Intelligent Organ-on-Chip (OoC) Systems: Integrating Artificial Intelligence in OoC models for Predictive, Adaptive, and Translational Bioengineering
Organ-on-chip (OoC) technologies have emerged as powerful microphysiological systems capable of recapitulating in vitro key aspects of human tissue structure and function. As these platforms increase in biological and architectural complexity, they generate high-dimensional, multimodal datasets that challenge conventional analysis and modeling approaches. In parallel, advances in artificial intelligence (AI), machine learning, and data-driven modeling are reshaping how complex engineered biological systems are designed, interpreted, and optimized.
The convergence of AI and OoC technologies offers an opportunity to move beyond descriptive in vitro models toward predictive and adaptive microphysiological platforms. AI methodologies can inform device design, guide experimental optimization, enable real-time control of microenvironments, and extract mechanistic and translational insights from integrated imaging, biosensing, and omics data.
This Special Topic seeks contributions that advance the conceptual and technological integration of AI within the OoC ecosystem—from computational modeling and digital twins to data-driven pharmacology and precision medicine applications. By fostering interdisciplinary dialogue, this collection aims to define the emerging framework of intelligent OoC systems and accelerate their impact on biomedical research and therapeutic development.
Topics covered include, but are not limited to:
- AI-assisted design and optimization of organ-on-chip platforms
- AI-assisted microfabrication and materials optimization
- Data-driven modeling of microphysiological systems
- Multiscale modeling of microphysiological systems
- Computational modeling of microenvironmental dynamics
- Hybrid mechanistic–machine learning models
- Digital twins and virtual OoC platforms
- Multimodal data integration (imaging, biosensors, omics)
- Real-time monitoring and adaptive control strategies
- Closed-loop microenvironment regulation
- Deep learning for high-content phenotypic analysis
- Predictive pharmacology and toxicology using OoC and AI
- Reinforcement learning for experimental optimization
- Physics-informed neural networks in microfluidics and tissue modeling
- Standardization, benchmarking, and reproducibility through AI
- Personalized and patient-specific OoC platforms
- Translational modeling from chip to clinic
- AI-enabled frameworks for preclinical-to-clinical translation and outcome prediction
Guest Editors
Paola Occhetta (Politecnico di Milano)
Liliana Moreira Teixeira (University of Twente)
Eugenio Martinelli (Università degli Studi di Roma Tor Vergata)