Enhanced recording of rescue events

1 . A tracking device, comprising:

a camera configured to capture an image of a medical device associated with a patient;

a microphone configured to detect an audible signal from the medical device;

a transceiver; and

a processor configured to:

determine, by inputting the image into a convolutional neural network (CNN) that is trained to identify medical devices, transforming the image into a feature map associated with the medical device, and analyzing a spectral feature of the audible signal and matching the spectral feature to a predetermined tone uniquely associated with a model of the medical device, an identifier of the medical device;

determine, by analyzing the audible signal, that the medical device has administered an electrical shock to the patient;

identify a physiological parameter of the patient, the physiological parameter being detected by a different device than the medical device;

generate an electronic record of the patient, the electronic record comprising the identifier, an indication of the electrical shock, and the physiological parameter; and

cause the transceiver to transmit the electronic record to a server;

wherein the tracking device is configured to operate independently without receiving a communication from the medical device.

2 . The tracking device of claim 1 , wherein the identifier comprises an identification number of the medical device, a manufacturer of the medical device, a model of the medical device, or a portion of the image.

3 . The tracking device of claim 1 , wherein the processor is configured to correlate the identifier determined from the image with the electrical shock determined from the audible signal to verify a source of the electrical shock within the electronic record.

4 . A device, comprising:

a sensor configured to detect a visual signal or an audible signal from a medical device associated with a patient; and

a processor configured to:

determine, by analyzing the visual signal or the audible signal using a first machine learning (ML) model, an identifier of the medical device;

determine, by analyzing the audible signal or the visual signal using a second ML model, an identifier of the patient;

identify a physiological parameter of the patient;

generate an electronic record of the patient, the electronic record comprising the identifier, the identifier of the patient, and the physiological parameter; and

output the electronic record,

wherein determining the identifier of the medical device comprises analyzing a spectral feature of the audible signal and matching the spectral feature to a predetermined tone uniquely associated with a model of the medical device; and

wherein the device is configured to operate independently without receiving a communication from the medical device.

5 . The device of claim 4 , wherein the sensor comprises a camera,

wherein the visual signal comprises an image of the medical device, and

wherein the ML model comprises a CNN.

6 . The device of claim 4 , wherein the sensor comprises a microphone configured to detect the audible signal from the medical device.

7 . The device of claim 6 , wherein the microphone is configured to detect an audio prompt output by the medical device, the audio prompt comprising an audible instruction for operating the medical device, the audio prompt being uniquely associated with a model of the medical device,

wherein the processor is configured to determine the identifier of the medical device by:

identifying the model of the medical device by analyzing the audio prompt, the identifier comprising the model of the medical device.

8 . The device of claim 4 , wherein the processor is configured to identify the physiological parameter of the patient by analyzing the visual signal or the audible signal.

9 . The device of claim 4 , the medical device being a first medical device, the device being a second medical device further comprising:

a treatment component configured to administer an additional treatment to the patient, wherein the electronic record further comprises an indication of the additional treatment.

10 . A method, comprising:

determining, by a processor of a device, by analyzing a visual signal and an audible signal detected by a sensor of a medical device using a machine learning (ML) model, an identifier of the medical device associated with a patient;

determining, by the processor, that a first treatment has been administered to the patient by the medical device by analyzing the visual signal or the audible signal,

identify, by the processor, a treatment parameter associated with the first treatment and a physiological parameter of the patient;

determining, by the processor, that the first treatment temporarily resolved a condition of the patient;

in response to determining that the first treatment temporarily resolved the condition of the patient, causing a treatment component of the device to administer, to the patient, a second treatment associated with the treatment parameter;

generating, by the processor, an electronic record of the patient, the electronic record comprising the identifier, the treatment parameter, and the physiological parameter; and

outputting the electronic record;

wherein determining the identifier of the medical device associated with the patient comprises analyzing a spectral feature of the audible signal and matching the spectral feature to a predetermined tone uniquely associated with a model of the medical device.

11 . The method of claim 10 , wherein detecting the visual signal comprises capturing an image of a display of the medical device.

12 . The method of claim 10 , wherein identifying the physiological parameter of the patient comprises:

detecting the physiological parameter of the patient; or

receiving an indication of the physiological parameter from an external device.

13 . The method of claim 10 , wherein the electronic record further comprises a time at which the sensor detects the visual signal and the audible signal, an identifier of a rescuer operating the medical device, demographic information about the patient, a condition of the patient, or a location of the patient.

14 . The method of claim 10 , wherein outputting the electronic record comprises transmitting the electronic record to an external device or storing the electronic record in a database.

15 . The method of claim 10 , wherein the first treatment comprises a first electrical shock and the second treatment comprises a second electrical shock.