Artificial Intelligence based Comparative Study of Mortality Prediction


The mortality prediction of the patient becomes an important and critical prediction problem in the area of artificial intelligence. The aim of machine learning algorithms is to help doctors to make critical decisions here. Mortality prediction can be very helpful for taking critical decisions which can help in optimising the resources available in the hospital and also an extra opinion for doctors and family members in cases of euthanasia i.e. ending life of patient to relieve pain and suffering. We have been collecting data many years from multiple sources such as E-commerce sites, government portals, hospitals and etc., now the same massive data is used as a training data for machine learning models. In this paper we are using different artificial intelligence approaches to predict the survival of a patient based on his or her medical record. In this paper we have presented a comparative study of different AI techniques including artificial neural network and widely used machine learning algorithms such as logistic regression, random forest, and support vector machine by calculating the performance for each algorithm. We observed from performance that the logistic regression perform better, hence we selected regression model for predicting the mortality of the patients.



Software And Hardware

• Hardware: Processor: i3 ,i5 RAM: 4GB Hard disk: 16 GB • Software: operating System : Windws2000/XP/7/8/10 Anaconda,jupyter,spyder,flask Frontend :-python Backend:- MYSQL