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.