KTI-RNN: Recognition of Heart Failure from Clinical Notes

Abstract

Although deep learning methods have recently attracted considerable attention in the medical field, analyzing large-scale electronic health record data is still a difficult task. In particular, the accurate recognition of heart failure is a key technology for doctors to make reasonable treatment decisions. This study uses data from the Medical Information Mart for Intensive Care database. Compared with structured data, unstructured data contain abundant patient information. However, this type of data has unsatisfactory characteristics, e.g., many colloquial vocabularies and sparse content. To solve these problems, we propose the KTI-RNN model for unstructured data recognition. The proposed model overcomes sparse content and obtains good classification results. The term frequency-inverse word frequency (TF-IWF) model is used to extract the keyword set. The latent dirichlet allocation (LDA) model is adopted to extract the topic word set. These models enable the expansion of the medical record text content. Finally, we embed the global attention mechanism and gating mechanism between the bidirectional recurrent neural network (BiRNN) model and the output layer. We call it gated-attention-BiRNN (GA-BiRNN) and use it to identify heart failure from extensive medical texts. Results show that the F 1 score of the proposed KTI-RNN model is 85.57%, and the accuracy rate of the proposed KTI-RNN model is 85.59%.

Categorization of different types of people based on their electroneurophysiological responses to fabric–skin contact

“…The differences come from neural activities of the subjects and these three types of subjects coincided well with the melancholic, sanguineous and phlegmatic temperament of Hippocrates’ temperament type theory, 34 as shown in Table 4. This theory categorizes people into four different types of temperament, namely, choleric, melancholic, sanguineous and phlegmatic temperament, which has been proved to correspond well to Pavlov’s higher neural activity type theory, 35 as shown in Table 5. The higher neural activity type theory concludes three characteristics of the neural system as strength, balance and flexibility.…”

Electroneurophysiological responses to fabric-skin dynamic contact with different fabrics among different types of people

“…The psychological factor is determined by the psychological characteristics of different people, which leads to different electroneurophysiological responses. 32 According to Hippocrates’ temperament type theory 33 and Pavlov’s higher neural activity type theory, 34 the ES people, correspond to the melancholic temperament type, have a strong and balanced neural system with high flexibility. The OR people, correspond to the sanguineous temperament type, and also have a strong and balanced neural system but low flexibility, which can be the reason why this type of people respond stably to tactile dynamic stimuli.…”

A Survey on Medical Health Records and AI

“…Additionally, an upgraded classifier is employed to accomplish the classification of medical texts. The KTI-RNN model consists of three modules: the input module for extracting TF-IWF keywords and LDA topic words, the GA-BiRNN module, and the classification output module [1]. The basic architecture diagram depicting these modules is illustrated in Figure 1.…”

“…The proposed system named KTI-RNN model helps the processing of data and its representation to doctors and medical works [1]. The model uses recurrent neural networks, keyword extraction techniques etc.…”