Brigham Research Institute Poster Session Site logo-1
Close this search box.

Srisruthi Udayakumar, B.Tech




Research Trainee




Research Trainee




Hui Chen, Sungwan Kim, Joseph Michael Hardie, Manoj Kumar Kanakasabapathy, Supriya Gharpure, Prudhvi Thirumalaraju, Sahar Rostamian, Srisruthi Udayakumar, Qingsong Lei, Gi-Won Cho, and Hadi Shafiee*

Deep learning-assisted sensitive detection of fentanyl using a bubbling-microchip

As a student researcher, I am currently working in a translational research lab and my research interest focuses on developing novel point-of-care devices and diagnostics for the detection of chemical adulterants and infectious diseases. I believe that participating in the WMSS will not just allow me to showcase my contribution as a researcher to the scientific community, but also learn and get inspired by the great research that my woman colleagues are into. It is very important to participate in this symposium as it encourages and promotes the extraordinary accomplishments of women in research.


Fentanyl centered opioid overdose epidemic is afflicting the United States and worldwide. To address this crisis, point-of-care (POC) fentanyl testing is among critical health intervention tools, providing insights into its diffusion among populations. Deep learning-enabled image processing has significant applications in point-of-care diagnostics. However, the generalizability of traditional supervised convolutional neural networks may be precluded by the need for large, specialist-annotated training datasets.


We used a combination of smartphone-based bubbling microchips and catalytic platinum nanoparticles (PtNPs) to achieve high analytical sensitivity. We trained the network using a limited dataset of 104 images with known fentanyl concentrations and a retrospective library of 17,573 images, including 16,000 images synthetically generated through an adversarial neural network.


Fentanyl at concentrations as low as 0.23 ng/mL in phosphate buffered saline, 0.43 ng/mL in human serum and 0.64 ng/mL in artificial human urine can be detected. Classifier accuracy, using a cutoff concentration of 1 ng/mL, was 95.55% in PBS; 90.5% in human serum; and 90.63% in artificial human urine.


We developed the first deep learning assisted POC fentanyl detection with high sensitivity and accuracy.