Page 1 of 23 - Cover Page Submission ID trn:oid:::1:3121392805

HH
B14 Synopsis
Thesis

PROJECT

ABES Engineering College

Document Details

Submission ID

trn:oid:::1:3121392805 18 Pages

Submission Date 2,439 Words

Dec 23, 2024, 4:26 PM GMT+5:30

14,901 Characters

Download Date

Dec 23, 2024, 4:33 PM GMT+5:30

File Name

Final_Sys.docx

File Size

299.6 KB

Page 1 of 23 - Cover Page Submission ID trn:oid:::1:3121392805

 Page 2 of 23 - Integrity Overview Submission ID trn:oid:::1:3121392805

13% Overall Similarity

The combined total of all matches, including overlapping sources, for each database.

Exclusions
33 Excluded Matches

Match Groups Top Sources

35 Not Cited or Quoted 13% 10% Internet sources

Matches with neither in-text citation nor quotation marks
8% Publications
0 Missing Quotations 0% 4% Submitted works (Student Papers)
Matches that are still very similar to source material

0 Missing Citation 0%
Matches that have quotation marks, but no in-text citation

0 Cited and Quoted 0%

Matches with in-text citation present, but no quotation marks

Integrity Flags
0 Integrity Flags for Review
Our system's algorithms look deeply at a document for any inconsistencies that
No suspicious text manipulations found. would set it apart from a normal submission. If we notice something strange, we flag
it for you to review.

A Flag is not necessarily an indicator of a problem. However, we'd recommend you

focus your attention there for further review.

Page 2 of 23 - Integrity Overview Submission ID trn:oid:::1:3121392805

 Page 3 of 23 - Integrity Overview Submission ID trn:oid:::1:3121392805

Match Groups Top Sources

35 Not Cited or Quoted 13% 10% Internet sources

Matches with neither in-text citation nor quotation marks
8% Publications
0 Missing Quotations 0% 4% Submitted works (Student Papers)
Matches that are still very similar to source material

0 Missing Citation 0%
Matches that have quotation marks, but no in-text citation

0 Cited and Quoted 0%

Matches with in-text citation present, but no quotation marks

Top Sources
The sources with the highest number of matches within the submission. Overlapping sources will not be displayed.

1 Internet

[Link] 1%

2 Publication

Pawan Singh Mehra, Dhirendra Kumar Shukla. "Artificial Intelligence, Blockchain,… 1%

3 Internet

[Link] 1%

4 Student papers

Coventry University 1%

5 Student papers

London School of Commerce 1%

6 Internet

[Link] 1%

7 Student papers

Higher Education Commission Pakistan 1%

8 Publication

Md. Sahadat Hossain, Md. Alamin Talukder, Md. Zulfiker Mahmud. "Advancement… 1%

9 Student papers

The Northcap University 1%

10 Internet

[Link] 1%

Page 3 of 23 - Integrity Overview Submission ID trn:oid:::1:3121392805

 Page 4 of 23 - Integrity Overview Submission ID trn:oid:::1:3121392805

11 Internet

[Link] 1%

12 Internet

[Link] 0%

13 Internet

[Link] 0%

14 Publication

Sadeq Darrab, David Broneske, Gunter Saake. "Exploring the predictive factors of … 0%

15 Student papers

Liverpool John Moores University 0%

16 Internet

[Link] 0%

17 Internet

[Link] 0%

18 Internet

[Link] 0%

19 Internet

[Link] 0%

20 Internet

[Link] 0%

21 Internet

[Link] 0%

22 Internet

[Link] 0%

23 Internet

[Link] 0%

24 Publication

H.L. Gururaj, Francesco Flammini, S. Srividhya, M.L. Chayadevi, Sheba Selvam. "Co… 0%

Page 4 of 23 - Integrity Overview Submission ID trn:oid:::1:3121392805

 Page 5 of 23 - Integrity Overview Submission ID trn:oid:::1:3121392805

25 Publication

Zhenya Qi, Zuoru Zhang. "Diagnosis of Heart Disease Using a Novel Membership … 0%

