Based on Moran index， hot spot analysis and geographically weighted regression model， this paper analyzed the spatial distribution characteristics and influencing factors of per capita hospitalization costs in 31 provinces of mainland China from 2017 to 2019. The results showed that the Moran’s I index of per capita hospitalization cost was greater than 0 from 2017 to 2019 （P<0.01）. Hot spot analysis showed that there were “hot spots” and “cold spots” in per capita hospitalization expenses. The number of licensed assistant physicians per 1 000 population and the urbanization rate had positive impact on the per capita hospitalization expenses， while the number of beds per 1 000 population had negative impact on the per capita hospitalization expenses. The per capita hospitalization expenses in China were on the rise as a whole， and clustered in geographical distribution. There were differences in the strength of influencing factors in different regions. Therefore， policies should be formulated according to the actual situation.