Web application for multiple disease prediction using machine learning and deep learning

The emergence of numerous infectious diseases has made online medical advice a crucial step. An essential significance is the application of data mining technologies to increase the effectiveness of disease diagnosis. Online medical guidance can save time and reduce travel costs for hospital visits. During the past decade, many professionals as well as researchers have proposed many variants of machine learning techniques in the medical field. Our project is trained on the different machine learning algorithms, where the user is required to upload their chest x-ray and they’ll get to know their test results instantly. There is no standard system where one comment can perform more than one disease prediction. The internet plays an essential role in connecting patients with medical services. Studies have shown that most people first go on the internet to search for medical information. Now people are moving towards online platforms, whether it may be medical consultation, buying medication, or any treatments. This project will provide accurate and instant results on which patients/ hospitals can rely for further treatment. Just uploading a chest x-ray to receive a diagnosis makes it user-friendly. Multiple disease detectors can be used in the health industry to provide the required treatment to the patient on time, saving costs and resources. Our web app was developed using Flask Web Framework and was deployed on a Local server. Large datasets were used to train the models that were used to forecast the diseases. All the links for datasets and the python notebooks are used for model creation, training, and for testing. To implement multiple disease analyses, machine learning algorithms, Tensor Flow, Flask API, and machine learning methods were used to implement multiple illness analyses. The relevant model will be called by the Flask API, which will then return the patient’s state. The significance of this research is to identify the most prevalent diseases so that we can monitor patient health and forewarn patients when necessary to reduce the death ratio.