Related Experiment Video
Updated: Jul 18, 2026
Symptom Assessment of Patients with Allergic Rhinitis Using an Allergen Exposure Chamber
Published on: March 3, 2023
[Artificial neural networks applied to study allergic conjunctivitis screening questionnaire]
Denise Atique Goulart1, Milena Atique Tacla, Patrícia Maria Fernandes Marback
1Setor de Córnea e Doenças Externas, Universidade Federal de São Paulo, São Paulo, SP, Brasil. dagoulart@uol.com.br
Insights
A new screening model using seven questions accurately predicts allergic conjunctivitis in children. This artificial neural network offers a simple tool for large-scale population screenings.
Area of Science:
- Ophthalmology
- Allergy and Immunology
- Biomedical Engineering
Background:
- Allergic conjunctivitis is a common condition in children.
- Accurate screening tools are needed for early diagnosis and management.
- Existing screening methods may have limitations in sensitivity and specificity.
Purpose of the Study:
- To evaluate the sensitivity and specificity of a screening questionnaire for allergic conjunctivitis.
- To compare diagnostic accuracy using multivariable analysis.
- To develop an artificial neural network (ANN) for improved future screenings.
Main Methods:
- An observational, cross-sectional study was conducted with 48 children diagnosed with allergic conjunctivitis and 54 controls.
- A screening questionnaire was administered to all participants.
- Multivariable statistical analysis and ANN modeling were performed.
Main Results:
- The ANN model achieved 100% accuracy in predicting allergic diagnosis using seven specific questionnaire items.
- Question five alone demonstrated good sensitivity (85.4%) and specificity (85.1%).
- The overall questionnaire showed low agreement with clinical examination (Kappa coefficient = 0.337).
Conclusions:
- An efficient, seven-question model was developed for screening allergic conjunctivitis.
- The ANN model shows promise for accurate, large-scale population screenings.
- This simplified model can facilitate easier application in public health settings.
Purpose:
To evaluate sensibility and specificity of a screening questionnaire with multivariable analysis, compare them and elaborate an artificial neural network for future screenings.
Methods:
Observational, transversal study performed at UNIFESP, with 48 patients with allergic conjunctivitis and 54 children without the disease. Their age ranged between 3 and 14 years and there was no restriction related to gender, systemic allergy or treatment. The questionnaire was applied and multivariable statistical analysis was performed. Finally, an artificial neural network was elaborated.
Results:
Mean age was 8.4 years (7-13) and male gender was more frequent (60.7%). Mean score was 10.04 (0-18), and it was higher in the study group (p < 0.001). Allergic diagnosis was increased with the inclusion of the fifth question in 68.8%. Kappa coefficient was low (0.337; p = 0.071) and showed no agreement between diagnosis made by the questionnaire and clinical examination. Only the question number five had good sensitivity (85.4%) and specificity (85.1%). The cutoff point to separate allergic patients was 10 (sensitivity = 77.08% and specificity = 79.63%). The artificial neural network predicted allergic diagnosis in 100% using 7 of the 15 existent items.
Conclusions:
An efficient model was developed using seven questions, in a manner that its application might be easy to large populations.
