Tehran University Medical Journal

---

Background: Warfarin is the most common oral anticoagulant. This drug is used for the prevention and treatment of thromboembolic patients. It is difficult for physician to predict the results of warfarin prescriptions because there is narrow boundary between therapeutic range and complications of warfarin. Therefore drug dose adjustment is normally performed by an expert physician. Decision support systems that use extracted knowledge from experts in the field of drug dose adjustment would be useful in reducing medical errors, especially in the clinics with limited access to experts. The aim of this study was to propose a method for boosting the maintenance dose of warfarin for a maximum period of three days to eliminate disruptions in International Normalized Ratio (INR). Methods: In a retrospective study, from December 2013 to February 2014 in Shahid Rajaee Heart Center, Tehran, Iran, 84 patients with International Normalized Ratio below (INR) the therapeutic range was selected who was undergone a boosting dose during three days. Patients with unstable maintenance dose were excluded from the study. In this study, data from 75 patients receiving warfarin therapy were used for developing and evaluation of the proposed model. The INR target range for 37 patients out of remaining 75 cases was between 2.5 and 3.5, while for 38 patients the intended INR range was between 2 and 3. A separate fuzzy model was designed for each of the above-mentioned therapeutic ranges. Results: The recommended dose for 37 patients having INR therapeutic range of 2.5 to 3.5 has mean absolute error and root mean squared error of 1.89 and 2.78 respectively for three days. These error rates are 1.97 and 2.88 respectively for 38 patients who are in therapeutic range 2 to 3. Conclusion: The results are promising and encourage one to consider this system for more study with the aim of possible use as a decision support system in the future.

---

Background: Warfarin is one of the most common oral anticoagulant, which role is to prevent the clots. The dose of this medicine is very important because changes can be dangerous for patients. Diagnosis is difficult for physicians because increase and decrease in use of warfarin is so dangerous for patients. Identifying the clinical and genetic features involved in determining dose could be useful to predict using data mining techniques. The aim of this paper is to provide a convenient way to select the clinical and genetic features to determine the dose of warfarin using artificial neural networks (ANN) and evaluate it in order to predict the dose patients.

Methods: This experimental study, was investigate from April to May 2014 on 552 patients in Tehran Heart Center Hospital (THC) candidates for warfarin anticoagulant therapy within the international normalized ratio (INR) therapeutic target. Factors affecting the dose include clinical characteristics and genetic extracted, and different methods of feature selection based on genetic algorithm and particle swarm optimization (PSO) and evaluation function neural networks in MATLAB (MathWorks, MA, USA), were performed.

Results: Between algorithms used, particle swarm optimization algorithm accuracy was more appropriate, for the mean square error (MSE), root mean square error (RMSE) and mean absolute error (MAE) were 0.0262, 0.1621 and 0.1164, respectively.

Conclusion: In this article, the most important characteristics were identified using methods of feature selection and the stable dose had been predicted based on artificial neural networks. The output is acceptable and with less features, it is possible to achieve the prediction warfarin dose accurately. Since the prescribed dose for the patients is important, the output of the obtained model can be used as a decision support system.