Classification Medical Data Series by Artificial Immune Methods

W. Wajs (Poland)


Artificial immune network, immune system, neuralnetwork.


The paper describes application of artificial immune algorithms in classification of medical data series that is used as the input data for Neural Network algorithms. Artificial immune network is created and trained for the purpose of Arterial Blood Gases parameters (pH, PaCO2, PaO2, HCO3) classification. The main goal of the paper is to develop neural networks technique for solving Arterial Blood Gases (ABG) short-term prediction. The main question, that is considered, is how to predict some parameters that describe blood gases nature. A model of a physical system has an error associated with its predictions due to the dependencies of the physical system's output on uncontrollable or unobservable quantities. We are expected to receive some parameter value on the proper level of probability. This would provide a direct feedback to the clinical staff on the progress of patients, the success of individual treatments and quality of care as well as predicting blood gases value.

Important Links:

Go Back