Detection of Helicobacter pylori Infection in Human Gastric Fluid Through Surface-Enhanced Raman Spectroscopy Coupled With Machine Learning Algorithms.

Diagnostic methods for Helicobacter pylori infection include, but are not limited to, urea breath test, serum antibody test, fecal antigen test, and rapid urease test. However, these methods suffer drawbacks such as low accuracy, high false-positive rate, complex operations, invasiveness, etc. Therefore, there is a need to develop simple, rapid, and noninvasive detection methods for H. pylori diagnosis. In this study, we propose a novel technique for accurately detecting H. pylori infection through machine learning analysis of surface-enhanced Raman scattering (SERS) spectra of gastric fluid samples that were noninvasively collected from human stomachs via the string test. One hundred participants were recruited to collect gastric fluid samples noninvasively. Therefore, 12,000 SERS spectra (n = 120 spectra/participant) were generated for building machine learning models evaluated by standard metrics in model performance assessment. According to the results, the Light Gradient Boosting Machine algorithm exhibited the best prediction capacity and time efficiency (accuracy = 99.54% and time = 2.61 seconds). Moreover, the Light Gradient Boosting Machine model was blindly tested on 2,000 SERS spectra collected from 100 participants with unknown H. pylori infection status, achieving a prediction accuracy of 82.15% compared with qPCR results. This novel technique is simple and rapid in diagnosing H. pylori infection, potentially complementing current H. pylori diagnostic methods.

Differentiation of closely-related species within Acinetobacter baumannii-calcoaceticus complex via Raman spectroscopy: a comparative machine learning analysis.

Bacterial species within the Acinetobacter baumannii-calcoaceticus (Acb) complex are very similar and are difficult to discriminate. Misidentification of these species in human infection may lead to severe consequences in clinical settings. Therefore, it is important to accurately discriminate these pathogens within the Acb complex. Raman spectroscopy is a simple method that has been widely studied for bacterial identification with high similarities. In this study, we combined surfaced-enhanced Raman spectroscopy (SERS) with a set of machine learning algorithms for identifying species within the Acb complex. According to the results, the support vector machine (SVM) model achieved the best prediction accuracy at 98.33% with a fivefold cross-validation rate of 96.73%. Taken together, this study confirms that the SERS-SVM method provides a convenient way to discriminate between A. baumannii, Acinetobacter pittii, and Acinetobacter nosocomialis in the Acb complex, which shows an application potential for species identification of Acinetobacter baumannii-calcoaceticus complex in clinical settings in near future.

Rapid Detection of Bacterial Pathogens Causing Lower Respiratory Tract Infections via Microfluidic-Chip-Based Loop-Mediated Isothermal Amplification.

Respiratory tract infections (RTIs) are among the most common problems in clinical settings. Rapid and accurate identification of bacterial pathogens will provide practical guidelines for managing and treating RTIs. This study describes a method for rapidly detecting bacterial pathogens that cause respiratory tract infections via multi-channel loop-mediated isothermal amplification (LAMP). LAMP is a sensitive and specific diagnostic tool that rapidly detects bacterial nucleic acids with high accuracy and reliability. The proposed method offers a significant advantage over traditional bacterial culturing methods, which are time-consuming and often require greater sensitivity for detecting low levels of bacterial nucleic acids. This article presents representative results of K. pneumoniae infection and its multiple co-infections using LAMP to detect samples (sputum, bronchial lavage fluid, and alveolar lavage fluid) from the lower respiratory tract. In summary, the multi-channel LAMP method provides a rapid and efficient means of identifying single and multiple bacterial pathogens in clinical samples, which can help prevent the spread of bacterial pathogens and aid in the appropriate treatment of RTIs.

Rapid profiling of carcinogenic types of Helicobacter pylori infection via deep learning analysis of label-free SERS spectra of human serum.

WHO classified Helicobacter pylori as a Group I carcinogen for gastric cancer as early as 1994. However, despite the high prevalence of H. pylori infection, only about 3 % of infected individuals eventually develop gastric cancer, with the highly virulent H. pylori strains expressing cytotoxin-associated protein (CagA) and vacuolating cytotoxin (VacA) being critical factors in gastric carcinogenesis. It is well known that H. pylori infection is divided into two types in terms of the presence and absence of CagA and VacA toxins in serum, that is, carcinogenic Type I infection (CagA+/VacA+, CagA+/VacA-, CagA-/VacA+) and non-carcinogenic Type II infection (CagA-/VacA-). Currently, detecting the two carcinogenic toxins in active modes is mainly done by diagnosing their serological antibodies. However, the method is restricted by expensive reagents and intricate procedures. Therefore, establishing a rapid, accurate, and cost-effective way for serological profiling of carcinogenic H. pylori infection holds significant implications for effectively guiding H. pylori eradication and gastric cancer prevention. In this study, we developed a novel method by combining surface-enhanced Raman spectroscopy with the deep learning algorithm convolutional neural network to create a model for distinguishing between serum samples with Type I and Type II H. pylori infections. This method holds the potential to facilitate rapid screening of H. pylori infections with high risks of carcinogenesis at the population level, which can have long-term benefits in reducing gastric cancer incidence when used for guiding the eradication of H. pylori infections.

