System and method for detection of HF decompensation based on signs and symptoms

• US 8,319,648 B2
• Filed: 09/21/2009
• Issued: 11/27/2012
• Est. Priority Date: 09/22/2008
• Status: Active Grant

• Current Assignee: Cardiac Pacemakers Incorporated (Boston Scientific Corporation)
• Original Assignee: Cardiac Pacemakers Incorporated (Boston Scientific Corporation)
• Inventors: Siejko, Krzysztof Z., Averina, Viktoria A., Patangay, Abhilash
• Primary Examiner(s): Previl, Daniel
• Application Number:
  US12/563,882
• Publication Number:
  US 20100073170A1
• Time in Patent Office: 1,163 Days
• Field of Search: 340/573.1, 340/539.1, 34053911-53912, 340/286.06, 340/286.07
• US Class Current: 340/573.1
• CPC Class Codes: A61B 5/0002 Remote monitoring of patients using telemetry, e.g. transmission of vital signals via a communication network A61B5/07 takes precedence; transmission systems for measured values G08C; transmission H04B; transmission of digital information H04L; wireless communication networks H04W
• 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 5/7264 Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems neural networks per se G06N3/00; expert systems per se G06N5/00
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems

Abstract

In an example, physiologic information about a patient can be obtained and mapped to a first set of fuzzy logic membership functions, and a symptom status can be derived from the mapping of the physiologic information using a first fuzzy logic inference. In an example, the symptom status can be mapped to a second set of fuzzy logic membership functions, and a disease status can be derived from the mapping of the symptom status to the second set of fuzzy logic membership functions using a second fuzzy logic inference.

Claims

1. A system comprising:

a physiologic monitor configured to obtain physiologic information about a patient; and

a processor coupled to the physiologic monitor and configured to receive the physiologic information about the patient, the processor comprising;

a symptom status detector including a first fuzzy logic inference module configured to derive a symptom status from the physiologic information using a first fuzzy logic inference; and

a disease status detector coupled to the symptom status detector, the disease status detector including a second fuzzy logic inference module configured to derive a disease status from the symptom status using a second fuzzy logic inference.

2. The system of claim 1, wherein the disease status detector is configured to detect a heart failure decompensation status.

3. The system of claim 2, comprising a physiologic sensor coupled to the physiologic monitor, wherein the physiologic sensor includes at least one of a weight scale, an electrocardiogram (ECG) sensor, a respiration sensor, a heart sound sensor, a blood pressure sensor, an accelerometer, or an intrathoracic impedance sensor.

4. The system of claim 2, comprising a display coupled to the processor, the display configured to report at least one of the symptom status or the heart failure decompensation status to a user.

5. The system of claim 2, comprising a user input coupled to the processor, the user input configured to receive at least some of the physiologic information from a user in response to a query including whether the patient has experienced at least one of a shortness of breath, an abnormal fatigue, an abnormal pain, an abnormal swelling, a chronic cough, a decreased appetite, or a need for an extra pillow when sleeping.

6. The system of claim 1, wherein the processor comprises a fuzzy logic rule selector configured to select at least one rule using information about whether at least one physiologic sensor is unreliable or unavailable;

and

wherein the first fuzzy logic inference module is configured to derive the symptom status in response to and using the at least one selected rule.

7. A method comprising:

obtaining physiologic information about a patient;

mapping the physiologic information to a first set of fuzzy logic membership functions;

deriving a symptom status from the mapping of the physiologic information to the first set of fuzzy logic membership functions using a first fuzzy logic inference;

mapping the symptom status to a second set of fuzzy logic membership functions; and

deriving a disease status from the mapping of the symptom status to the second set of fuzzy logic membership functions using a second fuzzy logic inference.

8. The method of claim 7, wherein the deriving the disease status includes deriving a heart failure decompensation status.

9. The method of claim 8, wherein the obtaining the physiologic information comprises monitoring at least one of an implantable or an external physiologic sensor.

10. The method of claim 9, wherein the obtaining the physiologic information includes obtaining information derived from at least one of a heart rate, a respiration rate, a respiration timing, a blood pressure, a lung tidal volume, a physical activity level, a weight, an intrathoracic impedance, a heart sound timing, or a heart sound magnitude.

11. The method of claim 9, wherein the deriving the symptom status using the first fuzzy logic inference comprises:

selecting a rule using information about whether at least one physiologic sensor is unreliable or unavailable; and

deriving the symptom status using the selected rule.

12. The method of claim 9, comprising:

querying a user for at least some of the physiologic information, wherein the query includes at least one of whether the patient has experienced shortness of breath, abnormal fatigue, abnormal pain, abnormal swelling, a chronic cough, a decreased appetite, or a need for an extra pillow when sleeping; and

receiving a user response including at least some of the physiologic information.

13. The method of claim 8, wherein the deriving the symptom status includes deriving at least one of a dyspnea score, a fluid overload index, a left ventricular filling pressure index, a fatigue index, or a cardiac output index.

14. The method of claim 8, comprising displaying at least one of the symptom status or the heart failure decompensation status to a user.

15. The method of claim 8, comprising providing an alert to a user when the heart failure decompensation status indicates an onset of acute heart failure decompensation.

16. The method of claim 7, wherein at least one membership function included in the first or second sets of fuzzy logic membership functions is categorized by a linguistic term.

17. The method of claim 16, wherein the linguistic term includes at least one of very low, low, medium, high, or very high.

18. The method of claim 16, wherein the linguistic term classifies at least one of the physiologic information or the symptom status by a degree of change from a baseline.

19. The method of claim 16, wherein the linguistic term classifies at least one of the physiologic information or the symptom status by a rate of change.

20. The method of claim 7, wherein at least one of the first or second fuzzy logic inferences uses at least one rule based on information obtained from historical patient data.