J-BHI publishes original papers describing recent advances in the field of biomedical and health informatics where information and communication technologies intersect with health, healthcare, life sciences and biomedicine. Papers must contain original content in theoretical analysis, methods, technical development, and/or novel clinical applications of information systems. Topics covered by J-BHI include but are not limited to: acquisition, transmission, storage, retrieval, management, processing and analysis of biomedical and health information; applications of information and communication technologies in the practice of healthcare, public health, patient monitoring, preventive care, early diagnosis of diseases, discovery of new therapies, and patient specific treatment protocols leading to improved outcomes; and the integration of electronic medical and health records, methods of longitudinal data analysis, data mining and discovery tools. Manuscripts may deal with these applications and their integration, such as clinical information systems, decision support systems, medical and biological imaging informatics, wearable systems, body area/sensor networks, informatics in biological and physiological systems, personalized and pervasive health technologies (u-, p-, m- and e-Health), telemedicine, home healthcare and wellness management. Topics related to integration include interoperability, protocol-based patient care, evidence-based medicine, and methods of secure patient data.

Specific topics covered by J-BHI include but are not limited to:

    Sensor Informatics – body sensor networks; wearable, ingestible and implantable systems; biosensor design, miniaturisation and embodiment; antennas, RF and intra-body communication; wireless communication standards, security and privacy, and QoS; smart point-of-care and wireless physiological monitoring devices (e.g. ECG, EMG, EEG and PPG); ASIC and embedded system design, on-node processing, smart devices and app development; autonomic sensing, distributed inference, context aware sensing and multi-sensor fusion; data compression; wearable and assistive devices for rehabilitation, well-being and ageing population;
    Bioinformatics – biological information systems and large scale ‘-omics’ databases, modelling, pattern matching and algorithms; systems biology, computational biology, and organ/system/disease-level informatics (e.g. physiome, neuro-informatics, cancer-informatics, and cardiovascular-informatics platforms);
    Imaging Informatics – image-enabled electronic medical records (EMR), PACS, hospital information systems (HIS), and radiology information systems (RIS) integration; computer aided diagnosis, database aggregation and distribution; image biomarkers and high-throughput systems; metadata, ontology and content-based image retrieval and decision support; multi-scale image fusion, visualization, high-content screening and image data mining;
    Medical Informatics – electronic health record, interoperability, connectivity, semantics, syntax, vocabulary, terminology, ontologies, standards, clinical guidelines/pathways, protocols; privacy, security, trust, PKI, smart card technology; regional and community health information networks, hospital information systems and clinical information systems, including PACS and disease management systems; collaborative technologies in health care delivery, including telemedicine; intelligent interpretation of health data, decision support systems, computer assisted, remote guidance and virtual reality applications in diagnostic and therapeutic procedures.
    Public Health Informatics – pervasive healthcare, wellness management utilising, e.g., ubiquitous computing, smart environments, embedded and wearable sensors; influenza monitoring and prediction; life-style chronic disease management and behaviour modification; personalized and pervasive health technologies (telemedicine, u-, p-, m- and e-Health) for public health.
    Modeling and AI in Informatics – Multiscale modeling molecular/cellular/tissue/organ/system/disease-level informatics, neuro-informatics, cancer-informatics, and cardiovascular-informatics platforms); data science and data engineering for biomedicine and health; network mining and modeling; biomedical and health data curation, augmentation and harmonization; machine learning and artificial intelligence methodologies for biomedical data analysis and interpretation; intelligent decision support systems for improving health outcomes; and intelligent informatics for extended digital health reality.

In the topics of Sensor Informatics, Imaging Informatics, Medical Informatics and Public Health Informatics only human studies are allowed, while in the area of Bioinformatics both human and animal studies are allowed.

