(PDF) Measuring Heart Attack Possibility using Different Types of Machine Learning

A Research Paper on
Application of Logistic Regression on Heart Attack Possibility
Submitted to: Submitted by:
Prof. Kamaljit Singh Saini Jitender Kumar
20MCA1050

University institute of computing, Chandigarh university, Punjab (Gharuan),India
Introduction:
People are very much concerned about their health. Heart attack is one of the major reasons
behind the deaths these days. A large population is prone to heart attacks. However, with the
advancements in Machine Learning one can predict the possibility of heart attacks in any
individual. With the study of various factors like age, sex, blood pressure, cholesterol level,
maximum heart rate achieved etc, we can predict the possibility of the heart attack. Logistic
regression is one if the ways to achieve this. Thus, we will discuss whether machine learning
algorithm i.e. Logistic Regression is useful or not or how much useful it is in the area of
Health Care.
The logistic model is used in statistics to model the probability of a particular class or event
existing such as win/lose, pass/fail, dead/alive or healthy/sick. This can be extended to model
several classes of events such as determining whether an image contains a cat, dog, lion, etc
or orange, apple, lemon, etc. Each object being detected in the image would be assigned a
probability between the values 0 and 1. Logistic regression is one of the statistical models
which are being used widely in the field of machine learning. This model uses a logistic
function to model a binary dependent variable.
History:
The name "logistic" was given by Pierre François Verhulst in the 1830s and 1840s as he
developed the logistic regression, under the guidance of Adolphe Quetelet. Earlier, Verhulst
did not specify how he fit the curves to the data. But later he determined the three parameters
of the model by making the curve pass through three observed points which resulted in poor
predictions. The logistic function was rediscovered as a model of population growth in 1920
by Raymond Pearl and Lowell Reed which led to its wide use in modern statistics. The probit
model was developed by Chester Ittner Bliss in 1930s. The probit model influenced the
further development of the logit model and these two models competed with each other.
Earlier logit model was used as an alternative to the probit model in bioassay. It was treated
as inferior to the probit model. But later, it gradually surpassed the probit model. This was
due the use of logit model outside the bioassay as the model gained much popularity. In 1973
Daniel McFadden linked the multinomial logit to the theory of discrete choice,stating that the
multinomial logit followed from the assumption of independence of irrelevant alternatives