26 Internet

[Link] 0%

27 Internet

[Link] 0%

Page 5 of 23 - Integrity Overview Submission ID trn:oid:::1:3121392805

 Page 6 of 23 - Integrity Submission Submission ID trn:oid:::1:3121392805

Synopsis Report
on

Advancing Smarter Healthcare with Machine Learning

Models for Heart Disease Detection
Submitted as requirement for the

Final Year Project

Session 2024-25

By:

Divyansh Pandey

2100321530068

Manish Kumar Pandey

2100321530096

Md Hasmat Ansari

210032153010

Under the guidance of:

Mr. Waseem Ahmed
Assistant Professor

DEPARTMENT OF CSE-AIML
ABES ENGINEERING COLLEGE, GHAZIABAD

AFFILIATED TO
DR. A.P.J. ABDUL KALAM TECHNICAL UNIVERSITY, U.P., LUCKNOW
(Formerly UPTU)

Page 6 of 23 - Integrity Submission Submission ID trn:oid:::1:3121392805

 Page 7 of 23 - Integrity Submission Submission ID trn:oid:::1:3121392805

Student’s Declaration
I / we hereby declare that the work being presented in this report entitled “Towards
Smarter Healthcare: Machine Learning Models for Heart Disease Detection” is an
authentic record of my/ our own work carried out under the supervision of Mr. Waseem
Ahmed, Assistant Professor, CSE-AIML. The matter embodied in this report has not
been submitted by us anywhere else.

Date:

Signature of student Signature of student

(Name: Divyansh Pandey) (Name: Manish Kumar Pandey)

(Roll No. 2100321530068) (Roll No. 210321530096)

Department: CSE-AIML Department: CSE-AIML

Signature of student

(Name: Md Hasmat Ansari)

(Roll No. 2100321530102)

Department: CSE-AIML

This is to certify that the above statement made by the candidate(s) is correct to the best
of my knowledge.

Signature of HOD Signature of Supervisor

…………………… Mr. Waseem Ahmed

CSE-AIML Assistant Professor

Date: CSE-AIML

i
Page 7 of 23 - Integrity Submission Submission ID trn:oid:::1:3121392805
 Page 8 of 23 - Integrity Submission Submission ID trn:oid:::1:3121392805

Acknowledgement

We would like to convey our sincere thanks to Mr. Waseem Ahmed for giving the
motivation, knowledge and support throughout the course of the project. The continuous
support helps in a successful completion of project. The knowledge provided is very useful
for us.
We also like to give a special thanks to the department of CSE-AIML for giving us the
continuous support and opportunities for fulfilling our mini project.

Signature of student Signature of student Signature of student

Divyansh Pandey Manish Kumar Pandey Md Hasmat Ansari

(Roll No. 2100321530068) (Roll No. 210321530096) (Roll No. 2100321530102)

ii
Page 8 of 23 - Integrity Submission Submission ID trn:oid:::1:3121392805
 Page 9 of 23 - Integrity Submission Submission ID trn:oid:::1:3121392805

Table of Contents

S. No. Contents Page No.

Student’s Declaration i
Acknowledgement ii
List of Figures iv
Abstract v

Chapter 1: Introduction 1

Chapter 2: Related Work/Methodology 3

2.1: Existing Approaches 3

2.2: Comparative Analysis of Existing Works 3

Chapter 3: Project Objective 4

Chapter 4: Proposed Methodology 5

Chapter 5: Design and Implementation 7

5.1: Work Flow Diagram 7

Chapter 6: Results and Discussion 8

Chapter 7: Conclusion and Future Scope 9

References 12

iii
Page 9 of 23 - Integrity Submission Submission ID trn:oid:::1:3121392805
 Page 10 of 23 - Integrity Submission Submission ID trn:oid:::1:3121392805

List of Figures

Figure No and name Page No.

