Method and device to monitor patients with kidney disease

• US 9,456,755 B2
• Filed: 04/19/2012
• Issued: 10/04/2016
• Est. Priority Date: 04/29/2011
• Status: Active Grant

• Current Assignee: Mozarc Medical US LLC
• Original Assignee: Medtronic Incorporated (Medtronic Plc)
• Inventors: Soykan, Orhan, Manda, VenKatesh R., Gerber, Martin T., Hobot, Christopher M.
• Primary Examiner(s): Cheng, Jacqueline
• Assistant Examiner(s): PREMRAJ, ANGELINE L
• Application Number:
  US13/451,461
• Publication Number:
  US 20120277546A1
• Time in Patent Office: 1,629 Days
• US Class Current: 1/1
• CPC Class Codes: A61B 2505/07 Home care
• 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 5/145 Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissuemeasuring of blood pressure or blood flow A61B5/02; non-radiation detecting or locating of foreign bodies in blood A61B5/06
• CPC Class Codes: A61B 5/316 Modalities, i.e. specific diagnostic methods
• CPC Class Codes: A61B 5/318 Heart-related electrical modalities, e.g. electrocardiography [ECG]
• CPC Class Codes: A61B 5/349 Detecting specific parameters of the electrocardiograph cycle
• CPC Class Codes: A61B 5/686 Permanently implanted devices, e.g. pacemakers, other stimulators, biochips A61B5/6861 takes precedence
• CPC Class Codes: A61M 1/14 Dialysis systems; Artificial kidneys; Blood oxygenators semi-permeable membranes characterised by the material, manufacturing processes therefor B01D71/00 ; Reciprocating systems for treatment of body fluids, e.g. single needle systems for hemofiltration or pheresis
• CPC Class Codes: A61M 1/1601 Control or regulation
• CPC Class Codes: A61M 2205/18 with alarm
• CPC Class Codes: A61M 2205/3553 remote, e.g. between patient's home and doctor's office
• CPC Class Codes: A61M 2205/3584 using modem, internet or bluetooth
• CPC Class Codes: A61M 2205/52 with memories providing a history of measured variating parameters of apparatus or patient
• CPC Class Codes: A61M 2230/005 Parameter used as control input for the apparatus
• CPC Class Codes: A61M 2230/06 Heartbeat rate only
• CPC Class Codes: A61M 2230/20 Blood composition characteristics
• CPC Class Codes: A61M 2230/208 pH-value
• CPC Class Codes: A61M 2230/30 Blood pressure A61M2230/04 takes precedence
• CPC Class Codes: A61M 2230/63 Motion, e.g. physical activity

Abstract

A medical monitoring device for monitoring electrical signals from the body of a subject is described. The medical monitoring device monitors electrical signals originating from a cardiac cycle of the subject and associates each cardiac cycle with a time index. The medical monitoring device applies a forward computational procedure to generate a risk score indicative of hyperkalemia, hypokalemia or arrhythmia of the subject. The medical monitoring device can adjust the forward computational procedure based upon clinical data obtained from the subject.

Claims

1. A medical monitor, comprising:

a medical device for determining body potassium status by monitoring electrical signals of the body of a subject;

a processor for applying a forward computational procedure to the electrical signals monitored from the body in communication with the medical device; and

a communication system indicating a condition of hyperkalemia, hypokalemia or arrhythmia of the subject based on at least one risk score;

wherein the medical device associates a cardiac cycle of the subject with a time index and calculates the at least one risk score, wherein the at least one risk score is associated with the time index;

wherein the at least one risk score is calculated by the forward computational procedure by the addition of a plurality of features converted to scalar feature scores on a common scale, wherein the addition of the feature scores can be weighted or non-weighted as provided in Equation 4;

Risk Score=

Σ

_k=1ⁿW_k*P_k 

 

(Eq.

     4)

wherein W_k is a weighting factor, P_k is a feature score, k is a feature number, and n is a number of features; and

wherein the addition of the features scores is non-weighted when W_k=1;

wherein the processor is configured to receive clinical information regarding the physiological state of the subject associated with the time index and makes an adjustment to the forward computational procedure based upon an error between the at least one risk score and the clinical information, and wherein the adjustment to the forward computational procedure based upon an error between the at least one risk score and the clinical information is done by the processor using a backward computational procedure, wherein the backward computational procedure adjusts exponential factors used to calculate the scalar feature score.

2. The medical monitor of claim 1, wherein the medical device is implantable in the subject.

3. The medical monitor of claim 1, wherein the medical device is an external device comprising a plurality of electrodes for placement on the skin of the subject.

4. The medical monitor of claim 1, wherein the processor identifies a plurality of features of the cardiac cycle and compares the plurality of features to determinant values to calculate the at least one risk score using the forward computational procedure.

5. The medical monitor of claim 4, wherein the plurality of features includes one or more selected from the group consisting of P-R interval, QRS width, Q-T interval, QT-dispersion, P-wave amplitude, P-wave peak, S-T segment depression, T-wave inversion, U-wave amplitude, T-wave peak amplitude, and heart rate variability.

