Search

Early detection of ESBL-producing bacteria is crucial for effective and accurate treatment and simultaneously limits the development and spread of MDR bacteria.

One of the most common human bacterial infections is the urinary tract infection (UTI).

Klebsiella pneumoniae (K. pneumoniae) is one of the most aggressive multidrug-resistant bacteria associated with human infections, resulting in high mortality and morbidity. We obtained 1190 K. pneumoniae isolates from different patients with urinary tract infections. The isolates were measured to determine their susceptibility regarding nine specific antibiotics. This study's primary goal is to evaluate the potential of infrared spectroscopy in tandem with machine learning to assess the susceptibility of K. pneumoniae within approximately 20 min following the first culture. Our results confirm that it was possible to classify the isolates into sensitive and resistant with a success rate higher than 80% for the tested antibiotics. These results prove the promising potential of infrared spectroscopy as a powerful method for a K. pneumoniae susceptibility test.

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.

Antimicrobial drugs have played an indispensable role in decreasing morbidity and mortality associated with infectious diseases. However, the resistance of bacteria to a broad spectrum of commonly-used antibiotics has grown to the point of being a global health-care problem. One of the most important classes of multi-drug resistant bacteria is Extended Spectrum Beta-Lactamase-producing (ESBL+) bacteria. This increase in bacterial resistance to antibiotics is mainly due to the long time (about 48 h) that it takes to obtain lab results of detecting ESBL-producing bacteria. Thus, rapid detection of ESBL+ bacteria is highly important for efficient treatment of bacterial infections. In this study, we evaluated the potential of infrared microspectroscopy in tandem with machine learning algorithms for rapid detection of ESBL-producing Klebsiella pneumoniae (K. pneumoniae) obtained from samples of patients with urinary tract infections. 285 ESBL+ and 365 ESBL-K. pneumoniae samples, gathered from cultured colonies, were examined. Our results show that it is possible to determine that K. pneumoniae is ESBL+ with ∼89% accuracy, ∼88% sensitivity and ∼89% specificity, in a time span of ∼20 minutes following the initial culture.

For effective treatment, it is crucial to identify the infecting bacterium at the species level and to determine its antimicrobial susceptibility. This is especially true now, when numerous bacteria have developed multidrug resistance to most commonly used antibiotics. Currently used methods need ∼ 48 h to identify a bacterium and determine its susceptibility to specific antibiotics. This study reports the potential of using infrared spectroscopy with machine learning algorithms to identify E. coli isolated directly from patients' urine while simultaneously determining its susceptibility to antibiotics within ∼ 40 min after receiving the patient's urine sample. For this goal, 1,765 E. coli isolates purified directly from urine samples were collected from patients with urinary tract infections (UTIs). After collection, the samples were tested by infrared microscopy and analyzed by machine learning. We achieved success rates of ∼ 96% in isolate level identification and ∼ 84% in susceptibility determination.

Physicians diagnose subjectively the etiology of inaccessible infections where sampling is not feasible (such as, pneumonia, sinusitis, cholecystitis, peritonitis), as bacterial or viral. The diagnosis is based on their experience with some medical markers like blood counts and medical symptoms since it is harder to obtain swabs and reliable laboratory results for most cases. In this study, infrared spectroscopy with machine learning algorithms was used for the rapid and objective diagnosis of the etiology of inaccessible infections and enables an assessment of the error for the subjective diagnosis of the etiology of these infections by physicians. Our approach allows for diagnoses of the etiology of both accessible and inaccessible infections as based on an analysis of the innate immune system response through infrared spectroscopy measurements of white blood cell (WBC) samples. In the present study, we examined 343 individuals involving 113 controls, 89 inaccessible bacterial infections, 54 accessible bacterial infections, 60 inaccessible viral infections, and 27 accessible viral infections. Using our approach, the results show that it is possible to differentiate between controls and infections (combined bacterial and viral) with 95% accuracy, and enabling the diagnosis of the etiology of accessible infections as bacterial or viral with94% sensitivity and90% specificity within one hour after the collection of the blood sample with error rate6%. Based on our approach, the error rate of the physicians' subjective diagnosis of the etiology of inaccessible infections was found to be23%.

Bacterial infections are significant causes of serious human health problems. Different bacterial pathogens might have similar symptoms, and it is important to detect the cause of the infection early in order to enable effective treatment. In many infections, a mixture of different bacteria might exist in the same tested sample. To treat such infections effectively, it is very important to identify the various types of infecting bacteria in the sample. In this pioneering study, we examined the potential of Fourier transform infrared (FTIR) microscopy for accurate identification and differentiation between different bacteria in experimentally mixed samples of bacteria in the genus level in time span of about 30 min. We have measured the FTIR spectra of bacteria in pure form as well as in various mixtures. Principal components analysis (PCA) was applied on the spectra of various classes, followed by linear discriminant analysis (LDA) as a linear classifier. Our results show that it is possible to differentiate between mixed categories of bacteria with high rates of success. The classification rate was higher when the mixed samples included Gram-positive and Gram-negative types. When the mixing range was comparable ([0.5,0.5] and [0.6,0.4]), a classification success rate > 95% was achieved using only the first 20 PCs.

Pseudomonas (P.) aeruginosa is a bacterium responsible for severe infections that have become a real concern in hospital environments. Nosocomial infections caused by P. aeruginosa are often hard to treat because of its intrinsic resistance and remarkable ability to acquire further resistance mechanisms to multiple groups of antimicrobial agents. Thus, rapid determination of the susceptibility of P. aeruginosa isolates to antibiotics is crucial for effective treatment. The current methods used for susceptibility determination are time-consuming; hence the importance of developing a new method. Fourier-transform infra-red (FTIR) spectroscopy is known as a rapid and sensitive diagnostic tool, with the ability to detect minor abnormal molecular changes including those associated with the development of antibiotic- resistant bacteria. The main goal of this study is to evaluate the potential of FTIR spectroscopy together with machine learning algorithms, to determine the susceptibility of P. aeruginosa to different antibiotics in a time span of ∼20 min after the first culture. For this goal, 590 isolates of P. aeruginosa, obtained from different infection sites of various patients, were measured by FTIR spectroscopy and analyzed by machine learning algorithms. We have successfully determined the susceptibility of P. aeruginosa to various antibiotics with an accuracy of 82-90%.