Hypertension ; Data mining ; Decision support system
Abstract
Background: This study examined the utility of data mining algorithms for the management of hypertension.
Methods: We studied 2,446 hospitalized patients with hypertension and 3,835 clinic patients with hypertension. Among data mining algorithms, we used clustering analysis and compared decision tree analysis with logistic regression.
Results: On the contrary to the previous studies, decision tree performed better than logistic regression. We have also developed a CDSS (Clinical Decision Support System) with three modules (doctor, nurse, and patient) based on data warehouse architecture. Data warehouse collects and integrates relevant information from various databases from hospital information system.
Conclusions: This study suggests that data mining algorithms may be an useful method for hypertension management and CDSS system can help improve decision making capability of doctors and improve accessibility of educational material for patients.