The biconcave shape and corresponding deformability of human RBC is an essential biological function. This property can be significantly altered by various pathophysiological conditions leading to the generation of morphological derivatives with abnormal shapes. Hence measuring the population morphology of blood samples, hold the key to understand the characteristics of different diseases. However the morphological studies, despite their potential clinical application, are compromised due to lack of rapid and accurate technique. In this study, we have precisely simulated the shape quantifying parameter of a RBC population, known as Morphological Index (MI) from the respective light scattering data obtained from a flow cytometer. Accordingly, the significant distribution parameters of forward and side scatter data were chosen to formulate a sophisticated artificial neural network (ANN) model with MI as output. The analysis yields a three layered network with 10 neurons in the hidden layer with MI as the sole output (R2 = 0.982). Moreover, for a set of 10 samples exclusive to model formulation, the model was observed to predict MI with commendable accuracy (R2 = 0.99). The proposed method was verified to rapid, cost effective and clinically simple for the measurement of population morphology of RBC. © 2014 Scientific Publishers. All Rights Reserved.