Development and multicenter validation of a novel radiomics-based model for identifying eosinophilic chronic rhinosinusitis with nasal polyps

An End-to-End CRSwNP Prediction with Multichannel ResNet on Computed Tomography

Chronic rhinosinusitis (CRS) is a global disease characterized by poor treatment outcomes and high recurrence rates, significantly affecting patients' quality of life. Due to its complex pathophysiology and diverse clinical presentations, CRS is categorized into various subtypes to facilitate more precise diagnosis, treatment, and prognosis prediction. Among these, CRS with nasal polyps (CRSwNP) is further divided into eosinophilic CRSwNP (eCRSwNP) and noneosinophilic CRSwNP (non-eCRSwNP). However, there is a lack of precise predictive diagnostic and treatment methods, making research into accurate diagnostic techniques for CRSwNP endotypes crucial for achieving precision medicine in CRSwNP. This paper proposes a method using multiangle sinus computed tomography (CT) images combined with artificial intelligence (AI) to predict CRSwNP endotypes, distinguishing between patients with eCRSwNP and non-eCRSwNP. The considered dataset comprises 22,265 CT images from 192 CRSwNP patients, including 13,203 images from non-eCRSwNP patients and 9,062 images from eCRSwNP patients. Test results from the network model demonstrate that multiangle images provide more useful information for the network, achieving an accuracy of 98.43%, precision of 98.1%, recall of 98.1%, specificity of 98.7%, and an AUC value of 0.984. Compared to the limited learning capacity of single-channel neural networks, our proposed multichannel feature adaptive fusion model captures multiscale spatial features, enhancing the model's focus on crucial sinus information within the CT images to maximize detection accuracy. This deep learning-based diagnostic model for CRSwNP endotypes offers excellent classification performance, providing a noninvasive method for accurately predicting CRSwNP endotypes before treatment and paving the way for precision medicine in the new era of CRSwNP.

Hyperuricemia Increases the Risk of Postoperative Recurrence in Chinese Patients with Chronic Rhinosinusitis

Background

Elevated serum uric acid is crucial in the pathophysiology of chronic inflammatory diseases. However, its impact on chronic rhinosinusitis (CRS) recurrence risk is unknown. This study investigates the association between elevated serum uric acid and the risk of CRS recurrence.

Methods

A retrospective cohort study was conducted on 1004 CRS patients (including 638 males and 366 females) who received functional endoscopic sinus surgery. All patients were followed up for more than 2 years, and categorized into subgroups based on phenotype, gender, and postoperative recurrence. Cox regression analysis was performed to evaluate the associations between serum uric acid and the risk of CRS recurrence.

Results

After categorization, 104 males had hyperuricemia, and 54 females presented hyperuricemia. The rate of recurrent CRS in the hyperuricemia group was significantly higher compared to the non-hyperuricemia group in both males and females (P<0.05). In both male and female patients, the rate of hyperuricemia and uric acid levels were elevated in the recurrent CRS group in comparison with the non-recurrent CRS group (P<0.05). Unadjusted and adjusted Cox regression analysis demonstrated that serum uric acid was an independent risk factor for CRS recurrence (P<0.05). The receiver operator characteristic curve showed that serum uric acid was a potential biomarker for predicting the recurrence of CRS and its phenotypes in both genders (P<0.05).

Conclusion

There is a close relationship between elevated serum uric acid and the recurrence risk of CRS and its phenotypes, suggesting that serum uric acid may be a novel biomarker for predicting recurrent CRS.

Abnormal S100A8 expression associates with postoperative recurrence in chronic rhinosinusitis with nasal polyps

Objective

To investigate the role of S100A8 in chronic rhinosinusitis with nasal polyps (CRSwNP) and assess its value in predicting disease recurrence after surgery.

Methods

Thirty healthy controls (HC), 30 patients with chronic rhinosinusitis without nasal polyp (CRSsNP), and 60 patients with CRSwNP were enrolled. Serum S100A8 concentration was measured by ELISA. Immunohistochemistry (IHC), western blotting (WB), and reverse transcription-polymerase chain reaction (RT-PCR)were performed to examine tissue expression levels of S100A8. The potential values of S100A8 in predicting postoperative recurrence of CRSwNP were assessed by the receiver operating characteristic (ROC)curve.

Results

Serum S100A8 concentrations in the CRSwNP group were higher than the HC group and the CRSsNP group， especially in the recurrent CRSwNP group (P < 0.05). Serum S100A8 levels were positively correlated with peripheral blood eosinophil numbers (r = 0.263, P = 0.043) and percentages (r = 0.336, P = 0.009), tissue eosinophil percentages (r = 0.273, P = 0.035), VAS score (r = 0.385, P = 0.002) and Lund-Kennedy score (r = 0.283, P = 0.029). IHC, WB, and RT-PCR results showed tissue S100A8 expression was significantly enhanced in the CRSwNP group, especially in the recurrence group (P < 0.05). Binary regression analysis showed that serum S100A8 concentration and tissue eosinophil percentage were correlated with postoperative recurrence of CRSwNP. ROC curve analysis showed that compared with tissue eosinophil percentage, the S100A8 level had a higher value for postoperative recurrence of CRSwNP.

Conclusion

Serum and tissue S100A8 levels were elevated in patients with CRSwNP， especially in the recurrent CRSwNP patients, and were correlated with the degree of peripheral blood and tissue eosinophilic inflammation. S100A8 seemed to be a potential objective biomarker to predict the postoperative recurrence of CRSwNP.