Microsystem Advances through Integration with Artificial Intelligence

Abstract

Microfluidics is a rapidly growing discipline that involves studying and manipulating fluids at reduced length scale and volume, typically on the scale of micro- or nanoliters. Under the reduced length scale and larger surface-to-volume ratio, advantages of low reagent consumption, faster reaction kinetics, and more compact systems are evident in microfluidics. However, miniaturization of microfluidic chips and systems introduces challenges of stricter tolerances in designing and controlling them for interdisciplinary applications. Recent advances in artificial intelligence (AI) have brought innovation to microfluidics from design, simulation, automation, and optimization to bioanalysis and data analytics. In microfluidics, the Navier-Stokes equations, which are partial differential equations describing viscous fluid motion that in complete form are known to not have a general analytical solution, can be simplified and have fair performance through numerical approximation due to low inertia and laminar flow. Approximation using neural networks trained by rules of physical knowledge introduces a new possibility to predict the physicochemical nature. The combination of microfluidics and automation can produce large amounts of data, where features and patterns that are difficult to discern by a human can be extracted by machine learning. Therefore, integration with AI introduces the potential to revolutionize the microfluidic workflow by enabling the precision control and automation of data analysis. Deployment of smart microfluidics may be tremendously beneficial in various applications in the future, including high-throughput drug discovery, rapid point-of-care-testing (POCT), and personalized medicine. In this review, we summarize key microfluidic advances integrated with AI and discuss the outlook and possibilities of combining AI and microfluidics.

Keywords: artificial intelligence; lab-on-a-chip; machine learning; micro total analysis system; microfluidic device; personalized medicine.

Figure 2

Selected examples of AI-enhanced smart platforms and automation. (a) A CNN framework to predict the outcome of flow sculpturing by micropillar microstructures [27]. Reproduced under Creative Commons Attribution 4.0 International license (CC–BY). (b) A DNN to predict particle patterning by surface acoustic waves in a shape library was proposed by Raymond et al. [64]. Reproduced under CC–BY license. (c) Machine-learning-empowered design automation of droplet microfluidics channel [34]. Reproduced under CC–BY license. (d) Machine-learning-assisted classification for droplet manipulation in a magnetic digital microfluidic platform [65]. Reproduced under CC–BY license.

Figure 3

Microfluidics integrated with machine learning for process optimization and drug discovery. (a) An automated microfluidic system for automated optimization of chemical synthesis. Reprinted with permission from [103]. Copyright 2010 American Chemical Society. The font size have been adjusted for sake of clarity. (b) A droplet microfluidic platform combined with AI for synthesizing poly(Lactide-co-glycolide) microparticles from precipitating out of dichloromethane (DCM) [119]. Reproduced under CC–BY license. The figure has been reproduced for sake of clarity. (c) Two-step drug synthesis microfluidic platform with machine learning optimization [110]. Reproduced under CC–BY license. (d) A micromixer microfluidic platform combined with generative AI for de novo drug design and synthesis [121]. Reproduced under CC BY–NC (noncommercial) license.

Figure 4

Micro- total analysis systems integrated with machine learning for clinical diagnostics. (a) A compact programmable microfluidic platform capable of performing multiplex immunoassay for POCT applications. Reprinted with permission from [150]. Copyright 2016 American Chemical Society. (b) A digital ELISA microarray for cytokine quantification with CNN-guided image processing. Reprinted with permission from [151] with permission from Elsevier. (c) A microfluidic platform with a convolutional neural network to predict drug efficacy based on the viability of cultured cancer spheres. Reprinted with permission from [171]. Copyright 2019 American Chemical Society. (d) A wearable sensor platform with AI data analysis for motion classification [172]. Reproduced under CC–BY license.

Figure 5

Microsystems integrated with AI for cell analysis. (a) An optofluidic time-stretch QPI cell sorter based on high-speed, label-free cell classification and sorting empowered by deep learning [213]. Reproduced under CC–BY license. (b) Frequency-multiplexed microscopy coupled with real-time machine learning processing and piezoelectric actuator for high-speed cell sorting. Reprinted from [226] with permission from Elsevier. (c) A microfluidic cell trap with AI phenotype prediction for yeast division tracking and survival analysis [250]. Reproduced under CC–BY license. (d) A deep learning framework to automatically classify cell cycles and track lineage trees [265]. Reproduced under CC–BY license.

Figure 6

Organ-on-chip platforms integrated with AI analysis. (a) A bone-on-chip for osteoporosis drug testing and development [298]. Reproduced under CC–BY license. (b) A blood–brain niche OoC for predicting the metastatic probability of brain cancer [299,300]. Adapted with permission from [300]. (c) A muscle-on-chip with AI image analysis for quantitative understanding of muscular cell phenotypes. Reprinted with permission from [302]. (d) An OoC to reconstitute immunocompetent tumor microenvironment in breast cancer [305,306]. Reproduced under CC–BY license. (e) A skin-on-chip for predicting adverse cutaneous drug reactions [301]. Components in the figure were designed by macrovector; brgfx/Freepik.

Figure 1

Diagram of microfluidic applications integrated with artificial intelligence (AI). μTAS stands for micro-total analysis systems.