CARDIAC PREDICTION WITH EXPLORATORY DATA ANALYSIS USING R3 TECHNOLOGY

Abstract

ABSTRACT Heart disease rates among Indian men are notably high compared to many other countries, and this has become a significant public health concern in India. More than that it is the major leading cause of death in India contributing to 35% of all types of death. Indian men are more likely to develop Coronary Artery Disease (CAD at a younger age. For example, the onset of CAD occurs literally 11 years earlier in Indian men compared to their Western counterparts. Statistics, Machine Learning and Deep Learning report on heart disease in Indian Men says 145 per 1,00,000, but in other west.side the rate is 109 per lakh one in four deaths in India is now caused by heart disease, and the burden is increasing, especially among younger populations (30-40 years old). Western countries have made significant progress in reducing heart disease rates through better healthcare systems, diet, stress management and high preventive measures, but our country is facing a rising burden due to changing lifestyle food habits, genetic factors, poor knowledge to healthcare, increasing rates of diabetes and hypertension and so on. Level is higher in urban areas because of their lifestyle and poor stress management. Besides genetics factor also play a vital role. Research has shown that Indian men are more likely to have a genetic predisposition to heart disease, which may explain why heart disease appears at a younger age compared to Western populations. Continues to rise due to a combination of genetic, environmental, and sedentary life style especially IT workers. Compared to other countries, Indian men are facing a disproportionately high incidence of heart disease, often at a younger age, making it a critical public health issue. Dated this 19th day of November 2024 Signature:- Name orthe signatory:- Dr.A.Ponnusamy PRINCIPAL Hindusthan College of Arts & Science (Autonomous), Hindusthan Gardens. Behind Nava India, Coimbatore - 641 028.

Specification

FORM 2
THE PATENT ACT 1970
(39 OF 1970)
&
The Patents Rules, 2003
PROVISIONAL / COMPLETE SPECIFICATION
See Section 10 and rule 13)

1. TITLE OF THE INVENTION
Cardiac Prediction with Exploratory Data Analysis using R3 Technology
2. APPLICANT(S)
a) NAME : HINDUSTHAN COLLEGE OF ARTS & SCIENCE
b) NATIONALITY:INDIAN
c) ADDRESS: HINDUSTHAN COLLEGE OF ARTS & SCIENCE, COIMBATORE 28
3. PREAMBLE TO-THE DESCRIPTION
PROVISIONAL COMPLETE
The following specification particularly
describes the invention and the manner in which it is to be performed.
4. DESCRIPTION (Description shall start from next page.)

Cardiac Prediction with Exploratory Data Analysis using R3 Technology
Technical Field of Invention
Computer Science

BACKGROUND OF THE INVENTION
Heart disease, remains a leading cause of mortality worldwide, presenting a significant public health concern. The challenge lies in identifying and understanding the intricate interplay of various factors contributing to heart disease. This project aims to leverage Power Bl's analytical capabilities to analyze a comprehensive heart disease dataset, with the objective of risk factors associated with heart disease based on the provided dataset. Develop predictive models using machine learning algorithms to assess heart disease risk based on identified predictors. Utilize Power BI to create intuitive, interactive visualizations that effectively communicate insights gleaned from the dataset to aid healthcare professionals in better understanding heart disease risks.

OBJECTIVES OF THE INVENTION
Comprehensive Analysis: A more thorough understanding of heart disease can be obtained by combining disparate information and investigating the complex interactions between different risk variables, made possible by Power BI.

Real-time Insights: Because Power BI is interactive, it allows for real-time analysis and visualization updates, giving medical practitioners access to the most up-to-date data for choices.

Predictive Modeling: Power BI facilitates the development of predictive models for heart disease risk assessment by seamlessly integrating with machine learning algorithms, providing more precise and individualized insights than conventional techniques.
Collaboration and Accessibility: Power Bl's cloud-based features make it possible to obtain insights from any location, which makes it easier for academics, policymakers, and healthcare teams to work together.