Special Issue on Role of AI and Explainable AI in Integrative Approaches for Healthcare Data Analysis
提出日: 2026-01-31

An Artificial Intelligence (AI) and Explainable AI (XAI) based smart healthcare ecosystem is an advanced framework integrating multi-model data analysis, transparent decision-making processes, and ethical medical informatics. In AI-driven healthcare systems, diverse data sources such as electronic health records (EHRs), genomic profiles, wearable device outputs, and imaging data are seamlessly analyzed using deep learning, machine learning, and explainable models to ensure accurate, interpretable, and patient-centric healthcare delivery. Key components of this evolving ecosystem include multi-model AI techniques, explainable AI frameworks, healthcare data analytics, cloud-edge computing, cybersecurity protocols, and ethical AI governance. The synergy of AI and XAI not only enhances predictive capabilities and diagnostic accuracy but also promotes transparency, trust, and shared decision-making between healthcare providers and patients. The main objective of this Special Issue is to bring together innovative research contributions addressing technological advancements, ethical challenges, application frameworks, real-world deployments, and future directions in the integration of AI and XAI for transformative smart healthcare solutions.

Special Issue on Applying Federated Machine Learning Approaches for Human-Robot-Interaction
提出日: 2026-01-31

Human-robot communication, abbreviated as HRI, is the study of efficient and effective communication or interplay between humans and robots. HRI is a multidisciplinary idea usually utilized in areas including natural language processing, smart computer vision, robotics systems, artificial intelligence, and psychological studies. In the field of human-robot interactions with a focus on machine learning in its broadest sense to enable social interactions between humans and robots. This technology explores how vision, speech and sound, small movements, gestures, and user proximity affect the way we perceive and work with social robots.

Special Issue on Multimodal Medical Data-driven Biomedical and Health Informatics: Challenges and Solutions
提出日: 2026-01-31

This special issue will improve the comprehensive application of medical data by exploring multimodal medical data fusion methods and tools based on deep learning and AI; explore emerging multimodal data fusion model architectures, training techniques, and optimization methods to improve the accuracy of data fusion and reduce computational complexity; study methods for assessing privacy and security risks to ensure the safe and compliant use of medical data; study the application of bioinformatics computing methods and multimodal data analysis in health testing and disease management to provide strong support for the intelligent development of the medical field. In addition, disease diagnosis and personalized treatment based on medical multimodal big data, the bioinformatics foundation of future holographic intelligent medicine, and the practice of high-performance computing in bioinformatics are also important contents of this special issue.

Special Issue on Biomedical and Healthcare Intelligence Using Imperfect Data: Challenges, Advances and Trend
提出日: 2026-02-28

Artificial intelligence (AI), especially deep learning, has greatly hastened the modern medical diagnostics, particularly the interpretation of medical data. For instance, AI assists to locate lesion areas from medical images, detect heart disease from electrocardiograms, analyze brain disease from electroencephalogram etc. Generally, the performance of AI models in medical diagnostics heavily depends on the labeled medical data. However, the collected medical data is usually imperfect, insufficient, imbalanced, or incorrectly labeled. It is time-consuming, expensive, and laborious to collect a large scale of high quality labeled medical data. How to use imperfect data for making precise diagnoses is a vital challenge in the field of biomedical and healthcare intelligence. In order to handle this challenge and facilitate smart healthcare, this special issue will focus on the challenges, advances, and trend of weakly supervised learning on biomedical and healthcare intelligence. Compared with traditional supervised learning, weakly supervised learning focuses on learning under incomplete supervision, inexact supervision, or inaccurate supervision. Medical data is different from classical machine learning data. Generally, medical data has special concerns which need doctors or researchers to pay attention. Therefore, it is critical to explore suitable weakly supervised learning model for achieving the best medical diagnoses in the biomedical and healthcare intelligence.

Special Issue on Harnessing Cutting-Edge Privacy Technologies to Address Data Security Challenges in Healthcare Informatics
提出日: 2026-03-06

This Special Issue aims to advance privacy-preserving technologies that enable secure and effective use of complex, multi-modal healthcare data. Topics include federated learning encrypted computation, differential privacy, and privacy-aware adaptations of large language models, with a focus on balancing data privacy with healthcare innovation.

