Majid Hassanzadeh, Iman Zabbah, Kamran Layeghi,
Volume 5, Issue 2 (9-2018)
Abstract
Introduction: Coronary Artery Disease (CAD) is one of the most common heart diseases and the main cause of mortality in men and women. This study aimed to predict the disease status using Neural Network compound (mixture of experts).
Methods: The present study was a diagnostic study conducted on 200 patients referred to a heart specialty center in Torbat-e-Heydarieh. Patients' files contained their demographic information including13 risk factors. A model for predicting CAD based on multilayer perceptron neural network and mixture of experts was produced.
Results: First, we used a neural network of multilayer perceptron with Propagation algorithm by different architectures. The best architecture could predict closed coronary artery with the accuracy of 71.7%. Then, by increasing the number of neural networks and training process, results were combined. Mixture of experts by liner method (majority voting) and nonlinear method (gating network) was applied and the accuracy rates of 75.8 percent and 78.3 percent were respectively obtained.
Conclusion: Angiography is an invasive diagnostic procedure with risk factors such as stroke and heart attack. Therefore, non-invasive methods should be used for the diagnosis of CAD. In this study, with increasing the number of learners and their nonlinear mixture, the accuracy of diagnosis was increased.
Seyedeh Raahil Mousavi, Mohammad Mehdi Sepehri,
Volume 5, Issue 4 (3-2019)
Abstract
Introduction: cardiovascular diseases are becoming the main cause of mortality and morbidity in most countries. This research goal was to predict the types of heart diseases for more accurate diagnosis by data mining and neural network technics.
Method: This research was an applied-survey study and after data preprocessing, three approaches of neural network, decision making tree and Bayes simple algorithm were used to predict and recognize in Rapidminer software and neural artificial network model was used for prediction in Matlab software.
Results: Genetic algorithm was used for selection of effective variables and neural artificial network models, decision making tree and Bayes simple algorithm were used to predict types of heart diseases in data mining. AHP model was used to determine a model with the best performance for predicting types of heart diseases.
Conclusion: Neural network had much better performance than other data mining models used to diagnose types of heart diseases in this research. Also, in detecting disease by artificial neural network, the model with accuracy of more than 80 percent was verified as good and acceptable
Narges Norouzkhani , Mohammad Mehdi Sepehri,
Volume 7, Issue 2 (9-2020)
Abstract
Introduction: Chronic diseases are among the most challenging health issues in the world. Although no definitive treatment has been found for such diseases, electronic health strategies can dramatically reduce their complications by enhancing patients' awareness and monitoring their treatment. The main objective of this study was to design an education-based follow-up system for cardiac patients based on mHealth.
Method: This research was an applied-developmental one. To determine the data elements, a questionnaire was developed and needs assessment was conducted with the faculty members at University of Mazandaran and 2 health system specialists. The data were analyzed using descriptive statistics and after identifying the entities, the conceptual model of the system was designed and implemented based on the Unified Modeling Language (UML). The questionnaire was finally provided to 30 cardiac patients to assess its usability and user satisfaction. The data were analyzed using descriptive statistics with SPSS Software (version 16).
Results: Some modifications were made to the system based on end users’ opinions and ultimately the system was developed with 7 parts including interaction with physician, remote visit, training, notification of medication intake, prescription, follow-up monitoring of patients, and communication with the emergency ward. The final evaluation of usability and user satisfaction showed that users rated the program with a mean score of 7.17 out of 9 at a good level.
Conclusion: Given that users evaluated the system as good, it can provide effective interaction between physician and patient and monitor patient care along with ongoing training to improve the treatment process.
Mostafa Langarizadeh , Amir Homayoun Rostampour , Fereydon Noshirvan Rahat Abad , Mohammad Hossein Langarizadeh , Fatemeh Sarpourian , Seyed Ali Fatemi Aghda ,
Volume 10, Issue 2 (9-2023)
Abstract
Introduction: Cardiovascular disease is one of the main causes of death worldwide. One of the important factors is readmission due to the lack of training. Considering the widespread use of mobile phones, this study aimed to design a recommender system for patients with cardiac arrhythmia.
Method: This is an applied-developmental study that was conducted in a quantitative (descriptive) method and in 2 stages. First, the recommended educational parameters and application requirements of the software were determined based on literature review. Then, the obtained contents were provided to 16 cardiologists working in Shahid Rajaei and Hazrat Rasool Akram Hospitals in Tehran. To evaluate the usability, the application was given to 50 patients with cardiac arrhythmia and was checked with the quiz questionnaire version 5.5.
Results: In the recommendations section, experts deemed all items except "Omega-3 consumption" necessary. In the usability evaluation section, the items "Identifying the nearest emergency center, sending the patient’s geographic location to the doctor, finding the nearest medical center, and the possibility of changing color, and calculating BMI" were not confirmed. The usability evaluation of the application with an average score of 7.98±0.62 indicates a good level.
Conclusion: The mobile-based recommender application can cause the patients to play a greater role in their treatment and acquire skills in the field of training after hospital discharge and lead to a reduction in re-hospitalization and cost.
