INTRODUCTION: Characterizing transitions of cognitive state, including reversion from mild cognitive impairment (MCI) to normal cognition (NC) and subsequent cognitive stability or deterioration for post-reversion, has so far remained limited. METHODS: Using a retrospective cohort of subjects with an MCI diagnosis at study entry and at least two follow-up visits between 2005 and December 2022, we developed a functional multistate model framework to estimate longitudinal patterns of transition probabilities between different cognitive states. RESULTS: The probability of reversion increased from 2% at baseline to a maximum of 8% by year 10 before gradual decline thereafter. For post-reversion, the probability of progression to MCI rose from 8% to 35.71% at Year 10 and subsequently stabilized. DISCUSSION: The instantaneous risk of MCI progressing was similar to the risk of re-progression to MCI for post-reversion. Post-reversion subjects remained at an increased risk of cognitive deterioration. HIGHLIGHTS: The instantaneous risk of MCI progressing to AD is similar to the risk of re-progression to MCI for post-reversion. The FMSM we developed effectively utilizes multiple longitudinal markers to reveal variable transition patterns between different cognitive states. Considering both spatiotemporal dimensions and sparse irregularities from longitudinal neuroimaging and neuropsychological scales, fMLFPCA and MVFPCA help to extract variation patterns, to capture detailed changes characterizing the multidimensional evolution patterns of MCI.