CBMS 2026 – Special Tracks

Green-Aware Artificial Intelligence for Network and Text Mining in Computational Biology and Medicine

Authors: Marianna Milano, Giuseppe Agapito and Chiara Zucco

This Special Track aims to advance environmentally sustainable and interpretable artificial intelligence for biomedical research. It integrates green-aware computing, network science, and biomedical text mining to design AI systems that are accurate, transparent, and energy-efficient. The focus is on developing algorithms and pipelines for analyzing multilayer biological networks—such as gene, protein, drug, and disease interactions—and large-scale biomedical text corpora from publications and clinical records. By combining serverless and edge computing, data reduction, and interpretable machine learning, the track seeks to minimize computational and environmental costs while maintaining analytical power. Applications include drug target discovery, disease mechanism analysis, and knowledge extraction from biomedical literature.

Multimodal Artificial Intelligence in Healthcare

Authors: Michela Gravina, Valerio Guarrasi, Antonio Galli, Meryeme Boumahdi, Angel Mario Garcia-Pedrero, and Consuelo Gonzalo-Martin

The intersection of Artificial Intelligence (AI) and Healthcare has opened new frontiers in research, heralding an era of innovation and discovery. The increasing availability of heterogeneous information has underscored the need for approaches capable of learning from diverse data types, driving the advancement of Multimodal Learning techniques. These approaches have significantly enhanced the capabilities of medical applications, offering transformative potential in areas such as diagnostic accuracy and personalized treatment plans. The Special Track Multimodal Artificial Intelligence in Healthcare seeks to bring together cutting-edge research and developments in this dynamic field. We invite contributions that push the boundaries of knowledge and application in Multimodal Learning, enhancing our ability to tackle complex medical challenges and improve patient outcomes. This track aims to unite researchers and practitioners working at the forefront of Multimodal AI techniques. It offers a platform to present and discuss recent advancements in methodologies, practices, strategies, and tools within this interdisciplinary field. By fostering discussion and knowledge exchange, this track encourages collaboration and the sharing of novel research findings, technological developments, and innovative applications, contributing to the advancement of AI in healthcare.

GEAI4ND — Generalizable & Explainable AI for the Care Continuum of Neurodegenerative Diseases

Authors: Gianluca Amprimo, Andreas Miltiadous, Claudia Ferraris, Gabriella Olmo and Alexandros Tzallas

Artificial intelligence (AI) is reshaping how we detect, stage, and monitor neurodegenerative diseases such as Alzheimer’s, Parkinson’s, Amyotrophic Lateral Sclerosis (ALS), and related conditions. From imaging to wearable devices and mobile platforms, digital biomarkers enable earlier detection, continuous real-world monitoring, and truly personalized interventions. Yet translating these advances into clinical workflows remains challenging as models often behave as black boxes; performance can degrade under domain shift; multimodal data are messy, incomplete, or siloed; and regulatory-grade evidence requires calibrated uncertainty, fairness assessments, transparency, and reproducibility. For clinic-to-home care pathways, methods must be interpretable and robust across heterogeneous devices, sites, and populations, while preserving privacy and aligning with clinician workflows. This special track aims to bring together researchers to advance clinically interpretable AI for digital biomarkers of neurodegeneration across the clinic–home continuum.

Interoperability and Federated Analytics in Biomedical Data Using OMOP CDM

Authors: João Almeida, José Luis Oliveira, Dani Alhambra, Agma Traina and Giuseppe Placidi

This Special Track focuses on advancing interoperability and federated analytics in biomedical data using the OMOP Common Data Model. It welcomes contributions related to data harmonisation, privacy-preserving analytics, distributed machine learning, real-world data integration, automated ETL processes, and scalable architectures for federated research networks within OHDSI community. The track aims to bring together researchers and practitioners to discuss methodologies, challenges, and innovations that enable secure, standardised and collaborative biomedical data analysis.

Network Medicine

Authors: Lucía Prieto-Santamaría, Alejandro Rodríguez-González and Emre Guney

The Special Track on Network Medicine at IEEE CBMS 2026 focuses on integrating network science with molecular biology, systems biology, and clinical data to better understand disease mechanisms and improve healthcare outcomes. By modeling interactions among genes, proteins, metabolites, cells, and environmental factors, Network Medicine enables researchers to identify key pathways, refine disease classification, discover biomarkers, and support drug repurposing and personalized therapeutic strategies. This track provides a forum for interdisciplinary collaboration, highlighting methodological advances as well as translational applications, and welcomes contributions ranging from computational approaches and data resources to clinically oriented studies.