Special Issue on Next Generation AI for Eye Healthcare — From Bench to Bedside
提出日: 2026-03-31

Recent advances in AI have revolutionized eye healthcare, creating unprecedented opportunities for academia, healthcare, and industry. Despite this progress, significant challenges persist, as ophthalmic data in real-world clinical settings are highly diverse, frequently incomplete, and often imperfect, with labels that may be scarce, noisy, or only partially available. There is a pressing need for novel AI methods capable of effectively handling such real-world data. This special issue seeks to unite researchers from a wide range of disciplines to present cutting-edge AI approaches for analysing incomplete and imperfect ophthalmic data, with the aim of advancing AI-driven eye healthcare from bench to bedside and ultimately enabling their translation into clinical practice.

Special Issue on Explainable AI 2.0 for Healthcare 4.0
提出日: 2026-03-31

Healthcare 4.0 uses AI, IoT, cloud computing, and cyber-physical systems to provide personalized, real-time medical services. Explainable AI (XAI) plays a pivotal role in developing trust and transparency in AI decisions. However, traditional XAI provides static explanations irrespective of the individual’s skill sets. Explainable AI 2.0 addresses this concern by providing context-sensitive and personalized explanations. However, implementing XAI 2.0 in Healthcare 4.0 poses severe concerns, including the trade-off between model performance and explainability, the complexity of unified models, and the need for true context-sensitive explanations. Additionally, lack of standard metrics to assess the effectiveness of XAI 2.0 systems and regulatory and ethical concerns for ensuring not only technical soundness but also legal defensibility are other paramount concerns. The aim of the special issue is to transform healthcare 4.0 through transparent, trustworthy, context-sensitive, personalized, and human-centric AI systems that enhance clinical decision-making.

Special Issue on Large Language Models with Applications in Bioinformatics and Biomedicine, Part II
提出日: 2026-06-01

This special issue is dedicated to examining the transformative role of advanced language models (LLMs) in bioinformatics and biomedicine. While LLMs have already revolutionized fields like natural language processing and computer vision, their potential within bioinformatics and biomedicine is only beginning to be realized. By focusing on their applications in areas such as drug discovery, genomics, transcriptomics, proteomics, and single-cell analysis, this issue seeks to address the current lack of focused coverage on this topic. The articles featured aim to highlight the advancements and possibilities that LLMs offer in navigating the complexities of multi-omics data and the intricate layers of human physiology, fostering a deeper understanding and promoting future innovations in these critical fields.

Special Issue on Explainable Artificial Intelligence and Cognitive Computation in the Learning of Human Physiological Systems
提出日: 2026-08-31

This Special Issue calls for work that integrates XAI with deep learning in physiology, prioritizing studies that: 1) Develop novel interpretability techniques tailored to physiological time-series data, 2) Validate model explanations against domain knowledge (e.g., through clinician-in-the-loop evaluations), or 3) Use XAI to derive testable biological hypotheses. By fostering collaboration between AI researchers and physiologists, we can advance not just predictive performance but also scientific understanding of human health and disease. The special issue will be comprised of extensions of some of the best works announced in the workshop, along with papers submitted within the open call, taking also into account the target audience of the JBHI journal.

Special Issue on Agentic AI for Healthcare: Towards Autonomous, Trustworthy, and Human-Centric Systems
提出日: 2026-08-31

This Special Issue will explore Agentic Artificial Intelligence (AI) in Healthcare, focusing on systems that move beyond prediction and assistance to proactive, autonomous, and goal-directed actions under human-defined constraints. By integrating multimodal biomedical data, medical imaging, sensor streams, and patient records, Agentic AI has the potential to deliver adaptive, context-aware, and personalized support for prevention, diagnosis, treatment, and long-term health monitoring. The issue welcomes contributions on architectures, frameworks, and applications of Agentic AI, as well as work addressing safety, transparency, ethical and regulatory considerations, and human-AI collaboration in clinical and home-care settings.