Clinical data monitoring and alarming apparatus and methods

• US 8,571,893 B2
• Filed: 05/06/2011
• Issued: 10/29/2013
• Est. Priority Date: 05/07/2010
• Status: Expired due to Fees

• Current Assignee: Nihon Kohden America Inc (Nihon Kohden Corporation)
• Original Assignee: Nihon Kohden America Inc (Nihon Kohden Corporation)
• Inventors: Dashefsky, Michael, Sanders, Neal
• Primary Examiner(s): NGUYEN, HIEP VAN
• Application Number:
  US13/102,761
• Publication Number:
  US 20110275905A1
• Time in Patent Office: 907 Days
• Field of Search: 705/3
• US Class Current: 705/3
• CPC Class Codes: G16H 40/67 for remote operation
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems

Abstract

Clinical data monitoring and alarming devices may have enhanced sensitivity by using sliding median filters on a clinical data stream. This enhanced sensitivity may be realized without introducing an increase in false negative alarm activation.

Claims

1. A clinical data monitoring system comprising:

a sliding median filter assembly disposed for receiving a data stream from a device providing vital signs data, the data stream corresponding to at least one vital sign of a patient being monitored, the median filter assembly configured to;

detect the data stream within a time window,

determine whether the detected data stream spans at least a predetermined percentage of the time window,

determine a false positive reading exists in response to the detected data stream not spanning the at least predetermined percentage,

ignore the detected data stream for alarming in response to the determination of the false positive reading; and

output a mean value of the data stream corresponding to the vital sign in response to the detected data stream spanning the at least predetermined percentage;

a comparative filter disposed for receiving and comparing the mean value output by an algorithm to predetermined data limits; and

an alert engine disposed for issuing an alarm when the comparative filter has determined that the mean value output is outside of the predetermined data limits.

2. The clinical data monitoring system of claim 1, including at least one device adapted to measure the at least one vital sign and send the data stream to the at least one sliding median filter.

3. The clinical data monitoring system of claim 1, wherein the at least one vital sign includes at least one of heart rate, pulse, oxygen saturation, and respiration rate.

4. The clinical data monitoring system of claim 1, the sliding median filter assembly including a respective sliding median filter for each respective vital sign.

5. The clinical data monitoring system of claim 1, wherein the data stream comprises information about multiple vital signs combined into a single output.

6. The clinical data monitoring system of claim 1, wherein the predetermined data limits are adjustable for a patient specific disease state or condition.

7. The clinical data monitoring system of claim 1, wherein the predetermined data limits are adjustable based on a database containing data representative of a varied patient population.

8. The clinical data monitoring system of claim 1, wherein the sliding median filter assembly is adjustable to compensate for clinical interventions.

9. The clinical data monitoring system of claim 1, wherein the time window is adjustable to reduce false positives.

10. The clinical data monitoring system of claim 1, including a database adapted to receive a single sample representation of a patient'"'"'s condition over time.

11. A method for monitoring clinical data, the method comprising:

measuring from a monitoring device at least one vital sign of a patient;

electronically passing a data stream containing the vital sign through a sliding median filter;

detecting with a computing device a portion of the data stream within a time window;

determining in the computing device a percentage of the time window corresponding to non-missing values of the portion of the data stream;

ignoring by the computing device the portion of the data stream when said determined percentage is below a threshold percentage of the time window;

outputting by the device a mean value of the portion of the data stream corresponding to the vital sign, when said determined percentage is at least the threshold percentage of the time window;

comparing by the computing device the mean value output to predetermined data limits; and

issuing by the computing device an alarm when the mean value output is outside of the predetermined data limits.

12. The method of claim 11, including measuring the vital sign over a predetermined duration of time.

13. The method of claim 12, wherein the predetermined duration of time is selected to reduce false positives while not creating false negative alarm states.

14. The method of claim 11, including adjusting the sliding median filter to compensate for clinical interventions.

15. The method of claim 11, wherein the threshold percentage is about 50%.

16. The method of claim 11, wherein the threshold percentage is 25%.