Explainable artificial intelligence predicts inflammatory and spatial heterogeneity from nasal polyp histology

Clinical Snapshot

Key Findings

• P Value: Not reported in abstract

• Effect Size: Strong correlations for 28/33 signature genes

• Primary Outcome: Prediction accuracy of inflammatory gene signatures and endotype classification

• Nnt Or Sensitivity: AUC values: T1 (0.833), T2 (0.903), T3 (0.935) for internal validation; T2 endotype AUC 0.716 in external cohort

• Confidence Interval: Not reported in abstract

Clinical Application

High - utilizes standard H&E histology available in all pathology laboratories. Requires computational infrastructure for deep learning model deployment Highly relevant to Australian ENT practice. Could inform PBS-subsidized biologic therapy decisions (dupilumab, mepolizumab). Aligns with RACGP chronic rhinosinusitis management guidelines emphasizing phenotyping Patients with chronic rhinosinusitis with nasal polyps requiring endotype classification for precision medicine approaches

Abstract

BACKGROUND: Chronic rhinosinusitis with nasal polyps is a heterogeneous disorder characterized by diverse inflammatory signatures and endotypes. OBJECTIVE: We sought to develop a histology-based deep learning network for predicting inflammatory gene signatures and spatial patterns in chronic rhinosinusitis with nasal polyps. METHODS: We developed HE2Signature, a deep learning model, using 70 hematoxylin and eosin-stained whole-slide images of nasal polyps paired with corresponding endotypic signature gene expression profiles derived from transcriptomic data. The model was validated in an internal cohort (n = 30) and tested in an independent external cohort (n = 224) from 4 medical centers. The performance was evaluated using correlation and confusion matrix analyses and receiver-operating characteristic curves. Spatial predictions were validated by immunohistochemistry. RESULTS: The HE2Signature demonstrated strong positive correlations between the predicted and actual expression levels of 28 of the 33 signature genes. The internal validation cohort was stratified into distinct endotypes on the basis of predicted signature gene expression, achieving area under the curve values of 0.833, 0.903, and 0.935 for the T1, T2, and T3 endotypes, respectively. In the external cohort, the combination of HE2Signature-predicted Fc epsilon receptor II and CST1 effectively identified the T2 endotype, with a receiver-operating characteristic value of 0.716. Histopathologic examination of high-prediction patches revealed characteristic features associated with signature gene expression. Heatmaps and immunohistochemistry confirmed the accuracy of the model in mapping spatial gene expression patterns. HE2Signature-predicted spatial expression of signature genes correlated with blood and tissue eosinophil counts, Lund-Kennedy score, and Sino-Nasal Outcome Test-22 score, particularly within subepithelial regions. CONCLUSIONS: Our study introduces the first histology-based, explainable deep learning model capable of predicting inflammatory gene signatures and spatial molecular heterogeneity. This proof-of-concept highlights that artificial intelligence-powered histopathologic analysis can generate digital biomarkers by linking tissue patterns with molecular profiles, providing a clinically applicable framework for endotype-guided precision medicine in chronic rhinosinusitis with nasal polyps.

References

1. 1.Wang, K., Ren, Y., Ma, L., Han, L., Xu, L., Guan, H., Cui, Y., Wu, L., Liu, C., Liu, W., Wang, J., Liu, H., Fan, Y., Shi, J., & Sun, Y. (2025). Explainable artificial intelligence predicts inflammatory and spatial heterogeneity from nasal polyp histology. Journal of Allergy and Clinical Immunology. https://doi.org/10.1016/j.jaci.2025.08.016