Extreme heat events are more frequent and intense as a result of global climate change, thus posing tremendous threats to public health. However, extant literature exploring the multidimensional features of heat-health risks from a spatial perspective is limited. This study revisits extreme heat-health risk and decomposes this concept by integrating multi-sourced datasets, identifying compositional features, examining spatial patterns, and comparing classified characteristics based on local conditions. Using Maryland as the focal point, we found that the components of heat-health risk are different from traditional risk dimensions (i.e., vulnerability, hazards, and exposure). Through a local-level clustering analysis, heat-health risks were compared with areas having similar features, and among those with different features. The findings suggest a new perspective for understanding the socio-environmental and socio-spatial features of heat-health risks. They also offer an apt example of applying cross-disciplinary methods and tools for investigating an ever-changing phenomenon. Moreover, the spatial classification mechanism provides insights about the underlying causes of heat-health risk disparities and offers reference points for decision-makers regarding identification of vulnerable areas, resource allocation, and causal inferences when planning for and managing extreme heat disasters.