AI & Machine Learning Sensing Systems for Biomedical Applications

Artificial intelligence and machine learning methods are finding growing use in biomedical sensing systems to enhance the accuracy and reliability of measurements. Advances in neural networks, low-power computing hardware, and sensor fabrication methods have enabled the integration of data-driven models into various types of sensors. These methods are now being used to improve signal-to-noise ratios, automate analyte classification, and enhance the performance of electrochemical biosensors, optical sensors, wearable sensors, and point-of-care diagnostic devices.

In parallel, the combination of AI with advanced microscopy, image-based sensing, and single-cell encapsulation technologies (e.g., microfluidic platforms) is creating new opportunities for highly sensitive biomedical analysis. These approaches can enable single-cell-level detection, low-abundance analyte sensing, and automated extraction of complex phenotypic or functional information from imaging and sensor data.

This themed collection focuses on recent developments in the application of AI and machine learning to biomedical sensing. The journal encourages original research articles and reviews that consider the application of new algorithms, hardware–software integration methods, and validation studies that advance translation to clinical use. Submissions should align with the scope of Sensors & Diagnostics, including the requirement for experimental validation in real-world or clinically relevant samples (or suitably complex matrices). Studies based solely on simulated data or model systems without experimental sensing validation are out of scope.

We welcome submissions on the following topics:

• Machine Learning Methods for Biosensor Signal Processing 
• Deep Learning for Biomedical Sensor Analysis
• AI-Enabled Microscopy and Image-Based Biomedical Sensing
• Single-Cell and Low-Abundance Detection Using Microfluidic and Encapsulation Platforms
• Multimodal Sensor Data Fusion 
• Edge Computing for Point-of-Care Devices
• Digital Twins and Predictive Models for Physiological Monitoring
• Benchmarking and Validation Approaches
• Translational Challenges

You are welcome to submit articles on the above mentioned themes. Sensors & Diagnostics is dedicated to publishing and disseminating the most exceptionally significant, breakthrough findings of interest to the sensors and diagnostics community. For more information on the journal scope, standards, article types and author guidelines, visit our Sensors & Diagnostics journal page.

If you would like to contribute to this themed issue, you can submit your article directly through the Sensors & Diagnostics journal page and inform the editorial office by emailing our team. Please mention that this submission is a contribution to “AI & Machine Learning Sensing Systems for Biomedical Applications”, in the ‘Themed issues’ section of the submission form and add a ‘Note to the Editor’ that this is from the Open Call. The Editorial Office reserves the right to check suitability of submissions in relation to the scope of the collection and inclusion of accepted articles in the collection is not guaranteed.

Please note that all submissions are subject to the journal’s normal peer review processes, with an initial assessment to confirm the manuscript's suitability for full peer review. If you have any questions about the journal or the collection, please email us.  We would be happy to answer them.