In the United States, trauma is the leading cause of death for those under the age of 45, and the fourth leading cause of death for all Americans. In the world as a whole, according to the World Health Organization, more than 1.3 billion people die from road traffic related injuries. Of people who are severely injured, approximately 50% live long enough to receive medical treatment, however, about a quarter of them will go on to develop acute traumatic coagulopathy (ATC), a condition which puts these people at four-fold higher risk of death. Acute traumatic coagulopathy arises when the coagulation and intrinsic immune responses misfire. This work seeks to understand how such dysfunction can occur. To understand ATC, we have built a small model of coagulation and fibrinolysis, and then embedded it into a physiologically based pharmacokinetic model of the human body. We have also explored the prediction of ATC from a data science prospective, using two emergency room datasets. Our modeling highlighted the importance of blood as a resuscitation fluid, a possible mechanism for tranexamic acid efficacy, and addressed how clotting capacity may be affected by acidosis and hypothermia, two common complications of injury. Our work to predict ATC from emergency room data demonstrated that logistic regression performs poorly on the problem, however, a recurrent neural network joined to a support vector machine may perform well at separating non-ATC from ATC patients.