Comparative Genomic Analysis Reveals the Emergence of ST-231 and ST-395 Klebsiella pneumoniae Strains Associated with the High Transmissibility of blaKPC Plasmids

Ensemble of Deep Learning Architectures with Machine Learning for Pneumonia Classification Using Chest X-rays

Pneumonia is a severe health concern, particularly for vulnerable groups, needing early and correct classification for optimal treatment. This study addresses the use of deep learning combined with machine learning classifiers (DLxMLCs) for pneumonia classification from chest X-ray (CXR) images. We deployed modified VGG19, ResNet50V2, and DenseNet121 models for feature extraction, followed by five machine learning classifiers (logistic regression, support vector machine, decision tree, random forest, artificial neural network). The approach we suggested displayed remarkable accuracy, with VGG19 and DenseNet121 models obtaining 99.98% accuracy when combined with random forest or decision tree classifiers. ResNet50V2 achieved 99.25% accuracy with random forest. These results illustrate the advantages of merging deep learning models with machine learning classifiers in boosting the speedy and accurate identification of pneumonia. The study underlines the potential of DLxMLC systems in enhancing diagnostic accuracy and efficiency. By integrating these models into clinical practice, healthcare practitioners could greatly boost patient care and results. Future research should focus on refining these models and exploring their application to other medical imaging tasks, as well as including explainability methodologies to better understand their decision-making processes and build trust in their clinical use. This technique promises promising breakthroughs in medical imaging and patient management.

Genomic analysis of extensively drug resistant (XDR) Klebsiella pneumoniae high-risk clone ST14 co-harboring blaNDM and blaOXA-48 recovered from Saudi Arabia

BACKGROUND

This study presents a comprehensive genomic analysis of NDM and OXA-48-producing Klebsiella pneumoniae in the Western region of Saudi Arabia, traversed by tens of millions of Muslims from various countries annually. This significant influx of visitors invariably leads to the spread and diversity of MDR bacteria.

METHODS

Genome sequencing was performed using MiSeq system of 29 CPKP isolates that were NDM and OXA-48-positive isolated from nosocomial infections and demonstrated resistance to most antibiotics, including carbapenems.

RESULTS

WGS analysis showed that 12 (41.3%) isolates co-harbored blaOXA-48,blaCTX-M-15 and blaNDM genes. Notably, 16 (55.1%) isolates were identified as high-risk clone ST14, with 50% of these isolates co-harbored blaOXA-48, blaNDM and blaCTX-M-15 genes. All ST14 isolates were identified as capsular genotype KL2 and O1/O2v1 antigen with yersiniabactin locus ypt 14 carried by ICEKp5. The two isolates were identified as ST2096/KL64 hypervirulent K. pneumoniae (hvKp) clone harboring several virulence factors, including the regulator of the mucoid phenotype rmpA2 and aerobactin (iuc-1). Interestingly, two of the hvKp ST383/KL30 isolates were resistant to all tested antimicrobials except colistin and tigecycline, and simultaneously carried numerous ESBLs and carbapenemase genes. These isolates also harbor several virulence factors such as rmpA1, rmpA2, carried on KpVP-1, and aerobactin (iuc-1).

CONCLUSION

this study provides insights into the spread and prevalence of high-risk clones of CPKP in the Western region of Saudi Arabia. The ST14 high-risk clone appears to be the predominant CPKP clone in this region, posing a significant threat to public health. This study also reports the presence of two globally disseminated hypervirulent K. pneumoniae (hvKp) clones, namely ST2096 and ST383. Therefore, it is essential to improve surveillance and implement strict infection control measures in this region, which receives a substantial number of visitors to effectively monitor and reduce the spread of high-risk clones of antimicrobial-resistant bacteria, including CPKP.