Intelligent Classification and Identification of Similar Respiratory System Diseases

DOI

10.2991/978-94-6239-648-7_68How to use a DOI?

Keywords

Respiratory Symptoms; Class Non-uniformity; Probability Calibration; Feature Overlap

Abstract

This study focuses on symptom classification models for the four most common respiratory diseases (COVID, FLU, COLD, and ALLERGY). The aim is to address the challenge of distinguishing between similar and troublesome respiratory illnesses while maintaining accuracy and minimizing unnecessary time wastage. Based on the project’s publicly available dataset, the models underwent standardization, cleaning, type unification, severity encoding, hierarchical segmentation, and standardized preprocessing. Three models were compared: Bernoulli Naive Bayes (an interpretable baseline), RBF-SVM (a traditional strong baseline), and MLP. In cases of imbalanced datasets, probability calibration and class threshold scanning were employed to find a balance between precision and recall. A macro-averaging metric was used to avoid the majority class “drowning” effect. In the overall output, RBF-SVM showed stable performance in macro F1 and macro AUC; after calibration and threshold adjustment, MLP improved the precision of easily confused classes while maintaining overall accuracy. The main confusion and low precision in the models stemmed from the significant overlap of features between COVID and COLD. This article provides a method for solving related problems using neural networks. The accuracy of these models cannot be fully trusted and requires subsequent manual verification to ensure accuracy.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Zhuoyang Liu
PY  - 2026
DA  - 2026/04/24
TI  - Intelligent Classification and Identification of Similar Respiratory System Diseases
BT  - Proceedings of the International Workshop on Advances in Deep Learning for Image Analysis and Computer Vision (IWADIC 2025)
PB  - Atlantis Press
SP  - 627
EP  - 635
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6239-648-7_68
DO  - 10.2991/978-94-6239-648-7_68
ID  - Liu2026
ER  -