Within-patient algorithm to predict heart failure decompensation

• US 7,629,889 B2
• Filed: 12/27/2006
• Issued: 12/08/2009
• Est. Priority Date: 12/27/2006
• Status: Expired due to Fees

• Current Assignee: Cardiac Pacemakers Incorporated (Boston Scientific Corporation)
• Original Assignee: Cardiac Pacemakers Incorporated (Boston Scientific Corporation)
• Inventors: Sweeney, Robert J., Sachanandani, Haresh G., Peterson, Jon, Cazares, Shelley, Stalsberg, Kevin J.
• Primary Examiner(s): HOFSASS, JEFFERY A
• Application Number:
  US11/616,450
• Publication Number:
  US 20080157980A1
• Time in Patent Office: 1,077 Days
• Field of Search: 340/573.1, 340/540, 600/481, 600/483, 600/484, 600/485, 600/508
• US Class Current: 340/573.1
• CPC Class Codes: A61B 2560/0242 adapted to measure environmental factors, e.g. temperature, pollution
• CPC Class Codes: A61B 5/0031 Implanted circuitry
• CPC Class Codes: A61B 5/0205 Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
• CPC Class Codes: A61B 5/02455 provided with high/low alarm devices
• CPC Class Codes: A61B 5/076 Permanent implantations telemetry using implanted circuitry A61B5/0031; implanted stimulators for therapy A61N1/3605, A61N1/362, A61N1/372
• CPC Class Codes: A61B 5/0816 Measuring devices for examining respiratory frequency measuring frequency of electric signals G01R23/00
• CPC Class Codes: A61B 5/145 Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissuemeasuring of blood pressure or blood flow A61B5/02; non-radiation detecting or locating of foreign bodies in blood A61B5/06
• CPC Class Codes: A61B 5/14532 for measuring glucose, e.g. by tissue impedance measurement
• CPC Class Codes: A61B 5/318 Heart-related electrical modalities, e.g. electrocardiography [ECG]
• CPC Class Codes: A61B 5/33 specially adapted for cooperation with other devices
• CPC Class Codes: A61B 5/7275 Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor
• CPC Class Codes: A61B 5/746 Alarms related to a physiological condition, e.g. details of setting alarm thresholds or avoiding false alarms alarms per se G08B
• CPC Class Codes: A61N 1/3627 for treating a mechanical deficiency of the heart, e.g. congestive heart failure or cardiomyopathy
• CPC Class Codes: A61N 1/37252 Details of algorithms or data aspects of communication system, e.g. handshaking, transmitting specific data or segmenting data
• CPC Class Codes: G16H 40/67 for remote operation
• CPC Class Codes: G16H 50/30 for calculating health indices; for individual health risk assessment

Abstract

This document discusses, among other things, systems and methods for predicting heart failure decompensation using within-patient diagnostics. A method comprises detecting an alert status of each of one or more sensors; calculating an alert score by combining the detected alerts; and calculating a composite alert score, the composite alert score being indicative of a physiological condition and comprising a combination of two or more alert scores.

Claims

1. A method comprising:

detecting an alert status of each of one or more sensors, the alert status being indicative of a likelihood of a first event occurring in a first timeframe, and the alert status being computed using a threshold associated with each of the one or more sensors;

communicating the alert status to a fusion machine;

calculating an alert score at the fusion machine by combining the alert status of each of the one or more sensors;

calculating a composite alert score, the composite alert score being indicative of a likelihood of a second event occurring in a second timeframe and comprising a combination of two or more alert scores;

comparing the composite alert score to a composite alert score threshold to obtain a result; and

providing an indication of the likelihood of the second event occurring in the second timeframe when the result indicates that the composite alert score violates the composite alert score threshold.

2. The method of claim 1, wherein calculating the alert score includes combining detected alerts occurring over time.

7. The method of claim 1, wherein detecting the alert status includes using a threshold value.

8. The method of claim 7, wherein the threshold value includes one of a relative change from a baseline value, an absolute value, or a specified deviation from a baseline value.

