Fortunately, plague risk is a relative thing.
It wasn't all that long ago that the plague was a regular, recurring feature of civilization at-large. It still is in some parts of the world, but in developed nations, the availability of antibiotics, along with increasing standards of sanitation, have kept full-on "bring out your dead"-style outbreaks at bay.
And yet the disease persists even in the first-world, albeit at much smaller scales. An Oregon teenager who contracted the infection while on a hunting trip in October got plenty of imaginations moving in very dark directions, though the event was, as expected, completely isolated.
The thing about plague is that it's still extremely common, but mostly in the wild. The aforementioned teen got it from a flea which presumably got it from sucking the blood of a rodent. The western United States happens to be home to among the highest concentrations of plague in the world, thanks largely to two particular hosts: the deer mouse and ground squirrel.
However isolated, human contacts with plague are certainly possible, and they aren't random either. A new study in the open-access journal PeerJ from researchers at State University of New York presents a map showing the likelihood of human beings coming into contact with the pathogen place by place. It's based on a machine learning algorithm trained on several different plague-favoring factors and offers a probabilistic view of the distribution of plague among deer mice.
"This model demonstrated good predictive ability and identified areas of high risk in central Colorado, north-central New Mexico, and southwestern and northeastern California," the authors write. "The presence of P. maniculatus [deer mouse], altitude, precipitation during the driest and wettest quarters, and distance to artificial surfaces, all contributed substantively to maximizing the gain function."
It'd be difficult for you to die of the plague if you tried, even in regions with the largest predicted concentrations of it and the most extreme wildland fragmentation (a predictor of human-animal contact, according to the paper). You'd really need to move in with a bunch of wild, flea-ridden mice for a while, and even then, no guarantees.
Still, the work could prove to be important, particularly if validated by studies in the field, as the authors write.
"While zoonotic transmission to humans is much less common in modern times, significant plague risk remains in parts of the western US," the authors note. "Moreover, risk to some threatened species that are part of the epizootic cycle can be quite substantive. This investigation attempted to predict the risk of plague across the western US by modeling the ecologic niche of plague in sylvan and domestic animals identified between 2000 and 2015."
Where plague occurrences are predicted to be in the 75 to 90 percent range, local health departments and land managers may want to institute trapping and testing programs. Better safe than sorry, even when it comes to the rarely contracted but persistent plague.