Component matching determination support tool

Abstract

The present invention provides a method for reducing variations in combination devices and a non-temporary computer-readable medium. [Solution] The method includes identifying potential combinations of at least first and second components, each combination forming one or more units of a combinational device, and for each potential combination, predicting the characteristics or results of the units of the combinational device when formed from at least the first and second components of the combination by applying the values ​​of at least one or more characteristics of the first components of the combination and the values ​​of one or more characteristics of the second components of the combination as input to a predictive model, and providing a subset of combinations from the potential combinations and an indication of the selected subset of combinations based on the predicted characteristics or results of the potential combinations.

Claims

1. A method for reducing variations in combination devices, Identifying, by one or more processors, a plurality of potential combinations of at least a first component and a second component, wherein each of the potential combinations can form one or more units of a combination device. For each of the aforementioned potential combinations, the one or more processors predict the characteristics or results of the unit of the combinational apparatus when it is formed from at least the first and second components of the combination, by applying at least (i) the values ​​of one or more characteristics of the first component of the combination and (ii) the values ​​of one or more characteristics of the second component of the combination as input to a predictive model. The one or more processors select a subset of combinations from the potential combinations based on the predicted characteristics or results of the potential combinations, The one or more processors provide instructions for the selected subset of combinations, A method that includes this.

2. Each of the aforementioned potential combinations is a different pair consisting of (i) a batch of the first component and (ii) a batch of the second component. For each of the aforementioned potential combinations, The values ​​of each of the one or more characteristics of the first component statistically represent each batch of the first component, The method according to claim 1, wherein the values ​​of each of the one or more characteristics of the second component statistically represent each batch of the second component.

3. Identifying the aforementioned multiple potential combinations is, Receiving a first set of identifiers for different batches of the first component, Receiving a second set of identifications of different batches of the second component, Each of the plurality of potential combinations is identified by forming a different pair consisting of an identifier from the first set and an identifier from the second set, The method according to claim 2, including the method described in claim 2.

4. The method according to any one of claims 1 to 3, wherein identifying the plurality of potential combinations includes eliminating combinations that are not feasible.

5. The method according to any one of claims 1 to 3, wherein identifying the plurality of potential combinations includes receiving instructions for each of the plurality of potential combinations.

6. The method according to any one of claims 1 to 5, wherein selecting the subset of the combinations comprises using the predicted characteristics or results of the potential combinations as input to the objective function and solving the objective function.

7. The method further includes, for each of the potential combinations, using one or more additional predictive models to predict one or more additional characteristics or results of the unit of the combination apparatus when it is formed from the first and second components of the combination, The method according to claim 6, wherein the objective function includes a plurality of functional terms, each corresponding to a different characteristic or result of the combination device.

8. The aforementioned combination device is a filled syringe, The first component is a syringe, The method according to any one of claims 1 to 7, wherein the second component is a fluid pharmaceutical.

9. The method according to claim 8, wherein the one or more characteristics of the first component include one or more of glide force, shield removal force, outer cylinder diameter, destructive test results, plunger diameter, or plunger weight.

10. The method according to claim 8 or 9, wherein the one or more properties of the second component include one or more of viscosity, density, or protein concentration.

11. The aforementioned combination device is an automatic injector. The first component is a pre-filled syringe, The method according to any one of claims 1 to 7, wherein the second component is an automatic injector subassembly.

12. The method according to claim 11, wherein the one or more properties of the first component include one or more of the following: extrusion force, sliding yield stress, protein concentration, or particle properties.

13. The method according to claim 11 or 12, wherein the one or more characteristics of the second component include one or more of the specification number, the result of a saline release test, the injection time, the operating force, or the spring force.

14. The method according to any one of claims 8 to 13, wherein predicting the characteristics or results of the unit of the combination apparatus includes predicting a value indicating variation in injection time or operating force across the unit of the combination apparatus.

15. The method according to any one of claims 1 to 14, wherein predicting the characteristics or results of the units of the combination apparatus includes predicting the probability distribution of the characteristics of the combination apparatus across the units of the combination apparatus.

16. The method according to any one of claims 1 to 14, wherein predicting the characteristics or results of the unit of the combination apparatus includes predicting the existence, quantity, frequency, or likelihood of user complaints associated with the unit of the combination apparatus.

