Lung cancer is the most prevalent form of cancer worldwide according to the World Health Organization. It also causes the largest number of deaths out of all cancer types. This is why determining genetic and environmental risk factors is crucial for the development of new methods of lung cancer prevention. To this end, various approaches of data mining are being increasingly used in the field of healthcare. Data mining has for some years now been proving to be one of the main focuses of practical computer science applications; also gaining influence across the industry and science, since it enables automatic processing of enormous amounts of data. Data analysis in healthcare is growing in complexity, mostly due to the development of new analysis techniques and the integrated analysis of data from multiple sources. While being a time and money consuming process, early detection and diagnosis of lung cancer is key in the progression of the disease. In this thesis we based on the research of Ahmed et al. (2013) and used the Java programming language to develop an application which uses the entered demographic and lifestyle data of the user, combined with a decision tree, to calculate the risk level of lung cancer formation. Thus the purpose of the application is to gauge the user's risk level and to raise their awareness of reducing said risk with various ways of helping to achieve a healthier lifestyle.
|
