Research Article: Development of an intelligent decision support system for ischemic stroke risk assessment in a population-based electronic health record database

Date Published: March 13, 2019

Publisher: Public Library of Science

Author(s): Chen-Ying Hung, Ching-Heng Lin, Tsuo-Hung Lan, Giia-Sheun Peng, Chi-Chun Lee, Nan Liu.

http://doi.org/10.1371/journal.pone.0213007

Abstract

Intelligent decision support systems (IDSS) have been applied to tasks of disease management. Deep neural networks (DNNs) are artificial intelligent techniques to achieve high modeling power. The application of DNNs to large-scale data for estimating stroke risk needs to be assessed and validated. This study aims to apply a DNN for deriving a stroke predictive model using a big electronic health record database.

The Taiwan National Health Insurance Research Database was used to conduct a retrospective population-based study. The database was divided into one development dataset for model training (~70% of total patients for training and ~10% for parameter tuning) and two testing datasets (each ~10%). A total of 11,192,916 claim records from 840,487 patients were used. The primary outcome was defined as any ischemic stroke in inpatient records within 3 years after study enrollment. The DNN was evaluated using the area under the receiver operating characteristic curve (AUC or c-statistic). The development dataset included 672,214 patients (a total of 8,952,000 records) of whom 2,060 patients had stroke events. The mean age of the population was 35.5±20.2 years, with 48.5% men. The model achieved AUC values of 0.920 (95% confidence interval [CI], 0.908–0.932) in testing dataset 1 and 0.925 (95% CI, 0.914–0.937) in testing dataset 2. Under a high sensitivity operating point, the sensitivity and specificity were 92.5% and 79.8% for testing dataset 1; 91.8% and 79.9% for testing dataset 2. Under a high specificity operating point, the sensitivity and specificity were 80.3% and 87.5% for testing dataset 1; 83.7% and 87.5% for testing dataset 2. The DNN model maintained high predictability 5 years after being developed. The model achieved similar performance to other clinical risk assessment scores.

Using a DNN algorithm on this large electronic health record database is capable of obtaining a high performing model for assessment of ischemic stroke risk. Further research is needed to determine whether such a DNN-based IDSS could lead to an improvement in clinical practice.

Partial Text

Globally, approximately 6.5 million stroke deaths happen each year–making stroke the second-leading cause of death and thus an important public health issue.[1] The mortality and disability associated with stroke significantly impact lives of patients and their families. Developing predictive risk assessment is essential in continuously improving stroke prevention by providing healthcare professionals reliable pre-screening analytics.[2,3] In fact, many existing clinical guidelines recommend the use of stroke risk assessment tools, e.g., the Framingham[4] and QRISK[5] scoring systems, to identify patients at a high risk of stroke.[6–8] However, large-scale deployment of these questionnaire-based assessments in outpatient departments or clinics is inefficient and impractical. This draw-back is especially evident when scaling up the assessment effort in places with large volumes of primary care, or for the general population. A scalable and reliable automated stroke risk assessment system could offer clinical decision support instruments for healthcare professionals and further benefit societal welfare.

In this study, our DNN model shows high performance in estimating future risk of ischemic stroke. Combining the use of DNN and EHR allows a rapid and potentially more precise stratification in identifying those patients with high stroke risk. Further prospective research is necessary to determine the feasibility of applying this algorithm in clinical practice and to see whether such a DNN based IDSS could improve stroke prevention in the general population.

 

Source:

http://doi.org/10.1371/journal.pone.0213007

 

Leave a Reply

Your email address will not be published.