Heat Map Based Feature Selection: A Case Study for Ovarian Cancer

Public health is a critical issue, therefore we can find a great research interest to find faster and more accurate methods to detect diseases. In the particular case of cancer, the use of mass spectrometry data has become very popular but some problems arise due to that the number of mass-to-charge ratios exceed by a huge margin the number of patients in the samples. In order to deal with the high dimensionality of the data, most works agree with the necessity to use pre-processing. In this work we propose an algorithm called Heat Map Based Feature Selection (HmbFS) that can work with huge data without the need of pre-processing, thanks to a built-in compression mechanism based on color quantization. Results shows that our proposal is very competitive against some of the most popular algorithms and succeeds where other methodologies may fail due to the high dimensionality of the data.