6. The medical monitor of claim 4, wherein a first risk score is calculated for a time index by applying a first forward computational procedure to one or more of the features of P-R interval, S-T segment depression, T-wave inversion and U-wave amplitude, wherein the processor increases a first alert counter by an incremental amount for each time index where the first risk score exceeds a predetermined risk score threshold and an alert is issued when the first alert counter exceeds a predetermined alert threshold.

7. The medical monitor of claim 6, wherein the predetermined risk score threshold is determined based upon a baseline risk score value of the subject.

8. The medical monitor of claim 6, wherein the first alert counter is increased for each consecutive time index where the first risk score exceeds the predetermined risk score threshold.

9. The medical monitor of claim 8, wherein the predetermined risk score threshold is determined based upon a baseline risk score value of the subject.

10. The medical monitor of claim 6, wherein the first alert counter is periodically reset if a sufficient number of time indices where the first risk score exceeds the predetermined risk score threshold is not observed over a time period.

11. The medical monitor of claim 10, wherein the predetermined risk score threshold is determined based upon a baseline risk score value of the subject.

12. The medical monitor of claim 6, wherein the first forward computational procedure determines a non-weighted or weighted sum of feature scores P1, P6, P7, P8 and P10 to calculate the first risk score and the feature scores are assigned a zero or non-zero value based on the following:

P1 based upon the feature P-R interval in time units,

P6 based upon the feature of depression of the S-T segment,

P7 based upon the feature of inversion of the T-wave,

P8 based upon the feature of U-wave amplitude in potential units, and

P10 is heart rate variation in time units.

13. The medical monitor of claim 4, wherein at least one feature is monitored at a first time index and at a second time index defining a curve, wherein the processor increases an alert when the area under the curve exceeds a predetermined threshold.

14. The medical monitor of claim 4, wherein the plurality of features includes one or more selected from the group consisting of QRS width, Q-T interval, P-wave amplitude, P-wave peak, T-wave amplitude and heart rate variation, and wherein a second risk score is calculated for a time index by applying a second forward computational procedure to the features of QRS width, Q-T interval, P-wave amplitude, P-wave peak, T-wave amplitude, and heart rate variation.

15. The medical monitor of claim 14, wherein the second forward computational procedure determines a non-weighted or weighted sum of feature scores P2, P3, P4, P5, P9 and P10 and feature scores are assigned a zero or non-zero value based on the following:

P2 based upon the feature QRS width in time units,

P3 based upon the feature Q-T interval in time units,

P4 based upon the feature P-wave amplitude in potential units per time unit,

P5 based upon the feature P-wave peak in potential units,

P9 based upon the feature of T-wave amplitude in potential units and,

P10 is heart rate variation in time units.

16. The medical monitor of claim 4, wherein a third risk score is calculated for a time index by applying a third forward computational procedure to one or more of the features of P-R interval, QRS width, Q-T interval, P-wave amplitude, P-wave peak, S-T segment, T-wave inversion, U-wave amplitude, T-wave peak amplitude, and heart rate variability.

17. The medical monitor of claim 16, wherein the third forward computational procedure determines a non-weighted or weighted sum of feature scores P1 through P10 and feature scores are assigned a zero or non-zero value based on the following:

P1 based upon the feature P-R interval in time units,

P2 based upon the feature QRS width in time units,

P3 based upon the feature Q-T interval in time units,

P4 based upon the feature P-wave amplitude in potential units per time unit,

P5 based upon the feature P-wave peak in potential units,

P6 based upon the feature of depression of the S-T segment,

P7 based upon the feature of inversion of the T-wave,

P8 based upon the feature of U-wave amplitude in potential units,

P9 based upon the feature of T-wave amplitude in potential units, and

P10 is heart rate variation in time units.

18. The medical monitor of claim 17, wherein the backward computational procedure adjusts one or more selected from the determinant values X_C, weighting factors W_k and an exponential factor k.

19. The medical monitor of claim 1, wherein the feature value P_k has a value of 0 or 1 or another integer value as determined by applying a discrete function to a corresponding feature of the cardiac function.

20. The medical monitor of claim 1, wherein the feature value P_k can have a non-integer value.

21. The medical monitor of claim 1, wherein the backward computational procedure adjusts weighting factors W_k.

22. The medical monitor of claim 1, wherein the backward computational procedure adjusts determinant values to calculate the risk score and feature scores P_k.

23. The medical monitor of claim 1, wherein the feature score P_k is determined by any one of the following computational procedures where x is a feature extracted from the electrical signals, x_c is a determinant value, and k is an exponential factor:

24. The medical monitor of claim 1, wherein the communication system indicates a condition of hyperkalemia or hypokalemia of the subject.

25. The medical monitor of claim 1, wherein the feature score P_k is determined by any one of the following computational procedures where x is a feature extracted from the electrical signals, x_c is a determinant value, and k is an exponential factor: