Rapid Prediction of Multidrug-Resistant Klebsiella pneumoniae through Deep Learning Analysis of SERS Spectra

Authors:
Open Access
Publisher website
Google Scholar
Abstract
This study focuses on the simultaneous discrimination and prediction ofKlebsiella pneumoniaestrains with carbapenem-sensitive, carbapenem-resistant, and polymyxin-resistant phenotypes. The implementation of CNN plus an attention mechanism makes the highest prediction accuracy at 99.46%, which confirms the diagnostic potential of the combination of SERS spectroscopy with the deep learning algorithm for antibacterial susceptibility testing in clinical settings.
Funding Information
  • National Natural Science Foundation of China (31900022)
  • Key Research and Development Project of Jiangsu Province (BE2020646)
  • Research Foundation for Advanced Talents of Guangdong Provincial People's hospitali (KJ012021097)
  • National Natural Science Foundation of China (81871734)
  • National Natural Science Foundation of China (82072380)
  • National Natural Science Foundation of China (82272423)
  • Jiang-Su Qing-Lan Project (2020)
  • Science and Technology Innovation Team of Young Scientists (TD202001)
  • Xuzhou Key R&D Plan Social Development Project (KC22300)

This publication has 50 references indexed in Scilit: