Rapid Detection of Urinary Tract Infection in 10 min by Tracking Multiple Phenotypic Features in a 30 s Large-Volume Scattering Video of Urine Microscopy

Fenni Zhang, Manni Mo, Jiapei Jiang, Xinyu Zhou, Michelle McBride, Yunze Yang, Kenta S. Reilly, Thomas E. Grys, Shelley E. Haydel, Nongjian Tao, Shaopeng Wang

Research output: Contribution to journalArticlepeer-review

Abstract

Rapid point-of-care (POC) diagnosis of bacterial infection diseases provides clinical benefits of prompt initiation of antimicrobial therapy and reduction of the overuse/misuse of unnecessary antibiotics for nonbacterial infections. We present here a POC compatible method for rapid bacterial infection detection in 10 min. We use a large-volume solution scattering imaging (LVSi) system with low magnifications (1-2×) to visualize bacteria in clinical samples, thus eliminating the need for culture-based isolation and enrichment. We tracked multiple intrinsic phenotypic features of individual cells in a short video. By clustering these features with a simple machine learning algorithm, we can differentiate Escherichia coli from similar-sized polystyrene beads, distinguish bacteria with different shapes, and distinguish E. coli from urine particles. We applied the method to detect urinary tract infections in 104 patient urine samples with a 30 s LVSi video, and the results showed 92.3% accuracy compared with the clinical culture results. This technology provides opportunities for rapid bacterial infection diagnosis at POC settings.

Original languageEnglish (US)
JournalACS Sensors
DOIs
StateAccepted/In press - 2022

Keywords

  • UTI screening
  • bacteria detection
  • machine learning
  • multiple phenotypic features
  • solution scattering imaging

ASJC Scopus subject areas

  • Bioengineering
  • Instrumentation
  • Process Chemistry and Technology
  • Fluid Flow and Transfer Processes

Cite this