DESCRIPTION OF THE INVENTION
This platform is used to find genetic susceptibilities to heart disease, include genetic data in the study. This would entail incorporating genetic testing data and using Power Bl's features to examine genetic variations and how they relate to the risk of heart disease. Collection of realtime patient health data, integrate remote patient monitoring devices, such as smart health devices and wearable fitness trackers. This data may be analyzed using Power Bl in conjunction with conventional clinical data to provide a more thorough picture of patient health and enable preventative measures. Improving interoperability and data interchange by strengthening integration with EHR systems. This would enable continuity of care across healthcare facilities and enable a more thorough study of patient health data.Investigate cutting-edge visualization strategies, like immersive virtual reality experiences and interactive 3D representations, to offer a more user-friendly and captivating study of heart disease data. To identify vulnerable populations and implement focused interventions, include heart disease analysis into larger population health management programmes. Power Bl can assist in monitoring health trends at the population level and monitoring the long-term efficacy of interventions.

Deep learning has the potential to revolutionize the detection, treatment, and management of heart
disease by providing more accurate, timely, and personalized care. From early detection through
medical imaging and ECG analysis to predicting risk and'tailoring treatment plans, Al-powered
models are making significant strides in improving cardiovascular health outcomes. However,
further advancements in data availability, model transparency, and integration into healthcare
systems will be key to fully realizing its potential in the fight against heart disease.
Power BI Data collection and analyzing

PROPOSED SYSTEM
Deep Learning , Machine Learning and Al technology has been increasingly applied to this
healthcare particularly.in the diagnosis, prediction, and management of heart disease. The role of
deep learning in this domain has expanded rapidly due to advancements in data availability, data
clensing , computational power, and Al algorithms. Here's how deep learning is contributing to the
fight against heart disease, Deep learning models, especially convolutional neural networks
(CNNs), can analyze these images with high accuracy to detect early signs of heart disease,
including coronary artery disease, heart failure, and valvular diseases
For example, CNNs have been shown to identify coronary artery blockages and plaques in
angiograms and CT coronary angiograms.

These models can detect arrhythmias, heart attacks, and other heart-related abnormalities by
learning from a vast dataset of ECG patterns.
Al-driven ECG analysis tools can help in diagnosing conditions like atrial fibrillation (AF),
ventricular tachycardia, and other rhythm disorders, often more efficiently and accurately than traditional methods.
These models can account for a range of variables like age, sex,. hypertension, diabetes,
cholesterol levels, and family history to provide a personalized risk assessment.
For example, deep learning algorithms can combine medical history, lifestyle factors, and lab
results to predict the likelihood of heart attack, stroke, or heart failure in the next 5 to 10 years.

Wearable data: With the proliferation of wearable health devices like smartwatches and fitness trackers, deep learning algorithms can now be applied to continuous data streams (e.g.,heart rate, blood oxygen levels, activity levels) to assess cardiovascular health in real tirne and predict acute events^ such as heart attacks or arrhythmias, before they occur.

Examining the dataset to comprehend its distributions, relationships, and structure is known as exploratory data analysis. To find trends and preliminary information about heart disease, visualizations , summary statistics, and correlation analysis are employed; It involves examining the dataset to understand its structure, relationships, and distributions. Visualizations, summary statistics, and correlation analyses are used to identify patterns and initial insights related to heart disease.

Designing phase : I Treatment Plans '
By analyzing historical patient data, including clinical outcomes, treatment responses, and genetic information, deep learning models can help predict which therapies or interventions are likely to be most effective for a particular patient. Deep learning models have been used to analyze a patient's medical history and suggest the most appropriate combination of medications, lifestyle changes, and interventions (e.g., stent placement, angioplasty, bypass surgery).

Designing phase : II Drug discovery and replacement:
Statistics analysis have to be examined whether prescribed medicine will help him for the. complete recovery or the risk of that disease will be come back. By analyzing protein structures, genomic data, and clinical outcomes, Al models can identify potential drug candidates to treat heart disease more.efficiently.

Phase III - DL and ML oriented monitoring system
Deep learning models can analyze a patient's heart rate, blood pressure, oxygen levels, and respiratory rate to detect early signs of cardiac arrest, arrhythmias, or heart failure.
Remote monitoring: With advancements in telemedicine, deep learning algorithms can monitor patients remotely, using data collected from wearable devices, smartphones, and other health tracking systems. These models can flag any deviations from normal patterns and send alerts to doctors or patients about possible heart-related events, facilitating early intervention.
Genomic Data Monitoring : □ Genomic data analysis, combined with deep learning, allows researchers to identify genetic mutations and variations associated with an increased risk of cardiovascular diseases.

