of biomedical informatics. Papers should focus on a real-world biomedical or clinical problem, develop a novel approach to address the problem, and evaluate its appropriateness in comparison to the current state-of-the-art (SoA) methods. Involvement of healthcare professionals in motivating the work and evaluation of results is expected. Focus Areas and Topics of Interest JBI seeks to publish papers that make a conceptual contribution to the field, typically by describing an innovation in methodology or technique or by discussing substantive generalizable lessons that have been learned in the context of an informatics project. When a methodological contribution has a theoretical basis, that theory is an appropriate emphasis for papers as well. Research papers may also present a novel "method of methods" explaining how to apply the existing methods to a space of biomedical problems that share unique characteristics influencing the choice of methods. JBI publishes papers on a wide range of informatics topics. However, across these topics, papers must build on deep understanding and utilization of medical domain knowledge and should consider pragmatic translation for clinical care or applications. Topics of interest include (but are not limited to) clinical decision support, patient safety, natural language processing, artificial intelligence and machine learning, knowledge representation for healthcare, translational bioinformatics, clinical research informatics, and clinical informatics. Additional considerations for papers in the areas of translational bioinformatics, machine learning, security and privacy are provided below. Irrespective of the topic, papers must focus on novel informatics methods and its comparison to the current approaches. Manuscripts can be submitted in the following categories: original research, methodological review, commentaries, special communication, letters to the editor, book reviews, and editorials (see additional details on each of these categories below). Given the international readership of JBI, country-specific health systems or approaches will be considered only if they offer generalizable lessons that are relevant to the broader readership, regardless of their country, language, culture, or health system. Specific considerations for manuscripts in certain topical areas have also been provided in recent editorials. If you are considering an article with a focus on translational bioinformatics , please read this editorial. Biologic discoveries based on the use of routine informatics techniques may be important biologic contributions, but are not suitable for JBI. In addition, please note that JBI publishes bioinformatics papers only if they deal with issues in translational (human) science (e.g., translational bioinformatics papers). If you are considering an article describing a new machine learning approach, please read this editorial. Machine learning papers would be considered only if the methods that are introduced demonstrate substantial novelty and advancement beyond the current SoA and their evaluation is sound and includes an assessment of the potential of the method to be used in clinical practice. For example, submissions reporting publishing marginally SoA findings without an in-depth analysis or discussion of how the methods are potentially generalizable (or applicable in a wider setting) would not be considered. Novel and important clinical problems addressed by existing machine learning methods may warrant Special Communication papers if their discussion includes novel insights or lessons learned for future research in such domains. Authors considering an article on biomedical privacy and security, please read this editorial. To be considered, the privacy and security methods that are introduced should demonstrate substantial novelty and advancement beyond the SoA, should be specific to the biomedical informatics domain, and their practical application and/or likely real-world usefulness in the biomedical domain. Please note that papers related to signal processing, imaging, medical devices, or communication networks are outside the scope of the journal unless they combine knowledge-intensive approaches involving ontologies. Please also consult the editorial that explains where to direct Artificial Intelligence in Medicine-related manuscripts for peer review and possible publication, considering the different scope of the three Elsevier medical informatics journals: JBI, Artificial Intelligence in Medicine, and Intelligence-based Medicine.
Última actualización por Admin Agent el

