Signal Analysis Method

• US 20080140403A1
• Filed: 05/06/2005
• Published: 06/12/2008
• Est. Priority Date: 05/07/2004
• Status: Active Grant

• Current Assignee: Obs Medical Limited
• Original Assignee: Isis Innovation Limited
• Inventors: Roberts, Stephen, Tarassenko, Lionel, Hughes, Nicholas
• Granted Patent: US 7,941,209 B2
• Time in Patent Office: Days
• US Class Current: 704/256.1
• CPC Class Codes: A61B 5/349 Detecting specific parameters of the electrocardiograph cycle
• CPC Class Codes: A61B 5/7221 Determining signal validity, reliability or quality A61B5/7207 and A61B5/7217 take precedence
• CPC Class Codes: A61B 5/726 using Wavelet transforms
• CPC Class Codes: A61B 5/7264 Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems neural networks per se G06N3/00; expert systems per se G06N5/00
• CPC Class Codes: A61B 5/7267 involving training the classification device
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems

Abstract

Improvement in the reliability of segmentation of a signal, such as an ECG signal, is disclosed through the use of duration constraints. The signal is analysed using a hidden Markov model. The duration constraints specify minimum allowed durations for specific states of the model. The duration constraints can be incorporated either in the model itself or in a Viterbi algorithm used to compute the most probable state sequence given a conventional model. Also disclosed is the derivation of a confidence measure from the model which can be used to assess the quality and robustness of the segmentation and to identify any signals for which the segmentation is unreliable, for example due to the presence of noise or abnormality in the signal.

Claims

1. A computer-implemented method for bio-medical signal segmentation using a hidden Markov model, the model comprising a plurality of states, the method comprising the steps of:

specifying a minimum duration constraint d_min for at least one of the states;

for each state in the model with a specified minimum duration, replacing the state by a set of sub-states, with the total number of sub-states equal to the value of the minimum duration constraint d_min;

connecting together the set of sub-states to form a left-right Markov chain, wherein the first d_min−

1 sub-states each have a self-transition probability of zero, a transition probability of one of transitioning to the state immediately to their right, and a transition probability of zero of transitioning to any other state in the model; and

applying the model to data representing the biomedical signal to obtain information on the segmentation of the signal into the states.

2. A method according to claim 1, wherein the last sub-state in the chain has the same transition probabilities as the original state that has been replaced.

3. A method according to claim 1, wherein the observation probability models for all d_min sub-states are tied, such that the parameters of the observation model for any of the d_min states in the Markov chain are equal to the corresponding parameters for any other state in the chain.

4. A method according to claim 3, wherein the parameters of the observation model for each sub-state in the Markov chain are set equal to the parameters of the observation model for the original state that has been replaced.

5. A method according to claim 1, wherein the step of applying the model comprises providing the model and the signal to be segmented to a Viterbi algorithm.

12. A method according to claim 1 wherein the signal is a bio-medical signal selected from the group consisting of an electrocardiogram signal, an electroencephalogram signal, an electromyogram signal, a cardiac electrophysiology signal, and an endocardial electrogram.

13. A method according to claim 1, further comprising displaying information on the result of the analysis of the signal.

14. A method according to claim 1, wherein the signal is an electrocardiogram signal and information on the QT interval is obtained from the signal segmentation.

15. A computer program capable of being executed on a computer system and capable when so executed of causing the computer system to perform a method according to claim 1.

16. A computer-readable medium storing a computer program according to claim 15.

6. A computer-implemented method for segmenting a signal, comprising a sequence of observations, into a sequence of states of a finite state discrete time Markov process using a modification to the Viterbi algorithm, the modification comprising:

defining a duration variable and a duration constraint for at least one state of the finite state discrete time Markov process incorporated into the Viterbi algorithm, the duration constraint specifying the minimum duration for said at least one state;

applying the modified Viterbi algorithm to the signal to compute the most probable duration-constrained state sequence which accounts for the sequence of observations;

wherein

at each time step in the computation of the most probable state sequence for each state in the finite state discrete time Markov process which accounts for the sequence of observations up to that time step and ends in said state;

for each state having a duration constraint, using the duration variable for that state to keep track of the length of the consecutive sequence of predecessor states which are comprised only of that state and end in that state at the previous time step;

if the duration variable for that state is greater than or equal to the specified duration constraint for that state, then transitions from that state to any other given state in the Markov process are considered in the state sequence computations at the given time step;

if the duration variable for that state is less than the specified duration constraint for that state, then transitions from that state to any other state in the Markov process are not considered in the state sequence computations at the given time step; and

following the computation of the set of most probable state sequences up to the given time step, updating the duration variable for each state having a duration constraint in order to keep track of the length of the consecutive sequence of predecessor states which are comprised only of that particular state and end in that state at the time step just considered.

7. A method according to claim 6, wherein a duration variable and duration constraint are provided for each state of the finite state discrete time Markov process.

8. A method according to claim 6, wherein the finite state discrete time Markov process comprises a hidden Markov model.

9. A computer-implemented method for analysing a signal which has been segmented according to a probabilistic segmentation algorithm, the method comprising:

calculating a confidence measure for each of a plurality of segmented signal features;

plotting the confidence measures against the respective signal feature lengths;

applying density modelling techniques to determine a suitable region of the data space associated with high confidence features;

determining whether the confidence measure for a specific signal feature falls outside this region.

10. A method according to claim 9, wherein the signal feature comprises a portion of a longer signal.

11. A method according to claim 9, wherein the confidence measure is one selected from the group consisting of:

the log likelihood of the signal feature given the model; and

the joint log likelihood of the signal feature and the most probable state sequence given the model.