Dynamic adjustment of algorithms for separation and collection of blood components
Blood is conveyed from a source into a separator, which separates at least one target blood component from the blood. The target blood component is then conveyed out of the separator, with the procedure continuing until an initial target amount of blood to be processed has been conveyed from the source into the separator and the target blood component separated from the initial target amount of blood to be processed has been conveyed out of the separator as an actual yield of the target blood component. An adjusted target amount of blood to be processed is then determined based at least in part on the difference between a target yield of the target blood component and the actual yield. The initial target amount of blood to be processed is then replaced with the adjusted target amount of blood to be processed when next executing the procedure.
1. A blood processing system, comprising:
a blood separation device including
a separator configured to receive a blood separation chamber,
a pump system, and
a controller configured to control the separator and the pump system to execute a blood separation procedure having a target yield of at least one target blood component using an initial target amount of blood from a blood source, with execution of the blood separation procedure resulting in an actual yield of said at least one target blood component; and
a data processing system configured to communicate with the controller, wherein
the data processing system is configured to
access or calculate the difference between a plurality of actual yields and target yields for blood separation procedures executed for a plurality of different blood sources,
select two or more of said differences,
determine an average of said two or more differences,
determine an adjusted target amount of blood to be processed when executing the blood separation procedure for a subsequent blood source or a scaling factor to be applied when determining the adjusted target amount of blood to be processed when executing the blood separation procedure for said subsequent blood source based at least in part on said average, and
transmit said adjusted target amount of blood or said scaling factor to the controller when the blood separation device is to be used to execute a blood separation procedure for said subsequent blood source and the controller is further configured to control the separator and the pump system to execute said blood separation procedure for said subsequent blood source, with the initial target amount of blood being replaced with said adjusted target amount of blood.
2. The blood processing system of claim 1 , wherein the data processing system is configured to select said two or more differences based on a similarity between at least one of the sex, height, weight, ethnicity, hematocrit, pre-count of a cellular component of interest, and protein count among the plurality of different blood sources.
3. The blood processing system of claim 1 , wherein the data processing system is configured to apply the same weight to each one of said two or more differences when determining said average.
4. The blood processing system of claim 1 , wherein the data processing system is configured to apply different weights to at least two of said two or more differences when determining said average.
5. The blood processing system of claim 4 , wherein the weight to be assigned to at least one of said differences is determined by the data processing system using exponential smoothing techniques.
6. The blood processing system of claim 4 , wherein the weight to be assigned to at least one of said differences is determined by the data processing system using double exponential smoothing techniques.
7. The blood processing system of claim 4 , wherein the weight to be assigned to at least one of said differences is determined by the data processing system using triple exponential smoothing techniques.
8. The blood processing system of claim 4 , wherein the data processing system is configured to calculate a moving average when determining said average.
9. The blood processing system of claim 8 , wherein the data processing system is configured to calculate a second moving average from the moving average when determining said average.
10. The blood processing system of claim 1 , wherein the data processing system is configured to employ machine learning techniques when selecting said two or more differences to determine the number of differences to be selected so as to produce the smallest mean squared error when determining said average.
11. A blood separation method, comprising:
(a) conveying blood from a blood source into a separator,
(b) separating at least one target blood component from the blood in the separator,
(c) conveying said at least one target blood component out of the separator,
(d) continuing to execute (a)-(c) until an initial target amount of blood to be processed has been conveyed from the blood source into the separator and said at least one target blood component separated from the initial target amount of blood to be processed has been conveyed out of the separator as an actual yield of said at least one target blood component,
(e) recording a difference between a target yield of said at least one target blood component and the actual yield,
(f) repeating (a)-(e) for a plurality of different blood sources,
(g) determining a scaling factor based at least in part on an average of at least two of said recorded differences, and
(h) executing (a)-(d) for a subsequent blood source, with the initial target amount of blood to be processed being replaced with an adjusted target amount of blood to be processed based at least in part on said scaling factor.
12. The blood separation method of claim 11 , wherein said two or more recorded differences are selected based on a similarity between at least one of the sex, height, weight, ethnicity, hematocrit, pre-count of a cellular component of interest, and protein count among the plurality of different blood sources.
13. The blood separation method of claim 11 , wherein the same weight is applied to each one of said two or more differences when determining said average.
14. The blood separation method of claim 11 , wherein different weights are applied to at least two of said two or more differences when determining said average.
15. The blood separation method of claim 14 , wherein the weight to be assigned to at least one of said recorded differences is determined using exponential smoothing techniques.
16. The blood separation method of claim 14 , wherein the weight to be assigned to at least one of said recorded differences is determined using double exponential smoothing techniques.
17. The blood separation method of claim 14 , wherein the weight to be assigned to at least one of said recorded differences is determined using triple exponential smoothing techniques.
18. The blood separation method of claim 14 , wherein a moving average is calculated when determining said average.
19. The blood separation method of claim 18 , wherein a second moving average is calculated from the moving average when determining said average.
20. The blood separation method of claim 11 , wherein machine learning techniques are employed when selecting said two or more recorded differences to determine the number of recorded differences to be selected so as to produce the smallest mean squared error when determining said average.