Reliability assessment of cardiac parameter measurements

Abstract

A method (200) for assessing the reliability of a cardiac parameter of a subject is disclosed. The method comprises: receiving data from a transesophageal echocardiography probe, a cardiac activity sensor, and a motion sensor (201); determining (202) TEE cardiac parameters relating to the cardiac parameters estimated using data from the transesophageal echocardiography probe; determining a cardiac activity cardiac parameter relating to the cardiac parameter estimated using data from the cardiac activity sensor; determining (203) the cardiac parameter based on at least one of the TEE and a cardiac activity parameter; evaluating the reliability of cardiac parameters based on TEE and cardiac activity parameters and the data from the motion sensor; and transmitting a feedback signal to an output device based on the reliability of the cardiac parameter. According to the invention, the method further comprises: determining (206) a cardiac parameter trend and whether the cardiac parameter trend exceeds a trend threshold; detecting (220) a motion of the object during a first time period based on the data of the motion sensor; and evaluating the reliability of the cardiac parameter based on whether the cardiac parameter trend exceeds the trend threshold and based on whether the motion of the subject has been detected. A computer program and a system (3) for implementing such a method are also disclosed.

Description

Technical Field

[0001] The present invention relates to a method, a computer program and a system for evaluating the reliability of cardiac parameter measurements of a subject based on a transesophageal echocardiographic probe, a cardiac activity sensor and a motion sensor. Background Art

[0002] Patients in critical care settings often require continuous monitoring of vital signs and cardiac parameters. Ultrasound (US) is one of the most widely used techniques for assessing cardiac parameters in critical care settings. In the intensive care unit (ICU), transthoracic cardiac assessment (transthoracic echocardiography - TTE) and transesophageal echocardiography (TEE) are prevalent modes of US-based cardiac assessment. TEE is the preferred modality for the assessment of cardiac surgical patients and is also used in situations where TTE is not feasible. TEE is superior to TTE in that it can be used for continuous cardiac parameter monitoring for long durations, such as from minutes to days.

[0003] For TEE, a special probe containing an ultrasound transducer at its tip is used. The probe enters the patient's esophagus for cardiac assessment. When the esophagus is directly behind the heart, TEE provides good visualization of the posterior structures of the heart (such as the aorta, pulmonary artery, and heart valves). One disadvantage of the TEE probe is that it may be displaced due to the patient's movement (body movement, tremor, seizure, etc.) or due to other surgical reasons. Thereafter, TEE still remains an operator-based manual process; TEE requires the operator to be present near the bedside for a long duration. Secondly, TEE still has a narrow field of view and may require continuous adjustment to keep the probe in a good position. This may be a very lengthy and physically challenging process, so it is prone to errors during acquisition.

[0004] Proper positioning of the TEE probe is important for continuous cardiac monitoring because even minor misalignment of the probe can result in measurement errors. It has been suggested that the TEE Doppler beam must be within 20° of axial flow to obtain a good measure of aortic blood flow. Maintaining proper position of the TEE probe can be challenging, especially when TEE is used for long duration cardiac assessments. Misalignment of the probe also makes it difficult to determine whether changes in a particular parameter are due to actual changes in cardiac status or due to probe displacement.

[0005] In addition to cardiac parameters, patients in the ICU also require continuous monitoring of vital signs, such as heart rate, blood pressure, oxygen saturation, electrocardiogram, etc. For example, an electrocardiogram (ECG) measures the electrical activity of the heart and can be used to derive certain cardiac parameters. In addition, photoplethysmography (PPG), ballistocardiography (BCG), and other techniques can also be used to derive cardiac parameters of patients.

[0006] In one way, both US and ECG are used to measure different properties of the heart. US measures mechanical (functional) properties, while ECG measures the electrical properties of the heart. Therefore, the simultaneous measurement and analysis of these two different properties can be used to better understand the overall heart state or track changes in heart state. The complementary relationship of these two modalities is well documented in the literature. Using this relationship, researchers have also proposed using one modality (e.g., TEE) as an alternative to another modality (e.g., ECG). In one such study, HA.Hosein-Nejad, P.Mohamaddiejad, A.Zeinodini, S.SeyedhossiniDavarani, and M.Banaie "A new modality for the estimation of corrected flow time via electrocardiography", Ann Noninvasive Electrocardiol, vol.23, no.1, Jan.2018 have demonstrated the use of ECG as an alternative to US to measure certain flow properties in the carotid artery.

[0007] Semiz Beren et al.: “Non-Invasive Wearable Patch Utilizing Seismodiography for Period Operative Use in Surgical Patients,” IEEE J BiomedHealth Inform, May 25, 2021: 1572-1582 doi: 10.1109 / JBHI.2020.3032938 shows the feasibility of a wearable patch system to continuously and non-invasively monitor SV, which is applicable to the preoperative, intraoperative, and postoperative stages.

