Multivariate Sequential Analytics for Cardiovascular Disease Event Prediction

Abstract

Background Automated clinical decision support for risk assessment is a powerful tool in combating cardiovascular disease (CVD), enabling targeted early intervention that could avoid issues of overtreatment or undertreatment. However, current CVD risk prediction models use observations at baseline without explicitly representing patient history as a time series. Objective The aim of this study is to examine whether by explicitly modelling the temporal dimension of patient history event prediction may be improved. Methods This study investigates methods for multivariate sequential modelling with a particular emphasis on long short-term memory (LSTM) recurrent neural networks. Data from a CVD decision support tool is linked to routinely collected national datasets including pharmaceutical dispensing, hospitalization, laboratory test results, and deaths. The study uses a 2-year observation and a 5-year prediction window. Selected methods are applied to the linked dataset. The experiments performed focus on CVD event prediction. CVD death or hospitalization in a 5-year interval was predicted for patients with history of lipid-lowering therapy. Results The results of the experiments showed temporal models are valuable for CVD event prediction over a 5-year interval. This is especially the case for LSTM, which produced the best predictive performance among all models compared achieving AUROC of 0.801 and average precision of 0.425. The non-temporal model comparator ridge classifier (RC) trained using all quarterly data or by aggregating quarterly data (averaging time-varying features) was highly competitive achieving AUROC of 0.799 and average precision of 0.420 and AUROC of 0.800 and average precision of 0.421, respectively. Conclusion This study provides evidence that the use of deep temporal models particularly LSTM in clinical decision support for chronic disease would be advantageous with LSTM significantly improving on commonly used regression models such as logistic regression and Cox proportional hazards on the task of CVD event prediction.

A comprehensive review of machine learning algorithms and their application in geriatric medicine: present and future

“…This problem of dealing with long-range dependencies was overcome with the development of RNNs including a long short-term memory (LSTM) hidden unit that remembers the activation patterns of hidden layers. This allows significant events from the distant past to be recalled and unimportant events to be forgotten when making current predictions [ 62 ]. Within the context of healthcare, LSTM networks retain the sequential information from patient histories making them especially suitable for long-term forecasting using EHR data.…”