Automatic classification of patient diagnosis records

• Main Author: Chow, Yew Wah
• Other Authors: Gabriela Elizabeth Davey
• Format: Final Year Project
• Language: English
• Published: 2014
• Subjects: DRNTU::Engineering::Computer science and engineering::Information systems::Information systems applications
• Online Access: http://hdl.handle.net/10356/61856
• Institution: Nanyang Technological University

Big data is a new and upcoming trend which many industries are keen to jump onto the bandwagon to improve their services or products. Doctors do not have 100% confidence about the illness the patient is suffering from based on a patient medical diagnosis. This is especially true for doctors who are relatively new in the field. Hence, doctors are looking towards Big Data to help them in assessing the patient situation better. In this report, the author proposes some methods for tackling classification of patient diagnosis into their corresponding disease classification. The author proposes a naive method of cleaning medical diagnosis coupled with feature set sub-selection methods to use existing algorithms. The results were compared against existing baseline results from other datasets as this is a pilot project hence there was no prior investigation done on this dataset.Finally, an optimal viable model is proposed.