Scribd
Upload
3 views

Predictive Modelling Report

Uploaded by

vadapav111204
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
3 views

Predictive Modelling Report

Uploaded by

vadapav111204
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 7

TRAINING/INTERNSHIP/PROJECT

REPORT
Predictive Modelling for Early Detection of Chronic Diseases Using
Electronic Health Records
Submitted in partial fulfillment of the requirements for the award of the degree of

BACHELOR OF TECHNOLOGY
In

Electronics and Communication Engineering (ECE)


By

Nityaa Goel

Roll No: 04301022023

Guided by

[Mentor’s Name]

[Mentor’s Designation]

[Mentor’s Department and Organization]

INDIRA GANDHI DELHI TECHNICAL UNIVERSITY FOR WOMEN

NEW DELHI – 110006

JULY 2024
CERTIFICATE
This is to certify that the project entitled “Predictive Modelling for Early Detection of
Chronic Diseases Using Electronic Health Records” is being submitted at IGDTUW, Delhi, for
the award of Bachelor of Technology in ECE degree. It contains the record of bonafide work
carried out by Nityaa Goel (Roll No: 04301022023) under my supervision and guidance. To
the best of my knowledge, the work presented here has not been submitted elsewhere for
any other degree or diploma.

[Mentor’s Name]

[Mentor’s Designation]

[Mentor’s Department and Organization]

Date:

Place:
UNDERTAKING REGARDING ANTI-PLAGIARISM
I, Nityaa Goel, hereby declare that the material/content presented in the report is free from
plagiarism and is properly cited and written in my own words. In case plagiarism is
detected at any stage, I shall be solely responsible for it.

Nityaa Goel

Roll No: 04301022023


ACKNOWLEDGEMENT
I sincerely thank my mentor [Mentor’s Name] for their invaluable guidance and support
throughout this project. I am also grateful to [Institution/Organization] for providing the
necessary resources and facilities. My heartfelt gratitude to my family, friends, and
colleagues for their encouragement and support throughout this journey.
DECLARATION
I, Nityaa Goel, solemnly declare that the project report “Predictive Modelling for Early
Detection of Chronic Diseases Using Electronic Health Records” is based on my own work
carried out during my study under the supervision of [Mentor’s Name, Department, and
Organization]. I further certify that:
1. The work contained in the report is original and has been done under the supervision of
my mentor.
2. The work has not been submitted elsewhere for any other degree or diploma.
3. I have followed the university guidelines in writing the report.
4. Wherever external material is used, proper credit has been given.

Nityaa Goel

Roll No: 04301022023


ABSTRACT
This study aims to address the critical need for early detection of chronic diseases such as
diabetes, cardiovascular disorders, and cancer. Using a novel approach integrating machine
learning (ML) and deep learning (DL) techniques, the system employs Convolutional Neural
Networks (CNNs) for automatic feature extraction and prediction. The dataset includes
patient demographics, symptoms, and medical history. Results demonstrated that CNN
models achieved 99.76% accuracy, significantly outperforming traditional algorithms like
Naïve Bayes and Decision Trees. This approach has potential applications in improving
patient care and reducing healthcare costs through early diagnosis and intervention.
CHAPTER 1: INTRODUCTION

1.1 Literature Review


Machine learning has been increasingly utilized in healthcare for disease detection and risk
prediction. This review highlights advancements in predictive modeling using electronic
health records (EHR) and their applications in diagnosing chronic diseases.

1.2 Scope of the Project


The project focuses on leveraging CNNs for chronic disease prediction using EHR data to
enhance diagnostic accuracy and efficiency.

1.3 Problem Statement


Chronic diseases pose significant global health challenges, necessitating early detection and
intervention. Traditional diagnostic methods are often inefficient, underscoring the need for
advanced predictive models.

1.4 Work Contribution


The study develops a CNN-based predictive model that achieves superior accuracy in
detecting five chronic diseases: diabetes, heart disease, breast cancer, hepatitis, and kidney
disease.

You might also like