Bell Eapen

eHealth and Information System Research

Combining Clinical Trials

English: Icon representing Bayesian statistics
English: Icon representing Bayesian statistics (Photo credit: Wikipedia)

BMC Medical Research Methodology | Abstract | Bayesian methods in clinical trials: a Bayesian analysis of ECOG trials E1684 and E1690:

Happy new year to all!

I have always wondered how to effectively combine data from a previous similar clinical trial into a new trial. If this is not attempted, the wealth of information already collected will be wasted. Besides if the trials give conflicting results, the entire effort in conducting both trials is lost and you end up with only confusion. The authors here have conceived a method to effectively combine data from similar trials conducted at different times using the Bayesian method. In short, the older trial is used to generate the prior probability distribution for the analysis of the new results. The methodology has been used in Melanoma studies. (I am happy that it is from my domain). I have also experimented with Bayesian methodology before.

I give 4 peels to this idea. (Pardon me for using a grading system envisaged for a different cause!)
GulfDoctor.net peel rating
My Rating: 4 peels
What is peel score?

Negative N to Unknown U

The identification of disease specific genes is pivotal in clinical informatics. This paper describes an improved algorithm for machine learning in which the negative N is classified more appropriately as Unknown U.

English: Weka Data Mining Open Software in Java
English: Weka Data Mining Open Software in Java (Photo credit: Wikipedia)

Peng Yang, Xiao-Li Li, Jian-Ping Mei, Chee-Keong Kwoh, and See-Kiong Ng. Positive-Unlabeled Learning for Disease Gene Identification
Bioinformatics first published online August 24, 2012 doi:10.1093/bioinformatics/bts504

SVMs are an important tool in bioinformaticians armamentarium. Weka is a collection of machine learning algorithms for data mining tasks.