Determination of Klebsiella pneumoniae Susceptibility to Antibiotics Using Infrared Microscopy

Significant reduction of the culturing time required for bacterial identification and antibiotic susceptibility determination by infrared spectroscopy

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.

Photoinduced force microscopy as a novel method for the study of microbial nanostructures

A detailed comparison of the capabilities of electron microscopy and nano-infrared (IR) microscopy for imaging microbial nanostructures has been carried out for the first time. The surface sensitivity, chemical specificity, and non-destructive nature of spectroscopic mapping is shown to offer significant advantages over transmission electron microscopy (TEM) for the study of biological samples. As well as yielding important topographical information, the distribution of amides, lipids, and carbohydrates across cross-sections of bacterial (Escherichia coli, Staphylococcus aureus) and fungal (Candida albicans) cells was demonstrated using PiFM. The unique information derived from this new mode of spectroscopic mapping of the surface chemistry and biology of microbial cell walls and membranes, may provide new insights into fungal/bacterial cell function as well as having potential use in determining mechanisms of antimicrobial resistance, especially those targeting the cell wall.

Quick Detection of Proteus and Pseudomonas in Patients' Urine and Assessing Their Antibiotic Susceptibility Using Infrared Spectroscopy and Machine Learning

Bacterial resistance to antibiotics is a primary global healthcare concern as it hampers the effectiveness of commonly used antibiotics used to treat infectious diseases. The development of bacterial resistance continues to escalate over time. Rapid identification of the infecting bacterium and determination of its antibiotic susceptibility are crucial for optimal treatment and can save lives in many cases. Classical methods for determining bacterial susceptibility take at least 48 h, leading physicians to resort to empirical antibiotic treatment based on their experience. This random and excessive use of antibiotics is one of the most significant drivers of the development of multidrug-resistant (MDR) bacteria, posing a severe threat to global healthcare. To address these challenges, considerable efforts are underway to reduce the testing time of taxonomic classification of the infecting bacterium at the species level and its antibiotic susceptibility determination. Infrared spectroscopy is considered a rapid and reliable method for detecting minor molecular changes in cells. Thus, the main goal of this study was the use of infrared spectroscopy to shorten the identification and the susceptibility testing time of Proteus mirabilis and Pseudomonas aeruginosa from 48 h to approximately 40 min, directly from patients' urine samples. It was possible to identify the Proteus mirabilis and Pseudomonas aeruginosa species with 99% accuracy and, simultaneously, to determine their susceptibility to different antibiotics with an accuracy exceeding 80%.

Detection of extended-spectrum β-lactamase-producing bacteria isolated directly from urine by infrared spectroscopy and machine learning

Resistant bacteria have become one of the leading health threats in the last decades. Extended-spectrum β-lactamase (ESBL) producing bacteria, including Escherichia (E.) coli and Klebsiella (K.) pneumoniae (the most frequent ones), are a significant class out of all resistant infecting bacteria. Due to the widespread and ongoing development of ESBL-producing (ESBL⁺) resistant bacteria, many routinely used antibiotics are no longer effective against them. However, an early and reliable ESBL⁺ bacteria detection method will improve the efficiency of treatment and limit their spread. In this work, we investigated the capability of infrared (IR) spectroscopy based machine learning tools [principal component analysis (PCA) and Random Forest (RF) classifier] for the rapid detection of ESBL⁺ bacteria isolated directly from patients' urine. For that, we examined 1881 E. coli samples (416 ESBL⁺ and 1465 ESBL^-) and 609 K. pneumoniae samples (237 ESBL⁺ and 372 ESBL^-). All samples were isolated directly from the urine of midstream patients. This study revealed that within 40 min of receiving the patient urine it is possible to determine the infecting bacterium as E. coli or K. pneumoniae with 95% success rate while it was possible to determine the ESBL⁺E. coli and ESBL⁺K. pneumoniae with 83% and 78% accuracy rates, respectively.

Instant detection of extended-spectrum β-lactamase-producing bacteria from the urine of patients using infrared spectroscopy combined with machine learning

Antibiotics are considered the most effective treatment against bacterial infections. However, most bacteria have already developed resistance to a broad spectrum of commonly used antibiotics, mainly due to their uncontrolled use. Extended-spectrum beta-lactamase (ESBL)-producing bacteria are an essential class of multidrug-resistant (MDR) bacteria. It is of extreme urgency to develop a method that can detect ESBL-producing bacteria rapidly for the effective treatment of patients with bacterial infectious diseases. Fourier transform infrared (FTIR) microscopy is a sensitive method that can rapidly detect cellular molecular changes. In this study, we examined the potential of FTIR spectroscopy-based machine learning algorithms for the rapid detection of ESBL-producing bacteria obtained directly from a patient's urine. Using 591 ESBL-producing and 1658 non-ESBL-producing samples of Escherichia coli (E. coli) and Klebsiella pneumoniae, our results show that the FTIR spectroscopy-based machine learning approach can identify ESBL-producing bacteria within 40 minutes from receiving a patient's urine sample, with a success rate of 80%.

Rapid determination of Proteus mirabilis susceptibility to antibiotics using infrared spectroscopy in tandem with random forest

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.

Fast identification and susceptibility determination of E. coli isolated directly from patients' urine using infrared-spectroscopy and machine learning

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.

Rapid Identification and Classification of Pathogens That Produce Carbapenemases and Cephalosporinases with a Colorimetric Paper-Based Multisensor

Infections caused by bacteria that produce β-lactamases (BLs) are a major problem in hospital settings. The phenotypic detection of these bacterial strains requires culturing samples prior to analysis. This procedure may take up to 72 h, and therefore it cannot be used to guide the administration of the first antibiotic regimen. Here, we propose a multisensor for identifying pathogens bearing different types of β-lactamases above the infectious dose threshold within 90 min that does not require culturing samples. Instead, bacterial cells are preconcentrated in the cellulose scaffold of a paper-based multisensor. Then, 12 assays are performed in parallel to identify whether the pathogens produce carbapenemases and/or cephalosporinases, including metallo-β-lactamases, extended-spectrum β-lactamases (ESBLs), and AmpC enzymes. The multisensor generates an array of colored spots that can be quantified with image processing software and whose interpretation leads to the detection of the different enzymes depending on their specificity toward the hydrolysis of certain antibiotics, and/or their pattern of inhibition or cofactor activation. The test was validated for the diagnosis of urinary tract infections. The inexpensive paper platform along with the uncomplicated colorimetric readout makes the proposed prototypes promising for developing fully automated platforms for streamlined clinical diagnosis.

Infra-red spectroscopy combined with machine learning algorithms enables early determination of Pseudomonas aeruginosa's susceptibility to antibiotics

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%.

Culture-independent susceptibility determination of E. coli isolated directly from patients’ urine using FTIR and machine-learning

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