How the dynamics of the El Niño-Southern Oscillation (ENSO) are being modified under a changing climate continues to be an open question with significant implications for global climate impacts. We present the first statistical attribution of how the spatio-temporal dynamics of ENSO have changed due to global warming over the last century using a non-homogeneous Hidden Markov Model of gridded tropical Pacific Sea Surface Temperature (SST) with smoothed global temperature as a covariate for the associated latent states. We identify 5 latent states whose space and time patterns correspond to classical El Niño and La Niña (LN), mild La Niña and Central Pacific El Niño (CP), and neutral ENSO patterns. The monthly probability of occurrence, and the transition probabilities of these states have changed significantly, and global temperature changes are identified as strong determinants of these changes. For instance, the probability of observing LN and CP has changed by 0.300 and 0.767 over the last 100 years. The estimated sensitivity of these probabilities to global temperature is (0.248±0.002)/℃ and (0.722±0.008)/℃, translating to 97% and 98% of the change, respectively, given the 1.22℃ warming. Similarly, the sensitivity of La Niña persistence to global temperature change is estimated as (28.9±0.2) month/℃, and this explains 98% of the variance in the increased persistence of La Niña patterns that are associated with recent recurrent droughts and floods in parts of the world.