Prediction of Sickle Cell Anemia Patient's Response to Hydroxyurea Treatment Using ARTMAP Network.
Hongyu Xu, Faramarz Valafar, Marko I. Vuskovic · 2003
This paper discusses the application of the newly devel-oped Mahalanobis distance-based ARTMAP (MART) network to the predication of sickle cell anemia patients’ response to Hydroxyurea treatment. Mahalanobis dis-tance-based ARTMAP is a modified version of the Fuzzy ARTMAP networks where the activation and choice func-tion are the same and equal to the Mahalanobis distance between the pattern and the template. A recurrent for-mula has been derived to update the inverse of a covari-ance matrix after it resonates with an input pattern. The full covariance matrices provide a better coverage of samples than the diagonal covariance matrices. The first part of the paper describes the MART network, with a short introduction of fuzzy ARTMAP and Gaussian ARTMAP networks, from which it was derived. The sec-ond part of the paper describes the clinical data and the procedures for data preprocessing, training and testing. The classification accuracy achieved with MART classi-fier was as high as 92.59%