Medical Equipment Monitoring Method and System

• US 20100011251A1
• Filed: 07/14/2008
• Published: 01/14/2010
• Est. Priority Date: 07/14/2008
• Status: Active Grant

• Current Assignee: General Electric Company
• Original Assignee: General Electric Company
• Inventors: Mannar, Kamal, Starasinich, Douglas E.
• Granted Patent: US 8,165,849 B2
• Time in Patent Office: Days
• US Class Current: 714/32
• CPC Class Codes: A61B 5/7221 Determining signal validity, reliability or quality A61B5/7207 and A61B5/7217 take precedence
• CPC Class Codes: A61B 5/7257 using Fourier transforms
• CPC Class Codes: G16H 40/40 for the management of medical equipment or devices, e.g. scheduling maintenance or upgrades

Abstract

A system and method to facilitate device monitoring and servicing is provided. In one embodiment, a system may include a medical device having at least one component, and monitoring circuitry configured to measure operational data of the component. The system can also include a data processing system configured to analyze the operational data and to output a report based on such analysis. The analysis, in turn, may include applying a transform to the operational data and comparing one or more actual coefficient and threshold coefficient characteristics.

Claims

1. A system comprising:

a medical device of interest including a device component;

monitoring circuitry configured to measure operational data of the device component; and

a data processing system configured to output a report based at least in part on an analysis of the operational data of the device component, wherein the analysis of the operational data includes applying a wavelet transform to separate at least one signal component in the operational data, and predicting at least one of a failure rate or a survival rate of the device over a time period based at least in part on comparison of a coefficient characteristic of the wavelet transform to one or more threshold coefficient characteristics.

2. The system of claim 1, wherein the medical device of interest includes an imaging system.

3. The system of claim 2, wherein the imaging system includes a refrigeration system having the device component, and the operational data includes at least one of pressure data or temperature data related to the device component.

4. The system of claim 1, wherein the one or more threshold coefficient characteristics are calculated at least in part from a statistical analysis of a population of additional medical devices similar to the medical device of interest.

5. The system of claim 1, wherein the medical device includes the monitoring circuitry.

6. A method comprising:

obtaining operational data of a device of interest, the operational data including a feature of interest;

applying a transform to extract the feature of interest from the operational data;

comparing a characteristic of a transform coefficient associated with the extracted feature of interest to a threshold derived at least in part from a statistical analysis of a population of additional devices similar to the device of interest;

calculating an operating state of the device of interest dependent at least in part on the comparison; and

outputting a report indicative of the operating state of the device.

7. The method of claim 6, further comprising the step of using a failure prediction model to calculate the threshold and to calculate the probability of device failure in a finite future time period.

8. The method of claim 7, further comprising the step of selecting a service action for the device based at least in part on the use of a reliability model, wherein selecting a service action includes calculating expected changes in the probability of device failure associated with execution of each of a plurality of potential service actions.

9. The method of claim 8, further comprising the steps of:

receiving additional operational data from the device following execution of a service action; and

calculating the effectiveness of an executed service action via the additional operational data and the reliability model.

10. The method of claim 6, wherein the step of receiving the operational data of the device includes receiving a first set of operational data of the device collected before an event of interest and a second set of operational data of the device collected after the event of interest.

11. The method of claim 10, further comprising the steps of:

applying a wavelet transform to each of the first and second sets of data to generate a first and second set of wavelet coefficients, respectively;

detecting a change between the first and second sets of wavelet coefficients; and

calculating a change in a life expectancy of the device dependent on the change between the first and second sets of wavelet coefficients.

12. The method of claim 6, further comprising the step of selecting the transform from a plurality of transforms to increase detection of a deterioration of the device, a transient event of the device, or a data trend in the operational data of the device.

13. The method of claim 6, wherein the step of applying the transform includes the step of applying a discrete wavelet transform.

14. The method of claim 6, wherein the step of comparing the characteristic of the transform coefficient includes the step of calculating a variance of the transform coefficient.

15. The method of claim 6, wherein the feature of interest includes a trend in a cyclic frequency in pressure data of a vessel.

16. The method of claim 6, wherein the report includes at least one of a probability of device failure in a finite future time period, a forecast change in the probability of device failure based on execution of a potential service action, or an indication of the effectiveness of an executed service action.

17. The method of claim 6, wherein the report illustrates a comparison of survival rates of the device of interest before and after execution of a device service action, wherein the survival rates are determined through wavelet transform analysis.

18. A manufacture comprising:

a computer-readable medium having executable instructions stored thereon, the executable instructions comprising;

instructions to apply a transform to an operational data of a device to extract a feature of interest from the operational data, wherein applying the transform generates a transform coefficient;

instructions to compare a characteristic of the transform coefficient to a threshold; and

instructions to output a report based at least in part on the comparison.

19. The manufacture of claim 18, wherein the instructions to apply the transform include instructions to apply a wavelet transform to a first set of operational data measured before an event of interest and to apply the wavelet transform to a second set of operational data measured after the event of interest, and wherein the executable instructions further include instructions to detect a change between the first and second sets of a wavelet coefficient resulting from the event of interest.

20. The manufacture of claim 18, wherein the executable instructions further include instructions to select a one of a plurality of service actions to the device to cause one of a greatest decrease in a probability of failure of the device in a future time interval.