Apparatus and method for patient activity estimation and classification
View Patent ↗A medical device includes a housing and an electrode arrangement coupled to the housing and configured to sense an electrical physiologic signal from a patient. The device also includes detection circuitry coupled to the electrode arrangement and configured to obtain a cardiac signal component and a non-cardiac signal component from the physiological signal. A processor is coupled to the detection circuitry. The processor is configured to detect patient activity using at least the non-cardiac signal component and discriminate between voluntary and involuntary activity of the patient based on a comparison of temporally aligned cardiac and non-cardiac signal components.
1. A method comprising:
sensing, from a patient, an electrical physiologic signal between a single electrode pair;
obtaining, using detection circuitry, a cardiac signal component from the electrical physiologic signal;
obtaining, using the detection circuitry, a non-cardiac signal component from the electrical physiologic signal;
comparing, using a processor, the cardiac and non-cardiac signal components to respective thresholds established for the patient;
detecting, using the processor, patient activity using the cardiac signal component;
detecting, using the processor, patient activity using the non-cardiac signal component;
determining, using the processor, whether the patient activity detected using the cardiac signal component corresponds to voluntary classified activity or involuntary classified activity of the patient and whether the patient activity detected using the non-cardiac signal component corresponds to voluntary classified activity or involuntary classified activity of the patient;
detecting, using the processor, an adverse patient condition in response to detecting that one of the cardiac and non-cardiac signal components indicates patient voluntary classified activity and the other of the cardiac and non-cardiac signal components indicates patient involuntary classified activity based on the comparison and temporal alignment of the cardiac signal component relative to the non-cardiac signal component; and
generating, by the processor, an output comprising the cardiac signal component, the non-cardiac signal component, and an indicator of dyssynchrony between the cardiac and non-cardiac signal components indicative of the detected adverse patient condition.
2. The method of claim 1 , wherein, for the non-cardiac signal component:
voluntary classified activity of the patient comprises sustained activity of the patient; and
involuntary classified activity of the patient comprises transient activity of the patient.
3. The method of claim 1 , wherein detecting the adverse patient condition further comprises performing a mathematical correlation between the temporally aligned cardiac and non-cardiac signal components.
4. The method of claim 1 , wherein detecting the adverse patient condition further comprises:
comparing a trajectory of the cardiac signal component to a trajectory of the non-cardiac signal component during a detection window.
5. The method of claim 1 , further comprising:
determining a sleep status of the patient using the non-cardiac signal component or the cardiac signal component;
wherein determining whether the detected patient activity corresponds to voluntary classified activity or involuntary classified activity of the patient is based at least in part on the sleep status of the patient.
6. The method of claim 1 , further comprising:
determining a duration of the non-cardiac signal component;
wherein determining whether the detected patient activity corresponds to voluntary classified activity or involuntary classified activity of the patient is based at least in part on the duration of the non-cardiac signal component.
7. The method of claim 1 , further comprising:
determining a power of the non-cardiac signal component;
wherein determining whether the detected patient activity corresponds to voluntary classified activity or involuntary classified activity of the patient is based at least in part on the power of the non-cardiac signal component.
8. The method of claim 1 , further comprising:
determining a periodicity of the non-cardiac signal component;
wherein determining whether the detected patient activity corresponds to voluntary classified activity or involuntary classified activity of the patient is based at least in part on the periodicity of the non-cardiac signal component.
9. The method of claim 1 , wherein the adverse patient condition is an indication of uncompensated cardiac rhythms.
10. The method of claim 1 , wherein the adverse patient condition is an indication of an episode of epileptic seizure.
11. The method of claim 1 , wherein:
the method comprises adjusting the threshold of the non-cardiac signal component over time based on changes in patient activity over time.
12. The method of claim 11 , comprising detecting a change in patient status based on a change in the thresholds.
13. The method of claim 1 , wherein the indicator of dyssynchrony comprises a marker that indicates a point in time of dyssynchrony between the cardiac and non-cardiac signal components indicative of the detected adverse patient condition.
14. A medical device comprising:
a housing;
an electrode arrangement coupled to the housing and configured to sense an electrical physiologic signal from a patient;
detection circuitry coupled to the electrode arrangement and configured to obtain a cardiac signal component and a non-cardiac signal component from the electrical physiologic signal;
an output device; and
a processor coupled to the detection circuitry and the output device, the processor configured to:
detect patient activity using the non-cardiac signal component and to detect patient activity using the cardiac signal component;
determine whether the patient activity detected using the cardiac signal component corresponds to voluntary classified activity or involuntary classified activity of the patient and whether the patient activity detected using the non-cardiac signal component corresponds to voluntary classified activity or involuntary classified activity of the patient;
detect an adverse patient condition in response to detecting that one of the cardiac and non-cardiac signal components indicates patient voluntary classified activity and the other of the cardiac and non-cardiac signal components indicates patient involuntary classified activity; and
cooperate with the output device to generate an output comprising the cardiac signal component, the non-cardiac signal component, and an indicator that indicates dyssynchrony between the cardiac and non-cardiac signal components indicative of the detected adverse patient condition.
15. The device of claim 14 , wherein, for the non-cardiac signal component:
voluntary classified activity of the patient comprises sustained activity of the patient; and
involuntary classified activity of the patient comprises transient activity of the patient.
16. The device of claim 14 , wherein the processor is configured to perform a mathematical correlation between the temporally aligned cardiac and non-cardiac signal components.
17. The device of claim 14 , wherein:
the detection circuitry is configured to compare the non-cardiac signal component to a threshold, and
the processor is configured to adjust the threshold over time based on changes in patient activity over time.
18. The device of claim 17 , wherein the processor is configured to detect a change in patient status based on a change in the threshold.
19. The device of claim 14 , wherein the indicator of dyssynchrony comprises a marker that indicates a point in time of dyssynchrony between the cardiac and non-cardiac signal components indicative of the detected adverse patient condition.