Multi-label rhinitis prediction using ensemble neural network chain with pre-training

Rhinitis is a kind of respiratory disease that is difficult to cure. Timely and accurate prediction in its early stage is an effective method for diagnosis of rhinitis. Machine learning is often applied in predicting clinical rhinitis. However, those problems like multi-label features, class imbalance, and poor generalization performance usually occur on rhinitis prediction. This paper introduces an ensemble neural network chain model with pre-training on rhinitis multi-label classification. We apply stacked autoencoders for denoising and feature dimensionality reduction, add pre-training networks to extract global correlations, and build neural network chain to extract local relevant information for single-label classification. This proposed model can use both global and local label correlations to reduce the influence of unreasonable label sequences on classification. A total of 2231 clinical rhinitis cases from Shanghai Tongji Hospital affiliated to Tongji University is conducted for training and test. The cross-validation results show that the average Hamming Loss, accuracy, recall and F1-score is 0.0195, 87.88%, 92.32% and 92.88%, respectively. Compared to various typical multi-label classifiers, the proposed model achieves better generalization performance in evaluation measures. In addition, we calculate the feature importance of rhinitis based on the purity of splitting nodes in Random Forest and study the correlations between rhinitis features and classification, which have a good reference value for diagnosis and treatment of clinical rhinitis. (C)& nbsp;2022 Elsevier B.V. All rights reserved.