Measuring patient mobility in the ICU using a novel non-invasive sensor
An embodiment in accordance with the present invention includes a technology to continuously measure patient mobility automatically, using sensors that capture color and depth images along with algorithms that process the data and analyze the activities of the patients and providers to assess the highest level of mobility of the patient. An algorithm according to the present invention employs the following five steps: 1) analyze individual images to locate the regions containing every person in the scene (Person Localization), 2) for each person region, assign an identity to distinguish ‘patient’ vs. ‘not patient’ (Patient Identification), 3) determine the pose of the patient, with the help of contextual information (Patient Pose Classification and Context Detection), 4) measure the degree of motion of the patient (Motion Analysis), and 5) infer the highest mobility level of the patient using the combination of pose and motion characteristics (Mobility Classification).
1. A method of measuring patient mobility comprising:
analyzing individual images from an RGB-D sensor to locate a region containing each person including a patient;
assigning an identity for each person in the region, to distinguish ‘patient’ vs. ‘not patient’;
determining a pose of the patient, with contextual information;
measuring a degree of motion of the patient; and
inferring a highest mobility level of the patient using the combination of pose and motion characteristics.
2. The method of claim 1 further comprising generating a volumetric representation of patient mobility.
3. The method of claim 1 further comprising generating a heatmap of patient mobility.
4. The method of claim 1 further comprising generating a heatmap of movement of regions of the patient's body.
5. The method of claim 1 further comprising classifying the pose of the patient into 4 discrete categories: (1) lying in bed, (2) sitting in bed, (3) sitting in chair, and (4) standing.
6. The method of claim 1 further comprising classifying patient motion as “in-bed activity” if a total body speed signature of the patient exceeds a threshold.
7. The method of claim 1 further comprising classifying patient motion as “nothing in bed” if a total body speed signature of the patient is below a threshold.
8. The method of claim 1 further comprising executing the method with a non-transitory computer readable medium.
9. The method of claim 1 further comprising defining a predetermined area for measuring patient mobility.
10. The method of claim 9 further comprising defining the predetermined area for measuring patient mobility as the patient room.
11. A system for measuring patient mobility comprising:
an RGB-D sensor;
a non-transitory computer readable medium programmed for:
analyzing individual images from the RGB-D sensor to locate a region containing each person, including the patient;
assigning an identity for each person in the region, to distinguish ‘patient’ vs. ‘not patient’;
determining a pose of the patient, with contextual information;
measuring a degree of motion of the patient; and
inferring the highest mobility level of the patient using the combination of pose and motion characteristics.
12. The system of claim 11 further comprising generating a volumetric representation of patient movement.
13. The system of claim 11 further comprising generating a heatmap of patient movement.
14. The system of claim 11 further comprising generating a heatmap of movement of regions of the patient's body.
15. The system of claim 11 further comprising classifying the pose of the patient into 4 discrete categories: (1) lying in bed, (2) sitting in bed, (3) sitting in chair, and (4) standing.
16. The system of claim 11 further comprising classifying patient motion as “in-bed activity” if a total body speed signature of the patient exceeds a threshold.
17. The system of claim 11 further comprising classifying patient motion as “nothing in bed” if a total body speed signature of the patient is below a threshold.
18. The system of claim 11 further comprising assigning a numerical mobility value to the patient mobility.
19. The system of claim 11 further comprising defining a predetermined area for measuring patient mobility.
20. The system of claim 19 further comprising defining the predetermined area for measuring patient mobility as the patient room.