Revolutionizing Medical Diagnosis with Convolutional Neural Network: A Data-Driven Solution to Improve Accuracy in Disease Detection

CNN-Based Data-Driven Solution to Improve Accuracy in Disease Detection

Abstract

Currently, the global mortality rate is on the rise due to the increasing prevalence of various diseases. This surge in deaths is largely attributed to the growing number of patients suffering from major health conditions. Unfortunately, many patients are often misled by medical practitioners, and in some cases, these physicians lack the necessary expertise to accurately diagnose specific diseases. This presents a significant challenge in healthcare today. Timely and accurate diagnosis of diseases remains a critical issue due to a shortage of specialists and a lack of experience in managing similar cases. Traditional manual diagnostic systems for diseases are often unreliable due to uncertainties in clinical data and medical knowledge. In this research, a deep learning algorithm is developed, specifically a Convolutional Neural Network (CNN), to detect diseases.  A datasets from the UCI Machine Learning Repository is utilized, applying machine learning techniques to diagnose these conditions without requiring the assistance of medical professionals. Additionally, the proposed model can predict whether an individual is at risk of developing a particular disease in the future based on key factors associated with the disease. The medical datasets used in the proposed study include Breast Cancer, Diabetes, Heart Disease, and Liver Disorders from UCI. The data underwent preprocessing before being input into the CNN. The accuracy of the proposed model is compared with previous research, demonstrating its effectiveness and superior training