Journal of Arak University of Medical Sciences

Search published articles

Showing 3 results for Data Mining

Determination of Relations between Systolic Blood Pressure and Heart Attack in Patients with Type 2 Diabetes with Association Rules

Seyyed Payam Shariatpanahi, Danial Habibi, Mohammad Rafiei, Yazdan Ghandi, Mehdi Anvari,
Volume 20, Issue 12 (3-2018)

Abstract

Abstract
Background: Today, the high prevalence of diabetes and its complications are one of the most important public health issues worldwide. For this reason, finding relations between diabetes risk factors is very effective in preventing and reducing complications. For discovering these relations, the data mining methods can be used. By extracting association rules, which is one of the data mining techniques, we can discover the relations between a large numbers of variables in a disease.
Materials and Methods: The population of this study was 1046 patients with type 2 diabetes, whose data had recorded between 2011 and 2014 at the Special Clinic for Diabetes in Tehran's Imam Khomeini Hospital. After pre-processing step with SPSS19 software, 573 people entered the analysis phase. The FP-Growth algorithm was applied to the data set to discover the relations between heart attack and other risk factors using Rapid miner5 software. Relations, after extraction, were given to the doctor to confirm clinical validation.
Results: The obtained results of studying these 573 people (Including 292 (51%) women and 281 (49%) men, with age range 27 to 82 years) showed that the lack of blood pressure, creatinine and diastolic blood pressure at its normal level, despite higher systolic blood pressure level than normal, doesn't increase the probability of heart attack.
Conclusion: Using association rules is a good way of identifying relations between the risk factors of a disease. Also, it can provide new hypotheses to do epidemiological studies for researchers.

Evaluation Risk Factors of Coronary Artery Disease Through Competing Risk Tree

Ehsan Salehi, Ebrahim Hagizadeh, Mohammad Alidoosti,
Volume 21, Issue 4 (8-2018)

Abstract

Background and Aim: Advances in the field of medicine over the past few decades enabled the identification of risk factors that may contribute toward the development of coronary artery disease (CHD). However, this knowledge has not yet helped in the significant reduction of CHD incidence. The purpose of this study is to assess the risk factors of coronary artery heart events, after receiving stent, by competing risks with composite events tree. We can reduce CHD incidence with control of this risk factors.
Materials and Methods: This sectional study includes the Coronary Artery Disease (CAD) patients that received Percutaneous Coronary Intervention (PCI) cure with at least planting one stent from May 21, 2007 to May 22, 2009 in Tehran heart center. We followed patients for three years. Revascularization, nonfatal myocardial infarction, and cardiac death are considered as major acute cardiovascular events (outcome). We used decision tree with competing risks with composite events model for classification of patients. The data were analyzed by IBM SPSS Statistics 24 and R 3.3.3 softwares.
Findings: Four factors including fasting blood sugar, diabetes mellitus, body mass index and age established six homogeneous subgroups of patients for nonfatal myocardial infarction and revascularization. Maximum Revascularization incidence after 50 months was 17.8% and Maximum Nonfatal myocardial infarction was 9.7%.
Conclusion: CAD patients can reduce serious cardiac events by controling their weight and diabetes status, after receiving stent.

A Two-stage Approach Using Artificial Neural Networks for Diagnosis of Heart Diseases Based on ECG Data

Majid Mehrad, Majid Nojavan, Sedigh Raissi, Mehrdad Javadi,
Volume 25, Issue 2 (5-2022)

Abstract

Background and Aim Most heart diseases show symptoms on ECG, but diagnosing heart disease with ECG requires the knowledge and experience of medical specialized. Because these specialists may not always be available, it is necessary to design tools to diagnose heart disease in these situations. In this paper, a two-stage approach based on artificial neural networks is designed to diagnose heart disease using ECG information.In this study, we aim to propose a two-stage approach using artificial neural network (ANN) to diagnose heart disease based ECG data.
Methods & Materials To design the proposed approach, first the ECG data of 861 patients referred to medical centers in Arak, Iran were collected. The data were examined based on the opinions of specialists. Then, 154 features from ECG were used as inputs to the proposed model. In the first stage, an ANN was used to detect the ECG status (usable and unusable). In the second stage, using the usable ECG data, an ANN was used to diagnose the presence or absence of heart disease. Finally, the performance of the two-stage approach was evaluated and its accuracy and precision in determining the ECG quality and heart disease diagnosis were determined.
Ethical Considerations This study was approved by the ethics committee of Arak University of Medical Sciences (Code: IR.ARAKMU.REC.1400.138).
Results In the proposed approach, the ANN used for the determining the ECG status had a precision of 97.1% and an accuracy of 97.3%. The ANN used for the diagnosis of heart disease had a precision of 95.8% and an accuracy of 95.4%.
Conclusion Considering the high efficiency of the proposed approach in determining of ECG status and diagnosing heart disease, it is possible to use this approach to help the treatment staff.

Page 1 from 1

Designed & Developed by : Yektaweb