Artificial intelligence is rapidly reshaping biosensor research, moving the field beyond conventional "design–fabricate–measure" workflows toward data-driven and increasingly autonomous sensing systems. AI now participates across the full biosensor pipeline: biomarker discovery, biorecognition element design, sensing-material screening, interface optimization, signal extraction, and diagnostic interpretation. In parallel, machine learning and deep learning have demonstrated concrete gains in immunosensor calibration, image-based particle counting, noise reduction, and multimodal data fusion—capabilities that are particularly consequential for low-abundance targets, wearable monitoring, and point-of-care testing. Recent work has begun to articulate a "fifth generation" of biosensors characterized by intelligent design, self-optimization, improved interference resistance, and closed-loop decision-making, signaling that AI is shifting from an auxiliary tool to a core functional component of biosensing systems. The primary goal of this special issue is to consolidate high-quality research that bridges artificial intelligence and biosensor engineering, and to clarify how AI can be embedded—rather than merely appended—across sensing material discovery, transducer design, signal processing, and end-use decision support.
We invite contributions that explore the broad theme of AI-integrated biosensing, with particular interest in interpretable and robust machine learning for complex biosensor signals, AI-assisted biorecognition and nanomaterial design, deep-learning-enabled imaging and digital immunoassays, and closed-loop or adaptive biosensing platforms for wearable and point-of-care applications. Submissions that report negative results, benchmark comparisons, or critical assessments of AI generalization in real-world biosensing conditions are also welcome, as they are essential for the field’s methodological maturation.
Potential topics include, but are not limited to:
- AI-assisted design of biorecognition elements (aptamers, peptides, antibodies) and sensing materials
- Machine learning for signal denoising, feature extraction, and calibration in electrochemical/optical biosensors
- Deep learning for image-based biosensing: digital ELISA, lateral flow assays, and particle counting
- Multimodal data fusion and uncertainty quantification in biosensor outputs
- AI-enabled wearable and real-time molecular monitoring
- Closed-loop and autonomous biosensing systems with adaptive decision-making
- Interpretable AI and generalization challenges in real-world biosensor deployment
- AI for point-of-care and resource-limited setting biosensing
Types of articles welcomed: Original research articles, review articles, case studies, benchmarking/methodological papers, and perspectives.
Through this special issue, we aim to provide a coherent reference point for the growing AI–biosensor interface, and to stimulate cross-disciplinary dialogue between sensor scientists, data scientists, and application-domain researchers. We welcome researchers from biomedical engineering, analytical chemistry, materials science, computer science, and clinical/agricultural diagnostics to contribute interdisciplinary perspectives. Your contributions will play a crucial role in advancing intelligent biosensing from proof-of-concept demonstrations toward robust, interpretable, and deployable technologies.