---

Background and purpose: Diseases have been the greatest threat for human being along the history. ‎Heart disease (HD) has gained special attention in medical studies. Recently studying on classification and ‎diagnosis of HD as a key topic and a lot of researches have been done in order to increase precise and reduce ‎error in this type of decisions. With development of intelligent learning systems, these systems have played a ‎great role in reducing the error of decision support systems (DSS).‎ Materials and methods: In this study, a simple hybrid model of logistic regression and single-layer ‎perceptron neural network was presented which was trained with four-different learning rules (separately). ‎The model for improving the classification and patterns recognition of HD has been used on clinical data of ‎‎270 patients from the Cleveland Clinic (UCI website). This method has been used in statistical data ‎normalization and detection of noisy data, network training with only 20% of the data exist was performed. ‎The model has been implemented in MATLAB.‎ Results: The mean-error of the proposed model on the total dataset was 11.11%, which was achieved a ‎significant improvement compared to recent similar methods. In addition, the results showed that the proposed ‎approach was very capable in dealing with noise in the data‏.‏ Conclusion: The results clearly showed that the linear proposed technique had large impact on ‎reducing the error in the classification and identification of patients more accurately in a shorter time than ‎conventional methods and complex nonlinear. The method can help physicians for early detection of disease ‎or as a DSS.‎

---

Background and purpose: This study aimed to investigate the factors associated with smoking initiation and continuation in Isfahan. Material and methods: An analytical cross-sectional study was conducted based on Isfahan Healthy Heart Program. To calculate the crude and adjusted odds ratios uni- and multi-variable logistic regressions were used. The group with lowest rate of smoking was considered as the base group and Odds Ratio with 95% confidence interval was reported. Results: The study population included 3164 individuals, of whom 12.3% (male 23.3%, female 01.4%) were current smokers. The odds ratio of smoking was 8.53 (CI: 4.37-16.57) in men, 1.17 (CI: 0.8-1.71) in rural areas and 4.52 (CI: 1.22-16.7) in illiterate people. Among the subjects the relative risk of smoking was seen higher in those aged 19-24 and 25-34 years of old. Home was found as the most common place for smoking (32.64%) and the most frequent condition for smoking was when the subjects were in angry moods (36.70%). The main cause of initiation or continuation of smoking was enjoyment (45.65%). Conclusion: Most consumers of cigarettes were men, individuals with low educational backgrounds, self-employed or unemployed and rural populations. Therefore, more training programs are needed to enhance the knowledge and attitude in these people and conducting efficient smoking cessation programs could be of great benefit in reducing the rate of smoking.

---

Background and purpose: Coronary artery disease (CAD) is the most common cause of death in many countries. Therefore, identification of risk factors for CAD is essential to carry out preventive measures. The aim of this study was using logistic regression model to determine the risk factors for cardiovascular disease in a population aged above 35 years.

Materials and methods: This cross-sectional study was carried out using the records of 477 patients over 35 years of age who had angiogram in Fatima_Zahra Heart Hospital in sari during 2015 to 2016. The information extracted included the age, gender, location, family history of premature CVD, smoking, body mass index (BMI), blood pressure, fasting blood sugar (FBS), total cholesterol, triglycerides (TG), HDL cholesterol, and LDL cholesterol. The patients were divided into two groups of with or without at least one vessel with stenosis above 50%.  Logistic regression model was used to study the risk factors associated with CAD.

Results: The patients included 158 male and 319 female, mean age 58.45± 10.7 years. There were 268 (56.2%) cases who had at least one vessel with stenosis above 50%.  The multivariate logistic regression model showed age (OR=1.57, P=0.003), gender (OR=7.38, P<0.001), FBS (OR=1.97, P=009) HDL cholesterol (R=2.42, P=0.018), and triglycerides (OR=1.97, P=0.012) to be significantly associated with increase in severity of CAD.

