Reduced lead set device and method for detecting acute cardiac ischemic conditions

• US 6,217,525 B1
• Filed: 01/13/1999
• Issued: 04/17/2001
• Est. Priority Date: 04/30/1998
• Status: Expired due to Fees

• Current Assignee: Physio-Control Incorporated (Stryker Corporation)
• Original Assignee: Medtronic Physio-Control Manufacturing Corp. (Medtronic Plc)
• Inventors: Joo, Tae H., Hampton, David R., Medema, Douglas K., Schmitt, Paul W., Niskanen, Robert A.
• Primary Examiner(s): EVANISKO, GEORGE ROBERT
• Application Number:
  US09/229,977
• Time in Patent Office: 825 Days
• Field of Search: 607/4-6, 600/508, 600/509, 600/512, 600/515, 600/516
• US Class Current: 600/508
• CPC Class Codes: A61B 5/30 Input circuits therefor
• CPC Class Codes: A61B 5/308 for electrocardiography [ECG]
• CPC Class Codes: A61B 5/327 Generation of artificial ECG signals based on measured signals, e.g. to compensate for missing leads
• CPC Class Codes: A61B 5/35 by template matching
• CPC Class Codes: A61B 5/7207 of noise induced by motion artifacts
• CPC Class Codes: A61B 5/7267 involving training the classification device
• CPC Class Codes: G16H 50/70 for mining of medical data, e.g. analysing previous cases of other patients

Abstract

A reduced lead set device (10) that detects and reports the presence of an acute cardiac ischemic condition in a patient includes a reduced set of sensing electrodes (12, 14, 16, 18, and 20) placed on a patient for acquiring ECG data from the patient. The reduced lead set device evaluates the ECG data on a reduced set of leads by analyzing local features and/or global features of the ECG data. Local features may include local morphological measures such as ST elevation and clinical information on the patient such as age and sex. Global features include projection coefficients calculated from projecting a concatenated vector of heartbeat data onto separate sets of basis vectors that define signal subspaces of ischemic and non-ischemic ECGs. One or more classifiers evaluate the local features and/or global features to determine whether an acute cardiac ischemic condition is detected. The operating point, i.e., sensitivity and specificity, of the reduced lead set device is adjustable. The result of the evaluation is reported to the user of the device.

Claims

1. A reduced lead set device for detecting and reporting a condition associated with acute cardiac ischemia in a patient, comprising:

(a) a reduced set of electrodes for sensing ECG signals of the patient, wherein the reduced set of electrodes includes less than ten electrodes;

(b) a processing unit in communication with the reduced set of electrodes, the processing unit configured to;

(i) derive a reduced set of lead data from the ECG signals;

(ii) calculate features from the reduced set of lead data; and

(iii) classify the features to determine whether the patient has an acute care ischemic or non-ischemic condition; and

(c) a user output in communication with the processing unit for directly reporting to a user of the reduced lead set device whether the patient'"'"'s cardiac condition was determined ischemic.

2. The reduced lead set device of claim 1, wherein the reduced set of electrodes includes defibrillator electrodes.

3. The reduced lead set of device of claim 1, wherein the reduced set of electrodes includes four limb electrodes and a precordial electrode.

4. The reduced lead set device of claim 1, wherein the processing unit is configured to:

(a) calculate measures of local morphological features in the reduced set of lead data to produce a set of local features; and

(b) include the set of local features in the features classified by the processing unit.

5. A reduced lead set device for detecting and reporting a condition associated with acute cardiac ischemia in a patient, comprising:

(a) a reduced set of electrodes for sensing ECG signals of the patient, wherein the reduced set of electrodes includes less than ten electrodes;

(b) a processing unit in communication with the reduced set of electrodes, the processing unit configured to;

(i) derive a reduced set of lead data from the ECG signals;

(ii) form a vector of heartbeat data from the reduced set of lead data;

(iii) produce a set of global features by projecting the vector of heartbeat data onto one or more predetermined basis vectors that define an acute cardiac ischemic ECG subspace or a non-ischemic ECG subspace; and

(iv) classify the global features to determine whether the features are indicative of an acute cardiac ischemic condition; and

(c) a user output in communication with the processing unit for reporting whether the acute cardiac ischemic condition is determined to be present.

