Mortality prediction for acute decompensated heart failure patient using fuzzy neural network

Abstract

It has been reported that patients admitted with acute decompensated heart failure (ADHF) face high risk of mortality where 30-day mortality rates are reaching 10%. Identifying patient with high and low risk of mortality could improve clinical outcomes and hospital resources allocation. This paper proposed the use of fuzzy neural network to predict mortality for the patient admitted with ADHF. Results show that fuzzy neural network can predict mortality for ADHF patient with good prediction accuracy with overall accuracy of 88.8% for partition 50 and 90.40% for partition 80.

Image Emotion Recognition Supporting Fuzzy Neural Network

“…Advanced Features: Due to the continuous development of deep learning techniques, researchers have devoted themselves to the study of deep architectures. High-level features describe semantic concepts in images and are mainly obtained by fine-tuning pre-trained neural networks to aid sentiment classification [16].…”

Fuzzy Neural Networks to Multi-source Information

“…Specifically, in the proposed TopFuzz4SA model, a topic-driven neural encoder-decoder architecture is first applied topic-driven neural encoder-decoder architecture combined with latent topic embedding and attention mechanisms in order to fully learn the rich contextual and global semantic information of the given text data [4]. Therefore, it is relevant to study the application of fuzzy neural networks with multiple sources of information [5].…”