Methods and apparatus for detecting heart failure event using patient chronic conditions

• US 10,251,563 B2
• Filed: 05/20/2014
• Issued: 04/09/2019
• Est. Priority Date: 05/20/2013
• Status: Active Grant

• Current Assignee: Cardiac Pacemakers Incorporated (Boston Scientific Corporation)
• Original Assignee: Cardiac Pacemakers Incorporated (Boston Scientific Corporation)
• Inventors: Sweeney, Robert J., Zhang, Yi, An, Qi, Thakur, Pramodsingh Hirasingh
• Primary Examiner(s): Messersmith, Eric J
• Application Number:
  US14/282,283
• Publication Number:
  US 20140343438A1
• Time in Patent Office: 1,785 Days
• 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 5/02055 Simultaneously evaluating both cardiovascular condition and temperature
• CPC Class Codes: A61B 5/024 Detecting, measuring or recording pulse rate or heart rate A61B5/0205, A61B5/021 take precedence
• CPC Class Codes: A61B 5/0245 by using sensing means generating electric signals, i.e. ECG signals
• CPC Class Codes: A61B 5/0809 by impedance pneumography
• CPC Class Codes: A61B 5/0826 Detecting or evaluating apnoea events A61B5/4818 takes precedence
• CPC Class Codes: A61B 5/1116 Determining posture transitions
• CPC Class Codes: A61B 5/1118 Determining activity level
• CPC Class Codes: A61B 5/14532 for measuring glucose, e.g. by tissue impedance measurement
• CPC Class Codes: A61B 5/14552 Details of sensors specially adapted therefor
• CPC Class Codes: A61B 5/4818 Sleep apnoea
• 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 5/7282 Event detection, e.g. detecting unique waveforms indicative of a medical condition A61B5/4094, A61B5/4818, A61B5/349, A61B5/0823 take precedence
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems

Abstract

Devices and methods for detecting physiological target event such as events indicative of HF decompensation status are described. A medical device is configured to receive at least a first and a second chronic condition indictors of a patient, receive one or more physiologic signals from the patient, and generate a plurality of signal metrics when the first and the second chronic condition indicators meet their respective criterion. The medical device can detect the target event or condition using one or more patient-specific signal metrics selected from a group including both the first and the second set of the signal metrics. The medical device and the methods can be configured to detect an event indicative of HF decompensation.

Claims

1. A medical device, comprising:

a patient status input unit configured to receive at least a first demographic characteristic indicator and a second demographic characteristic indicator of a patient, the second demographic characteristic indicator non-identical to the first demographic characteristic indicator;

a signal receiver circuit configured to receive one or more physiologic signals of the patient;

a signal metrics generator circuit, coupled to the signal receiver circuit, configured to generate a plurality of signal metrics from the received one or more physiologic signals, including to generate a first set of one or more signal metrics from the received one or more physiologic signals according to a first association with the first demographic characteristic indicator and in response to the first demographic characteristic indicator meeting at least one first specified criterion, and to generate a second set of signal metrics from the received one or more physiologic signals according to a second association with the second demographic characteristic indicator and in response to the second demographic characteristic indicator meeting at least one second specified criterion;

a patient-specific signal metric selector circuit configured to select a subset of patient-specific signal metrics from the first and second sets of signal metrics using signal metric performance measures of at least one metric from the first and second sets of signal metrics; and

a target event or condition detector circuit configured to detect a target heart failure event or condition of the patient when the selected subset of patient-specific signal metrics satisfies a detection threshold criterion, wherein the target event or condition detector circuit is further configured to generate an alert of the detected target heart failure event.

2. The device of claim 1, wherein the target heart failure event or condition includes either an event indicative of heart failure decompensation status of the patient, or an event of worsening heart failure.

3. The device of claim 1, wherein the patient status input unit is configured to receive a first chronic disease indicator and a second chronic disease indicator of the patient, wherein the signal metrics generator circuit is configured to generate the first set of signal metrics further based on the first chronic disease indicator, and to generate the second set of signal metrics further based on the second chronic disease indicator.

4. The device of claim 3, wherein the first chronic disease indicator includes a renal disease indicator, and the second chronic disease indicator includes a prior thoracic surgery indicator.

