Discriminating two bacteria via laser-induced breakdown spectroscopy and artificial neural network

Area of Science:

• Microbiology
• Analytical Chemistry
• Spectroscopy

Background:

• Accurate bacterial identification is crucial for clinical diagnosis and treatment of infections.
• Conventional methods for bacterial differentiation are often time-consuming and laborious.
• Laser-induced breakdown spectroscopy (LIBS) offers a modern approach for bacterial analysis.

Purpose of the Study:

• To discriminate between Pseudomonas aeruginosa and Proteus mirabilis using nano-enhanced LIBS (NELIBS).
• To improve the sensitivity and accuracy of LIBS for bacterial species differentiation.
• To evaluate the effectiveness of NELIBS combined with artificial neural networks (ANN) for rapid bacterial identification.

Main Methods:

• Utilized nano-enhanced laser-induced breakdown spectroscopy (NELIBS) with biogenic silver nanoparticles (AgNPs).
• Applied conventional laser-induced breakdown spectroscopy (LIBS) for comparison.
• Employed an artificial neural network (ANN) model for data analysis and differentiation assessment.

Main Results:

• NELIBS demonstrated superior differentiation between the two bacterial species compared to conventional LIBS.
• Identification was achieved by analyzing specific elemental spectral lines and their intensities.
• NELIBS provided higher sensitivity, more intense spectral lines, and increased detectable elements.

Conclusions:

• NELIBS combined with ANN successfully differentiates between Pseudomonas aeruginosa and Proteus mirabilis with high precision and speed.
• The NELIBS technique offers significant advantages over conventional microbiological methods, requiring minimal sample preparation.
• This approach enhances bacterial identification capabilities for clinical and research applications.