Fig.1. Proposed Approach 4

5
Fg.2. Work Flow Diagram
6
Fig.3. Proportion of positive, negative and neutral
tweets.

iv
Page 10 of 23 - Integrity Submission Submission ID trn:oid:::1:3121392805
 Page 11 of 23 - Integrity Submission Submission ID trn:oid:::1:3121392805

ABSTRACT

3 Cardiovascular diseases (CVDs) remain a leading cause of death globally, responsible for an

estimated 17.9 million deaths each year. According to the World Health Organization (WHO),

this figure represents 32% of all global deaths, with heart disease being the most common

14 type of cardiovascular ailment. Despite advances in medical technology and healthcare, the

early detection and timely diagnosis of heart disease are often constrained by the limitations

of traditional diagnostic approaches. These traditional methods, which include physical

examinations, medical imaging, and invasive procedures, typically occur after symptoms

have manifested, leading to late-stage interventions when the damage to the heart may

already be irreversible. The challenge lies in the identification of heart disease risk before

symptoms occur, enabling preventative treatments or lifestyle interventions that could

21 significantly reduce the mortality rate. The advent of machine learning (ML) and artificial

1 intelligence (AI) in healthcare has opened new avenues for the prediction and diagnosis of

heart disease. Machine learning, by leveraging vast amounts of clinical data, offers the

13 potential for faster, more accurate diagnosis. ML models can identify subtle patterns and

relationships within the data that may be overlooked by traditional statistical methods.

23 Additionally, ML can handle complex, multi-dimensional datasets, allowing for the inclusion

of a broad range of patient characteristics, including demographic data, lifestyle factors,

medical history, and non-invasive test results.

v
Page 11 of 23 - Integrity Submission Submission ID trn:oid:::1:3121392805
 Page 12 of 23 - Integrity Submission Submission ID trn:oid:::1:3121392805

Chapter 1

Introduction

Heart Disease, a broad term encompassing various cardiovascular conditions such as

coronary artery disease, heart failure, arrhythmia, and cardiomyopathy, remains a leading

cause of death globally. Despite remarkable advances in medical science and healthcare

26 systems, cardiovascular diseases (CVDs) continue to account for a significant portion of global

mortality rates. According to the World Health Organization (WHO), CVDs are responsible for

approximately 17.9 million deaths annually, representing nearly 32% of all deaths worldwide.

16 Coronary artery disease, in particular, stands out as one of the most prevalent and deadliest

forms of heart disease, primarily due to its ability to cause heart attacks, strokes, and other

critical cardiovascular events.

6 Early detection of heart disease is crucial in reducing mortality and improving patient

outcomes. However, diagnosing heart disease early remains a challenging task for

healthcare providers due to the complexity of the condition. Heart disease is a multifactorial

condition with numerous interacting risk factors, including lifestyle choices (such as smoking,

diet, and physical activity), genetics, co-morbidities (like diabetes, hypertension, and

obesity), and environmental influences. These risk factors are not only varied but also

1 interact in complex ways, making the accurate prediction of heart disease difficult. Moreover,

the nature of heart disease often leads to the manifestation of symptoms only in the later

stages of the condition, when irreversible damage to the heart and blood vessels may have

already occurred.

11 Heart disease encompasses a wide range of cardiovascular conditions, including coronary

artery disease, heart failure, arrhythmia, and cardiomyopathy, and it remains a leading

1
Page 12 of 23 - Integrity Submission Submission ID trn:oid:::1:3121392805
 Page 13 of 23 - Integrity Submission Submission ID trn:oid:::1:3121392805

global health challenge. Despite advancements in medical science and healthcare

infrastructure, cardiovascular diseases (CVDs) continue to dominate global mortality

5 statistics. The World Health Organization (WHO) reports that CVDs are responsible for

approximately 17.9 million deaths annually, accounting for nearly 32% of all deaths

worldwide. Among these, coronary artery disease is particularly concerning due to its

prevalence and severity. This condition is a major contributor to heart attacks, strokes, and

other life-threatening cardiovascular events, underscoring its role as one of the deadliest

forms of heart disease.

The importance of early detection in combating heart disease cannot be overstated.

