Training data for classification of a position of a catheter in relation to a diaphragm

1 . A computer implemented method for preparing training data and training a machine learning model for use in classifying a position of a catheter in relation to a diaphragm of a patient in a substance delivery apparatus or ventilation control system, the method comprising:

(a) receiving a set of bioelectrical signals detected by a catheter carrying a plurality of electrodes at respective positions along a length of the catheter, the electrodes forming a plurality of electrode pairs located at respectively different distances from a diaphragm of a patient, each signal comprising an electrocardiographic (ECG) component;

(b) preprocessing the signals by at least one of:

(i) segmenting into heartbeats using R-wave or PQRST detection;

(ii) retaining data in a temporal window about each heartbeat and deleting data between heartbeats;

(iii) reducing electromyographic (EMG) components;

(iv) augmenting via stretching or compressing the signal in time; and/or

(v) downsampling the signals;

(c) identifying, from the set of bioelectrical signals, one or more first bioelectrical signals, each first bioelectrical signal detected by an electrode pair on the catheter determined to be closest to the diaphragm;

(d) dividing the set of bioelectrical signals into a plurality of overlapping subsets of bioelectrical signals, each subset corresponding to a sequence of consecutively placed electrodes along the length of the catheter;

(e) labelling each subset by labelling any subset comprising at least one of the first bioelectrical signals as correctly positioned and subsets not comprising any of the first bioelectrical signals as incorrectly positioned;

(f) storing the labelled subsets as training data and training the machine learning model with the training data;

(g) deploying the trained model to a catheter-position monitoring system configured to receive bioelectrical signals from a catheter during patient treatment;

(h) generating, during patient treatment, per-subset position classifications with the trained model and applying a classification function that maps the per-subset position classifications to an overall catheter-position classification and an associated confidence value; and

(i) monitoring a position of the catheter when inserted in a patient based on the overall catheter position classification and the confidence value and outputting a position status of the catheter on a display unit to indicate to a clinician whether the catheter is positioned correctly, too low, or too high.

2 . The method of claim 1 , wherein the step of labelling a subset of bioelectrical signals not comprising the first bioelectrical signal as a subset of bioelectrical signals detected from incorrectly positioned electrodes comprises:

determining whether the electrodes associated with detecting of the one or more bioelectrical signals of the subset are positioned above the diaphragm or below the diaphragm, wherein upon determining that the electrodes are positioned above the diaphragm, labelling the subset of bioelectrical signals as a subset of bioelectrical signals detected from electrodes being above the diaphragm, and upon determining that the electrodes are positioned below the diaphragm, labelling the subset of bioelectrical signals as a subset of bioelectrical signals detected from electrodes being below the diaphragm.

3 . The method according to claim 2 , wherein the dividing of the set of bioelectrical signals into the at least two subsets of bioelectrical signals is performed such that the number of subsets which are determined to be associated with correctly positioned electrodes and are labelled as a subset of signals detected from correctly positioned electrodes is in a predetermined ratio with the number of subsets which are determined to be associated with electrodes positioned above or below the diaphragm and are labelled as a subset of signals detected from electrodes being above the diaphragm or being below the diaphragm.

4 . The method according to claim 2 , wherein upon a first bioelectrical signal being identified as being associated with an electrode which is a distalmost or proximalmost electrode of the plurality of electrodes relative to the length of the catheter, the set of bioelectrical signals is not included in the training data.

5 . The method of claim 1 , further comprising augmenting each bioelectrical signal in a subset, wherein augmenting a bioelectrical signal comprises varying the amplitude of the bioelectrical signal.

6 . The method according to claim 1 , wherein the reducing electromyographic (EMG) components further comprises:

applying a filtering algorithm to each bioelectrical signal among the set of bioelectrical signals, wherein the filtering algorithm is configured to at least reduce the respective electromyographic, EMG, component from the respective bioelectrical signal.

7 . The method according to claim 6 , wherein applying the filtering algorithm to a bioelectrical signal comprises:

identifying a plurality of subparts of the bioelectrical signal, each subpart comprising data detected during a heartbeat of a patient; and

calculating an average bioelectrical signal from the plurality of subparts of the bioelectrical signal.

8 . The method according to claim 1 , wherein each bioelectrical signal from the set of bioelectrical signals comprises data detected during a plurality of heartbeats of a patient, wherein the method further comprises

in each bioelectrical signal from the set of bioelectrical signals, identifying data detected in an intermediate period between two consecutive heartbeats among the plurality of heartbeats; and

deleting the identified data from the bioelectrical signal.

9 . The method according to claim 1 , wherein the step of identifying, from the set of bioelectrical signals, the one or more first bioelectrical signals comprises:

in at least one bioelectrical signal from the set of bioelectrical signals, detecting a presence and a size of an electromyographic, EMG, component, and selecting, as the one of more first bioelectrical signals, at least one bioelectrical signals based on the size of the respective EMG component.

10 . The method according to claim 1 , wherein the step of labelling a subset not comprising any of the first bioelectrical signals further comprises labelling a subset not comprising any of the first bioelectrical signals with a distance between electrodes associated with the subset and electrodes associated with a correctly positioned subset of bioelectrical signals.

11 . The method according to claim 10 , wherein each electrode pair is a pair of neighbouring electrodes.

12 . The method according to claim 1 , wherein the dividing of the set of bioelectrical signals is performed such that at least two subsets of bioelectrical signals are partially overlapped, such that an electrode associated with detecting of one or more bioelectrical signals of a first subset is also associated with detecting of one or more bioelectrical signals of a second subset.

