PROJECT TITLE :
Disease Prediction by Machine Learning over Big Data from Healthcare Communities - 2017
With big data growth in biomedical and healthcare communities, accurate analysis of medical information advantages early disease detection, patient care, and community services. However, the analysis accuracy is reduced when the quality of medical knowledge is incomplete. Moreover, totally different regions exhibit distinctive characteristics of certain regional diseases, which may weaken the prediction of disease outbreaks. In this paper, we streamline machine learning algorithms for effective prediction of chronic disease outbreak in disease-frequent communities. We experiment the modified prediction models over real-life hospital information collected from central China in 2013-2015. To beat the problem of incomplete knowledge, we use a latent issue model to reconstruct the missing data. We have a tendency to experiment on a regional chronic disease of cerebral infarction. We tend to propose a brand new convolutional neural network (CNN)-primarily based multimodal disease risk prediction algorithm using structured and unstructured knowledge from hospital. To the simplest of our knowledge, none of the prevailing work targeted on each knowledge sorts in the realm of medical huge information analytics. Compared with many typical prediction algorithms, the prediction accuracy of our proposed algorithm reaches ninety four.eightp.c with a convergence speed, which is quicker than that of the CNN-based mostly unimodal disease risk prediction algorithm.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here