Identifying the condition in its initial stages is vital for reducing mortality rates and enhancing

patient outcomes. However, early diagnosis remains a formidable challenge for healthcare

19 providers due to the intricate nature of heart disease. It is a multifactorial condition influenced

18 by a complex interplay of risk factors, such as lifestyle habits (e.g., smoking, poor diet, and

lack of physical activity), genetic predispositions, co-morbid conditions (such as diabetes,

hypertension, and obesity), and environmental factors. The interactions among these

diverse risk elements add layers of complexity, making accurate prediction and timely

diagnosis particularly difficult.

Compounding these challenges is the often subtle or asymptomatic progression of heart

disease. Symptoms frequently emerge only in the advanced stages, when significant and

sometimes irreversible damage to the heart and blood vessels has already occurred. This

late manifestation further complicates the timely initiation of treatment, highlighting the need

for innovative diagnostic tools and strategies to detect heart disease early and mitigate its

impact on global health.

2
Page 13 of 23 - Integrity Submission Submission ID trn:oid:::1:3121392805
 Page 14 of 23 - Integrity Submission Submission ID trn:oid:::1:3121392805

Chapter 2

Related Work

The related work associated with our project is given below:

2.1. Existing Approaches

22  Heart Disease Prediction using Logistic Regression:

 Logistic Regression (LR) is widely used for binary classification tasks such as

predicting heart disease. The primary goal is to classify patients as high or low

risk for heart disease based on historical data [7].

 Random Forest for Heart Disease Prediction

 Random Forest (RF), an ensemble learning method, has been applied

20 to heart disease prediction to improve accuracy and reduce overfitting

[6].

25  Support Vector Machines (SVM) for Heart Disease Classification

 SVM is effective for classifying high-dimensional data, making it a suitable

approach for heart disease prediction [5].

 Artificial Neural Networks (ANN) for Complex Data Relationships

 To Artificial Neural Networks (ANN) have demonstrated great potential

in heart disease prediction [9].

2.2. Comparative Analysis of Existing Works

2.2.1. In existing works, most heart disease prediction models focus on

classifying individual patient data into binary outcomes.

2 2.2.2. Existing projects do not focus on identifying the best-performing machine

learning model for heart disease prediction

3
Page 14 of 23 - Integrity Submission Submission ID trn:oid:::1:3121392805
 Page 15 of 23 - Integrity Submission Submission ID trn:oid:::1:3121392805

Chapter 3

Project Objective
9  Implement multiple machine learning models such as Logistic Regression (LR),

2 Support Vector Machines (SVM), Random Forest (RF), and Artificial Neural Networks

(ANN) for heart disease prediction.

 Use patient data, including demographic information, medical history, and test

24 results, to train and validate the machine learning models.

4  Identify which machine learning algorithm provides the optimal balance between

accuracy and clinical interpretability for heart disease prediction.

4  Identify which machine learning algorithm provides the optimal balance between

accuracy and clinical interpretability for heart disease prediction.

4
Page 15 of 23 - Integrity Submission Submission ID trn:oid:::1:3121392805
 Page 16 of 23 - Integrity Submission Submission ID trn:oid:::1:3121392805

Chapter 4

Proposed Methodology

The proposed methodology related to our project is given below:

Step 1: Collect data from reliable healthcare datasets or medical records available through

8 online repositories like UCI Machine Learning Repository or Kaggle.

8 Gather high-quality data from trusted online repositories like the UCI Machine Learning

Repository or Kaggle, which offer curated healthcare datasets. Alternatively, use medical

records from hospitals, ensuring compliance with privacy regulations like HIPAA or GDPR.

6 Focus on collecting diverse data, including demographic information, clinical

measurements (e.g., blood pressure, cholesterol), lifestyle factors, and medical history.

Reliable and well-documented datasets are crucial for building accurate, generalizable

machine learning models, while adhering to ethical and legal standards ensures responsible

data usage.

