Title:

Experiment Automation for an Electrochemical Sensor

The composition and properties of bodily fluids like saliva change in response to a variety of illnesses. Sepsis is one such illness that is expensive to diagnose using traditional methods. The SEEDS lab intends to use an electrochemical sensor combined with machine learning to diagnose sepsis (and other conditions) by leveraging the changes in bodily fluids composition and properties. To do this, they need to find the sensor surface that will best detect the properties of a fluid indicating sepsis. This involves running many experiments, each of which involves recording hours of data and spending all day managing the devices; time which would be better spent developing new surfaces and analyzing experiment results. Our goal is to create a robust automated experiment framework which will enable researchers to run more experiments in parallel, and to provide a data analysis application to expedite analyzing the experimental data. The automation will enable researchers to run roughly three times as many experiments per day, saving 20 minutes of researcher attention per experiment; researchers currently must manually toggle the pump which moves the fluid. The analysis application will similarly expedite processing the experiment data and deriving conclusions.

Name

Comment*

Comments are viewable only by submitter

Captcha*