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

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.

Infrared spectroscopy-based machine learning algorithms for rapid detection of Klebsiella pneumoniae isolated directly from patients' urine and determining its susceptibility to antibiotics

Among the most prevalent and detrimental bacteria causing urinary tract infections (UTIs) is Klebsiella (K.) pneumoniae. A rapid determination of its antibiotic susceptibility can enhance patient treatment and mitigate the spread of resistant strains. In this study, we assessed the viability of using infrared spectroscopy-based machine learning as a rapid and precise approach for detecting K. pneumoniae bacteria and determining its susceptibility to various antibiotics directly from a patient's urine sample. In this study, 2333 bacterial samples, including 636 K. pneumoniae were investigated using infrared micro-spectroscopy. The obtained spectra (27996spectra) were analyzed with XGBoost classifier, achieving a success rate exceeding 95 % for identifying K. pneumoniae. Moreover, this method allows for the simultaneous determination of K. pneumoniae susceptibility to various antibiotics with sensitivities ranging between 74 % and 81 % within approximately 40 min after receiving the patient's urine sample.

Fluorescence Spectroscopy Based Identification of Pseudomonas Aeruginosa and Escherichia Coli Suspensions

In this article, Fluorescence spectroscopy has been employed for the identification of Pseudomonas aeruginosa (PA) and Escherichia coli (E. coli) in water suspension. Emission spectra of PA and E. coli suspensions have been acquired by using excitation wavelengths from 270 to 420 nm with steps of 10 nm to explore their spectral features. It has been found that the emission spectra of tryptophan, tyrosine, NADH and FAD, being the intracellular biomolecules present in both bacteria, can be used as fingerprints for their identification, differentiation and quantification. Both bacterial strains can clearly be differentiated from water and from each other by using λex 270-290 nm through spectral analysis and from λex: 300-500 nm by applying statistical analysis. Furthermore, calibration curves for different bacterial loads of PA and E. coli suspensions have been produced between colonies forming units per ml (CFUs/ml) the integrated intensities of their emission spectra. CFUs/ml of both bacterial suspensions have been determined through plate count method which was used as cross-reference for the analysis of emission spectra of both bacterial suspensions. These curves may be used to estimate CFU/ml of both PA and E. coli in unknown water suspensions by determining the integrating intensity of their emission spectra.

Antimicrobial susceptibility testing using infrared attenuated total reflection (IR-ATR) spectroscopy to monitor metabolic activity

Fast and accurate detection of antimicrobial resistance in pathogens remains a challenge, and with the increase in antimicrobial resistance due to mis- and overuse of antibiotics, it has become an urgent public health problem. We demonstrate how infrared attenuated total reflection (IR-ATR) can be used as a simple method for assessment of bacterial susceptibility to antibiotics. This is achieved by monitoring the metabolic activities of bacterial cells via nutrient consumption and using this as an indicator of bacterial viability. Principal component analysis of the obtained spectra provides a tool for fast and simple discrimination of antimicrobial resistance in the acquired data. We demonstrate this concept using four bacterial strains and four different antibiotics, showing that the change in glucose concentration in the growth medium after 2 h, as monitored by IR-ATR, can be used as a spectroscopic diagnostic technique, to reduce detection time and to improve quality in the assessment of antimicrobial resistance in pathogens.

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.

Online detection of concentrate grade in the antimony flotation process based on in situ Raman spectroscopy combined with a CNN-GRU hybrid model

Froth flotation is the most critical process for separating stibnite from raw ore. Concentrate grade is a vital production indicator in the antimony flotation process. It is a direct reflection of the product quality of the flotation process and an essential basis for the dynamic adjustment of its operating parameters. Existing methods of measuring concentrate grades suffer from expensive measurement equipment, difficult maintenance of complex sampling systems, and extended testing times. This paper presents a nondestructive and fast methodology to quantify the concentrate grade in the antimony flotation process based on in situ Raman spectroscopy. A particular Raman spectroscopic measuring system is designed for on-line measurement of the Raman spectra of the mixed minerals from the froth layer during the antimony flotation process. To obtain representative Raman spectra that better characterize the concentrate grades, a traditional Raman spectroscopic system has been redesigned to account for the different interferences during actual flotation field acquisition. A one-dimensional convolutional neural network (1D-CNN) is combined with a gated recurrent unit (GRU) and applied to construct a model for online prediction of concentrate grades based on continuously collected Raman spectra of mixed minerals in the froth layer. With an average prediction error of 4.37% and a maximum prediction deviation of 10.56%, the quantitative analysis of concentrate grade by the model demonstrates that our method is distinguished by high accuracy, low deviation, and in situ analysis, and it essentially satisfies the requirements for online quantitative determination of concentrate grade in the antimony flotation site.