12 Step 2: Train different machine learning algorithms on the dataset, such as:

 Logistic Regression

 Random Forest

 Support Vector Machines (SVM)

 K-Nearest Neighbors (KNN)

Step 3: Compare the performance of all models using the evaluation metrics.

Step 4: Develop a web application or software tool that allows medical practitioners to input

2 patient data and predict the likelihood of heart disease using the trained model.

Step 5: The results are represented using different charts.

5
Page 16 of 23 - Integrity Submission Submission ID trn:oid:::1:3121392805
Page 17 of 23 - Integrity Submission Submission ID trn:oid:::1:3121392805

• Collect heart disease data

• Clean, normalize, and encode data for model readiness

• Train and test multiple machine learning models

• Evaluate performance, tune hyperparameters

• Visualize results and select the best model

Fig.1. Proposed Approach

6
Page 17 of 23 - Integrity Submission Submission ID trn:oid:::1:3121392805
Page 18 of 23 - Integrity Submission Submission ID trn:oid:::1:3121392805

Chapter 5

Design and Implementation

The design and implementation of our project is as follows:

5.1. Work Flow Diagram

Fig.2. Work Flow Diagram

7
Page 18 of 23 - Integrity Submission Submission ID trn:oid:::1:3121392805
 Page 19 of 23 - Integrity Submission Submission ID trn:oid:::1:3121392805

Chapter 6

Results and Discussion

The result we got from analyzing the performance of each algorithm is given below in Fig.3.

Fig.3. Performance of each algorithm.

Fig.3. shows that Random Forest has good performance compare to other three with

respect to every performance metrics.

8
Page 19 of 23 - Integrity Submission Submission ID trn:oid:::1:3121392805
 Page 20 of 23 - Integrity Submission Submission ID trn:oid:::1:3121392805

Chapter 7

Conclusion and Future Scope

 As datasets expand and wearable technology advances, machine learning models

will provide more accurate, real-time monitoring, enabling early detection and

intervention for heart disease.

 In Future efforts will focus on enhancing model interpretability through explainable AI

(XAI), ensuring that healthcare professionals trust and understand model predictions.

 Machine learning models will contribute to personalized treatment plans and be

seamlessly integrated with electronic health records (EHR), optimizing patient care

and outcomes.

 As healthcare systems become more digitized, integrating machine learning models

with electronic health records (EHR) and other digital health systems will enable more

seamless workflows, resulting in faster diagnosis, better monitoring, and improved

patient outcomes.

 The future of machine learning in heart disease detection and management holds

immense promise, driven by advancements in data collection, wearable technology,

and AI methodologies. Here's an elaboration on the outlined points:

 As healthcare datasets grow larger and wearable technology becomes more

sophisticated, machine learning models will enable precise, real-time monitoring of

1 cardiovascular health. Devices like smartwatches and fitness trackers already collect

data on metrics such as heart rate, blood pressure, and physical activity. Integrating

this data with machine learning algorithms will enhance early detection by identifying

9
Page 20 of 23 - Integrity Submission Submission ID trn:oid:::1:3121392805
 Page 21 of 23 - Integrity Submission Submission ID trn:oid:::1:3121392805

subtle patterns or anomalies indicative of heart disease. This proactive monitoring will

empower timely interventions, potentially preventing severe outcomes like heart

attacks or strokes.

 Future efforts in machine learning for healthcare will prioritize explainable AI (XAI) to

address the "black box" nature of many models. XAI techniques will help demystify

how predictions are made, providing clear insights into the factors influencing a

diagnosis or risk assessment. For instance, an XAI-driven model could highlight how

elevated cholesterol levels or abnormal ECG readings contributed to its prediction.

17 This interpretability will foster trust among healthcare professionals and patients,

ensuring that the models are used confidently in clinical decision-making.

 Machine learning models will move beyond detection to play a pivotal role in

personalizing treatment plans. By analyzing individual patient data—such as genetic

predispositions, lifestyle factors, and medical history—models can recommend

tailored interventions. For example, they might suggest specific medications, dietary

adjustments, or exercise regimens optimized for a patient’s unique profile. This

personalized approach will enhance treatment efficacy and improve patient

compliance, ultimately leading to better health outcomes.