17. The method according to any one of claims 1 to 16, wherein the prediction model is a gradient boosted tree model or a neural network.

18. The method according to any one of claims 1 to 17, wherein providing the instruction for the selected subset of the combinations includes causing a display to show the selected subset of the combinations to the user.

19. The method according to any one of claims 1 to 18, wherein providing the instruction for the selected subset of the combination comprises transmitting data indicating the selected subset of the combination to a computing system or application.

20. The method according to any one of claims 1 to 19, further comprising assembling a plurality of units of the combination device according to the selected subset of combinations.

21. One or more non-temporary computer-readable media, When executed by one or more processors, the one or more processors, Identifying a plurality of potential combinations of at least a first component and a second component, wherein each of the potential combinations can form one or more units of a combination device. For each of the aforementioned potential combinations, the characteristics or results of the unit of the combinational apparatus when it is formed from at least the first and second components of the combination are predicted by applying at least (i) the value of one or more characteristics of the first component of the combination and (ii) the value of one or more characteristics of the second component of the combination as input to a predictive model, Selecting a subset of combinations from the potential combinations based on the predicted characteristics or results of the potential combinations, To provide instructions for the selected subset of combinations, One or more non-temporary computer-readable media containing instructions for performing a certain action.

22. Each of the aforementioned potential combinations is a different pair consisting of (i) a batch of the first component and (ii) a batch of the second component. For each of the aforementioned potential combinations, The values ​​of each of the one or more characteristics of the first component statistically represent each batch of the first component, The value of each of the one or more characteristics of the second component statistically represents each batch of the second component, one or more non-temporary computer-readable media according to claim 21.

23. Identifying the plurality of potential combinations includes excluding combinations that are not feasible, one or more non-temporary computer-readable media according to claim 22.

24. Selecting the subset of the combinations comprises solving the objective function using the predicted characteristics or results of the potential combinations as input to the objective function, one or more non-temporary computer-readable media according to any one of claims 21 to 23.

25. The aforementioned combination device is a filled syringe, The first component is a syringe, The one or more non-temporary computer-readable media according to any one of claims 21 to 24, wherein the second component is a fluid pharmaceutical.

26. The one or more non-temporary computer-readable media according to claim 24, wherein the one or more characteristics of the first component include one or more of glide force, shield removal force, outer cylinder diameter, destructive test results, plunger diameter, or plunger weight.

27. The one or more non-temporary computer-readable media according to claim 25 or 26, wherein the one or more properties of the second component include one or more of viscosity, density, or protein concentration.

28. The aforementioned combination device is an automatic injector. The first component is a pre-filled syringe, The one or more non-temporary computer-readable media according to any one of claims 21 to 24, wherein the second component is an automatic injector subassembly.

29. The one or more non-temporary computer-readable media according to claim 28, wherein the one or more properties of the first component include one or more of extrusion force, sliding yield stress, protein concentration, or particle properties.

30. The one or more non-temporary computer-readable media according to claim 28 or 29, wherein the one or more characteristics of the second component include one or more of a specification number, a saline release test result, an injection time, an operating force, or a spring force.

31. One or more non-temporary computer-readable media according to any one of claims 25 to 30, wherein predicting the characteristics or results of the units of the combination apparatus includes predicting values ​​indicating variations in injection time or operating force across the units of the combination apparatus.

32. One or more non-temporary computer-readable media according to any one of claims 21 to 31, wherein predicting the characteristics or results of the units of the combination apparatus includes predicting the probability distribution of the characteristics of the combination apparatus across the units of the combination apparatus.

33. One or more non-temporary computer-readable media according to any one of claims 21 to 30, wherein predicting the characteristics or results of the unit of the combination device includes predicting the existence, quantity, frequency, or likelihood of user complaints associated with the unit of the combination device.

34. The prediction model is a gradient boosted tree model or a neural network, one or more non-temporary computer-readable media according to any one of claims 21 to 33.

35. To provide the indication of the selected subset of combinations is to To display the selected subset of the combination to the user on the display, or To transmit data indicating the selected subset of the combinations to a computing system or application. One or more non-temporary computer-readable media according to any one of claims 21 to 34, comprising at least one of the above.

Images