| Autor: |
Suleiman M; Department of Microbiology, Immunology, and Genetics, Faculty of Health Sciences, Ben-Gurion University of the Negev, Beer-Sheva 84105, Israel. mahmoudh@bgu.ac.il., Abu-Aqil G; Department of Microbiology, Immunology, and Genetics, Faculty of Health Sciences, Ben-Gurion University of the Negev, Beer-Sheva 84105, Israel. mahmoudh@bgu.ac.il., Lapidot I; Department of Electrical Engineering, ACLP-Afeka Center for Language Processing, Afeka Tel-Aviv Academic College of Engineering, Tel-Aviv 69107, Israel.; Laboratoire Informatique d'Avignon (LIA), Avignon Université, 339 Chemin des Meinajaries, 84000 Avignon, France., Huleihel M; Department of Microbiology, Immunology, and Genetics, Faculty of Health Sciences, Ben-Gurion University of the Negev, Beer-Sheva 84105, Israel. mahmoudh@bgu.ac.il., Salman A; Department of Physics, SCE - Shamoon College of Engineering, Beer-Sheva 84100, Israel. ahmad@sce.ac.il. |
| Abstrakt: |
Rapid testing of bacteria for antibiotic susceptibility is essential for effective treatment and curbing the emergence of multidrug-resistant bacteria. The misuse of antibiotics, coupled with the time-consuming classical testing methods, intensifies the threat of antibiotic resistance, a major global health concern. In this study, employing infrared spectroscopy-based machine learning techniques, we significantly shortened the time required for susceptibility testing to 10 hours, a significant improvement from the 24 hours in our previous studies as well as the conventional methods that typically take at least 48 hours. This remarkable reduction in turnaround time (from 48 hours to 10 hours), achieved by minimizing the culturing period, offers a game-changing advantage for clinical applications. Our study involves a dataset comprising 400 bacterial samples (200 E. coli , 100 Klebsiella pneumoniae , and 100 Pseudomonas aeruginosa ) with an impressive 96% accuracy in the taxonomic classification at the species level and up to 82% accuracy in bacterial susceptibility to various antibiotics. |
