Dynamic prediction of cardiovascular disease using improved LSTM
Authors:
- Kuang JunweiKJKuang Junwei
- Hangzhou YangHYHangzhou Yang
- Liu JunjiangLJLiu Junjiang
- Yan ZhijunYZYan Zhijun
Open Access
- 10 May 2019
- journal article
- research article
- Published by Tsinghua University Press in International Journal of Crowd Science
- Vol. 3 (1) , 14-25
Abstract
Purpose: Previous dynamic prediction models rarely handle multi-period data with different intervals, and the large-scale patient hospital records are not effectively used to improve the prediction performance. This paper aims to focus on the prediction of cardiovascular disease using the improved long short-term memory (LSTM) model. Design/methodology/approach: A new model based on the traditional LSTM was proposed to predict cardiovascular disease. The irregular time interval is smoothed to obtain the time parameter vector, and it is used as the input of the forgetting gate of LSTM to overcome the prediction obstacle caused by the irregular time interval. Findings: The experimental results show that the dynamic prediction model proposed in this paper obtained a significant better classification performance compared with the traditional LSTM model. Originality/value: In this paper, the authors improved the LSTM by smoothing the irregular time between different medical stages of the patient to obtain the temporal feature vector.Keywords
This publication has 21 references indexed in Scilit:
- Clinical impact of sedentary behaviors in adult survivors of acute lymphoblastic leukemia: A report from the St. Jude Lifetime Cohort studyCancer, 2017
- Enhancing Seasonal Influenza Surveillance: Topic Analysis of Widely Used Medicinal Drugs Using Twitter DataJournal of Medical Internet Research, 2017
- PEACE-Home: Probabilistic estimation of abnormal clinical events using vital sign correlations for reliable home-based monitoringPervasive and Mobile Computing, 2017
- Healthcare Predictive Analytics for Risk Profiling in Chronic Care: A Bayesian Multitask Learning Approach1MIS Quarterly, 2017
- Hospital Information System adoption: Expert perspectives on an adoption framework for Malaysian public hospitalsComputers in Human Behavior, 2017
- Understanding disease processes by partitioned dynamic Bayesian networksJournal of Biomedical Informatics, 2016
- 5 year mortality predictors in 498 103 UK Biobank participants: a prospective population-based studyThe Lancet, 2015
- Identification and Progression of Heart Disease Risk Factors in Diabetic Patients from Longitudinal Electronic Health RecordsBioMed Research International, 2015
- Chronic disease prevention: health effects and financial costs of strategies to reduce salt intake and control tobacco useThe Lancet, 2007
- Long Short-Term MemoryNeural Computation, 1997