Droplet-based microfluidic devices hold immense potential in becoming inexpensive alternatives to existing screening platforms across life science applications, such as enzyme discovery and early cancer detection. However, the lack of a predictive understanding of droplet generation makes engineering a droplet-based platform an iterative and resource-intensive process. We present a web-based tool, DAFD, that predicts the performance and enables design automation of flow-focusing droplet generators. We capitalize on machine learning algorithms to predict the droplet diameter and rate with a mean absolute error of less than 10 μm and 20 Hz. This tool delivers a user-specified performance within 4.2% and 11.5% of the desired diameter and rate. We demonstrate that DAFD can be extended by the community to support additional fluid combinations, without requiring extensive machine learning knowledge or large-scale data-sets. This tool will reduce the need for microfluidic expertise and design iterations and facilitate adoption of microfluidics in life sciences.

In this review article, we surveyed the applications of machine learning in microfluidic design and microfluidic control.

In 2019, the first cases of SARS-CoV-2 were detected in Wuhan, China, and by early 2020 the cases were identified in the United States. SARS-CoV-2 infections increased in the US causing many states to implement stay-at-home orders and additional safety precautions to mitigate potential outbreaks. As policies changed throughout the pandemic and restrictions lifted, there was an increase in demand for Covid-19 testing which was costly, difficult to obtain, or had long turn-around times. Some academic institutions, including Boston University, created an on-campus Covid-19 screening protocol as part of planning for the safe return of students, faculty, and staff to campus with the option for in-person classes. At BU, we stood up an automated high-throughput clinical testing lab with the capacity to run 45,000 individual tests weekly by fall of 2020, with a purpose-built clinical testing laboratory, a multiplexed RT-PCR test, robotic instrumentation, and trained CLIA certified staff. There were challenges to overcome, including the supply chain issues for PPE testing materials, and equipment that were in high demand. The Boston University Clinical Testing Laboratory was operational at the start of the fall 2020 academic year. The lab performed over 1 million SARS-CoV-2 RT-PCR tests during the 2020-2021 academic year.

Electrode integration significantly increases the versatility of droplet microfluidics, enabling label-free sensing and manipulation at a single-droplet (single-cell) resolution. However, common fabrication techniques for integrating electronics into microfluidics are expensive,...