Granted Patent B2

US 12,573,495 · App. 18/092,023 · Granted Mar 10, 2026

Inventors: Frederick E. Shelton, IV (Hillsboro, OH); Jason L. Harris (Lebanon, OH)

Assignee: Cilag GmbH International

G16H20/40G06F21/6245G16H50/20

Abstract

Claims (68)

1 . A surgical computing system comprising:

a processor configured to:

receive surgical data comprising a plurality of subsets of surgical data;

determine a first classification for a first subset of the plurality of subsets of surgical data, wherein the first classification is associated with a first privacy level;

determine a second classification for a second subset of the plurality of subsets of surgical data, wherein the second classification is associated with a second privacy level;

determine a first processing goal and a second processing goal, wherein the first processing goal is associated with a first processing task and a first data need, and wherein the second processing goal is associated with a second processing task and a second data need;

determine a first classification threshold associated with the first processing task and a second classification threshold associated with the second processing task;

determine a first data package based on the first processing goal, the first data need, and the first classification threshold, wherein the first data package comprises at least a first portion of the surgical data, and wherein a first machine learning (ML) model is associated with processing the first data package;

determine a second data package based on the second processing goal, the second data need, and the second classification threshold, wherein the second data package comprises at least a second portion of the surgical data, wherein the second portion of the surgical data comprises the first portion of the surgical data, and wherein a second ML model is associated with processing the second data package;

determine whether the first classification for the first subset is below the first classification threshold;

based on the first classification for the first subset being below the first classification threshold, transmit the first subset as part of the first data package to a first processing system included in a facility network configured to execute the first ML model;

determine whether the second classification for the second subset is below the second classification threshold; and

based on the second classification for the second subset being below the second classification threshold, transmit the second subset as part of the second data package to a second processing system that is included in a cloud network outside the facility network and is configured to execute the second ML model.

2 . The surgical computing system of claim 1 , wherein the processor is further configured to:

transmit the first data package to the first ML model; and

transmit the second data package to the second ML model.

3 . The surgical computing system of claim 1 , wherein the first classification threshold is associated with the first privacy level, wherein the second classification threshold is associated with the second privacy level, and wherein the second privacy level is associated with more privacy than the first privacy level.

4 . The surgical computing system of claim 1 , wherein the first classification threshold is a first privacy classification threshold associated with a first location associated with the first processing task, and wherein the second classification threshold is a second privacy classification threshold associated with a second location associated with the second processing task.

5 . The surgical computing system of claim 1 , wherein the first processing task is performed using the first ML model, and wherein the second processing task is performed using the second ML model.

6 . The surgical computing system of claim 1 , wherein the first classification threshold is determined based on the first processing goal, and wherein the second classification threshold is determined based on the second processing goal.

7 . The surgical computing system of claim 6 , wherein the processor is configured to:

determine that the first processing goal has changed;

based on the determination that the first processing goal has changed, determine an updated first processing goal;

determine an updated first classification threshold based on the updated first processing goal;

determine a third data package based on the updated first processing goal and the updated first classification threshold;

determine an updated second processing goal based on the determination that the first processing goal has changed;

determine an updated second classification threshold based on the updated second processing goal; and

determine a fourth data package based on the updated second processing goal and the updated second classification threshold.

8 . A method, the method comprising:

receiving surgical data comprising a plurality of subsets of surgical data;

determining a first classification for a first subset of the plurality of subsets of surgical data, wherein the first classification is associated with a first privacy level;

determining a second classification for a second subset of the plurality of subsets of surgical data, wherein the second classification is associated with a second privacy level;

determining a first processing goal and a second processing goal, wherein the first processing goal is associated with a first processing task and a first data need, and wherein the second processing goal is associated with a second processing task and a second data need;

determining a first classification threshold associated with the first processing task and a second classification threshold associated with the second processing task;

determining a first data package based on the first processing goal, the first data need, and the first classification threshold, wherein the first data package comprises at least a first portion of the surgical data, and wherein a first machine learning (ML) model is associated with processing the first data package;

determining a second data package based on the second processing goal, the second data need, and the second classification threshold, wherein the second data package comprises at least a second portion of the surgical data, wherein the second portion of the surgical data comprises the first portion of the surgical data, and wherein a second ML model is associated with processing the second data package;

determining whether the first classification for the first subset is below the first classification threshold;

based on the first classification for the first subset being below the first classification threshold, transmitting the first subset as part of the first data package to a first processing system included in a facility network configured to execute the first ML model;

determining whether the second classification for the second subset is below the second classification threshold; and

based on the second classification for the second subset being below the second classification threshold, transmitting the second subset as part of the second data package to a second processing system that is included in a cloud network outside the facility network and is configured to execute the second ML model.

9 . The method of claim 8 , wherein the method further comprises:

transmitting the first data package to the first ML model; and

transmitting the second data package to the second ML model.

10 . The method of claim 8 , wherein the first classification threshold is associated with the first privacy level, wherein the second classification threshold is associated with the second privacy level, and wherein the second privacy level is associated with more privacy than the first privacy level.

11 . The method of claim 8 , wherein the first classification threshold is a first privacy classification threshold associated with a first location associated with the first processing task, and wherein the second classification threshold is a second privacy classification threshold associated with a second location associated with the second processing task.

12 . The method of claim 8 , wherein the first processing task is performed using the first ML model, and wherein the second processing task is performed using the second ML model.

13 . The method of claim 8 , wherein the first classification threshold is determined based on the first processing goal, and wherein the second classification threshold is determined based on the second processing goal.

14 . The method of claim 8 , wherein the method further comprises:

determining that the first processing goal has changed;

based on the determination that the first processing goal has changed, determining an updated first processing goal;

determining an updated first classification threshold based on the updated first processing goal;

determining a third data package based on the updated first processing goal and the updated first classification threshold;

determining an updated second processing goal based on the determination that the first processing goal has changed;

determining an updated second classification threshold based on the updated second processing goal; and

determining a fourth data package based on the updated second processing goal and the updated second classification threshold.

15 . A surgical computing system comprising:

a processor configured to:

receive surgical data comprising a plurality of subsets of surgical data;

determine a first classification for a first subset of the plurality of subsets of surgical data, wherein the first classification is associated with a first privacy level;

determine a second classification for a second subset of the plurality of subsets of surgical data, wherein the second classification is associated with a second privacy level;

determine a first processing goal and a second processing goal, wherein the first processing goal is associated with a first processing task and a first data need, and wherein the second processing goal is associated with a second processing task and a second data need;

determine a first privacy threshold associated with the first processing task and a second privacy threshold associated with the second processing task;

determine a first data package based on the first processing goal, the first data need, and the first privacy threshold, wherein the first data package comprises at least a first portion of the surgical data, and wherein a first machine learning (ML) model is associated with processing the first data package;

determine a second data package based on the second processing goal, the second data need, and the second privacy threshold, wherein the second data package comprises at least a second portion of the surgical data, wherein the second portion of the surgical data comprises the first portion of the surgical data, and wherein a second ML model is associated with processing the second data package;

determine whether the first classification for the first subset is below the first privacy threshold;

based on the first classification for the first subset being below the first privacy threshold, transmit the first subset as part of the first data package to a first processing system included in a facility network configured to execute the first ML model;

determine whether the second classification for the second subset is below the second privacy threshold; and

based on the second classification for the second subset being below the second privacy threshold, transmit the second subset as part of the second data package to a second processing system that is included in a cloud network outside the facility network and is configured to execute the second ML model.

Assignments (1)

Continuity (1)

References Cited (117)