Rapid determination of Proteus mirabilis susceptibility to antibiotics using infrared spectroscopy in tandem with random forest |
| |
Authors: | Uraib Sharaha George Abu-Aqil Manal Suleiman Klaris Riesenberg Itshak Lapidot Mahmoud Huleihel Ahmad Salman |
| |
Affiliation: | 1. Department of Microbiology, Immunology and Genetics, Faculty of Health Sciences, Ben-Gurion University of the Negev, Beer-Sheva, Israel;2. Internal Medicine E, Soroka University Medical Center, Beer-Sheva, Israel;3. Department of Electrical and Electronics Engineering, ACLP-Afeka Center for Language Processing, Afeka Tel-Aviv Academic College of Engineering, Tel-Aviv, Israel;4. Department of Physics, SCE - Shamoon College of Engineering, Beer-Sheva, Israel |
| |
Abstract: | Bacterial infections cause serious illnesses that are treated with antibiotics. Currently used methods for detecting bacterial antibiotic susceptibility consume 48–72 h, leading to overuse of antibiotics. Thus, many bacterial species have acquired resistance to a broad range of available antibiotics. There is an urgent need to develop efficient methods for rapid determination of bacterial susceptibility to antibiotics. The combination of machine learning and Fourier-transform infrared (FTIR) spectroscopy has generated a promising diagnostic approach in medicine and biology. Our main goal is to examine the potential of FTIR spectroscopy to determine the susceptibility of urinary tract infection-Proteus mirabilis to a specific range of antibiotics, within about 20 min after 24 h culture and identification. We measured the infrared spectra of 489 different P. mirabilis isolates and used random forest to analyze this spectral database. A classification success rate of ~84% was achieved in differentiating between the resistant and sensitive isolates based on their susceptibility to ceftazidime, ceftriaxone, cefuroxime, cefuroxime axetil, cephalexin, ciprofloxacin, gentamicin, and sulfamethoxazole antibiotics in a time span of 24 h instead of 48 h. |
| |
Keywords: | antibiotics resistance infrared spectroscopy machine learning Proteus mirabilis urinary tract infections |
|
|