Method for setting a blood transfusion parameter

• US 9,646,375 B2
• Filed: 11/05/2013
• Issued: 05/09/2017
• Est. Priority Date: 07/09/2011
• Status: Active Grant

• Current Assignee: Gauss Surgical, Gauss Surgical, Inc. (Stryker Corporation)
• Original Assignee: Gauss Surgical, Inc. (Stryker Corporation)
• Inventors: Satish, Siddarth, Zandifar, Ali, Miller, Kevin
• Primary Examiner(s): YANG, WEI WEN
• Application Number:
  US14/072,632
• Publication Number:
  US 20140128838A1
• Time in Patent Office: 1,281 Days
• Field of Search: None
• CPC Class Codes: A61M 1/024 Means for controlling the quantity of transfused blood, e.g. by weighing the container and automatic stopping of the transfusion after reaching a determined amount
• CPC Class Codes: A61M 1/60 Containers for suction drainage, adapted to be used with an external suction source containers not adapted for subjection to vacuum A61M1/69
• CPC Class Codes: A61M 2202/0429 Red blood cells; Erythrocytes
• CPC Class Codes: A61M 2205/3306 Optical measuring means
• CPC Class Codes: A61M 2205/3379 Masses, volumes, levels of fluids in reservoirs, flow rates
• CPC Class Codes: G06T 2207/10024 Color image
• CPC Class Codes: G06T 2207/30024 Cell structures in vitro; Tissue sections in vitro
• CPC Class Codes: G06T 7/0012 Biomedical image inspection

Abstract

One variation of a method for setting a blood transfusion parameter for a patient includes identifying a blood transfusion bag in a photographic image; extracting a color feature from a region of the photographic image corresponding to the blood transfusion bag; estimating a blood component content within the blood transfusion bag based on the color feature; and triggering transfusion from the blood transfusion bag based on the blood component content within the blood transfusion bag and an estimated volemic status of the patient.

Claims

1. A method for setting a blood transfusion parameter for a patient, the method comprising:

identifying, at a computing system, a blood transfusion bag in a photographic image generated using an optical sensor in communication with the computing system, and, in a region of the photographic image, a fluid surface within the blood transfusion bag;

extracting, at the computing system, a color feature from a region of the photographic image corresponding to the blood transfusion bag;

identifying, at the computing system, a volume marker printed on the blood transfusion bag in the region of the photographic image;

generating, at the computing system, an estimated volume of fluid in the blood transfusion bag based on the volume marker and the fluid surface;

estimating, at the computing system, a blood component content within the blood transfusion bag based on the color feature and the estimated volume of fluid; and

triggering transfusion from the blood transfusion bag based on the blood component content within the blood transfusion bag and an estimated volemic status of the patient.

2. The method of claim 1, wherein extracting the color feature from the region of the photographic image comprises extracting the color value in the red component space from the region of the photographic image, and wherein estimating the blood component content within the blood transfusion bag comprises estimating a concentration of red blood cells in the blood transfusion bag based on the redness value of the region of the photographic image.

3. The method of claim 2, wherein extracting the color feature from the region of the photographic image further comprises extracting a second color value in the blue component space and a third color value in the green component space from the region of the photographic image, and wherein estimating the blood component content within the blood transfusion bag further comprises estimating a concentration of free hemoglobin in the blood transfusion bag based on the color value, the second color value, and the third color value.

4. The method of claim 2, wherein identifying the blood transfusion bag in the photographic image comprises implementing optical character recognition to identify text printed on the blood transfusion bag and further comprising determining a volume of fluid in the blood transfusion bag based on identified text printed on the blood transfusion bag, estimating a red blood cell mass in the blood transfusion bag based on the concentration of red blood cells and the volume of fluid in the blood transfusion bag, and calculating a blood transfusion stop time based on the red blood cell mass in the blood transfusion bag and the volemic status of the patient.

5. The method of claim 1, further comprising

receiving a second image of a physical substrate,

extracting a feature from a region of the second image corresponding to the physical substrate,

estimating the blood component content in the physical substrate based on the extracted feature,

updating a blood loss history of the patient with the blood component content based on a timestamp of the second image,

predicting a current hematocrit of the patient based on the blood loss history of the patient, and

estimating the volemic status of the patient, the volemic status of the patient defining a difference between the current hematocrit of the patient and a target hematocrit of the patient.

6. The method of claim 5, wherein extracting the feature from the region of the second image comprises extracting the feature from the region of the second image corresponding to one of a suction canister, a gauze sponge, a surgical towel, and a surgical drape.

7. The method of claim 5, further comprising estimating an intracirculatory blood volume of the patient based on the blood loss history and an infusion history of the patient, wherein triggering transfusion from the blood transfusion bag comprises predicting achievement of the target hematocrit of the patient based on the intracirculatory blood volume of the patient, the current hematocrit of the patient, and the blood component content within the blood transfusion bag.

8. The method of claim 1, further comprising estimating a preferred transfusion rate from the blood transfusion bag to achieve a target hematocrit of the patient, based on the estimated volemic status and the blood component content within the blood transfusion bag.

9. The method of claim 5, further comprising extrapolating a volemic status trend of the patient from the blood loss history of the patient, wherein calculating the transfusion rate from the blood transfusion bag comprises calculating the transfusion rate from the blood transfusion bag to offset a predicted future volemic status of the patient based on the volemic status trend of the patient.

10. The method of claim 8, further comprising updating the transfusion rate over time based on the volemic status trend and an estimated blood component content in a second physical substrate.

