FURI | Spring 2021

Using Machine Learning to Quantify Colorimetric Assays from Cell Phone Photos

Health icon, disabled. A red heart with a cardiac rhythm running through it.

Finding a method to objectively quantify results of colorimetric assays without special equipment is important to increasing the accessibility and portability of point-of-care testing. Point-of-care testing is inexpensive, has quick response times, and has numerous applications ranging from roadside alcohol testing to detecting infections such as COVID-19 or HPV. The focus of this study is to design a machine learning algorithm that can quantify the concentration of samples on colorimetric alcohol test strips from cell phone photos taken under non-standard conditions. The accuracy of this algorithm will be evaluated and is expected to be able to adequately provide quantitative results.

Student researcher

Rachel Fisher

Rachel Fisher

Biomedical engineering

Hometown: Gilbert, Arizona, United States

Graduation date: Spring 2021