5. The device of claim 1, wherein:

the signal receiver circuit is configured to be coupled to at least one physiologic sensor configured to sense the one or more physiologic signals from the patient;

the signal metrics generator circuit comprises a signal metrics performance analyzer circuit configured to generate, for the plurality of signal metrics, respective signal metrics performance measures including at least one of a signal quality measure, a signal sensitivity measure, or a signal specificity measure; and

the patient-specific signal metrics selector circuit is configured to select the subset of patient-specific signal metrics using the respective signal metric performance measures.

6. The device of claim 5, wherein the signal metrics performance analyzer circuit is configured to generate the signal sensitivity measure including a relative change of the respective signal metric from a first state to a second state, the second state including temporal information non-identical to that of the first state.

7. The device of claim 6, wherein the signal metrics performance analyzer circuit is configured to generated a sensitivity of a daily maximum respiration rate (MRR) indicative of a relative change from a baseline daily MRR, and wherein the signal metrics generator circuit is configured to generate a set of signal metrics including the daily MRR when the patient has no prior renal disease.

8. The device of claim 1, wherein the patient-specific signal metrics selector circuit is configured to select, for the subset of patient-specific signal metrics, at least one signal metric from an intersection of the first set and the second set of signal metrics.

9. The device of claim 1, wherein the patient-specific signal metrics selector circuit is configured to select, for the subset of patient-specific signal metrics, at least one signal metric from the first set of signal metrics and at least one signal metric from the second set of signal metrics.

10. A method, comprising:

receiving at least a first demographic characteristic indicator and a second demographic characteristic indicator of a patient, the second demographic characteristic indicator non-identical to the first demographic characteristic indicator;

sensing one or more physiologic signals of the patient;

generating a plurality of signal metrics from the sensed one or more physiologic signals, including generating a first set of one or more signal metrics according to a first association with the first demographic characteristic indicator and in response to the first demographic characteristic indicator meeting at least one first specified criterion, and generating a second set of signal metrics according to a second association with the second demographic characteristic indicator and in response to the second demographic characteristic indicator meeting at least one second specified criterion;

selecting from the first and second sets of signal metrics a subset of patient-specific signal metrics using signal metric performance measures of at least one metric from the first and second sets of signal metrics;

applying a target event detection algorithm to the selected patient-specific signal metric subset to detect a target heart failure event or condition of the patient; and

generating an alert of the detected target heart failure event.

11. The method of claim 10, wherein applying a target event detection algorithm to detect a target heart failure event or condition includes detecting either an event indicative of heart failure decompensation status of the patient, or an event of worsening heart failure.

12. The method of claim 10, further comprising receiving a first chronic disease indicator and a second chronic disease indicator of the patient, generating the first set of signal metrics further based on the first chronic disease indicator, and generating the second set of signal metrics further based on the second chronic disease indicator.

13. The method of claim 10, wherein:

generating the plurality of signal metrics includes generating, for the plurality of signal metrics, respective signal metrics performance measures including at least one of a signal quality measure, a signal sensitivity measure, or a signal specificity measure; and

selecting the subset of patient-specific signal metrics includes using the respective signal metric performance measures.

14. The method of claim 13, wherein generating the signal sensitivity measure includes calculating a relative change of the respective signal metric from a first state to a second state, the second state including temporal information non-identical to that of the first state.

15. The method of claim 10, wherein selecting the subset of patient-specific signal metrics includes selecting at least one signal metric from an intersection of the first set and the second set of signal metrics.

16. The method of claim 10, wherein selecting the subset of patient-specific signal metrics includes selecting at least one signal metric from the first set of signal metrics and at least one signal metric from the second set of signal metrics.

17. The method of claim 10, wherein applying the target event detection algorithm includes:

generating a target event risk index using the selected subset of patient-specific signal metrics;

determining a detection criterion associated with the target heart failure event or condition using the at least one first or second demographic characteristic indicator; and

detecting the target heart failure event or condition when the target event risk index meets the detection criterion.

18. The method of claim 17, wherein generating the target event risk index includes generating, for each signal metric of the selected subset of patient-specific signal metrics, a respective weight factor, and calculating the target event risk index using a combination of the subset of patient-specific signal metrics each being weighted by the respective weight factor.