 The digitization of healthcare systems presents a significant opportunity to integrate

machine learning models seamlessly with EHRs and other digital health platforms.

Such integration will enable:

 Models can instantly analyse patient records, lab results, and imaging data to provide

accurate diagnostic support.

 Continuous data flow between wearable devices, EHRs, and predictive models will

10
Page 21 of 23 - Integrity Submission Submission ID trn:oid:::1:3121392805
 Page 22 of 23 - Integrity Submission Submission ID trn:oid:::1:3121392805

allow ongoing assessment of patient health.

 Streamlined workflows will reduce delays, enhance care coordination, and allow

healthcare providers to focus on patient-centric care.

11
Page 22 of 23 - Integrity Submission Submission ID trn:oid:::1:3121392805
 Page 23 of 23 - Integrity Submission Submission ID trn:oid:::1:3121392805

References
15 [1] Taneja, A. (2016). A Machine Learning-Based Model for Heart Disease Prediction.
International Journal of Computer Applications.

7 [2] Jabbar, M.A., Chandra, P., & Deekshatulu, B.L. (2016). Heart Disease Prediction System
using Decision Trees and K-Nearest Neighbor. IEEE Conference on Signal Processing and
Communication Engineering Systems

[3] Singh, A., & Kaur, I. (2018). A Hybrid Model for Heart Disease Prediction Using Machine
Learning. Procedia Computer Science.

[4] Yuan, X., Chen, J., Zhang, K., Wu, Y., & Yang, T. (2021). A stable AI-Based binary and
multiple class heart disease prediction model for IOMT. IEEE Transactions on Industrial
Informatics, 18(3), 2032–2040.

[5] Rahim, A., Rasheed, Y., Azam, F., Anwar, M. W., Rahim, M. A., & Muzaffar, A. W. (2021).
An integrated machine learning framework for effective prediction of cardiovascular
diseases. IEEE Access, 9, 106575–106588.

[6] Ahmad, Ghulab & Fatima, Hira & Shafiullah, & Saidi, Abdelaziz & Imdadullah, (2022).
Efficient Medical Diagnosis of Human Heart Diseases Using Machine Learning Techniques with
27 and Without GridSearchCV. IEEE Access. 10. 1-1. 10.1109/ACCESS.2022.3165792.

[7] Rahman, T., Al-Ruweidi, M. K. a. A., Sumon, M. S. I., Kamal, R. Y., Chowdhury, M. E. H., &
Yalcin, H. C. (2023). Deep learning Technique for congenital heart disease detection using
Stacking-Based CNN-LSTM models from Fetal Echocardiogram: a pilot study. IEEE
Access, 11, 110375–110390.

[8] Jafar, A., & Lee, M. (2023). HYPGB: High accuracy GB classifier for predicting heart disease
with HyperOpt HPO Framework and LASSO FS Method. IEEE Access, 11, 138201–138214.

[9] Yang, HuaZhong & Chen, Zhongju & Yang, Huajian & Tian, Maojin. (2023). Predicting
Coronary Heart Disease Using an Improved LightGBM Model: Performance Analysis and
10 Comparison. IEEE Access. PP. 1-1. 10.1109/ACCESS.2023.3253885.

[10] Yongcharoenchaiyasit, Khomkrit & Arwatchananukul, Sujitra & Temdee, Punnarumol &
Prasad, Ramjee. (2023). Gradient Boosting Based Model for Elderly Heart Failure, Aortic
10 Stenosis, and Dementia Classification. IEEE Access. PP. 1-1.
10.1109/ACCESS.2023.3276468.

[11] Anitha, Mallipuram. (2024). Cardiovascular Diseases Detection in ECG images using deep
learning methods. International Journal of scientific research in Engineering and Management.
08. 1-5. 10.55041/IJSREM31353.

12
Page 23 of 23 - Integrity Submission Submission ID trn:oid:::1:3121392805