International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 11 Issue: 06 | Jun 2024
www.irjet.net
p-ISSN: 2395-0072
Multi-Disease Prediction Web Application: A Step Towards Integrated Healthcare Diagnosis and Prevention. Dr. Subha Subramaniam
Biswajit Mohanty
Divyesh Pahurkar
Pranav Jha
HoD, Assistant Professor Department of Electronics and Computer Science Shah & Anchor Kutchhi Engineering college Chembur, India
Department of Electronics and Computer Science Shah & Anchor Kutchhi Engineering college Chembur, India
Department of Electronics and Computer Science Shah & Anchor Kutchhi Engineering college Chembur, India
Department of Electronics and Computer Science Shah & Anchor Kutchhi Engineering college Chembur, India
Roshan Bakka Department of Electronics and Computer Science Shah & Anchor Kutchhi Engineering college Chembur, India
-----------------------------------------------------------------------***-----------------------------------------------------------------------Abstract— Early disease identification and correct diagnosis are extremely difficult for the healthcare industry to achieve, which frequently leads to treatment delays, higher medical expenses, and worse patient outcomes. In order to solve these issues, this project proposes the creation of a disease prediction model that makes use of convolutional neural networks (CNNs) and machine learning techniques. In order to accurately diagnose six prevalent diseases using medical data, this research outlines the construction of a disease prediction model that makes use of convolutional neural networks (CNNs) and machine learning techniques. Targeted illnesses include brain tumors, diabetes, Alzheimer's disease, heart disease, pneumonia, and breast cancer. The work centers on two main approaches:
2. CNN architectures for illnesses identified by imaging tests (such brain tumors, pneumonia, and breast cancer). Keywords— Multi-disease detection, Diagnosis, Healthcare, treatment, Cancer, Disease, CNN, ConvNet, XGboost.
I. INTRODUCTION Advances in technology and the growing accessibility of healthcare data are driving constant change in the healthcare industry. Despite these progress, global healthcare systems continue to face obstacles such postponed illness identification, imprecise diagnosis, and
|
Impact Factor value: 8.226
In order to diagnose six major diseases—pneumonia, breast cancer, diabetes, Alzheimer's disease, heart disease, and brain tumors—this research aims to develop a flexible and precise illness prediction tool. Our goal is to improve the effectiveness and precision of disease detection by utilizing various datasets that include medical images and related metadata. This will allow us to fully utilize the power of machine learning algorithms and CNNs.
II. RESEARCH METHODOLOGY
1. Conventional machine learning algorithms for illnesses with structured data (like diabetes, heart disease), and
© 2024, IRJET
rising medical expenses. Accurate diagnosis and early detection are essential for managing diseases effectively and enhancing patient outcomes. This project aims to use machine learning techniques and convolutional neural networks (CNNs) to construct a robust disease prediction model in response to these obstacles.
|
The research methodology for a Multi-Disease Prediction Web Application involves data collection, preprocessing, and model training. Data from medical records and imaging are curated, anonymized, and cleaned to ensure quality. Various machine learning algorithms, particularly deep learning models like CNNs and RNNs, are trained on labeled datasets for multiple diseases. Model performance is validated using cross-validation and fine-tuned for accuracy. The final model is deployed in a web app for realtime disease prediction and integrated healthcare diagnostics. CNN and machine learning algorithms were utilized in this project to train the model on the dataset and forecast the disease. When MRI scans or chest X-rays are used as inputs for disorders like pneumonia, brain tumors, and alzheimer's, CNN is used to determine whether or not the patients have these conditions. To train the model for additional diseases, machine learning algorithms such as
ISO 9001:2008 Certified Journal
|
Page 827