9. The method of claim 1, wherein calculating the alert score includes calculating a weighted function of two or more detected alert statuses.

10. The method of claim 9, wherein calculating the weighted function includes using one or more weights, wherein the weights are one of:

equal, unequal, or adaptive.

11. The method of claim 9, wherein calculating the weighted function includes using one or more weights that are related to one or more of:

time, a number or type of the one or more sensors, a patient population, or one or more characteristics of a current patient.

12. The method of claim 1, wherein the composite alert score indicates a likelihood of death in the second timeframe.

13. The method of claim 1, wherein the composite alert score indicates a likelihood of a change in quality of life in the second timeframe.

14. The method of claim 1, wherein calculating the composite alert score includes using a weighted function.

15. The method of claim 1, comprising:

choosing an initial value for the composite alert score threshold; and

dynamically adjusting the composite alert score threshold to improve one or more performance measures related to false positives or false negatives for a particular patient.

16. The method of claim 15, wherein choosing the initial value includes using a value determined during a learning period.

17. The method of claim 15, wherein adjusting the composite alert score is performed automatically.

18. The method of claim 15, wherein the initial value is set to an artificially high or low value.

19. The method of claim 1, wherein the composite alert score threshold is dynamically adjusted.

3. The method of 1, wherein detecting the alert status includes detecting a discrete value or a binary value.

4. The method of claim 3, wherein the discrete value is indicative of one of two or more states.

5. The method of claim 3, wherein the binary value is indicative of a higher likelihood of death in the first timeframe or a lower likelihood of death in the first timeframe.

6. The method of claim 3, wherein the binary value is indicative of a higher likelihood of a change in quality of life in the first timeframe or a lower likelihood of a change in quality of life in the first timeframe.

20. A system comprising:

a patient device comprising;

a communication module adapted to detect an alert status of each of one or more sensors, the alert status being indicative of a likelihood of a first event occurring in a first timeframe, and the alert status being computed using a threshold associated with each of the one or more sensors; and

an analysis module adapted to;

calculate an alert score by combining the detected alerts;

calculate a composite alert score, the composite alert score being indicative of a likelihood of a second event occurring in a second timeframe and comprising a combination of two or more alert scores; and

compare the composite alert score to a composite alert score threshold to obtain a result;

wherein the communication module is adapted to provide an indication of the likelihood of the second event occurring in the second timeframe when the result indicates that the composite alert score violates the composite alert score threshold.

21. The system of claim 20, wherein calculating the alert score includes combining detected alerts occurring over time.

22. The system of claim 20, comprising a sensor adapted to output a binary value indicative of a heart failure decompensation condition or a non-heart failure decompensation condition.

23. The system of claim 22, wherein the sensor is adapted to set the alert status using a threshold value.

24. The system of claim 23, wherein the threshold value includes one of a relative change from a baseline value, an absolute value, or a specified deviation from a baseline value.

25. The system of claim 20, wherein the analysis module is adapted to calculate the alert score using a weighted function of two or more detected alert statuses.

26. The system of claim 20, wherein the second event is heart failure decompensation and wherein the composite alert score indicates a likelihood of heart failure decompensation in the second timeframe.

27. The system of claim 20, wherein the second event is death and wherein the composite alert score indicates a likelihood of death in the second timeframe.

28. The system of claim 20, wherein the second event is a change in quality of life and wherein the composite alert score indicates a likelihood of the change in quality of life in the second timeframe.

29. An apparatus comprising:

means for detecting an alert status of each of one or more sensors, the alert status being indicative of a likelihood of a first event occurring in a first timeframe, and the alert status being computed using a threshold associated with each of the one or more sensors;

means for calculating an alert score by combining the detected alerts;

means for calculating a composite alert score, the composite alert score being indicative of a likelihood of a second event occurring in a second timeframe and comprising a combination of two or more alert scores;

means for comparing the composite alert score to a composite alert score threshold to obtain a result; and

means for providing an indication of the likelihood of the second event occurring in the second timeframe when the result indicates that the composite alert score violates the composite alert score threshold.