Predictive modeling for eosinophilic chronic rhinosinusitis: Nomogram and four machine learning approaches.

Eosinophilic chronic rhinosinusitis (ECRS) is a distinct subset of chronic rhinosinusitis characterized by heightened eosinophilic infiltration and increased symptom severity, often resisting standard treatments. Traditional diagnosis requires invasive histological evaluation. This study aims to develop predictive models for ECRS based on patient clinical parameters, eliminating the need for invasive biopsy. Utilizing logistic regression with lasso regularization, random forest (RF), gradient-boosted decision tree (GBDT), and deep neural network (DNN), we trained models on common clinical data. The predictive performance was evaluated using metrics such as area under the curve (AUC) for receiver operator characteristics, decision curves, and feature ranking analysis. In a cohort of 437 eligible patients, the models identified peripheral blood eosinophil ratio, absolute peripheral blood eosinophil, and the ethmoidal/maxillary sinus density ratio (E/M) on computed tomography as crucial predictors for ECRS. This predictive model offers a valuable tool for identifying ECRS without resorting to histological biopsy, enhancing clinical decision-making.

[The expression and significance of Piezo1 in chronic rhinosinusitis with nasal polyps].

Objective:To explore the expression and importance of Piezo1, E-cadherin, and Vimentin in nasal polyps patients. Methods:Thirty-five patients undergoing endoscopic sinus surgery under general anesthesia were streamed into 20 cases of nasal polyps（NP group） and 15 cases of simple septoplasty without any sinus disease（Control group）. Immunofluorescence staining and Western Blot were applied to detect the protein level of Piezo1, E-cadherin, and Vimentin in NP tissues and nasal polyp-derived primary human nasal epithelial cells（pHNECs）. Also, BEAS-2B cell lines were treated with human TGF-ß1 protein to establish epithelial mesenchymal transition（EMT） model in vitro and quantitative real-time polymerase chain reaction were used to calculate Piezo1 and above biomarkers in the model. Results:Compared with control group, Piezo1 and Vimentin showed higher level while E-cadherin was lower in NP tissues and pHNECs.In EMT model in vitro, Piezo1 and Vimentin were demonstrated higher expression with decreased level of E-cadherin. Conclusion:The tendency of Piezo1 is consistent with the mesenchymal-related biomarker Vimentin, going against with epithelial-related biomarker E-cadherin, implying its involvement with EMT process in nasal polyps.