Method and system for dynamical systems modeling of electrocardiogram data
View Patent ↗Electrocardiogram data is received in association with a subject, the electrocardiogram data comprising a series of RR intervals and a series of QT intervals. A first value which indicates an amount by which uncertainty associated with the QT intervals is reduced given the RR intervals is generated. A second value which indicates an amount by which uncertainty associated with the RR intervals is reduced given the QT intervals is generated. The subject is determined to be associated with a low risk of cardiac dysfunction responsive to the first value exceeding the second value and a result of the determination is provided.
1. A computer-implemented method for diagnosing a risk of cardiac dysfunction associated with a subject, the method executed by one or more computer systems and comprising:
receiving electrocardiogram data associated with a subject, the electrocardiogram data comprising a series of RR intervals and a series of QT intervals, wherein the series RR intervals corresponds, in part, to the series of QT intervals;
generating a first value which indicates an amount by which uncertainty associated with the series of QT intervals is reduced given the series of RR intervals;
generating a second value which indicates an amount by which uncertainty associated with the series of RR intervals is reduced given the series of QT intervals;
determining the subject to be associated with a low risk of cardiac dysfunction responsive to the first value exceeding the second value; and
providing a result of the determination.
2. The method of claim 1 , wherein determining the subject to be associated with the low risk of cardiac dysfunction further comprises:
determining that a histogram generated based on the series of RR intervals fits an Erlang distribution.
3. The method of claim 2 , wherein determining that the histogram generated based on the series of RR intervals fits an Erlang distribution comprises:
generating a coefficient, wherein the coefficient describes a fit between the series of RR intervals and an Erlang distribution; and
determining that the coefficient does not exceed a threshold value.
4. The method of claim 1 , wherein the first value and the second value represent Komolgorov-Sinai mutual information values and are generated using a lag of 500.
5. The method of claim 1 , further comprising:
determining that the subject is associated with a high risk of cardiac dysfunction responsive to the second value exceeding the first value.
6. The method of claim 5 , wherein determining that the subject is associated with the high risk of cardiac dysfunction further comprises:
determining that a histogram generated based on the series of RR intervals does not fit an Erlang Distribution.
7. The method of claim 5 , further comprising:
determining whether the high risk of cardiac dysfunction is due to intrinsic dysfunction or extrinsic dysfunction.
8. The method of claim 7 , wherein determining whether the high risk of cardiac dysfunction is due to intrinsic dysfunction or extrinsic dysfunction comprises:
determining whether a stationarity value exceeds a threshold value;
determine that the high risk of cardiac dysfunction is due to intrinsic dysfunction responsive to the stationarity metric exceeding the threshold value; and
determine that the high risk of cardiac dysfunction is due to extrinsic function responsive to the stationarity metric not exceeding the threshold value.
9. The method of claim 5 , wherein electrocardiogram data is derived from a subject who has been treated with a compound.
10. The method of claim 1 , wherein determining that the subject is associated with the low risk of cardiac dysfunction further comprises:
determining one or more Lyapunov coefficients based on the series of RR intervals; and
determining that the subject is associated with a low risk of cardiac dysfunction responsive to the one or more Lyapunov coefficients exceeding a value of zero.
11. A computer system for diagnosing a risk of cardiac dysfunction associated with a subject, the system comprises one or more computer systems and a memory, the system further comprising:
a reporting module stored in the memory and adapted to receive electrocardiogram data associated with a subject, the electrocardiogram data comprising a series of RR intervals and a series of QT intervals, wherein the series RR intervals corresponds, in part, to the series of QT intervals;
a mutual information module stored in the memory and adapted to generate a first value which indicates an amount by which uncertainty associated with the series of QT intervals is reduced given the series of RR intervals and a second value which indicates an amount by which uncertainty associated with the series of RR intervals is reduced given the series of QT intervals;
a diagnosis module stored in the memory and adapted to determine the subject to be associated with a low risk of cardiac dysfunction responsive to the first value exceeding the second value; and
a visualization module stored in the memory and adapted to provide a result of the determination.
12. The system of claim 11 , further comprising an Erlang fitting module stored in the memory and adapted to:
determine that a histogram generated based on the series of RR intervals fits an Erlang distribution.
13. The system of claim 12 , wherein the diagnosis module is further adapted to:
generate a coefficient, wherein the coefficient describes a fit between the histogram generated based on the series of RR intervals and an Erlang distribution; and
determine that the subject is associated with a low risk of cardiac dysfunction responsive to the coefficient below a threshold value.
14. The system of claim 13 , wherein the first value and the second value represent Komolgorov-Sinai mutual information values and the mutual information module is further adapted to generate the first value and the second value based on a lag of 500.
15. The system of claim 14 , wherein the diagnosis module is further adapted to:
determine that the subject is associated with a high risk of cardiac dysfunction responsive to determining that the series of RR intervals do not fit an Erlang Distribution.
16. The system of claim 11 , wherein the diagnosis module is further adapted to:
determine that the subject is associated with a high risk of cardiac dysfunction responsive to the second value exceeding the first value.
17. The system of claim 16 , wherein the diagnosis module is further adapted to:
determine whether the high risk of cardiac dysfunction is due to intrinsic dysfunction or extrinsic dysfunction.
18. The system of claim 17 , wherein the diagnosis module is further adapted to:
determine whether a stationarity value exceeds a threshold value;
determine that the high risk of cardiac dysfunction is due to intrinsic cardiac dysfunction responsive to the stationarity metric exceeding the threshold value; and
determine that the high risk of cardiac dysfunction is due to extrinsic cardiac dysfunction responsive to the stationarity metric not exceeding the threshold value.
19. A computer-readable storage medium encoded with executable computer program code for diagnosing a risk of cardiac dysfunction associated with a subject, the program code comprising program code for:
receiving electrocardiogram data associated with a subject, the electrocardiogram data comprising a series of RR intervals and a series of QT intervals, wherein the series RR intervals corresponds, in part, to the series of QT intervals;
generating a first value which indicates an amount by which uncertainty associated with the QT intervals is reduced given the RR intervals;
generating a second value which indicates an amount by which uncertainty associated with the RR intervals is reduced given the QT intervals; and
determining the subject to be associated with a low risk of cardiac dysfunction responsive to the first value exceeding the second value; and
providing a result of the determination.
20. The medium of claim 19 , wherein program code for determining the subject to be associated with a low risk of cardiac dysfunction comprises program code for:
determining that a histogram generated based on the series of RR intervals fits an Erlang distribution.
21. The medium of claim 20 , wherein program code for determining that the histogram generated based on the series of RR intervals fits an Erlang distribution comprises program code for:
generating a coefficient, wherein the coefficient describes a fit between the series of RR intervals and an Erlang distribution; and
determining that the coefficient does not exceed a threshold value.
22. The medium of claim 19 , further comprising program code for:
determining that the subject is associated with a high risk of cardiac dysfunction responsive to the second value exceeding the first value.
23. The medium of claim 22 , wherein the diagnosis module is further adapted to:
determine whether the high risk of cardiac dysfunction is due to intrinsic dysfunction or extrinsic dysfunction.
24. The medium of claim 23 , wherein the diagnosis module is further adapted to:
determine whether a stationarity value exceeds a threshold value;
determine that the high risk of cardiac dysfunction is due to intrinsic cardiac dysfunction responsive to the stationarity value exceeding the threshold value; and
determine that the high risk of cardiac dysfunction is due to extrinsic function responsive to the stationarity value not exceeding the threshold value.
25. The medium of claim 22 , wherein program code for determining that the subject is associated with a high risk of cardiac dysfunction further comprises program code for:
determining that a histogram generated based on the series of RR intervals does not fit an Erlang Distribution.