Existing techniques assume that all time varying covariates are confounding and thus attempts to balance a full state representation of a plurality of historical observants. The present disclosure processes a plurality of historical observants and treatment at a timestep t specific to each patient using an encoder network to a obtain a state representation s t . A first set of disentangled representations comprising an outcome, a confounding and a treatment representation is learnt to predict an outcome ŷ t +1 . The first set of disentangled representations are concatenated to obtain a unified representation and the decoder network is initialized using the unified representation to obtain a state representation s t +1 . A second set of disentangled representations is learnt and concatenated to predict outcome ŷ t + m +1 m + 1 timesteps ahead of the timestep t and proceeding iteratively until m = τ — 1.