METHOD AND APPARATUS FOR DETECTION OF NERVOUS SYSTEM DISORDERS

• US 20100130881A1
• Filed: 01/27/2010
• Published: 05/27/2010
• Est. Priority Date: 04/21/2006
• Status: Active Grant

• Current Assignee: Medtronic Incorporated (Medtronic Plc)
• Original Assignee: Medtronic Incorporated (Medtronic Plc)
• Inventors: Virag, Nathalie, Vetter, Rolf
• Granted Patent: US 8,068,903 B2
• Time in Patent Office: Days
• US Class Current: 600/521
• CPC Class Codes: A61B 5/02405 Determining heart rate variability
• CPC Class Codes: A61B 5/352 Detecting R peaks, e.g. for synchronising diagnostic apparatus; Estimating R-R interval
• CPC Class Codes: A61B 5/369 Electroencephalography [EEG] devices for psychotechnics A61B5/16
• CPC Class Codes: A61B 5/375 using biofeedback
• CPC Class Codes: A61B 5/4094 Diagnosing or monitoring seizure diseases, e.g. epilepsy
• CPC Class Codes: A61B 5/7221 Determining signal validity, reliability or quality A61B5/7207 and A61B5/7217 take precedence
• 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: A61N 1/36082 Cognitive or psychiatric applications, e.g. dementia or Alzheimer's disease
• CPC Class Codes: G16H 20/30 relating to physical therapies or activities, e.g. physiotherapy, acupressure or exercising
• 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

Systems and methods for detecting and/or treating nervous system disorders, such as seizures, are disclosed. Certain embodiments of the invention relate generally to implantable medical devices (IMDs) adapted to detect and treat nervous system disorders in patients with an IMD. Certain embodiments of the invention include detection of seizures based upon comparisons of long-term and short-term representations of physiological signals. Other embodiments include prediction of seizure activity based upon analysis of physiological signal levels. An embodiment of the invention monitors the quality of physiological signals, and may be able to compensate for signals of low signal quality. A further embodiment of the invention includes detection of seizure activity following the delivery of therapy.

Claims

1-34. -34. (canceled)

35. A computer-readable medium programmed with instructions for performing a method of predicting a seizure event, the medium comprising instructions for causing a programmable processor to:

acquire an electroencephalograph (EEG) signal;

extract one or more EEG features from the EEG signal;

acquire a cardiovascular (CV) signal;

extract one or more CV features from the CV signal;

derive a discriminant measure from the EEG and CV features, including comparing at least one of the EEG and CV features to features extracted from a reference seizure to form at least one similarity measure, the discriminant measure being a logical function of the at least one similarity measure and the EEG and CV features.

compare the discriminant measure to a predetermined threshold; and

predict a seizure event when the discriminant measure exceeds the predetermined threshold.

36. The medium of claim 35 wherein the instruction to extract one or more EEG features includes instructions to compute a statistical representation of the time intervals between zero crossings of the EEG signal.

37. The medium of claim 35 wherein the extracted CV features include data derived from ECG signals.

38. The medium of claim 35 wherein the extracted CV features include data derived from blood pressure signals.

39. A system for predicting a seizure event, comprising:

means for acquiring electroencephalograph (EEG) signals;

means for acquiring cardiovascular (CV) signals; and

an implantable medical device (IMD) having a power supply, housing, memory, and a processor, the processor being adapted to

receive EEG signals and extract one or more EEG features;

receive CV signals and extract one or more CV features;

derive a discriminant measure from the EEG and CV features, including comparing at least one of the EEG and CV features to features extracted from a reference seizure to form at least one similarity measure, the discriminant measure being a logical function of the at least one similarity measure and the EEG and CV features; and

predict a seizure event when the discriminant measure exceeds a predetermined threshold.