Automatically identifying pressure injuries

A system, comprising:

• at least one processor;
• and
• memory operably connected to the at least one processor, the memory storing instructions that, when executed by the at least one processor, cause the at least one processor to perform operations comprising:
• receiving, from a plurality of sensors, sensor data indicating a plurality of parameters of a patient, at least one of the plurality of sensors comprising a camera, the sensor data comprising images of the patient over a time period;
• inputting the sensor data into a trained machine learning model, wherein the machine learning model is trained using sensor data and EMR data:
• determining, using an output of the trained machine learning model input with the sensor data indicating the plurality of parameters of the patient, a plurality of potential root causes for a pressure injury;
• determining a certainty for each of the plurality of potential root causes, wherein the certainty is proportional to a risk of each potential root cause of the plurality of root causes contributing to a pressure injury;
• predicting, based on the certainty, that the patient is in danger of acquiring the pressure injury from a potential root cause of the plurality of root causes;
• electronically updating an electronic medical record (EMR) of the patient to indicate a risk of the pressure injury;
• and
• transmitting, to an external computing device, an alert indicating that the patient is in danger of acquiring the pressure injury.