Artificial neural network analysis of malaria severity through aggregation and deformability parameters of erythrocytes.

The erythrocyte aggregation and deformability of blood samples obtained from normal subjects and malaria patients are determined by microscopic imaging and laser aggregometry techniques, and optical hemorheometer, respectively. By these techniques several parameters are determined but four parameters, aggregate sedimentation velocity (ASV), effective number of cells (ENC), process completion time (PCT) and mean filtration time (MFT), show significant variation in malaria patients compared to that of healthy subjects. For malaria severity analysis artificial neural network (ANN), based on feedforward-error back-propagation algorithm in a supervisory training mode is proposed. This network is first trained for different number of epochs ranging from 20 to 50 by set of patterns and at 30 epochs training session the minimum mean square error (MSE) between desired and actual output is obtained. By applying the same procedure the test patterns belonging to normal, non-severe, severe, and highly severe malaria (NSM, SM and HSM) are identified. The results show that malaria with high severity is classified accurately (100%). The success of classification for non-severe and mildly-severe malaria ranges from 60% to 80%.