11. The method of claim 1, wherein identifying the blood transfusion bag in the photographic image comprises identifying an autologous blood transfusion bag in the photographic image.

12. The method of claim 1, wherein identifying the blood transfusion bag in the photographic image comprises extracting a barcode from the region of the photographic image corresponding to the blood transfusion bag and retrieving, from a database, a set of data pertaining to allogeneic blood contained in the blood transfusion bag based on the extracted barcode.

13. The method of claim 12, further comprising capturing the photographic image with a camera integrated into a mobile computing device, receiving a Global Positioning System location from a corresponding sensor in the mobile computing device, and transmitting delivery confirmation for the blood transfusion bag to the database in response to the Global Positioning System location with a threshold range of a target location specified in the set of data pertaining to the blood transfusion bag.

14. The method of claim 13, wherein triggering transfusion from the blood transfusion bag comprises displaying an alarm to initiate transfusion from the blood transfusion bag on a display integrated into the mobile computing device.

15. The method of claim 1, wherein identifying the blood transfusion bag in the photographic image comprises implementing edge detection to identify the region of the photographic image corresponding to the blood transfusion bag and estimating a volume of fluid in the blood transfusion bag based on a perimeter shape of the region.

17. The method of claim 2, wherein extracting the color feature from the region of the photographic image comprises extracting the color value in the red component space from the region of the photographic image, and wherein estimating the blood component content within the blood transfusion bag comprises estimating a concentration of red blood cells in the blood transfusion bag based on the redness value of the region of the photographic image.

18. The method of claim 17, wherein extracting the color feature from the region of the photographic image further comprises extracting a second color value in the blue component space and a third color value in the green component space from the region of the photographic image, and wherein estimating the blood component content within the blood transfusion bag further comprises estimating a concentration of free hemoglobin in the blood transfusion bag based on the color value, the second color value, and the third color value.

19. The method of claim 17, wherein identifying the blood transfusion bag in the photographic image comprises implementing optical character recognition to identify text printed on the blood transfusion bag and further comprising determining a volume of fluid in the blood transfusion bag based on identified text printed on the blood transfusion bag, estimating a red blood cell mass in the blood transfusion bag based on the concentration of red blood cells and the volume of fluid in the blood transfusion bag, and calculating a blood transfusion stop time based on the red blood cell mass in the blood transfusion bag and the volemic status of the patient.

16. A method for setting a blood transfusion parameter for a patient, the method comprising:

identifying, at a computing system, a blood transfusion bag in a photographic image generated using an optical sensor in communication with the computing system, comprising extracting a barcode, from a region of the photographic image corresponding to the blood transfusion bag and retrieving, from a database, a set of data pertaining to allogeneic blood contained in the blood transfusion bag based on the extracted barcode;

extracting, at the computing system, a color feature from a region of the photographic image corresponding to the blood transfusion bag;

identifying, at the computing system, a volume marker printed on the blood transfusion bag in the region of the photographic image;

estimating, at the computing system, a blood component content within the blood transfusion bag based on the color feature; and

triggering transfusion from the blood transfusion bag based on the blood component content within the blood transfusion bag and an estimated volemic status of the patient.

20. The method of claim 16, further comprising

receiving a second image of a physical substrate,

extracting a feature from a region of the second image corresponding to the physical substrate,

estimating the blood component content in the physical substrate based on the extracted feature,

updating a blood loss history of the patient with the blood component content based on a timestamp of the second image,

predicting a current hematocrit of the patient based on the blood loss history of the patient, and

estimating the volemic status of the patient, the volemic status of the patient defining a difference between the current hematocrit of the patient and a target hematocrit of the patient.

21. The method of claim 20, wherein extracting the feature from the region of the second image comprises extracting the feature from the region of the second image corresponding to one of a suction canister, a gauze sponge, a surgical towel, and a surgical drape.

22. The method of claim 20, further comprising estimating an intracirculatory blood volume of the patient based on the blood loss history and an infusion history of the patient, wherein triggering transfusion from the blood transfusion bag comprises predicting achievement of the target hematocrit of the patient based on the intracirculatory blood volume of the patient, the current hematocrit of the patient, and the blood component content within the blood transfusion bag.

23. The method of claim 16, further comprising estimating a preferred transfusion rate from the blood transfusion bag to achieve a target hematocrit of the patient, based on the estimated volemic status and the blood component content within the blood transfusion bag.

24. The method of claim 20, further comprising extrapolating a volemic status trend of the patient from the blood loss history of the patient, wherein calculating the transfusion rate from the blood transfusion bag comprises calculating the transfusion rate from the blood transfusion bag to offset a predicted future volemic status of the patient based on the volemic status trend of the patient.

25. The method of claim 23, further comprising updating the transfusion rate over time based on the volemic status trend and an estimated blood component content in a second physical substrate.

26. The method of claim 16, further comprising capturing the photographic image with a camera integrated into a mobile computing device, receiving a Global Positioning System location from a corresponding sensor in the mobile computing device, and transmitting delivery confirmation for the blood transfusion bag to the database in response to the Global Positioning System location with a threshold range of a target location specified in the set of data pertaining to the blood transfusion bag.

27. The method of claim 26, wherein triggering transfusion from the blood transfusion bag comprises displaying an alarm to initiate transfusion from the blood transfusion bag on a display integrated into the mobile computing device.

28. The method of claim 16, wherein identifying the blood transfusion bag in the photographic image comprises implementing edge detection to identify the region of the photographic image corresponding to the blood transfusion bag and estimating a volume of fluid in the blood transfusion bag based on a perimeter shape of the region.