Medical data mining on small datasets
Principal Investigator
Name
Ron Wolfslast
Degrees
B.Sc.
Institution
University Hamburg
Position Title
Student of Business Informatics
About this CDAS Project
Study
NLST
(Learn more about this study)
Project ID
NLST-266
Initial CDAS Request Approval
Dec 16, 2016
Title
Medical data mining on small datasets
Summary
The goal of my master thesis is to work out what data mining methods are necessary to classify a patient if he is affected by a specific disease.
Aims
The aim is to find out what kind of data preparation and modeling techniques are necessary to provide a reliable prediction model for small datasets with proportionally many features as it is common for medical purposes. The unusually large size of the NLST lung cancer patient dataset makes it possible to experiment with different amounts of training data and to evaluate the fit of the trained model reliably.
Collaborators
University Hamburg