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

Srisruthi Udayakumar



Job Title

Research Trainee

Academic Rank




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

Principal Investigator

Hadi Shafiee

Research Category: Opioid


Scientific Abstract

Background: 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.
Methods: 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.
Results: 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.
Conclusion: We developed the first deep learning assisted POC fentanyl detection with high sensitivity and accuracy.

Lay Abstract

Fentanyl is a powerful synthetic opioid that has been widely prescribed for pain medication for cancer and chronic pain patients since the 1990s. Apart from the treatment purpose, fentanyl is also the leading cause of death from drug overdoses in the United States. Since fentanyl is estimated to be at least 50 to 100 times more potent than morphine, administration, and monitoring of fentanyl is a great challenge in clinical and forensic laboratories. Inaccurate detection of fentanyl can lead to several complications, and therefore, it is important to quickly diagnose fentanyl levels, so that rapid and appropriate levels of opioid antagonists can be administered and an adequate level of clinical treatment can be provided. Though the conventional detection methods provide sensitive detection of fentanyl in biological samples, the complex instrumentation and the laborious multistep processes limit the use of such methods for point-of-care purposes. There is an urgent clinical need for diagnostic tools to detect fentanyl with high sensitivity, ease of use for end-users, and rapid turnaround time for analysis. We have developed a portable, rapid, and user-friendly bubbling fentanyl assay with a smartphone as the readout and data analyzing device.

Clinical Implications

Fentanyl is a major drug implicated in the current opioid overdose epidemic worldwide. Accurate, sensitive, and rapid detection of fentanyl levels in the patient samples is essential to control drug abuse and provide appropriate treatment.