The aim of this project is to be able to develop a system that uses machine learning algorithms and give a probability of disease risk.The system shall focus on the major diseases that are dependent on a person’s lifestyle and a few factors rather than all the diseases. The system will be provided data relevant to his/her medical history and other details. The system shall analyze the data and mine it with datasets of various medical backgrounds. The purpose of such an application is to help user to understand different medical threats that he/she might be prone to.
- Analytics in healthcare would ameliorate the decision making process where the biological knowledge appears to be restricted. Effective analysis of the present health data can help in providing newer solutions to the present diseases.
- Properly examined, the data can also provide vital statistics which can provide information on epidemic outbreaks and thus swift contingency protocols, disease risk prediction, etc. Also would identify various interrelated diseases based on clustering techniques.
- This System would also helpful for the different users like individual users, doctors, government agencies and insurance companies.
The algorithm used for the implementation of this project is Backpropagating Neural Networks, an abbreviation for "backward propagation of errors", is a common method of training artificial neural networks used in conjunction with an optimization method such as gradient descent. The method calculates the gradient of a loss function with respect to all the weights in the network.
The language of choice was R.
There were 4 modules in the system, their accuracy is as follows:
- Heart disease prediction: 73%
- Liver disorder: 67%
- Thyroid: 94%
- Breast Cancer: 98%