Intelligent Microfluidics: The Convergence of Machine Learning and Microfluidics in Materials Science and Biomedicine

Summary Microfluidics permit the automated manipulation of fluids at the microscale with high throughput and spatiotemporal precision, enabling the generation of large, multidimensional datasets. Machine intelligence provides powerful predictive tools with the ability to learn from data. The analysis of microfluidics-generated data via machine learning has been applied in a variety of contexts, achieving impressive results. Here, we elaborate on the potential of operating microfluidic platforms via closed-loop data-driven models by leveraging multimodal monitoring and data-acquisition instrumentation. We believe this approach will provide a robust framework for fundamental explorations in materials science and biomedicine, with implications in fields such as drug discovery, nanomaterials, in vitro organ modeling, and developmental biology. We identify challenges and propose research strategies in the context of the prediction and optimization of chemical reactions and materials syntheses and the development of the next generation of more robust and functional organs-on-chips and emerging organoids-on-chips.