13 . The method according to claim 1 , wherein upon a first bioelectrical signal being identified as being associated with an electrode which is a distalmost or proximalmost electrode of the plurality of electrodes relative to the length of the catheter, the set of bioelectrical signals is not included in the training data.

14 . The method according to claim 1 , wherein each electrode pair is a pair of neighbouring electrodes.

15 . The method according to claim 14 , wherein the one or more first bioelectrical signals comprises a single first bioelectrical signal detected by an electrode pair on the catheter being the electrode pair among the plurality of electrode pairs positioned closest to the diaphragm.

16 . The method of claim 1 , wherein the catheter is a nasogastric or an orogastric catheter.

17 . One or more non-transitory computer-readable media storing instructions executable by one or more processors, wherein the instructions, when executed, cause the one or more processors to perform operations comprising:

(a) receiving a set of bioelectrical signals detected by a catheter carrying a plurality of electrodes at respective positions along a length of the catheter and thereby causing the electrodes to be located at respectively different distances from a diaphragm of a patient, the plurality of electrodes being divided into a plurality of electrode pairs, each signal being detected by an electrode pair of the plurality of electrode pairs, each signal comprising an electrocardiographic, ECG, component;

(b) preprocessing the set of bioelectric signals by at least one of:

(i) segmenting the signals into heartbeats using R-wave or PQRST detection;

(ii) retaining data in a temporal window about each heartbeat and deleting data between heartbeats;

(iii) reducing electromyographic (EMG) components;

(iv) augmenting the signals via stretching or compressing the signal in time; and/or

(v) downsampling the signals;

(c) identifying, from the set of bioelectrical signals, one or more first bioelectrical signals detected by an electrode pair on the catheter determined to be closest to the diaphragm;

(d) dividing the set of bioelectrical signals into a plurality of overlapping subsets, each subset corresponding to a sequence of consecutively placed electrodes along the length of the catheter;

(e) labelling each subset by labelling any subset comprising at least one of the first bioelectrical signals as correctly positioned and labelling subsets not comprising any of the first bioelectrical signals as incorrectly positioned;

(f) training a machine learning model with the labelled subsets;

(g) deploying the trained model to a catheter-position monitoring system configured to receive bioelectrical signals from a catheter during patient treatment;

(h) generating, during patient treatment, per-subset position classifications with the trained model and applying a classification function that maps the per-subset position classifications to an overall catheter-position classification and an associated confidence value; and

(i) monitoring a position of the catheter when inserted in a patient based on the overall catheter position classification and the confidence value and outputting a position status of the catheter on a display unit to indicate to a clinician whether the catheter is positioned correctly, too low, or too high.

18 . A catheter position monitoring system comprising:

(a) a catheter including a plurality of electrodes disposed along a length of the catheter, the electrodes forming electrode pairs located at respective distances from a diaphragm of a patient; each electrode configured to detect a bioelectrical signal comprising an electrocardiographic (ECG) component;

(b) one or more processors operatively coupled to the electrodes; and

(c) one or more non-transitory computer-readable media storing first computer executable instructions that, when executed by the one or more processors, cause system to perform actions comprising:

(i) receiving a set of bioelectrical signals detected by a catheter carrying a plurality of electrodes at respective positions along a length of the catheter and thereby causing the electrodes to be located at respectively different distances from a diaphragm of a patient, the plurality of electrodes being divided into a plurality of electrode pairs, each signal being detected by an electrode pair of the plurality of electrode pairs, each signal comprising an electrocardiographic, ECG, component;

(ii) preprocessing the set of bioelectric signals by at least one of:

segmenting the signals into heartbeats using R-wave or PQRST detection;

retaining data in a temporal window about each heartbeat and deleting data between heartbeats;

reducing electromyographic (EMG) components;

augmenting the signals via stretching or compressing the signal in time; and/or

downsampling the signals;

(iii) identifying, from the set of bioelectrical signals, one or more first bioelectrical signals, each first bioelectrical signal detected by an electrode pair on the catheter determined to be closest to the diaphragm;

(iv) dividing the set of bioelectrical signals into a plurality of overlapping subsets corresponding to sequences of consecutively placed electrodes along the length of the catheter;

(v) labelling each subset of the plurality of subsets, wherein the labelling comprises:

labelling a subset comprising at least one of the first bioelectrical signals as a subset of signals detected from correctly positioned electrodes; and

labelling a subset not comprising any of the first bioelectrical signals as a subset of signals detected from incorrectly positioned electrodes; and

(vi) training a machine learning model with the labelled subsets to generate classification parameters for catheter position in relation to a diaphragm; and

(vii) during patient treatment, applying the trained model to bioelectrical signals received from the catheter to generate an overall catheter position classification and associated confidence value, and outputting a position status on a display unit to indicate to a clinician whether the catheter is positioned correctly, too high, or too low.

19 . The catheter position monitoring system of claim 18 , wherein each electrode pair is a pair of neighboring electrodes.

20 . The catheter position monitoring system of claim 19 , wherein the one or more first bioelectrical signals comprises a single first bioelectrical signal detected by an electrode pair on the catheter being the electrode pair among the plurality of electrode pairs positioned closest to the diaphragm.

21 . The catheter position monitoring system of claim 18 , wherein the reducing electromyographic (EMG) components further comprises applying a filtering algorithm to each bioelectrical signal among the set of bioelectrical signals, wherein the filtering algorithm is configured to at least reduce the respective electromyographic, EMG, component from the respective bioelectrical signal.

22 . The catheter position monitoring system of claim 18 , wherein upon a first bioelectrical signal being identified as being associated with an electrode which is a distalmost or proximalmost electrode of the plurality of electrodes relative to the length of the catheter, the set of bioelectrical signals is not included in the training data.