IP Library Granted Patent US 12688910
Granted Patent B2
US 12688910 · App. 17/447,606 · Granted Jul 21, 2026

System and method for configuration, scheduling, and/or execution of analyzing services for medical data based on usage data

Inventors: Daphne Yu (Yardley, PA); Anthony Dass Sowrirajan (Princeton Junction, NJ)
Assignee: Siemens Healthineers AG
G16H10/60G06N3/08G06Q10/0633
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12688910
App. No.
17/447,606
Granted
Jul 21, 2026
Kind
B2
Abstract

A medical data processing system includes: a medical data storage configured to collect one or more pieces of medical data from one or more input devices, a data analyzer configured to execute one or more analyzing services on the one or more pieces of medical data so as to output one or more corresponding pieces of analyzed medical data, a results manager configured to collect usage data, related to how the one or more pieces of analyzed medical data are analyzed by the data analyzer and/or used by one or more users, and a processing optimizer configured to control operation of the data analyzer based on the usage data.

Claims (18)

1 . A medical data processing system comprising:

a medical data storage implemented by a memory coupled with a processor, the medical data storage configured to store one or more pieces of medical data from one or more input devices,

a data analyzer implemented by the processor, the data analyzer configured to execute one or more analyzing services on the one or more pieces of medical data so as to output one or more corresponding pieces of analyzed medical data,

a results manager implemented by the processor, the results manager configured to collect usage data related to how the one or more pieces of analyzed medical data are analyzed by the data analyzer and/or used by one or more users at a particular hospital institution, wherein the usage data comprises at least a queueing time, based on a time from collecting of the one or more pieces of medical data to executing of the one or more analyzing services on the one or more pieces of medical data and an analyzing time based on a time used for executing of the one or more analyzing services on the one or more pieces of medical data, and

a processing optimizer implemented by the processor, the processing optimizer configured to control operation of the data analyzer by prioritizing execution of specific analyzing services of the one or more analyzing services based on the usage data and a level of computing resources made available for the execution of the one or more analyzing services on the one or more pieces of medical data so that an output most likely to be used by a particular user at a particular time at a particular hospital institution is provided by the one or more analyzing services, wherein the processing optimizer comprises a neural network trained through reinforcement learning, wherein the neural network is configured to receive at least the usage data as input for computing a cumulative reward related to the operation of the data analyzer.

2 . The medical data processing system according to claim 1 , wherein the processing optimizer is further configured to control operation of the data analyzer by control of: which of the one or more analyzing services is executed on which of the one or more pieces of medical data or a level of computing resources made available for the execution of the one or more analyzing services on the one or more pieces of medical data.

3 . The medical data processing system according to claim 1 , wherein the neural network is configured to be continuously trained based on at least the usage data.

4 . The medical data processing system according to claim 1 , wherein the neural network is configured to further receive at least configuration data as additional input for computing the cumulative reward.

5 . The medical data processing system according to claim 1 , wherein the neural network is configured to further receive clinical case information associated to the one or more pieces of medical data as additional input for computing the cumulative reward.

6 . The medical data processing system according to claim 1 , wherein the usage data further comprises:

correlation between use of the one or more pieces of analyzed medical data by the one or more users and meta-data associated to the one or more pieces of medical data.

7 . The medical data processing system according to claim 1 , further comprising a configuration storage implemented by the memory coupled with the processor, the configuration storage configured to store configuration data, related to processing preferences, wherein the processing optimizer is further configured to control operation of the data analyzer based on the configuration data.

8 . The medical data processing system according to claim 1 , further comprising a workflow analytics engine implemented by the processor, the workflow analytics engine is configured to evaluate the usage data so as to identify, for a given user of the one or more users, how the one or more pieces of analyzed medical data are used by the given user,

wherein the results manager is further configured to output the one or more pieces of analyzed medical data to a plurality of output devices based on the results of the evaluation of the workflow analytics engine.

9 . The medical data processing system according to claim 8 , wherein the workflow analytics engine comprises a second neural network trained through reinforcement learning,

wherein the second neural network is configured to receive at least the usage data as input for computing a cumulative reward related to the output of the one or more pieces of analyzed medical data to the plurality of output devices.

10 . The medical data processing system according to claim 9 , wherein the second neural network is configured to be continuously trained based on at least the usage data.

11 . The medical data processing system according to claim 9 , wherein the second neural network is configured to further receive clinical case information associated to the one or more pieces of analyzed medical data and/or associated to the one or more pieces of medical data as additional input for computing the cumulative reward.