For example, deep learning models are being used to analyze single nucleotide polymorphisms. (SNPs) and gene expression data to pinpoint specific genetic markers for heart disease, which could eventually lead to more targeted therapies.
Predictive genomics: By integrating genomic data with other clinical parameters, deep learning can predict the risk of heart disease based on an individual's genetic makeup, facilitating personalized prevention and treatment strategies.
Enriching sound decision via correlation and regression analysis:
These systems are trained on vast datasets of patient information, medical literature, and clinical outcomes, helping doctors make more informed decisions.
For instance, Al-powered tools can suggest whether a patient should undergo additional testing (e.g., coronary angiography or stress testing) based on their risk profile, or whether they would benefit from lifestyle interventions or medications.

General Dataset for Algorithm approach:
The dataset used for this research purpose was the Public Health Dataset and it is dating from 2020 and consists of four databases from four parts of the world. It contains more than 100 attributes, including the predicted attribute, but all published experiments refer to using a subset of 15 of them. The "target" field refers to the presence of heart disease in the patient. It is integer-valued 0 = no disease and 1 = disease. Some of the attributes are Blood pressure, gene, age, sex, chest pain type, chol, Fasting blood sugar, resting electrocardiographic results, maximum heart rate achieved, Angina is a type of chest pain caused by reduced blood flow to the heart. Angina is a symptom of coronary artery disease.
3.2. Preprocessing or cleaning the dataset:
Using slopes and intercept, adequate distribution methods the results achieved are quite promising. Various plotting techniques were used for checking the skewness of the data, outlier detection, and. the distribution of the data. All these preprocessing techniques play an important role when passing the data for classification or prediction purposes.
3.2.1
Data distribution
Predict classification of heart disease and causes no disease and disease within the disease finding how many of them the root causes, withing the root causes the categorize the attributes of
So, we need to balance the dataset or otherwise it might get overfit. This will help the model to find a pattern in the dataset that contributes to heart disease and which does not as shown in Figure L
Old peak-ST depression induced by exercise relative to rest. Slope-the slope of the peak exercise ST segment. Ca-number of major vessels (0-3) colored by fluoroscopy,. Target (T)-no disease = 0 and disease = 1, (angiographic disease status).
3.2.2
Checking the linear relationship of the data
For checking the attribute values and determining the skewness of the data (the asymmetry of a distribution), many distribution plots are plotted so that some interpretation of the data can be seen.. Different plots are shown, so an overview of the data could be analyzed. The distribution of age and sex, the distribution of chest pain and trestbps, the distribution of cholesterol and fasting blood, the distribution of ecg resting electrode and thalach
3.2.4 Best fit algorithm selection
For selecting the features and only choosing the important feature, the Lasso algorithm is used which is a part of embedded methods while performing feature selection. It shows better predictive accuracy than filter methods. It renders good feature subsets for the used algorithm. And then for selecting the selected features, select from the model which is a part of feature selection in the scikit-leam library.
3.2.5checking and removing duplication and unwanted datas
The duplicates should be tackled down safely or otherwise would affect the generalization of the model. There might be a chance if duplicates are not dealt with properly; they might show up in the test dataset which is also in the training dataset.
3.5 Deep learning Proposed
There are two ways a deep learning approach can be applied. Functional deep learning approach is used. Connected dense layer is used, with the flatten and dropout layers to prevent the overfitting and the results are compared of the machine learning and deep learning and variations in the learning including computational time and accuracy can be analyzed and can be seen in the figures further discussed in the Results section.

SUMMARY OF THE INVENTION
An eye-catching graphic was created by combining exploratory data with Power BI. The platform aims to provide good healthy diet and prediction about the heart disease and its effects towards human body.

5. CLAIMS (not applicable for provisional specification. Claims should start with the preamble -
"I/We claim" on separate page)

We Claim
1. Using the techniques of Exploratory, data analysis and the software POWER BI, theproposed
system enhances the analysis which results good healthy diet and prediction about the heart disease and its effects towards human body.
2. Accurate results will be produced using software POWER BI

6. DATE. AND SIGNATURE (to be given at the end of last page of specification).

Dated this 19th day of November 2024
Signature:-
Name orthe signatory:- Dr.A.Ponnusamy
PRINCIPAL
Hindusthan College of Arts & Science (Autonomous),
Hindusthan Gardens. Behind Nava India,
Coimbatore - 641 028.

7. ABSTRACT OF THE INVENTION( to be given along with complete specification on separate
page)

Documents