Machine-learning methods for handling missing data in medical questionnaires

Abstract

This dissertation will provide web-based software tools to handle the problem of missing data in medical questionnaires. Different methods and techniques to create these tools will be studied and analysed. Different imputation techniques which could be used to address the problem of missing data, would also be analysed. A study of software technologies and language will also be examined in order to be able to develop an application using the most appropriate methods. Already available tools/addons (such as found in MATLAB) will be extended for this application.