Special Issues

Special Issue on Agentic AI for Real-World Evidence Life Cycle Support - Scaling Trustworthy Evaluation of Treatment Safety and Effectiveness Día de Entrega: 2026-11-15 Real-world evidence (RWE) derived from observational health data, including electronic health records, administrative claims, registries, and patient-generated data, is a cornerstone of modern clinical and translational research. However, generating trustworthy RWE requires sophisticated workflows spanning data harmonization, phenotype development, cohort construction, causal inference, and reproducible study execution across clinical research environments. Equally challenging are the processes of translating RWE into practice as a learning health system [1], which monitors its impact, and evolves new research questions to complete the evidence generation cycle. Agentic AI has recently emerged as a paradigm that advances generative AI by adding coordinated management of specialized agents, tool-based task execution, and complete workflow orchestration.[2] These advances create opportunities for novel approaches to assist investigators throughout the RWE lifecycle. Tools and frameworks for RWE agentic systems are already emerging for different stages of the life-cycle of evidence generation and translation into practice. These include agentic research platforms for clinical studies and autonomous causal analysis systems (e.g., Causal-copilot [3], TrialGenie [4], and EHRFlow [5], and FastOMOP [6]) illustrate how agents can support tasks such as cohort definition, analytic code generation, data transformation, and causal analysis. However, some evidence suggests that current agentic designs might only offer modest performance benefits while 1 Role of the Advisory Committee: The advisory committee will facilitate and advise the Guest Editors, working closely with the Managing Guest Editor, to: (1) solicit submissions for the special issue, (2) assist in reviewing submitted papers relevant to their expertise, (3) help recruit reviewers with expertise relevant to the submissions, (4) provide guidance on the thematic coherence of the issue, (5) contribute editorials or papers to the issue, (6) support the promotion and dissemination of the special issue within the academic and professional communities. increasing resource demands [7]. Also, foundational methodological challenges remain in the design, evaluation, and governance of agentic AI systems. These include ensuring trustworthiness and reproducibility of AI-generated analyses, mitigating bias and fairness risks, supporting privacy-preserving research, developing rigorous benchmarks [8], and ensuring that users of Agentic AI retain professional competence and accountability. This special issue will focus on methodological advances in agentic AI to facilitate the generation of RWE for treatment effectiveness and safety. We adopt the definition of agentic AI systems as "multiagent collaboration, dynamic task decomposition, persistent memory, and coordinated autonomy" [2] that "plan to achieve complex, high-level objectives" [9]. Therefore, single, tool-augmented AI agents designed for isolated task executions are out of scope for this special issue Guest editors: Name: Richard Boyce Affiliation: Department of Biomedical Informatics, School of Medicine,University of Pittsburgh, Pittsburgh, PA, USA Email Address: [email protected] Name: Scott Alexander Malec Affiliation: Translational Informatics Division, School of Medicine, University of New Mexico, Albuquerque, NM, USA Email Address: [email protected] Name: Chunhua Weng Affiliation: Biomedical Informatics, Data Science Institute, Columbia University, New York, NY, USA Email Address: [email protected] Advisory Committee: Daniel Capurro, [email protected], School of Computing and Information Systems, Department of Medicine, University of Melbourne, Melbourne, Victoria, Australia Gongbo Zhang, [email protected], Associate Research Scientist, Columbia University Irving Medical Center, Columbia, University, New York, NY, USA Yonghui Wu, [email protected], Department of Health Outcomes & Biomedical Informatics, College of Medicine at the University of Florida, Gainesville, FL, USA Yifan Peng, [email protected], Population Health Sciences, Weill Cornell Medical College, New York, NY, USA Special issue information: Examples of Suitable Topics for the Special Issue To reflect the full lifecycle of real-world evidence generation, from data acquisition and study design to continuous monitoring, evidence evolution, and integration within learning health systems, this special issue seeks contributions that advance agentic AI methods across interconnected stages of this process. The following topics illustrate areas of particular interest, with an emphasis on multi-agent coordination, iterative learning, and system-level evaluation: Agentic Data Acquisition and Harmonization - Examples could include systems that identify and correct real-world data transformation and data-quality problems; assist with mapping clinical data to controlled medical terminologies, ontologies, and common data models (e.g., OMOP, FHIR, PCORNet, SENTINEL, etc.) for semantic data integration; and/or harmonize of multi-modal data. Agentic Phenotype Development and Cohort Construction - For example, systems that assist users with extracting data from real-world datasets for participants who qualify for study inclusion. Agentic Study Design and Protocol Specification - This could include critique of causal assumptions, tradeoff analysis across design choices, executable representations for study protocols that can be leveraged by agentic systems, and continuous protocol refinement. Multi-agent Systems for Causal Analysis and Effect Estimation - Examples might include services for target trial emulation, phenotype and time-at-risk definition, confounder mitigation, bias diagnosis, evidence-linked rationale, sensitivity analyses, validating external control arms, and identifying negative controls. Reproducibility, Evaluation frameworks, and Distributed Research Execution - Potentially including provenance tracking, auditability, and explainability of multi-agent research workflows. Monitoring, Evidence Evolution, and Learning Health Systems - This may include methods for aligning agentic systems with clinical workflows to support ongoing decision-making and feedback. Trustworthiness, Governance, and Safe Deployment of Agentic AI - For example, methods to help humans audit the workflow, output, and stability of agentic AI systems. https://www.sciencedirect.com/special-issue/334546/agentic-ai-for-real-world-evidence-life-cycle-support-scaling-trustworthy-evaluation-of-treatment-safety-and-effectiveness
Última actualización por Admin Agent el

Las personas que vieron esto también vieron

CCFNombre CompletoFactor de ImpactoEditorISSN
CImage and Vision Computing5.0Elsevier0262-8856

Revistas Relacionadas

CCFNombre CompletoFactor de ImpactoEditorISSN
Biomedical InformaticsELSP3005-3862
Biomedical Signal Processing and Control4.9Elsevier1746-8094
Applied Computing and InformaticsElsevier2210-8327
Journal of Biomedical Semantics2.0Springer2041-1480
Journal of Pathology InformaticsElsevier2229-5089
International Journal of Information Management27.0Elsevier0268-4012
Journal of Computational Science3.7Elsevier1877-7503
Sustainable Computing: Informatics and Systems5.7Elsevier2210-5379
Egyptian Informatics Journal4.3Elsevier1110-8665
Journal of Manufacturing Systems14.2Elsevier0278-6125

Conferencias Relacionadas

Comentarios 0

Aún no hay comentarios.

Por favor Iniciar sesión para publicar un comentario