Development of an Algorithm for Stroke Prediction: A National Health Insurance Database Study in Korea

Abstract

Background: Stroke is the second leading cause of death worldwide and remains an important health burden both for the individuals and for the national healthcare systems. Potentially modifiable risk factors for stroke include hypertension, cardiac disease, diabetes, and dysregulation of glucose metabolism, atrial fibrillation, and lifestyle factors. Objects: We aimed to derive a model equation for developing a stroke pre-diagnosis algorithm with the potentially modifiable risk factors. Methods: We used logistic regression for model derivation, together with data from the database of the Korea National Health Insurance Service (NHIS). We reviewed the NHIS records of 500,000 enrollees. For the regression analysis, data regarding 367 stroke patients were selected. The control group consisted of 500 patients followed up for 2 consecutive years and with no history of stroke. Results: We developed a logistic regression model based on information regarding several well-known modifiable risk factors. The developed model could correctly discriminate between normal subjects and stroke patients in 65% of cases. Conclusion: The model developed in the present study can be applied in the clinical setting to estimate the probability of stroke in a year and thus improve the stroke prevention strategies in high-risk patients. The approach used to develop the stroke prevention algorithm can be applied for developing similar models for the pre-diagnosis of other diseases.

A predictive analytics approach for stroke prediction using machine learning and neural networks

“…Similarly, Luk et al studied 878 Chinese subjects to understand if age has an impact on stroke rehabilitation outcomes [10]. Min et al in [11] developed an algorithm for predicting stroke from potentially modifiable risk factors. Singh and Choudhary in [12] have used decision tree algorithm on Cardiovascular Health Study (CHS) dataset for predicting stroke in patients.…”

نماذج تعلم الآلة للتنبؤ بالسکتات الدماغیة

“…The result shows that the linear functions reached a greater accuracy of 91%. Others in [18] used logistic regression for building the predictive model. In [8], they developed a stroke predictive model using three machine learning classification algorithms: Decision Tree, Naïve Bayes, and Neural Network.…”

“…The most important two steps to reduce the risk of stroke are: control risk factors and know the warning signs for strokes [9]. Most previous studies were based on just building a predictive model for brain strokes by using classical classification algorithms [10] [11] [12], but few studies employed the Ensemble Methods to improve the accuracy of the individual algorithms [13] [14] [15]. Also, studies that use ensemble methods have not highlighted all types of ensemble methods that affect the model accuracy.…”

Patient-Centric HetNets Powered by Machine Learning and Big Data Analytics for 6G Networks

“…However, this also means that it suffers from high sensitivity to feature vector values. This classifier is a popular tool in disease prediction as in [19], [20], [37]. The logistic model is based on the logistic function given in (3).…”