Image Processing and Machine Vision for Intelligent Healthcare

Authors: Abdussalam Elhanashi and Massimiliano Donati

The IEEE CBMS 2026 Special Track on Image Processing and Machine Vision for Intelligent Healthcare focuses on the convergence of artificial intelligence, computer vision, and biomedical imaging to address challenges in modern healthcare. Over the past decade, deep learning and image understanding have revolutionized the way clinicians diagnose, monitor, and treat diseases — from early detection in radiology to precision-guided surgeries and real-time patient monitoring. This special track aims to bring together researchers, clinicians, engineers, and industry experts to discuss breakthroughs and emerging trends that empower medical imaging systems with intelligence, efficiency, and interpretability. It will serve as a venue to present novel algorithms, architectures, and applications that push the limits of visual computing in healthcare — emphasizing accuracy, explainability, and adaptability for real-world clinical environments. The track particularly encourages contributions that explore lightweight and TinyML-based models for embedded healthcare devices, federated and privacy-preserving learning, and real-time image or video analysis for diagnostic and monitoring systems. By connecting academia and industry, this track aims to strengthen collaboration toward AI-driven, patient-centered healthcare innovation.

Artificial Intelligence for Inclusion, Accessibility and Well-Being of Vulnerable Populations

Authors: Jose Luis Avila, Vanesa Cantón-Habas and Sebastián Ventura

This Special Track is focused on vulnerable populations, specifically older adults, children, persons with disabilities and patients with chronic or acute conditions and on how artificial intelligence (AI) can be designed, developed and deployedto improve their quality of life, autonomy, inclusion and well-being. We expect to receive contributions that present novel AI-based systems, assistive technologies, validated prototypes and field-evaluated applications in clinical, community or home care settings. By centring on inclusion, accessibility and vulnerable populations, this track offers a dedicated focus on socially impactful AI that complements broader themes of health and biomedical informatics.

Synthetic Healthcare Data Generation and Clinical Decision Support

Authors: Dimitris Iakovidis, Mary Maleckar and Vajira Thambawita

This special track on Synthetic Healthcare Data Generation and Clinical Decision Support (CDS) solicits novel and high-impact research focused on the generation, validation, and translational application of synthetic data for CDS. It welcomes submissions proposing novel SDG models applied to complex and diverse clinical data modalities. This includes, but is not limited to, structured electronic health records (EHRs), biosignals (e.g., ECG, EEG, PPG) radiological images (e.g., CT, MRI), endoscopic images, and histopathological and genomic data. It also welcomes novel methods and metrics for assessing synthetic data, covering aspects that include quality, credibility, fidelity, utility, diversity, and privacy. It aims to serve as an interactive workshop bringing together scientists from various disciplines related to this research field, to present advanced concepts in Synthetic Data Generation (SDG), to demonstrate the impact of SDG in the context of CDS, and to discuss best practices, open issues, and research perspectives.

Computational Intelligence in Medical Imaging (CIMI)

Authors: Saúl Zapotecas-Martínez and Diego Oliva

Computational intelligence (CI) in medical imaging is a rapidly growing field that leverages artificial intelligence (AI) techniques to analyze and process medical images, with the ultimate goal of enhancing diagnosis, early disease detection, and treatment monitoring. The most popular techniques and approaches in this field include the use of deep learning and Evolutionary Algorithms.  This track aims to generate implementations that present single or hybrid computational intelligence methods for solving problems in medical image processing and computer vision. The special track will be an excellent opportunity for researchers working on CI in medical imaging to exchange their recent ideas and investigations on this topic. In this respect, we welcome high-quality papers on the theoretical, developmental, implementational, and application of CI approaches in medical imaging. More specifically, the special track will encourage original research contributions that address new and existing IC approaches and related methodologies for use in the field of medical imaging. Thus, the topics of interest include (but are not limited to) the following: Image Segmentation, anomaly detection and Early Markers, Diagnosis and Classification, Image Registration, Computer-Aided Diagnosis (CAD), Synthetic Image Generation, and Integration with Clinical Data.

Management and Quality of Data Lifecycle in Health and Medicine

Authors: Evdokimos Konstantinidis, Panagiotis Bamidis and Despoina Petsani

Every day, vast amounts of health and medical data are generated—from hospital information systems and laboratory results to data collected through wearables, sensors, and mobile health applications. These diverse data sources hold enormous potential to improve healthcare services, enable personalized care, and foster evidence-based innovation. Yet, their full value remains largely untapped due to persistent challenges in data quality, interoperability, accessibility, ethical governance, and compliance with European legislation.

This special track focuses on the complete lifecycle of health and medical data, exploring how data can be responsibly collected, managed, shared, and reused to drive meaningful impact in healthcare. We invite researchers, clinicians, innovators, and policymakers to contribute approaches, frameworks, and case studies that demonstrate how real-world data can be transformed into actionable insights supporting research, clinical decision-making, and healthcare innovation.

Contributions are particularly encouraged to highlight practical experiences and solutions aligned with European frameworks such as the GDPR, the AI Act, and the European Health Data Space.