A hybrid decision support system for heart failure diagnosis using neural networks and statistical process control

Abstract

Timing and precision are two primary keys for myocardial infarction diagnosis. Even minor errors in diagnosis can dramatically increase the treatment process, increase treatment costs, and put the patient in dangerous health states. This paper presents a decision support system (DSS) based on neural networks and statistical process control charts for diagnosing and controlling myocardial infarction (MI) and continuously monitoring the patient’s blood pressure. To this aim, the data was collected from 175 medical documents of patients with MI and 92 recorded successful diagnoses of MI type. A group of patients was used to validate the effectiveness of the proposed system. The results prove that the proposed hybrid model can diagnose MI with high accuracy and precision compared to machine learning algorithms. Tighter control limits with a confidence level of L=2 (confidence interval of 95.45%) in the control determination stage and wider control limits with a confidence level of L=3 (confidence interval of 99.73%) in the condition determination stage led to higher overall accuracy. This method can help physicians make better decisions on diagnosing cardiovascular diseases.

Keywords

• Decision support model
• Myocardial infarction
• Blood pressure monitoring
• Artificial neural network
• EWMA control chart