Granted Patent B2

US 12,211,593 · App. 17/163,427 · Granted Jan 28, 2025

Inventors: Jaydeep Bhattacharyya (Acton, MA); James Bolognese (Woodbridge, NJ); Alexandre Buer (Holliston, MA); Eric Edwards (Nolensville, TN); Stanley Y. Huang (Wellesley, MA); Yannis Jemiai (Lexington, MA); Cyrus Mehta (Cambridge, MA); Nitin Patel (Cambridge, MA); Anne Pelz (Arlington, MA); Ajay Prabhakar Sathe (Pune, IN); Joshua A. Schultz (Boston, MA); Pralay Senchaudhuri (Cambridge, MA)

Assignee: Cytel Inc.

G16H10/20G06F30/10G06F30/12G06F30/20G06N5/04G06N20/00G06Q10/06315G06Q10/067G06Q30/0205G16H40/20G16H50/70G06F2111/02G06F2111/04G06F2111/06G06F2111/08G06F2111/16

Abstract

Claims (74)

1. A method comprising:

generating simulation parameters, wherein at least one parameter includes a placeholder value comprising an estimated value and/or a predicted value;

simulating trial designs based on the simulation parameters;

obtaining trial design simulation results for a set of trial designs;

supplementing the placeholder value of the trial design simulation results with substitute data comprising historical data and/or real-world data;

determining a set of Pareto designs in the set of trial designs based at least in part on the trial design simulation results and one or more performance parameters;

determining a set of convex hull designs in the set of trial designs;

determining a set of recommended designs based at least in part on the set of Pareto designs and the set of convex hull designs; and

transmitting the set of recommended designs.

2. The method of claim 1 further comprising:

filtering one or more of the set of trial designs that are dominated by at least one of the set of convex hull designs.

3. The method of claim 1 further comprising:

filtering one or more of the set of trial designs that are dominated by at least one of the set of Pareto designs.

4. The method of claim 1 , wherein determining the set of recommended designs comprises:

determining at least one of the set of recommended designs within an epsilon-distance from at least one of the set of Pareto designs.

5. The method of claim 1 , wherein determining the set of recommended designs comprises:

determining at least one of the set of recommended designs within an epsilon-distance from at least one of the set of convex hull designs.

6. The method of claim 1 , wherein determining a set of recommended designs comprises:

performing simulated annealing on one or more of the set of trial designs.

7. The method of claim 6 , wherein simulated annealing is based at least in part on facets of the set of convex hull designs.

8. The method of claim 1 further comprising:

identifying different design types in the set of Pareto designs.

9. The method of claim 1 , wherein:

the set of Pareto designs is determined prior to the set of convex hull designs;

the set of convex hull designs is derived from the set of Pareto designs such that each of the set of convex hull designs is in the set of Pareto designs; and

at least one of the set of recommended designs is in the set of convex hull designs.

10. The method of claim 1 , wherein:

the set of convex hull designs is determined prior to the set of Pareto designs;

the set of Pareto designs is derived from the set of convex hull designs such that each of the set of Pareto designs is in the set of convex hull designs; and

at least one of the set of recommended designs is in the set of convex hull designs.

11. The method of claim 1 further comprising:

identifying a number of trial designs in the set of Pareto designs;

wherein:

determining the set of convex hull designs occurs when the number is greater-than-or-equal-to a threshold; and

the set of convex hull designs is derived from the set of Pareto designs.

12. The method of claim 1 further comprising:

identifying a number of trial designs in the set of Pareto designs; and

if the number is less-than-or-equal-to a threshold, identifying, for inclusion in the set of recommended designs, one or more of the set of trial designs within an epsilon distance of at least one of the set of Pareto designs.

13. The method of claim 1 further comprising:

for each of the set of Pareto designs, determining a design type;

determining a first trial design of the set of Pareto designs is of a different design type from and within an epsilon-distance to a second trial design of the set of Pareto designs; and

including the first trial design and the second trial design in the set of recommended designs.

14. The method of claim 1 , further comprising:

evaluating historical trial design selections to identify one or more trial design parameters based at least in part on one or more trial design criteria determined from a user via an interactive interface, wherein obtaining trial design simulation results is based at least in part on a quick search data structure and the one or more trial design parameters;

generating a substitute for at least some of the trial design simulation results based at least in part on a relationship between the trial design simulation results and supplemental data;

generating a performance surface based at least in part on a set of trial designs corresponding to the trial design simulation results;

evaluating one or more trial designs based at least in part on the performance surface; and

calculating a score based on normalized score component values corresponding to the trial design simulation results.

15. An apparatus comprising:

an evaluation circuit structured to generate simulation parameters, wherein at least one parameter includes a placeholder value comprising an estimated value and/or a predicted value;

a simulation circuit structured to simulate trial designs based on the simulation parameters;

a results processing circuit structured to interpret trial design simulation results for a set of trial designs;

a substitute circuit structured to supplement the placeholder value of the trial design simulation results with substitute data comprising historical data and/or real-world data;

a Pareto evaluation circuit structured to determine a set of Pareto designs in the set of trial designs based at least in part on the trial design simulation results and one or more performance parameters;

a convex hull evaluation circuit structured to determine a set of convex hull designs in the sct of trial designs;

a recommendation circuit structured to determine a set of recommended designs based at least in part on the set of Pareto designs and the set of convex hull designs; and

a recommendation provisioning circuit structured to transmit the set of recommended designs.

16. The apparatus of claim 15 further comprising:

a filtering circuit structured to filter one or more of the set of trial designs that are dominated by at least one of the set of convex hull designs.

17. The apparatus of claim 15 further comprising:

a filtering circuit structured to filter one or more of the set of trial designs that are dominated by at least one of the set of Pareto designs.

18. The apparatus of claim 15 , wherein the recommendation circuit is further structured to:

determine at least one of the set of recommended designs within an epsilon-distance from at least one of the set of Pareto designs.

19. A non-transitory computer-readable medium storing instructions that adapt at least one processor to:

generate simulation parameters, wherein at least one parameter includes a placeholder value comprising an estimated value and/or a predicted value;

simulate trial designs based on the simulation parameters;

interpret trial design simulation results for a set of trial designs;

supplement the placeholder value of the trial design simulation results with substitute data comprising historical data and/or real-world data;

determine a set of Pareto designs in the set of trial designs based at least in part on the trial design simulation results and one or more performance parameters;

determine a set of convex hull designs in the set of trial designs;

determine a set of recommended designs based at least in part on the set of Pareto designs and the set of convex hull designs; and

transmit the set of recommended designs.

20. The non-transitory computer-readable medium of claim 19 , wherein the stored instructions further adapt the at least one processor to:

filter one or more of the set of trial designs that are dominated by at least one of the set of convex hull designs.

Assignments (1)

Continuity (7)

References Cited (123)