Automatically identifying pressure injuries

1 . An automatic pressure injury identification system, comprising:

a bed configured to support a patient;

the bed comprising one or more sensors configured to detect one or more parameters of the patient, and to generate sensor data from the detection of the one or more parameters, wherein the sensors are contact-free continuous monitoring sensors selected from pressure sensors, moisture sensors, temperature sensors, and cameras;

a transceiver;

at least one processor operably connected to the transceiver and the one or more sensors; and

memory operably connected to the at least one processor, the memory storing:

a database comprising an electronic medical record (EMR) of the patient; and

instructions that, when executed by the at least one processor, cause the at least one processor to perform operations comprising:

determining, based on the EMR of the patient, that the patient has a pressure injury;

identifying sensor data, from one or more sensors, obtained prior to a time at which the EMR was updated to indicate the pressure injury, the sensor data indicating one or more parameters of the patient;

determining at least one root cause of the pressure injury, wherein determining the at least one root cause of the pressure injury comprises:

determining the time at which the EMR was updated to indicate the pressure injury,

determining, using an output from a machine learning model input with the sensor data indicating the one or more parameters of the patient, that the patient experienced at least one risk factor associated with the pressure injury, wherein the machine learning model is trained using sensor data and EMR data:

 prior to the time at which the EMR was updated, and for greater than a threshold period of time; and

determining, based on the EMR, that the patient experienced the at least one risk factor prior to the time at which the EMR was updated;

electronically updating the EMR to indicate the at least one root cause of the pressure injury; and

causing the transceiver to output, to an external computing device, a report indicating the pressure injury and the at least one root cause of the pressure injury.

2 . The pressure injury identification system of claim 1 , wherein the contact-free continuous monitoring sensors are configured to detect a pressure of the patient on the bed, detect moisture on the bed, detect a temperature of the patient, generate at least one infrared image of the patient, or generate at least one video of the patient.

3 . The identification system of claim 1 , wherein the risk factor is a condition of the patient, the condition of the patient comprising patient diagnosis and/or current medication.

4 . The identification system of claim 1 , wherein the pressure sensors are load cells located at each corner of a resting surface of the bed.

5 . A method, comprising:

receiving, from one or more sensors, sensor data indicating one or more parameters of a patient;

determining, based on an electronic medical record (EMR) of the patient, that the patient has a pressure injury;

determining, based on the sensor data indicating the one or more parameters of the patient, at least one root cause of the pressure injury, wherein determining the at least one root cause of the pressure injury comprises:

determining a time at which the EMR was updated;

inputting the sensor data and the EMR data into a trained machine learning model;

and

determining, based on the sensor data indicating the one or more parameters of the patient and an output of the trained machine learning model, that the patient experienced a risk factor associated with the pressure injury prior to the time at which the EMR was updated;

determining an estimated contribution of a potential root cause to the pressure injury of the patient; and

transmitting, to an external computing device, a report indicating the pressure injury and the estimated contribution of the associated at least one root cause of the pressure injury.

6 . The method of claim 5 , wherein determining that the patient has the injury comprises:

identifying a note in the EMR of the patient; and

identifying, in the note, at least one keyword associated with the injury via natural language processing.

7 . The method of claim 6 , wherein the one or more sensors are in a bed supporting the patient, the one or more sensors comprising at least one of a load cell, a moisture sensor, a temperature sensor, an infrared camera, or a video camera, and

wherein the one or more parameters of the patient comprise at least one of a movement of the patient, a moisture of a bed supporting the patient, a nutrition level of the patient, or a temperature of the patient.

8 . The method of claim 6 , wherein determining the at least one root cause of the injury comprises:

determining that the one or more parameters are within one or more threshold ranges for greater than one or more time periods.

9 . The method of claim 6 , further comprising:

determining, based on the EMR of the patient, a nutrition level of the patient,

wherein determining the at least one root cause of the injury further comprises:

determining that the nutrition level of the patient has remained under a threshold level for greater than a time period; and

determining that the nutrition level of the patient is an additional root cause of the injury.

10 . The method of claim 6 , the patient being a first patient, the injury being a first injury, the EMR being a first EMR, the method further comprising:

identifying, based on second EMRs of second patients, that the second patients have second injuries;

determining, based on the sensor data, that the second patients experienced a second risk factor associated with a pressure injury, wherein the second risk factor is a same risk factor as the risk factor of the first patient;

determining in real-time that the second injuries have the same type of root cause as the first injury of the first patient; and

transmitting, to an external computing device, a report indicating the type of root cause of the second injuries and a treatment plan.

11 . The method of claim 6 , the patient being a first patient, the injury being a first injury, and the EMR being a first EMR, the method further comprising:

predicting, based on a second EMR of a second patient, that the second patient is at risk for developing second injuries based on a same type of root cause as the first patient; and

transmitting, to an external computing device in real time, a report indicating the risk of the second patient developing the second injury.