Melding artificial intelligence with organ-on-chip technology

Artificial intelligence and machine learning are transforming biomedical research, including in image analysis, drug discovery, and diagnostics. These tools are also poised to catapult organ-on-chip (OOC) platforms — three-dimensional in vitro spheroids and organoids that provide microenvironments for studying diseases, drugs, and therapeutic responses.

The datasets generated from OOC platforms — such as real-time biosensor outputs, and high-content imaging — are complex, noisy, and multi-dimensional, making them a natural target for analysis with AI and ML. Yet the development of these technologies has yet to progress synergistically, leading to missed opportunities for advancing OOC systems.

To facilitate a more coherent framework for developing AI/ML for use with OOC platforms, Khurana et al. present a foundational overview of the technologies that appeals to researchers from a range of backgrounds.

“This work aims to encourage closer integration between microfluidics, biology, computational modelling, and machine learning, while providing a structured perspective to help guide future developments toward more predictive and clinically relevant platforms for drug delivery,” said author Kiran Raj M. “It also seeks to inspire early-career researchers to engage with this rapidly evolving and interdisciplinary field.”

The review synthesizes current approaches to optimizing OOC systems and identifies key challenges such as data standardization and interpretability. The researchers expect that a deeper coupling between AI/ML and OOC systems in the coming years will allow for improved studies of drug responses and biological variability, which would accelerate advances in personalized medicine.

“What excites us the most is the steady convergence toward personalized and predictive medicine, where complex biological systems can be studied and interpreted in patient-specific terms instead of generalized models,” Raj M said.

Source: “Intelligent organ-on-chip platforms: Machine learning in predictive and personalized drug delivery,” by Tanishq Khurana, Sourav Ganguly, and Kiran Raj M., Biomicrofluidics (2026). The article can be accessed at https://doi.org/10.1063/5.0306883 .