Utilizing artificial intelligence to detect objects or patient safety events in a patient room
Methods and systems are provided for detecting objects or patient safety events in a patient room. Artificial intelligence is utilized to enhance safety issue recognition capabilities by the methods and systems. Sensors collect a series of images and depth data in a room of a patient. Data (corresponding to images and depth data of an object or patent safety event) is received from the sensors and compared to stored data to identify the object or patient safety event. The images are communicated to a central video monitoring system and a user may be prompted to confirm if the object requires learning or a patient safety event occurred (or identify the object or patient safety event) or to provide additional parameters or actions. A patient safety learning system analyzes the data and incorporates the user response to enhance safety issue recognition capabilities of the system and reduce false alerts.
1. A method comprising:
collecting images of a scene including an object;
detecting, based on the images, that an event involving the object has occurred in the scene, wherein the event is detected in-part by comparing one or more features of the object to one or more reference features;
comparing the object to a database object to determine if the object is associated with a known object in a database, wherein, if the object is not determined to be associated with the known object, the database is updated with reference data associated with the object;
in response to detecting that the event has occurred within the scene, presenting at least one of the object and information associated with the event in a graphical user interface;
receiving an indication that the object or the event has been confirmed; and
in response to receiving the indication that the object or event has been confirmed, updating a machine learning model with i) the event, ii) the object, iii) the reference data associated with the object, or iv) combinations of i)-iii), wherein the machine learning model is configured to recognize objects and events occurring in the scene.
2. The method of claim 1 , wherein the images are collected by an image capturing device located in the scene.
3. The method of claim 1 , wherein the scene includes a medical patient and the event involves a motion of the medical patient.
4. The method of claim 1 , wherein the object is a medical device and the event involves a medical patient manipulating the medical device.
5. The method of claim 1 , wherein comparing the one or more features of the at least one object to one or more reference features comprises assigning one or more reference points to the one or more features of the at least one object.
6. The method of claim 1 , wherein the images are first images and the event is a first event, the method further comprising:
collecting second images of the scene; and
predicting, using the machine learning model, that a second event involving the object has occurred in scene.
7. The method of claim 6 , further comprising:
in response to predicting that the second event has occurred in the scene, providing an alert.
8. A system comprising:
a processing system; and
one or more computer readable storage media storing instructions which, when executed by the processing system, cause the processing system to perform operations comprising:
collecting images of a scene including an object;
detecting, based on the images, that an event involving the object has occurred in the scene, wherein the event is detected in-part by comparing one or more features of the object to one or more reference features;
comparing the object to a database object to determine if the object is associated with a known object in a database, wherein, if the object is not determined to be associated with the known object, the database is updated with reference data associated with the object;
in response to detecting that the event has occurred within the scene, presenting at least one of the object and information associated with the event in a graphical user interface;
receiving an indication that the object or the event has been confirmed; and
in response to receiving the indication that the object or event has been confirmed, updating a machine learning model with i) the event, ii) the object, iii) the reference data associated with the object, or iv) combinations of i)-iii), wherein the machine learning model is configured to recognize objects and events occurring in the scene.
9. The system of claim 8 , wherein the images are collected by an image capturing device located in the scene.
10. The system of claim 8 , wherein the scene includes a medical patient and the event involves a motion of the medical patient.
11. The system of claim 8 , wherein the object is a medical device and the event involves a medical patient manipulating the medical device.
12. The system of claim 8 , wherein comparing the one or more features of the at least one object to one or more reference features comprises assigning one or more reference points to the one or more features of the at least one object.
13. The system of claim 8 , wherein the images are first images and the event is a first event, the operations further comprising:
collecting second images of the scene; and
predicting, using the machine learning model, that a second event involving the object has occurred in scene.
14. The system of claim 13 , the operations further comprising:
in response to predicting that the second event has occurred in the scene, providing an alert.
15. One or more non-transitory computer-readable media storing computer-readable instructions that, when executed by a processing system, cause a system to perform operations comprising:
collecting images of a scene including an object;
detecting, based on the images, that an event involving the object has occurred in the scene, wherein the event is detected in-part by comparing one or more features of the object to one or more reference features;
comparing the object to a database object to determine if the object is associated with a known object in a database, wherein, if the object is not determined to be associated with the known object, the database is updated with reference data associated with the object;
in response to detecting that the event has occurred within the scene, presenting at least one of the object and information associated with the event in a graphical user interface;
receiving an indication that the object or the event has been confirmed; and
in response to receiving the indication that the object or event has been confirmed, updating a machine learning model with i) the event, ii) the object, iii) the reference data associated with the object, or iv) combinations of i)-iii), wherein the machine learning model is configured to recognize objects and events occurring in the scene.
16. The one or more non-transitory computer-readable media of claim 15 , wherein the images are collected by an image capturing device located in the scene.
17. The one or more non-transitory computer-readable media of claim 15 , wherein the scene includes a medical patient and the event involves a motion of the medical patient.
18. The one or more non-transitory computer-readable media of claim 15 , wherein the object is a medical device and the event involves a medical patient manipulating the medical device.
19. The one or more non-transitory computer-readable media of claim 15 , wherein comparing the one or more features of the at least one object to one or more reference features comprises assigning one or more reference points to the one or more features of the at least one object.
20. The one or more non-transitory computer-readable media of claim 15 , wherein the images are first images and the event is a first event, the operations further comprising:
collecting second images of the scene; and
predicting, using the machine learning model, that a second event involving the object has occurred in scene.