Conclusion: The multivariate logistic regression model showed some factors such as gender, HDL cholesterol, triglycerides, fasting blood glucose and age as the main risk factors for developing CAD.

---

Background and purpose: Understanding of the risk factors for cardiovascular artery disease, which is the leading cause of death worldwide, can lead to essential changes in its etiology, prevalence, and treatment. The aim of this study was to compare the results of logistic regression model and Classification and Regression Tree Analysis (CART) in determining the prognostic factors for coronary artery disease in people living in Mashhad, Iran.
Materials and methods: The present case-control study used the cohort data of Mashhad stroke and heart atherosclerotic disorder (MASHAD STUDY), 2009. The prognostic factors for coronary artery disease were determined by CART and Logistic regression models using R and Stata 14. Then, the efficiency of the models was compared by computing the area under the performance characteristic curve (AUC). All patients with coronary artery disease were considered as the case and for each case, three controls were selected.
Results: According to Logistic model, prognostic factors for coronary artery disease included age, history of myocardial infarction, diabetes, history of hyperlipidemia, and family history of heart disease (father and brother). The CART algorithm showed age, history of myocardial infarction, history of hypertension, depression, physical activity level, and body mass index as prognostic factors for coronary artery disease in people in Mashhad.
Conclusion: Myocardial infarction and age were common prognostic factors for coronary artery disease according to the models applied. According to the efficiency of logistics model, binary multiple logistic regression model is suggested to be used in identifying the factors affecting coronary artery disease, if there is no interaction between the predictors.

---

 Background and purpose: Hypertension is a global problem due to its consequences. Recognizing warning signs and taking necessary measures are effective in preventing the disease and its complications. We used the logistic regression model to determine the factors affecting blood pressure based on the results of the Tabari Cohort Study.
Materials and methods: This cross-sectional descriptive-analytical study was conducted in people older than 35 years old in Sari, whose information (demographic and anthropometric characteristics, and risk factors) was available at the Tabari Cohort Center in Mazandaran province. Logistic regression model was used to determine the factors affecting hypertension. We did statistical analyses using SPSS V26.
Results: The participants included 6622 people (41.3% men) with an average age of 48.97±8.94 years old. There were 1481 people with high blood pressure (22.4%). According to multivariate logistic regression model, age (10-year period) (OR=2.04-8.11), body mass index (OR=1.72-2.35), total cholesterol (OR=1.34), triglyceride (OR=1.30), the ratio of waist to hip circumferences (OR=1.31), history of cardiovascular diseases (OR=2.09), and diabetes (OR=1.81) were among the factors associated with hypertension (P<0.05).
Conclusion: According to the results of the multivariable logistic regression model, obesity management as the main factor and screening of people for diagnosis, follow-up, and prevention of hypertension are suggested.
 

---

Background and purpose: The status of axillary lymph nodes (ALN) is the most important prognostic factor in patients with primary breast cancer. The aim of this study is to measure the relationship between the factors influencing metastasis to the lymph nodes in patients with breast cancer.
Materials and methods: The present study is a retrospective cohort study. The research data were extracted from telephone interviews and medical records of 241 breast cancer patients in Mazandaran Medical Sciences Hospitals. For data analysis, the chi-square test and multiple logistic regression model using principal component analysis were used to determine the relationship between factors affecting metastasis to lymph nodes. All statistical analyses were performed using Stata software version 17, R and SPSS software version 26.
Results: The average age of patients at diagnosis is 52.03±10.932 years test revealed a significant correlation between the markers ER, PR, P53, Her2 and Ki67(P<0.05). After removing collinearity using principal component analysis, the variables age, tumor size, skin involvement, grade, tubule formation and nuclear pleomorphism were selected as input variables for multiple regression. The variable grade was significant with a p-value of 0.012.
Conclusion: It is very important to identify the factors that may be effective in predicting response to treatment or disease progression. In short, there is a significant correlation between the markers ER, PR, P53, Her2 and Ki67, and the variable grade is an important factor for lymph node metastasis.