There are 123 Burn Intensive Care Units within the United States. These are smaller than traditional ICUs and require longer stays. Currently about 79% of total burn surface area (TBSA) calculations are incorrect, because physicians estimate this value resulting in unnecessary transfers to Burn ICUs limiting bed space, incorrect resuscitation, and patient deaths.
The project objective is to develop an approach to accurately and consistently estimate patient TBSA in trauma centers so that transfer to a Burn ICU is validated and fluid resuscitation does not fail. To do this, our team created an Android application where a physician inputs patient vitals, history, and takes photographs of the burned areas. A neural network determines the burn surface area and degree from the photos. The application’s algorithm combines TBSA with the patient’s vitals to output necessary fluid volume for resuscitation of the patient. Additionally, this application compares the patient data against the American Burn Association’s transfer criteria to determine if transfer to an upper level burn center is necessary.
This solution aims to improve burn treatment by introducing modern technologies to accurately estimate burn surface area, prevent the overburdening of upper level burn centers, and improve the overall treatment of a patient.
