Integrating Artificial Intelligence in the Design Automation of Microfluidic Platforms

Artificial intelligence is increasingly transforming microfluidic and lab-on-a-chip development for diagnostics, biosensing, drug delivery, and wearable/point-of-care technologies. However, microfluidic device design remains largely expert-driven and iterative, relying on repeated CAD revisions, CFD simulations, and experimental prototyping, making it slow to optimize complex geometries, interfaces, and operating conditions. While recent advances in machine learning, deep learning, and computer vision have enabled promising tools for design-space exploration, geometry optimization, predictive modeling, and image-based performance assessment, fully integrated, end-to-end AI workflows for automated microfluidic design and operation are still underdeveloped.This Research Topic welcomes experimental, computational, and translational contributions that advance AI-enabled design, analysis, and optimization of microfluidic platforms, with a clear emphasis on methods that outperform or meaningfully augment traditional manual pipelines. Contributions may include (but are not limited to):• Automated AI/ML-based design and optimization tools for capillary and droplet microfluidics• Deep learning and computer vision for segmentation, flow-path detection, monitoring, and quality control• Hybrid frameworks combining CFD/physics-based modeling with data-driven learning and optimization• AI-enabled control strategies for self-powered, wearable, or autonomous microfluidic devices• AI for point-of-care diagnostics and biosensing (including electrochemical and MIP-based sensing workflows)• Benchmark datasets, reproducible pipelines, and evaluation standards for AI in microfluidic design• Case studies demonstrating clinically relevant or resource-limited deployment Topic editors: Azam Zare, Abhishek Raj Source: https://www.frontiersin.org/research-topics/78810/integrating-artificial-intelligence-in-the-design-automation-of-microfluidic-platforms