Granted Patent B2

US 12,451,239 · App. 18/037,976 · Granted Oct 21, 2025

Inventors: Kristen Brown (Roswell, GA); Kiran Bhattacharyya (Atlanta, GA); Anthony Michael Jarc (Johns Creek, GA); Sue Kulason (Baltimore, MD); Linlin Zhou (Alpharetta, GA); Aneeq Zia (Atlanta, GA)

Assignee: Intuitive Surgical Operations, Inc.

G16H40/20

Abstract

Claims (67)

1. A computer-implemented method for generating a score based upon surgical data, the method comprising:

determining generating one or more metric values of a plurality of operational performance indicators (OPIs) from based at least upon surgical data;

establishing identifying a data structure comprising a mapping of each of the plurality of OPIs to at least one skill of a plurality of skills;

selecting, from the data structure comprising the mapping, one or more OPIs of the plurality of OPIs based at least on a skill from the plurality of skills;

identifying one or more metric values of the selected one or more OPIs for the user; and

generating a score for the skill of the user at least in part, by providing the one or more metric values for the selected one or more OPIs of the user as input to a machine learning model trained for the skill.

2. The computer-implemented method of claim 1 , wherein generating the score comprises:

providing the one or more metric values based upon the surgical data to the machine learning model implementation to generate a prediction; and

mapping the prediction to the score.

3. The computer-implemented method of claim 2 , wherein the prediction indicates whether the surgical data is more closely associated with a first classification or with a second classification.

4. The computer-implemented method of claim 3 , wherein,

the first classification and the second classification are associated with different surgeon skill levels, and wherein,

the machine learning model implementation is configured to receive metric values corresponding to surgical data associated with a particular surgical task.

5. The computer-implemented method of claim 4 , wherein the surgical data comprises patient-side kinematics data, operator-side kinematics data, visualization tool video data, and system events data.

6. The computer-implemented method of claim 2 , wherein,

determining the one or more metric values based upon the surgical data comprises providing the surgical data to a filtered corpus of metrics determined from annotated surgical data, wherein,

generating the score comprises:

inputting the metric values to the machine learning model implementation; and

applying the output of the machine learning model implementation to a mapping of predictions to scores, and wherein,

the machine learning model implementation is configured to receive metric values corresponding to the filtered corpus of metrics.

7. The computer-implemented method of claim 6 , the method further comprising:

presenting the score as one of several scores generated over the course of at least a portion of a surgeon's surgical performance.

8. A non-transitory computer-readable medium comprising instructions configured to cause a computer system to perform a method for generating a score based upon surgical data, the method comprising:

determining generating one or more metric values of a plurality of operational performance indicators (OPIs) from based at least upon surgical data;

establishing identifying a data structure comprising a mapping of each of the plurality of OPIs to at least one skill of a plurality of skills;

selecting, from the data structure comprising the mapping, one or more OPIs of the plurality of OPIs based at least on a skill from the plurality of skills;

identifying one or more metric values of the selected one or more OPIs for the user; and

generating a score for the skill of the user at least in part, by providing the one or more metric values for the selected one or more OPIs of the user as input to a machine learning model trained for the skill.

9. The non-transitory computer-readable medium of claim 8 , wherein generating the score comprises:

providing the one or more metric values based upon the surgical data to the machine learning model implementation to generate a prediction; and

mapping the prediction to the score.

10. The non-transitory computer-readable medium of claim 9 , wherein the prediction indicates whether the surgical data is more closely associated with a first classification or with a second classification.

11. The non-transitory computer-readable medium of claim 10 , wherein,

the first classification and the second classification are associated with different surgeon skill levels, and wherein,

the machine learning model implementation is configured to receive metric values corresponding to surgical data associated with a particular surgical task.

12. The non-transitory computer-readable medium of claim 11 , wherein the surgical data comprises patient-side kinematics data, operator-side kinematics data, visualization tool video data, and system events data.

13. The non-transitory computer-readable medium of claim 9 , wherein,

determining the one or more metric values based upon the surgical data comprises providing the surgical data to a filtered corpus of metrics determined from annotated surgical data, wherein,

generating the score comprises:

inputting the metric values to the machine learning model implementation; and

applying the output of the machine learning model implementation to a mapping of predictions to scores, and wherein,

the machine learning model implementation is configured to receive metric values corresponding to the filtered corpus of metrics.

14. The non-transitory computer-readable medium of claim 13 , the method further comprising:

presenting the score as one of several scores generated over the course of at least a portion of a surgeon's surgical performance.

15. A computer system comprising:

at least one processor;

at least one memory comprising instructions configured to cause the computer system to perform a method for generating a score based upon surgical data, the method comprising:

determining generating one or more metric values of a plurality of operational performance indicators (OPIs) from based at least upon surgical data;

establishing identifying a data structure comprising a mapping of each of the plurality of OPIs to at least one skill of a plurality of skills;

selecting, from the data structure comprising the mapping, one or more OPIs of the plurality of OPIs based at least on a skill from the plurality of skills;

identifying one or more metric values of the selected one or more OPIs for the user; and

generating a score for the skill of the user at least in part, by providing the one or more metric values for the selected one or more OPIs of the user as input to a machine learning model trained for the skill.

16. The computer system of claim 15 , wherein generating the score comprises:

providing the one or more metric values based upon the surgical data to the machine learning model implementation to generate a prediction; and

mapping the prediction to the score.

17. The computer system of claim 16 , wherein the prediction indicates whether the surgical data is more closely associated with a first classification or with a second classification.

18. The computer system of claim 17 wherein,

the first classification and the second classification are associated with different surgeon skill levels, and wherein,

the machine learning model implementation is configured to receive metric values corresponding to surgical data associated with a particular surgical task.

19. The computer system of claim 16 , wherein,

determining the one or more metric values based upon the surgical data comprises providing the surgical data to a filtered corpus of metrics determined from annotated surgical data, wherein,

generating the score comprises:

inputting the metric values to the machine learning model implementation; and

applying the output of the machine learning model implementation to a mapping of predictions to scores, and wherein,

the machine learning model implementation is configured to receive metric values corresponding to the filtered corpus of metrics.

20. The computer system of claim 19 , the method further comprising:

presenting the score as one of several scores generated over the course of at least a portion of a surgeon's surgical performance.

Assignments (1)

Continuity (2)

References Cited (192)