Special Session 1: CONNECT- Collaborative Network for Next-generation Cardiorespiratory Technologies
Brief Description
Cardiorespiratory disease assessment continues to rely heavily on subjective interpretation of heart and lung sounds. Despite advances in biomedical signal processing, digital auscultation, and AI-enabled diagnostic tools, clinical practice still lacks standardised, sharable, and analysable data. This gap limits reproducibility, training, and technology translation into healthcare. CONNECT is an interdisciplinary initiative bridging academia, clinicians, and industry partners to advance next-generation cardiorespiratory technologies. This special session will showcase emerging methods, datasets, collaborative frameworks, and translational pathways that support a more open, interoperable, data-driven approach to heart and lung sound analysis. The session is designed to bring together experts in biomedical signal processing, machine learning, digital auscultation, clinical decision support, and real-world deployment. It highlights collaborative models that accelerate innovation and demonstrates how AI-driven acoustic analysis can improve diagnosis, training, and preventive medicine. The session aligns with IFSP’s goal of presenting cutting-edge research in signal processing and promotes a global dialogue on the technological, clinical, and practical challenges in building the next generation of cardiorespiratory diagnostic tools.
Session Organizer
Assoc. Prof. Wei Quan, University of Lancashire, United Kingdom
The topics of interest include, but are not limited to:
▪ Digital auscultation
and sensor technologies
▪ Cardiac and respiratory sound acquisition,
enhancement, segmentation, and
classification
▪ AI, deep learning and multimodal fusion
for clinical acoustic analysis
▪ Real-world evaluation of medical signal
processing algorithms
▪ Clinical decision support systems for
respiratory and cardiac diagnostics
▪ Explainable and trustworthy AI in
healthcare
▪ Data governance, interoperability, and
standardisation for biomedical signals
▪ Collaborative models between academia,
healthcare, and industry
▪ Applications in telemedicine, remote
monitoring, and digital health
Submission Method
Submit your Full Paper
(no less than 6 pages in length (one-column)) or
your paper abstract-without publication
(200-400 words) via
Online Submission
System, then choose Special Session
1 (CONNECT- Collaborative Network for Next-generation Cardiorespiratory Technologies )
Template
Download
Introduction of Session Organizer
Assoc. Prof. Wei Quan
University of Lancashire, United Kingdom
Bio: Dr Wei Quan is an Associate Professor in Computer Vision and
Machine Learning at the University of Lancashire and leads
interdisciplinary research in biomedical signal processing, machine
learning, digital health technologies, and non-contact sensing. He
has published over 40 peer-reviewed papers, receiving several
best-paper awards (ICPRAM 2015, ICIGP 2021, IFSP 2025). Dr Quan
leads projects in advanced cardiorespiratory sound analysis in
collaboration with UK NHS Trusts and industry partners, with a
research focus on translational AI for clinical diagnostics,
training, and decision support.
