Quantifying variation in surgical approaches

1 . A system comprising:

a machine learning training system comprising one or more machine learning models that are trained to identify a plurality of surgical phases in a video of a surgical procedure; and

a data analysis system configured to quantify variation in surgical approaches in a plurality of videos capturing a same type of surgical procedure, wherein the quantifying variation in surgical approaches comprises:

receiving a plurality of surgical videos, each of the plurality of surgical videos capturing a workflow of the same type of surgical procedure;

segmenting each of the plurality of surgical videos into a segmented workflow comprising a plurality of surgical phases, the segmenting based on surgical phases identified by the machine learning training system;

aligning phases in the segmented workflows to an average workflow of the segmented workflows to create a plurality of aligned workflows, wherein the average workflow is calculated based on the workflows captured in the plurality of surgical videos by analyzing a plurality of medoid workflows in the plurality of surgical videos, selecting the average workflow from the plurality of medoid workflows, and executing adaptive dynamic time warping-barycenter-averaging (ADBA) using each of the medoid workflows as an initial average, and wherein the analyzing is optimized for categoric data and is based at least in part on mode values of phases across the segmented workflows;

calculating an entropy for each phase in the aligned workflows, the calculating based on a Chao-Shen estimator which reduces bias for small sample sizes; and

outputting the entropy for each phase in the aligned workflows to a display device for display, wherein the entropy represents variation in surgical approaches to the surgical procedure.

2 . The system of claim 1 , wherein calculating the entropy comprises scaling the entropy by its maximum possible value to a value that falls in a specified range of values.

3 . The system of claim 1 , wherein the optimization comprises modifying a length of the average workflow by one of adding a phase to the average workflow or removing a phase from the average workflow.

4 . The system of claim 1 , wherein the outputting further comprises outputting an indication of a surgical service provider associated with one or more of the aligned workflows to the display device for display.

5 . A computer-implemented method comprising:

receiving, by a processor, a plurality of surgical videos, each of the plurality of surgical videos capturing a workflow of a same type of surgical procedure and each of the plurality of surgical videos segmented into a segmented workflow comprising surgical phases;

analyzing a plurality of the segmented workflows to calculate an average workflow, wherein the average workflow is calculated based on the workflows captured in the plurality of surgical videos by analyzing a plurality of medoid workflows in the plurality of surgical videos, selecting the average workflow from the plurality of medoid workflows, and executing adaptive dynamic time warping-barycenter-averaging (ADBA) using each of the medoid workflows as an initial average, and wherein the analyzing is optimized for categoric data and is based at least in part on mode values of phases across the segmented workflows;

aligning the plurality of the segmented workflows to the average workflow; and

based on the aligning, quantifying a variation in the surgical approaches in the plurality of segmented workflows.

6 . The computer-implemented method of claim 5 , wherein the analyzing is optimized for categoric data and is based at least in part on mode values of phases across the segmented workflows.

7 . The computer-implemented method of claim 6 , wherein the optimization comprises modifying a length of the average workflow by one of adding a phase to the average workflow or removing a phase from the average workflows.

8 . The computer-implemented method of claim 5 , further comprising outputting, by the processor to a display device, a graphical representation of the aligned segmented workflows and the variation in the surgical approaches.

9 . The computer-implemented method of claim 8 , wherein the graphical representation identifies a surgical service provider associated with each of the workflows.

10 . The computer-implemented method of claim 5 , wherein a scaled entropy value is used to quantify the variation in the surgical approaches.

11 . A computer program product comprising a memory device having computer-executable instructions stored thereon, which when executed by one or more processors cause the one or more processors to perform operations comprising:

visualizing variations in surgical approaches to performing a surgical procedure, the visualizing comprising:

receiving a plurality of surgical videos, each of the plurality of surgical videos capturing a workflow of a same type of surgical procedure and each of the plurality of surgical videos segmented into a segmented workflow comprising surgical phases;

analyzing a plurality of the segmented workflows to calculate an average workflow, wherein the average workflow is calculated based on the workflows captured in the plurality of surgical videos by analyzing a plurality of medoid workflows in the plurality of surgical videos, selecting the average workflow from the plurality of medoid workflows, and executing adaptive dynamic time warping-barycenter-averaging (ADBA) using each of the medoid workflows as an initial average, and wherein the analyzing is optimized for categoric data and is based at least in part on mode values of phases across the segmented workflows;

aligning the plurality of the segmented workflows to the average workflow;

based on the aligning, quantifying a variation in the workflows in the plurality of surgical videos; and

outputting to a display device, a graphical representation of the quantified variation.

12 . The computer program product of claim 11 , wherein the visualizing further comprises:

receiving user input via a user interface of the graphical representation; and

in response to the user input, outputting to the display device, a second graphical representation that includes additional information describing characteristics of one or both of a service provider or a patient.

13 . The computer program product of claim 11 , wherein the graphical representation of the quantified variation comprises a graph of the variation over a duration of the surgical procedure.

14 . The computer program product of claim 11 , wherein each of the plurality of surgical videos is segmented into surgical phases, and the quantifying is based at least in part on the surgical phases.