Related Experiment Video
Updated: Aug 5, 2026
08:47
Symptom Assessment of Patients with Allergic Rhinitis Using an Allergen Exposure Chamber
Published on: March 3, 2023
Enhanced Early Detection of Allergic Rhinitis: A Prospective Study on a Symptom-Based Predictive Model
Ke-Zhang Zhu1,2,3, Chao He1,2,3, Si-Zhe Zhu1,2,3
1Department of Otolaryngology-Head and Neck Surgery, Tongji Hospital, Tongji Medical College Huazhong University of Science and Technology Wuhan China.
Summary
A new symptom-based model accurately predicts allergic rhinitis (AR) using visual analogue scale (VAS) data. This tool aids early detection and management, outperforming traditional clinical experience.
Area of Science:
- Allergy and Immunology
- Computational Medicine
- Diagnostic Tools
Background:
- Allergic rhinitis (AR) and non-allergic rhinitis (NAR) present similar symptoms but differ in cause and treatment.
- Current diagnostic methods like skin prick testing (SPT) and IgE quantification are complex.
- There is a need for simpler, early detection methods for AR.
Purpose of the Study:
- To develop a symptom-based model for early detection of allergic rhinitis (AR).
- To explore relationships between specific allergens and symptoms.
- To evaluate the model's diagnostic performance compared to clinical judgment.
Main Methods:
- A prospective cohort study enrolled 1150 patients with suspected AR.
- Visual analogue scale (VAS) questionnaires captured symptom severity.
- Logistic regression (LR) and machine learning algorithms built a predictive model.
- Diagnosis was confirmed by SPT; patients were split into training and testing sets.
Main Results:
- 758 patients (65.9%) were diagnosed with AR, exhibiting more severe symptoms.
- Dust mites were the most common allergen; sneezing was the strongest individual predictor (AUC=0.758).
- The multivariable LR model achieved an AUC of 0.771 (training) and 0.765 (test), surpassing clinician experience.
Conclusions:
- A symptom-based predictive model using VAS data offers a practical, cost-effective approach for early AR detection.
- The model enhances diagnostic accuracy and supports personalized management strategies.
- This tool can minimize diagnostic delays and optimize treatment decisions for allergic rhinitis.
