top of page

A Novel Approach Towards Automated Disease Predictor System Using Machine Learning Algorithms

In this study, a disease prediction system is examined that employs predictive modelling to identify the user’s condition and bases its diagnosis on the user’s symptoms input. The model makes a prediction about whether a disease might exist based on the symptoms entered. The illness prediction method employs a variety of classifiers. These classifiers estimate how likely the illness is to occur. As big data is used more and more in the biomedical and healthcare industries, accurate healthcare data analysis can help with early disease identification, patient prognosis and additional medical procedures, and community services. However, the accuracy of the analysis is lowered by incomplete or subpar medical data. Additionally, different regional ailments have their own characteristics in various locations, which could make it more difficult to predict when sickness will spread. To predict sicknesses, machine learning techniques are applied. Under the category of supervised learning, both artificial intelligence and machine learning belong. Its unique selling point is the way it uses tagged datasets to teach computers how to categorise information accurately or possibly forecast. To ensure the model has been appropriately fitted, as input data is introduced, the model weights are altered by the cross-validation method. While categorisation algorithms may benefit organisations by enhancing automation and providing comprehensive data insights, there are numerous difficulties in creating supervised learning models that endure over an extended period of time. It may be important to have a certain amount of knowledge to use supervised learning models. It could take a long time to train using a supervised learning model. In some datasets, where human error is more likely to occur, algorithms may inadvertently draw wrong conclusions. Unlike unsupervised learning techniques, supervised learning cannot classify or arrange data on its own. The article discussed the system’s methodology and offered a breakdown of the results of the models.

Keywords

  • Disease prediction

  • Random Forest

  • Decision Tree

  • Naïve Bias

  • K-means

  • AI University Montana

  • AI For Research Student Community


AI University Montana
AI University Montana

12 views0 comments

Comments


bottom of page