6. The reduced lead set device of claim 5, wherein the processing unit is configured to classify the global features to produce a first classification statistic, and wherein the processing unit is further configured to:

(a) obtain a set of local features from the patient;

(b) classify the local features to produce a second classification statistic, and

(c) classify the first and second classification statistics to determine whether the first and second classification statistics are indicative of the acute cardiac ischemic condition.

7. The reduced lead set device of claim 5, wherein the processing unit is further configured to obtain a set of local features from the patient and jointly classify the global features and the local features to determine whether the acute cardiac ischemic condition present.

8. A reduced lead set device for detecting and reporting a condition associated with acute cardiac ischemia in a patient, comprising:

(a) a reduced set of electrodes for sensing ECG signals of the patient, wherein the reduced set of electrodes includes less than ten electrodes;

(b) a processing unit in communication with the reduced set of electrodes, the processing unit configured to;

(i) derive a reduced set of lead data from the ECG signals;

(ii) calculate features from the reduced set of lead data;

(iii) generate a classification statistic from the features; and

(iv) compare the classification statistic with a predetermined threshold to determine whether the features are indicative of an acute cardiac ischemic condition, the threshold reflecting a desired sensitivity/specificity operating point of the reduced lead set device; and

(c) a user output in communication with the processing unit for reporting whether the acute cardiac ischemic condition is determined to be present.

9. The reduced lead set device of claim 8, further comprising an input device in communication with the processing unit for permitting a user of the reduced lead set device to select the sensitivity/specificity operating point.

10. The reduced lead set device of claim 8, wherein the processing unit is further configured to automatically adjust the sensitivity/specificity operating point in accordance with the number of electrodes in the reduced set of electrodes.

11. The reduced lead set device of claim 8, further comprising additional electrodes for sensing ECG signals, wherein the processing unit is configured to:

(a) advise a user of the reduced lead set device to attach the additional electrodes to the reduced lead device; and

(b) obtain and classify additional ECG data using the additional electrodes if the acute cardiac ischemic condition is determined to be present.

12. The reduced lead set device of claim 11, wherein the processing unit is further configured to detect attachment of the additional electrodes to the reduced lead set device and automatically adjust the sensitivity/specificity operating point to a higher level of specificity when the additional electrodes are attached to the reduced lead set device.

13. A method of using a reduced set of lead data to detect and report a condition associated with acute cardiac ischemia in a patient, comprising:

(a) sensing ECG signals of the patient using a reduced set of electrodes placed on the patient, wherein the reduced set of electrodes includes less than ten electrodes;

(b) generating the reduced set of lead data from the sensed ECG signals;

(c) deriving a local morphological measure from the reduced set of lead data;

(d) deriving a set of local features from the patient and including the local morphological measure in the set of local features;

(e) classifying the set of local features to determine whether the patient has an acute cardiac ischemic or non-ischemic condition; and

(f) directly reporting whether the patient'"'"'s cardiac condition was determined ischemic.

14. The method of claim 13, further comprising:

(a) concatenating the set of local features to form a local feature vector;

(b) evaluating the local feature vector relative to a predetermined local feature vector representative of a training population to produce a classification statistic; and

(c) comparing the classification statistic with a threshold to determine whether the patient has an acute cardiac ischemic condition.

15. The method of claim 14, further comprising selecting the threshold in accordance with a desired sensitivity/specificity tradeoff.

16. The method of claim 13, wherein classifying the set of local features includes applying heuristic rules to the set of local features.

17. A method of using a reduced set of lead data to detect and report a condition associated with acute cardiac ischemia in a patient, comprising:

(a) sensing ECG signals of the patient using a reduced set of electrodes placed on the patient, wherein the reduced set of electrodes includes less than ten electrodes;

(b) generating the reduced set of lead data from the sensed ECG signals;

(c) forming a vector of heartbeat data from the reduced set of lead data;

(d) producing a set of global features by projecting the vector of heartbeat data onto one or more basis vectors that define an acute cardiac ischemic ECG subspace or a non-ischemic ECG subspace;

(e) classifying the set of global features to determine whether the global features are indicative of an acute cardiac ischemic condition; and

(f) reporting whether the acute cardiac ischemic condition is determined to be present.