Identification of chronic non-atrophic gastritis and intestinal metaplasia stages in the Correa's cascade through machine learning analyses of SERS spectral signature of non-invasively-collected human gastric fluid samples.

The progression of gastric cancer involves a complex multi-stage process, with gastroscopy and biopsy being the standard procedures for diagnosing gastric diseases. This study introduces an innovative non-invasive approach to differentiate gastric disease stage using gastric fluid samples through machine-learning-assisted surface-enhanced Raman spectroscopy (SERS). This method effectively identifies different stages of gastric lesions. The XGBoost algorithm demonstrates the highest accuracy of 96.88% and 91.67%, respectively, in distinguishing chronic non-atrophic gastritis from intestinal metaplasia and different subtypes of gastritis (mild, moderate, and severe). Through blinded testing validation, the model can achieve more than 80% accuracy. These findings offer new possibilities for rapid, cost-effective, and minimally invasive diagnosis of gastric diseases.

Quantitative Polymerase Chain Reaction (qPCR)-Based Rapid Diagnosis of Helicobacter pylori Infection and Antibiotic Resistance.

Helicobacter pylori is a major human pathogen that infects approximately half of the global population and is becoming a serious health threat due to its increasing antibiotic resistance. It is the causative agent of chronic active gastritis, peptic ulcer disease, and gastric cancer and has been classified as a Group I Carcinogen by the International Agency for Research on Cancer. Therefore, the rapid and accurate diagnosis of H. pylori and the determination of its antibiotic resistance are important for the efficient eradication of this bacterial pathogen. Currently, H. pylori diagnosis methods mainly include the urea breath test (UBT), the antigen test, the serum antibody test, gastroscopy, the rapid urease test (RUT), and bacterial culture. Among them, the first three detection methods are noninvasive, meaning they are easy tests to conduct. However, bacteria cannot be retrieved through these techniques; thus, drug resistance testing cannot be performed. The last three are invasive examinations, but they are costly, require high skills, and have the potential to cause damage to patients. Therefore, a noninvasive, rapid, and simultaneous method for H. pylori detection and drug resistance testing is very important for efficiently eradicating H. pylori in clinical practice. This protocol aims to present a specific procedure involving the string test in combination with quantitative polymerase chain reaction (qPCR) for the rapid detection of H. pylori infection and antibiotic resistance. Unlike bacterial cultures, this method allows for easy, rapid, noninvasive diagnosis of H. pylori infection status and drug resistance. Specifically, we used qPCR to detect rea for H. pylori infection and mutations in the 23S rRNA and gyrA genes, which encode resistance against clarithromycin and levofloxacin, respectively. Compared to routinely used culturing techniques, this protocol provides a noninvasive, low-cost, and time-saving technique to detect H. pylori infection and determine its antibiotic resistance using qPCR.

MicroRNA-146a regulates the production of cytokines in lymphocytes stimulated by Porphyromonas gingivalis lipopolysaccharide.

OBJECTIVES: This study aimed to investigate the effects of microRNA-146a (miR-146a) on the production of cytokines in lymphocytes stimulated by Porphyromonas gingivalis (P.gingivalis) lipopolysaccharide (LPS). METHODS: Lymphocytes were harvested from mouse spleen and cultured in vitro. The cells were treated with P. gingivalis LPS, miR-146a mimic, or miR-146a inhibitor. Scramble RNA served as the negative control of mimic and inhibitor. The production of inflammatory cytokines was detected by quantitative real-time polymerase chain reaction and enzyme-linked immunosorbent assay. RESULTS: Compared with non-LPS-stimulated group, P. gingivalis LPS could increase the levels of interleukin (IL)-1ß, IL-6, receptor activator NF-κB ligand (RANKL), and IL-10 (P<0.05) and decrease the mRNA level of osteoprotectin (OPG) (P<0.05). However, it did not significantly change the secretion of OPG. Compared with the negative control group, miR-146a mimic upregulated the levels of IL-10 and OPG (P<0.05), downregulated IL-1ß, IL-6, and RANKL (P<0.05). Meanwhile, miR-146a inhibitor had a reverse effect on these cytokines (P<0.05) in P.gingivalis LPS-treated-lymphocytes. CONCLUSIONS: MiR-146a can provide a suitable microenvironment for bone formation by preventing the inflammatory effects of P.gingivalis LPS through the inhibition of IL-1ß, IL-6, and RNAKL, thereby enhancing IL-10 and OPG.