A Fuzzy expert system for prescribing atorvastatin optimum dose

authors:

avatar ensiyeh Dosthoseini , avatar Majid Hassanpourezatti ORCID , * , avatar Hamieza Navidi , avatar Taha Abachi


how to cite: Dosthoseini E, Hassanpourezatti M, Navidi H, Abachi T. A Fuzzy expert system for prescribing atorvastatin optimum dose. koomesh. 2011;13(1):e152489. 

Abstract

  Introduction: Today, Fuzzy expert systems have helped physicians in cases of uncertainty in medical decision making for prescribing drugs. Narrowing of coronary heart and reduction in heart blood flow are important causes of coronary heart disease (CHD). Control of blood lipid level is a routine treatment in CHD patients. But damage to liver is a common side effect of lipid lowering drug medication. Measurement of plasma Alanine aminotransferase level is considered as a marker of liver damage. The aim of this study was to determination of optimal dose of atorvastatin using Fuzzy expert system.   Materials and Methods: in this study, Fuzzy expert system based on drug dose determination was chosen for prescribing atorvastatin dose as a lipid lowering drug that sets with demographic information of patients. Here, optimum dose is defined as a dose that decreases plasma LDL with the least side effects. In our model, decrease in LDL, Cholesterol and LDL/ HDL blood ratio consider as positive consequence and increase in plasma ALT as the side effect of this drug.   Results: output of our model is compared double blindly with prescription of many different randomly chosen expert physicians in the same practical case and the physician decision shows %65 similarity with our model. Practically, this percent of similarity between model and practical results was considered to be sufficient to approve this model.   Conclusion: This result showed that the quality of this fuzzy models output is close to clinically approved decision. Thus this model can be considered as an applicable decision making model for physician and pharmaceutical industries about dosing of this drug in a similar situation.