Search or add a thesis

Advanced Search (Beta)
Home > Statistical Analysis of the Risk Factors of Myocardial Infarction in Pakistan Using Logistic Regression and Neural Network

Statistical Analysis of the Risk Factors of Myocardial Infarction in Pakistan Using Logistic Regression and Neural Network

Thesis Info

Access Option

External Link

Author

Khan, Muhammad Zubair

Program

PhD

Institute

Hajvery University

City

Lahore

Province

Punjab

Country

Pakistan

Thesis Completing Year

2018

Thesis Completion Status

Completed

Subject

Statistics

Language

English

Link

http://prr.hec.gov.pk/jspui/bitstream/123456789/12317/1/MUhammad%20zubair%20khan%202018%20hajvery%20lhr%20prr.pdf

Added

2021-02-17 19:49:13

Modified

2024-03-24 20:25:49

ARI ID

1676727236741

Similar


Heart attack is a life threatening disease and its prevalence in Pakistan is 6.2%. Pakistan comprises of four provinces and its estimated population is over 190 million. Relevant literature about the MI occurrence and its epidemiology has established that both are regionspecific. A reasonable research literature about the risk factors of heart diseases exists in advanced countries, but the same is not true for an emerging state like Pakistan. Additionally, its cure necessitates extraordinary expenditures. Pakistan being the rising country is struggling to encounter this contest with insufficient resources nevertheless with tiny achievement. This work offers a compact procedure of research work in which presentation of statistical / parametric (binary LR) along with non-parametric (the ANN model) methods are used to an epidemiological research. On the contrary, this work demonstrates an instance of how the logistic regression & neural network modeling methods can be applied to investigate the etiologies & risk factors for an MI. Prior to the construction of the multiple logistic regression, simple regression analysis is performed and only the independent variables holding p-value < 0.2 are selected for the ultimate inclusion to the Multiple Logistic Regression model. Outlier’s detection, autocorrelation examination and multicollinearity Identification are performed in advance. On the other hand the neural network model is run with all the collected data for comparison of results to the LR model. On relating the outcomes from both the methods, 16 variables are significantly linked to heart attack. It is possibly established that a harmonious group of etiologies & risk factors, from both logistic regression and neural networks is recognized which indicates that ANN is a powerful alternative technique to recognize etiologies & risk factors for heart attack in Pakistan. Generally, both models performed at equal level. In all the models chest pain remained the most significant variable proving that it is the most alarming etiology / symptom of a heart attack in our country. The risk factors found significant in both male and female models are; chest pain, family history, obesity, cholesterol level, smoking, physical activity, hypertension, diabetes mellitus, breathing problem, less intake of fish, psychosocial factors, & easily angered. Similarly, on provincial classification of data, and on comparison, the variables gender, living environment, marital status, ethnicity, sleeping duration, obesity, tobacco use, life style and hypertension are not the same (differ significantly) in all the four provinces and vary from one province to other. In short, it is certified in the study that certain probable etiologies & risk factors belong to eating habits, psychological activities, family history, medical history and socioeconomic status of the cases. But most of the variables are associated to case’s medical history which expose that these factors are leading to myocardial infarction in the country. Analysis is performed using SPSS version 19 & AMOS version 18 at Aksaray University, Turkey.
Loading...

Similar Thesis

Showing 1 to 20 of 100 entries
TitleAuthorSupervisorDegreeInstitute
PhD
Hajvery University, Lahore, Pakistan
PhD
Government College University, Lahore, Pakistan
PhD
Government College, Lahore, Pakistan
PhD
University of Karachi, Karachi, Pakistan
Mphil
Quaid-i-Azam University, Islamabad, Pakistan
MS
International Islamic University, Islamabad, Pakistan
PhD
Quaid-I-Azam University, Islamabad, Pakistan
PhD
Allama Iqbal Open University, Islamabad, Pakistan
Mphil
Quaid-i-Azam University, Islamabad, Pakistan
Mphil
Allama Iqbal Open University, Islamabad, Pakistan
Mphil
Quaid-i-Azam University, Islamabad, Pakistan
Allama Iqbal Open University, Islamabad, Pakistan
PhD
Government College University, Lahore, Pakistan
PhD
Government College, Lahore, Pakistan
PhD
Government College University, Lahore, Pakistan
Allama Iqbal Open University, Islamabad, Pakistan
Mphil
Quaid-i-Azam University, Islamabad, Pakistan
PhD
University of Peshawar, Peshawar, Pakistan
University of Engineering and Technology, Lahore, Pakistan
MS
International Islamic University, Islamabad, Pakistan
TitleAuthorSupervisorDegreeInstitute
Showing 1 to 20 of 100 entries

Similar News

Loading...

Similar Articles

Loading...

Similar Article Headings

Loading...