18. The method of claim 17, wherein forming the vector of heartbeat data includes:

(a) analyzing the reduced set of lead data to identify one or more heartbeats;

(b) generating representative heartbeat data for each lead in the reduced set of lead data; and

(c) concatenating the representative heartbeat data for each lead in the reduced set of lead data to form the vector of heartbeat data.

19. The method of claim 17, wherein producing the set of global features includes:

(a) calculating an inner product of the vector of heartbeat data and one or more basis vectors that define the acute cardiac ischemic ECG subspace to produce a corresponding number of ischemic condition projection coefficients;

(b) calculating an inner product of the vector of heartbeat data and one or more basis vectors that define the non-ischemic ECG subspace to produce a corresponding number of non-ischemic condition projection coefficients; and

(c) using the ischemic condition projection coefficients and the non-ischemic condition projection coefficients as the set of global features.

20. The method of claim 17, further comprising:

(a) defining a plurality of groups wherein each group has basis vectors associated therewith that define the acute cardiac ischemic ECG subspace and the non-ischemic ECG subspace;

(b) categorizing the reduced set of lead data into a group in the plurality of groups; and

(c) using the basis vectors of the group into which the reduced set of lead data is categorized as the basis vectors onto which the vector of heartbeat data is projected.

21. The method of claim 20, wherein categorizing the reduced set of lead data into a group includes:

(a) defining each group of the plurality of groups to correspond to a location of an acute cardiac ischemic condition;

(b) deriving from the patient one or more local features;

(c) selecting a local feature derived from the patient;

(d) categorizing the reduced set of lead data into a group based on the selected local feature; and

(e) if the acute cardiac ischemic condition is determined to be present, then reporting the location of the acute cardiac ischemic condition corresponding to the group into which the reduced set of lead data is categorized.

22. The method of claim 21, wherein the local feature is an ST elevation measured on a lead in the reduced set of leads, and wherein the reduced set of lead data is categorized into a group according to the lead with the greatest ST elevation.

23. The method of claim 17, wherein classifying the set of global features includes:

(a) concatenating the set of global features to form a global feature vector;

(b) producing a classification statistic by evaluating the global feature vector relative to a predetermined global feature vector representative of a training population; and

(c) comparing the classification statistic with a threshold to determine whether an acute cardiac ischemic condition is detected.

24. The method of claim 23, further comprising selecting the threshold in accordance with a desired sensitivity/specificity tradeoff.

25. A method of using a reduced set of lead data to detect and report a condition associated with acute cardiac ischemia in a patient, comprising:

(a) sensing ECG signals of the patient using a reduced set of electrodes placed on the patient, wherein the reduced set of electrodes includes less than ten electrodes;

(b) generating the reduced set of lead data from the sensed ECG signals;

(c) forming a vector of heartbeat data from the reduced set of lead data;

(d) generating a local classification statistic by

(i) deriving a set of local features from the patient; and

(ii) classifying the set of local features to produce the local classification statistic;

(e) generating a global classification statistic by

(i) producing a set of global features by projecting the vector of heartbeat data onto one or more basis vectors that define an acute cardiac ischemic ECG subspace or a non-ischemic ECG subspace; and

(ii) classifying the set of global features to produce the global classification statistic;

(f) classifying the local classification statistic and the global classification statistic to determine whether the local and global classification statistics are indicative of an acute cardiac ischemic condition; and

(g) reporting whether the acute cardiac ischemic condition is determined to be present.

26. The method of claim 25, wherein forming the vector of heartbeat data includes:

(a) analyzing the reduced set of lead data to identify one or more heartbeats;

(b) generating representative heartbeat data for each lead in the reduced set of lead data; and

(c) concatenating the representative heartbeat data for each lead in the reduced set of lead data to form the vector of heartbeat data.

27. The method of claim 25, wherein classifying the set of local features includes:

(a) concatenating the set of local features to form a local feature vector; and

(b) evaluating the local feature vector relative to a predetermined local feature vector representative of a training population to produce the local classification statistic.

28. The method of claim 25, wherein classifying the set of local features includes:

(a) producing a composite local feature from calculating a probability of detection by applying one or more local features in the set of local features to a logistic regression equation; and

(b) classifying the composite local feature in producing the local classification statistic.

29. The method of claim 25, wherein classifying the set of local features includes:

(a) concatenating the set of local features to form a local feature vector;

(b) producing a composite local feature from calculating a Mahalanobis distance between the local feature vector and a predetermined local feature vector representative of a training population; and

(c) classifying the composite local feature in producing the local classification statistic.

30. The method of claim 25, wherein producing the set of global features includes:

(a) calculating an inner product of the vector of heartbeat data and one or more basis vectors that define the acute cardiac ischemic ECG subspace to produce a corresponding number of ischemic condition projection coefficients;

(b) calculating an inner product of the vector of heartbeat data and one or more basis vectors that define the non-ischemic ECG subspace to produce a corresponding number of non-ischemic condition projection coefficients; and

(c) using the ischemic condition projection coefficients and the non-ischemic condition projection coefficients as the set of global features.

31. The method of claim 25, further comprising:

(a) defining a plurality of groups wherein each group has basis vectors associated therewith that define the acute cardiac ischemic ECG subspace and the non-ischemic ECC subspace;

(b) categorizing the reduced set of lead data into a group in the plurality of groups; and

(c) using the basis vectors of the group into which the reduced set of lead data is categorized as the basis vectors onto which the vector of heartbeat data is projected.

32. The method of claim 31, wherein categorizing the reduced set of lead data into a group includes:

(a) defining each group of the plurality of groups to correspond to a location of an acute cardiac ischemic condition;

(b) deriving from the patient one or more local features;

(c) selecting a local feature derived from the patient;

(d) categorizing the reduced set of lead data into a group based on the selected local feature; and

(e) if the acute cardiac ischemic condition is determined to be present, then reporting the location of the acute cardiac ischemic condition corresponding to the group into which the reduced set of lead data is categorized.

33. The method of claim 32, wherein the local feature is an ST elevation measured on a lead in the reduced set of leads, and wherein the reduced set of lead data is categorized into a group according to the lead with the greatest ST elevation.

34. The method of claim 25, wherein classifying the set of global features includes:

(a) concatenating the set of global features to form a global feature vector; and

(b) evaluating the global feature vector relative to a predetermined global feature vector representative of a training population to produce the global classification statistic.

35. The method of claim 25, wherein classifying the local and global classification statistics includes:

(a) producing a combined classification statistic by evaluating the local and global classification statistics relative to corresponding predetermined local and global classification statistics representative of a training population; and

(b) comparing the combined classification statistic with a threshold to determine whether an acute cardiac ischemic condition is detected.

36. The method of claim 35, further comprising selecting the threshold in accordance with a desired sensitivity/specificity tradeoff.

37. A method of using a reduced set of lead data to detect and report a condition associated with acute cardiac ischemia in a patient, comprising:

(a) sensing ECG signals of the patient using a reduced set of electrodes placed on the patient, wherein the reduced set of electrodes includes less than ten electrodes;

(b) generating the reduced set of lead data from the sensed ECG signals;

(c) forming a vector of heartbeat data from the reduced set of lead data;

(d) producing a set of global features by projecting the vector of heartbeat data onto one or more basis vectors that define an acute cardiac ischemic ECG subspace or a non-ischemic ECG subspace;

(e) deriving a set of local features from the patient;

(f) jointly classifying the set of global features and the set of local features to determine whether the global features and local features are indicative of an acute cardiac ischemic condition; and

(g) reporting whether the acute cardiac ischemic condition is determined to be present.

38. The method of claim 37, wherein forming the vector of heartbeat data includes:

(a) analyzing the reduced set of lead data to identify one or more heartbeats;

(b) generating representative heartbeat data for each lead in the reduced set of lead data; and

(c) concatenating the representative heartbeat data for each lead in the reduced set of lead data to form the vector of heartbeat data.

39. The method of claim 37, wherein the set of local features jointly classified with the set of global features includes a composite local feature based on a probability of detection calculated by applying one or more local features in the set of local features to a logistic regression equation.

