Prediction of blood culture outcome using hybrid neural network model based on electronic health records
- PDF / 1,783,727 Bytes
- 10 Pages / 595 x 791 pts Page_size
- 28 Downloads / 170 Views
RESEARCH
Open Access
Prediction of blood culture outcome using hybrid neural network model based on electronic health records Ming Cheng1* , Xiaolei Zhao1 , Xianfei Ding2 , Jianbo Gao3* , Shufeng Xiong4,5 and Yafeng Ren6 From 5th China Health Information Processing Conference Guangzhou, China. 22-24 November 2019
Abstract Background: Blood cultures are often performed to detect patients who has a serious illness without infections and patients with bloodstream infections. Early positive blood culture prediction is important, as bloodstream infections may cause inflammation of the body, even organ failure or death. However, existing work mainly adopts statistical models with laboratory indicators, and fails to make full use of textual description information from EHRs. Methods: We study the problem of positive blood culture prediction by using neural network model. Specifically, we first construct dataset from raw EHRs. Then we propose a hybrid neural network which incorporates attention based Bi-directional Long Short-Term Memory and Autoencoder networks to fully capture the information in EHRs. Results: In order to evaluate the proposed method, we constructe a dataset which consists of totally 5963 patients who had one or more blood cultures tests during hospitalization. Experimental results show that the proposed neural model gets 91.23% F-measure for this task. Conclusions: The comparison results of different models demonstrated the effectiveness of our model. The proposed model outperformed traditional statistical models. Keywords: Hybrid neural network, Long short-term memory, Electronic health records, Positive blood cultures prediction
Background With the rapid development of computing technologies, more and more medical monitoring equipments and software systems are used in clinical practice, generating a large amount of data. This provides opportunities and challenges to accelerate clinical science using large scale of practical clinical data in less expense [1, 2]. For this *Correspondence: [email protected]; [email protected] Department of Medical Information, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, China 3 Department of Radiology, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, China Full list of author information is available at the end of the article 1
reason, machine learning has been increasing impact for medical information research. Various machine learning techniques have been used to mine clinical knowledge [3–7]. Earlier work demonstrated the feasibility of building predictive models with clinical data [8, 9]. Ideally, we wish to be able to establish such models from data routinely collected in Electronic Health Records (EHRs) [10]. In the present research, our aim is to construct a novel model for predicting the risk of bloodstream infection of patients during hospitalization by predicting positive Blood Cultures (BCs). The positive BCs is defined as a blood sample in which bacteria or fungi are present. The growth of bacterial or fungi in
Data Loading...
