Adaptive surgical data throttle
A surgical computer-implement surgical system may include a surgical computing system (e.g., a surgical hub), one or more surgical data sources in communication with the surgical computing system, a surgical device in communication with the surgical computing system, and a processor. Data generated by the one or more surgical data sources may be received by the processor. Such data may be used, by the processor, to train a machine learning (ML) model (e.g., a neural network). The ML model may be deployed to affect an operation of the surgical device. For example, the ML model may be deployed to the surgical hub to affect an operation of the surgical device.
1 . A device, comprising:
a processor configured to:
receive a first data set for performing a surgical task, wherein:
the first data set is generated by a surgical data source associated with the performance of the surgical task by a surgical computing system,
the first data set has a first data volume, and
the first data set indicates a first level of available resources of the surgical computing system to perform the surgical task;
evaluate the first data volume and the first level of available resources used by the surgical computing system via a neural network, wherein the neural network is trained to determine a second data volume;
based on the evaluation, obtain the second data volume from the neural network, wherein the second data volume is less than the first data volume and maximizes a quantity of data associated with performing the surgical task without exceeding the first level of available resources of the surgical computing system; and
send a control signal to the surgical data source to generate a second data set associated with performing the surgical task at the second data volume.
2 . The device of claim 1 , wherein the neural network is trained to determine the second data volume based on historical data sets including volume data and surgical performance data.
3 . The device of claim 1 , wherein the second data volume is associated with a second level of available resources that is adequate to perform the surgical task.
4 . The device of claim 3 , wherein the second level of resources is provided by edge network processing.
5 . The device of claim 1 , wherein the neural network is trained to determine the second data volume based on patient outcomes associated with the surgical task.
6 . The device of claim 1 , wherein the neural network is trained to determine the second data volume based on aggregate performances of a plurality of similar surgical tasks to the surgical task.
7 . The device of claim 1 , wherein the second data set associated with performing the surgical task at the second data volume is associated with a staffing allocation for patient monitoring.
8 . The device of claim 7 , wherein the second data volume indicates a minimum amount of healthcare staff and a monitoring frequency associated with the patient monitoring.
9 . The device of claim 1 , wherein the first data volume and the second data volume are associated with a patient risk ratio.
10 . A method, comprising:
receiving a first data set for performing a surgical task, wherein:
the first data set is generated by a surgical data source associated with the performance of the surgical task by a surgical computing system,
the first data set has a first data volume, and
the first data indicates a first level of available resources of the surgical computing system to perform the surgical task;
evaluating the first data volume and the first level of available resources used by the surgical computing system via a neural network, wherein the neural network is trained to determine a second data volume;
based on the evaluation, obtaining the second data volume from the neural network, wherein the second data volume is less than the first data volume and maximizes a quantity of data associated with performing the surgical task without exceeding a maximum amount of available resources of the surgical computing system; and
sending a control signal to the surgical data source to generate a second data set associated with performing the surgical task at the second data volume.
11 . The method of claim 10 , wherein the neural network is trained to determine the second data volume based on historical data sets including volume data and surgical performance data.
12 . The method of claim 10 , wherein second data volume is associated with a second level of available resources that is adequate to perform the surgical task.
13 . The method of claim 12 , wherein the second level of resources are provided by edge network processing.
14 . The method of claim 10 , wherein the neural network is trained to determine the second data volume based on patient outcomes associated with the surgical task.
15 . The method of claim 10 , wherein the neural network is trained to determine the second data volume based on aggregate performances of a plurality of similar surgical tasks to the surgical task.
16 . A method, comprising:
training a neural network with a first data set generated by a surgical data source, and wherein the first data has a first data volume and indicates a first level of available resources of a surgical computing system to perform a surgical task;
inputting the first data volume, using a first level of available resources for performing the surgical task to the neural network, to determine a second data volume, wherein the second data volume is less than the first data volume and maximizes a quantity of data associated with performing the surgical task without exceeding a maximum amount of available resources of the surgical computing system; and
outputting a control signal to the surgical data source to generate a second data set associated with performing the surgical task at the second data volume.
17 . The method of claim 16 , wherein the neural network is trained to determine the second data volume based on historical data sets including volume data and surgical performance data.
18 . The method of claim 16 , wherein second data volume is associated with a second level of available resources that is adequate to perform the surgical task.
19 . The method of claim 16 , wherein the neural network is trained to determine the second data volume based on patient outcomes associated with the surgical task.
20 . The method of claim 16 , wherein the neural network is trained to determine the second data volume based on aggregate performances of a plurality of similar surgical tasks to the surgical task.