40. The method of claim 37, wherein the set of local features jointly classified with the set of global features includes a composite local feature calculated by

(a) concatenating the set of local features to form a local feature vector;

and

(b) calculating a Mahalanobis distance between the local feature vector and a predetermined local feature vector representative of a training population.

41. The method of claim 37, wherein producing the set of global features includes:

(a) calculating an inner product of the vector of heartbeat data and one or more basis vectors that define the acute cardiac ischemic ECG subspace to produce a corresponding number of ischemic condition projection coefficients;

(b) calculating an inner product of the vector of heartbeat data and one or more basis vectors that define the non-ischemic ECG subspace to produce a corresponding number of non-ischemic condition projection coefficients; and

(c) using the ischemic condition projection coefficients and the non-ischemic condition projection coefficients as the set of global features.

42. The method of claim 37, further comprising:

(a) defining a plurality of groups wherein each group has basis vectors associated therewith that define the acute cardiac ischemic ECG subspace and the non-ischemic ECG subspace;

(b) categorizing the reduced set of lead data into a group in the plurality of groups; and

(c) using the basis vectors of the group into which the reduced set of lead data is categorized as the basis vectors onto which the vector of heartbeat data is projected.

43. The method of claim 42, wherein categorizing the reduced set of lead data into a group includes:

(a) defining each group of the plurality of groups to correspond to a location of an acute cardiac ischemic condition;

(b) deriving from the patient one or more local features;

(c) selecting a local feature derived from the patient;

(d) categorizing the reduced set of lead data into a group based on the selected local feature; and

(e) if the acute cardiac ischemic condition is determined to be present, then reporting the location of the acute cardiac ischemic condition corresponding to the group into which the reduced set of lead data is categorized.

44. The method of claim 43, wherein the local feature is an ST elevation measured on a lead in the reduced set of leads, and wherein the reduced set of lead data is categorized into a group according to the lead with the greatest ST elevation.

45. The method of claim 37, wherein jointly classifying the set of global features and the set of local features includes:

(a) concatenating the set of local features and the set of global features to form a global/local feature vector; and

(b) producing a global/local classification statistic by evaluating the global/local feature vector relative to a predetermined global/local feature vector representative of a training population; and

(c) comparing the global/local classification statistic with a threshold to determine whether an acute cardiac ischemic event is detected.

46. The method of claim 45, further comprising selecting the threshold in accordance with a desired sensitivity/specificity tradeoff.

47. A method of using a reduced set of lead data to detect and report a condition associated with acute cardiac ischemia in a patient, comprising:

(a) sensing ECG signals of the patient using a reduced set of electrodes placed on the patient, wherein the reduced set of electrodes includes less than ten electrodes;

(b) generating the reduced set of lead data from the sensed ECG signals

(c) deriving at least one characteristic from the reduced set of lead data that is reflective of cardiac condition;

(d) calculating a classification statistic based on the derived characteristic;

(e) comparing the classification statistic with a threshold to determine whether an acute cardiac ischemic condition is detected, wherein the threshold is selected in accordance with a desired sensitivity/specificity operating point; and

(f) reporting whether the acute cardiac ischemic condition is determined to be present.

48. The method of claim 47, further comprising adjusting the sensitivity/specificity operating point in response to an instruction by a user, wherein the sensitivity/specificity operating point is adjusted by adjusting the threshold with which the classification statistic is compared.

49. The method of claim 48, further comprising:

(a) determining the number of electrodes in the reduced set of electrodes; and

(b) adjusting the sensitivity/specificity operating point based on the number of electrodes in the reduced set of electrodes.

50. The method of claim 47, further comprising advising a user to increase the number of electrodes in the reduced set of electrodes in response to a detected acute cardiac ischemic condition and after the number of electrodes in the reduced set of electrodes is increased, repeating steps (a)-(f) to confirm whether acute cardiac ischemia is determined to be present.

51. The method of claim 50, further comprising adjusting the sensitivity/specificity operating point to a higher level of specificity prior to repeating steps (a)-(f).

52. The method of claim 50, wherein if the number of electrodes in the reduced set of electrodes is not increased but a user override has been initiated, then repeating steps (a)-(f).