We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
MedicHub -- Disease Detection Using Deep Learning.
- Authors
Patil, Nilesh; Gadiyar, Aaditya; Mehta, Darshan; Khatri, Harsh
- Abstract
The integration of technology in healthcare is rapidly revolutionizing the sector and transforming the traditional modus operandi that used to be followed into a more efficient and accurate automated system. Machine Learning is a sophisticated technology used to analyze clinical symptoms to predict diseases and deliver accurate diagnoses based on strong evidence. The major advantage of using technology to assist in diagnosis is to understand more about underlying illnesses that are often overlooked while searching for a more severe disease, or when the patient is not in imminent danger. This offers patients a very reliable and accessible alternative for immediate results and also minimizes the risk of errors. Another extremely good utility of technology is withinside the discipline of medical image analysis. Convolutional Neural Networks (CNN) are neural networks which are capable of recognizing patterns in pictures and hence must be included in the system to increase its accuracy and efficacy. CNN can recognize and identify patterns in medical pictures like X-rays, MRI scans, or CT scans, allowing it to accurately diagnose complicated diseases such as Brain Tumor, COVID-19, Alzheimer's disease, and Pneumonia. With the increasing number of patients and variety of diseases, it is important to handle large datasets efficiently, while maintaining accuracy. The use of CNN to predict illnesses based on symptoms can benefit the patients as well as the medical fraternity as it may assist in expediting the diagnosis and treatment process.
- Subjects
DEEP learning; AUTOMATION; MEDICAL technology; CONVOLUTIONAL neural networks; MACHINE learning; NATURAL language processing
- Publication
Mapana Journal of Sciences, 2023, Vol 22, p37
- ISSN
0975-3303
- Publication type
Article
- DOI
10.12723/mjs.sp2.3