Determining the utility of standard hospital microbiology testing: Comparing standard microbiology cultures with DNA sequence analysis in patients with chronic sinusitis

Deep Learning Model for Pathogen Classification Using Feature Fusion and Data Augmentation

Background:

Bacterial pathogens are deadly for animals and humans. The ease of their dissemination, coupled with their high capacity for ailment and death in infected individuals, makes them a threat to society.

Objective:

Due to high similarity among genera and species of pathogens, it is sometimes difficult for microbiologists to differentiate between them. Their automatic classification using deep-learning models can help in reliable, and accurate outcomes.

Method:

Deep-learning models, namely; AlexNet, GoogleNet, ResNet101, and InceptionV3 are used with numerous variations including training model from scratch, fine-tuning without pre-trained weights, fine-tuning along with freezing weights of initial layers, fine-tuning along with adjusting weights of all layers and augmenting the dataset by random translation and reflection. Moreover, as the dataset is small, fine-tuning and data augmentation strategies are applied to avoid overfitting and produce a generalized model. A merged feature vector is produced using two best-performing models and accuracy is calculated by xgboost algorithm on the feature vector by applying cross-validation.

Results:

Fine-tuned models where augmentation is applied produces the best results. Out of these, two-best-performing deep models i.e. (ResNet101, and InceptionV3) selected for feature fusion, produced a similar validation accuracy of 95.83 with a loss of 0.0213 and 0.1066, and a testing accuracy of 97.92 and 93.75, respectively. The proposed model used xgboost to attained a classification accuracy of 98.17% by using 35-folds cross-validation.

Conclusion:

The automatic classification using these models can help experts in the correct identification of pathogens. Consequently, they can help in controlling epidemics and thereby minimizing the socio-economic impact on the community.

Increased lipopolysaccharide content is positively correlated with glucocorticoid receptor-beta expression in chronic rhinosinusitis with nasal polyps

Introduction

Chronic rhinosinusitis with nasal polyps (CRSwNP) is a common and frequently occurring disease of the upper respiratory tract. The nasal instillation of the Gram‐negative (G⁻) bacterial product lipopolysaccharide (LPS) can induce not only acute sinusitis but also the development of CRSwNP in animal models. Nevertheless, the expression and distribution of LPS in patients with CRSwNP have not been investigated. And the study was to investigate the expression of LPS and its relationship with glucocorticoid receptors (GRs) in CRSwNP.

Methods

Multiple methods, including bacterial culture and immunohistochemistry, were used to detect and analyze nasal bacteria, plasma LPS content, and the levels of LPS and GR‐α/β, cluster of differentiation 68 (CD68), and myeloperoxidase (MPO) expression, as well as their relationship in CRSwNP.

Results

The number of G⁻ bacteria and Escherichia coli (E. coli) was not significantly different between CRSwNP subjects and the controls. However, the positive rate of LPS was much higher than that of E. coli in CRSwNP subjects and was significantly higher in noneosinophilic CRSwNP subjects than in eosinophilic CRSwNP subjects. Moreover, the LPS levels were positively correlated with GR‐β but not GR‐α expression in CRSwNP. Immunofluorescence assays showed that LPS was mainly detected in CD68⁺ macrophages and MPO⁺ neutrophils, in addition to histiocytes, in CRSwNP.

Conclusions

Persistent LPS in CRSwNP can lead to unresolved mucosal inflammation, eventually leading to tissue remodeling and the development of CRSwNP. Our findings suggest that increased LPS content and possible resistance to glucocorticoids may be one of the important pathogenic mechanisms of G⁻ bacteria in CRSwNP.

Detection of Microbiota in Post Radiation Sinusitis

OBJECTIVES

A shift in the microbiota of chronic rhinosinusitis has been described after radiotherapy to the sinonasal cavity and skull base. There is a paucity of literature characterizing the bacteriology of post radiation sinusitis using next-generation gene sequencing techniques. This study aims to describe and compare the microbial flora of rhinosinusitis after radiotherapy using both culture and molecular techniques for microbial DNA detection.

METHODS

The medical records of patients treated with external beam radiation for sinonasal, nasopharyngeal, or skull base malignancy were reviewed at a tertiary care facility. Patients' sinonasal cavities were swabbed for routine culture or brushed for molecular gene sequencing. Swab specimens were processed for standard microbial culture, and brush specimens were sent for gene sequencing at Micro GenX Laboratory (Lubbock, Texas, USA).

RESULTS

Twenty-two patients were diagnosed with chronic sinusitis after undergoing radiotherapy. Staphylococcus aureus was the most common organism identified by both culture and gene sequencing, followed by Pseudomonas aeruginosa. Several additional organisms were detected by gene sequencing that were not isolated by routine culture techniques. Gene sequencing identified pathogens differing from culture results in 50% of patients examined.

CONCLUSION

The bacteriology of post radiation sinusitis appears to resemble the microorganisms responsible for chronic sinusitis in healthy adults. Next generation gene sequencing techniques may reveal additional organisms responsible for sinusitis and provide complementary results that may impact the medical treatment of post radiation sinusitis.