FaFCNN: A General Disease Classification Framework Based on Feature Fusion Neural Networks

TL;DR

FaFCNN is a novel neural network framework that effectively fuses multiple features for disease classification, improving robustness and performance especially on low-quality datasets with missing data.

Contribution

The paper introduces FaFCNN, a general disease classification framework that incorporates feature-aware interaction and alignment modules based on domain adversarial learning.

Findings

FaFCNN outperforms baseline methods on low-quality datasets.

Pre-training with gradient boosting decision trees enhances performance.

The model demonstrates robustness and component effectiveness through extensive experiments.

Abstract

There are two fundamental problems in applying deep learning/machine learning methods to disease classification tasks, one is the insufficient number and poor quality of training samples; another one is how to effectively fuse multiple source features and thus train robust classification models. To address these problems, inspired by the process of human learning knowledge, we propose the Feature-aware Fusion Correlation Neural Network (FaFCNN), which introduces a feature-aware interaction module and a feature alignment module based on domain adversarial learning. This is a general framework for disease classification, and FaFCNN improves the way existing methods obtain sample correlation features. The experimental results show that training using augmented features obtained by pre-training gradient boosting decision tree yields more performance gains than random-forest based methods. On the low-quality dataset with a large amount of missing data in our setup, FaFCNN obtains a consistently optimal performance compared to competitive baselines. In addition, extensive experiments demonstrate the robustness of the proposed method and the effectiveness of each component of the model\footnote{Accepted in IEEE SMC2023}.