[0008] Emmanuel Lorne et al.: “Respiratory variations of R-wave amplitude in lead II are correlated with storke volume variations evaluated by transesophgeal Doppler echocardiography” J Cardiohourac Vasc Anesth, 2012 Jun; 26(3): 381-6. doi:10.1053 / j.jvca.2012.01.048 It was concluded that respiratory R-wave variations in lead II (ΔRII) are correlated with stroke volume variations determined by transesophageal Doppler echocardiography in mechanically ventilated patients and can identify a 15% stroke volume variation cutoff that was previously determined to be the cutoff for volume responsiveness. Summary of the invention

[0009] In particular, the object of the present invention is to at least partially solve the problem of checking the reliability of a cardiac parameter of a subject calculated by a TEE probe and another sensor capable of detecting cardiac activity.

[0010] The invention is defined by the independent claims. Advantageous embodiments are defined in the dependent claims.

[0011] A first aspect of the present invention provides a method for assessing the reliability of a cardiac parameter of a subject, the method comprising:

[0012] Receives data from a transesophageal echocardiography probe,

[0013] Receives data from the heart activity sensor,

[0014] Receive data from motion sensors,

[0015] determining a TEE cardiac parameter that is correlated with the cardiac parameter estimated using data from the transesophageal echocardiographic probe,

[0016] determining a cardiac activity cardiac parameter related to said cardiac parameter estimated using data from said cardiac activity sensor,

[0017] determining the cardiac parameter based on at least one of TEE and a cardiac activity parameter,

[0018] determining a cardiac parameter trend and whether the cardiac parameter trend exceeds a trend threshold,

[0019] detecting motion of the object during a first time period based on the data from the motion sensor,

[0020] assessing the reliability of the cardiac parameter based on TEE and cardiac activity parameters and the data from the motion sensor and based on whether a trend of the cardiac parameter exceeds the trend threshold and based on whether motion of the subject has been detected; and

[0021] A feedback signal is transmitted to an output device based on the reliability of the cardiac parameter.

[0022] The solution provided by the present invention involves monitoring one or more cardiac parameters of a subject using a TEE probe together with a sensor capable of monitoring cardiac activity and a sensor capable of detecting motion. The reliability of the monitored cardiac parameters is evaluated based on signals derived from the TEE probe, the cardiac activity sensor and the motion sensor.

[0023] Any known TEE probe may be used, for example, using M-mode, Doppler, 2D, 3D echocardiography.

[0024] According to the present invention, TEE cardiac parameters and cardiac activity cardiac parameters are determined. Determining these parameters includes determining TEE and cardiac activity cardiac parameters, such as cardiac output derived from data from a TEE probe and a cardiac activity monitor, respectively, or alternatively, determining TEE cardiac parameter signals related to TEE cardiac parameters and cardiac activity cardiac parameter signals related to cardiac activity cardiac parameters derived from a TEE probe and a cardiac activity probe, respectively.

[0025] In order to evaluate the reliability of the cardiac parameters, it is necessary to determine the cardiac parameters themselves. This is the cardiac parameter, i.e. the measurement result, the reliability of which the method is intended to evaluate. In the example, the cardiac parameter is the cardiac output of the object, and therefore the method is intended to evaluate whether the measurement result is reliable. The cardiac parameters can be determined based only on TEE cardiac parameters (i.e., cardiac parameters estimated using data from the TEE probe), can also be determined based only on cardiac activity cardiac parameters (i.e., cardiac parameters estimated using data from a cardiac activity sensor), or alternatively, can be determined based on both TEE and cardiac activity cardiac parameters. In the latter case, for example, the cardiac parameter can be an average or weighted average of the TEE and cardiac activity cardiac parameters, or another commonly used statistical analysis can be used.

[0026] According to the present invention, the complementary relationship between TEE and the cardiac activity sensor is used to check the reliability of the evaluation of other modalities (e.g., TEE) using one modality (e.g., cardiac activity sensor). However, it is not possible to detect errors such as probe misalignment or cardiac activity sensor displacement by only jointly analyzing the TEE probe and cardiac activity sensor data. This is feasible if data from the motion sensor is considered. Therefore, the reliability of the cardiac parameters of the object being measured can be evaluated by utilizing data from all three TEE probes, cardiac activity sensors, and motion sensors.

[0027] The motion sensor may be an inertial sensor (i.e., an accelerometer or gyroscope), a magnetometer, an optical sensor (e.g., a camera), a radar, an electromyography (EMG) sensor, a pressure sensor, or a mattress. Where the motion sensor is attached to the subject's body, it is preferably positioned at the subject's torso, as this location may provide easier or more accurate detection of body movement than a limb. More preferably, the motion sensor is positioned on the subject's chest surface above the heart, as this is a preferred area for detecting any significant movement that may displace the TEE probe.

[0028] Alternatively or additionally, the motion sensor can be an inertial sensor or a magnetometer included in a device including a cardiac activity sensor. For example, such a device can be a wearable biosensor for monitoring the vital signs of a subject, including a cardiac activity (e.g., ECG) sensor and a motion sensor. This embodiment has the advantage of simplifying the workflow because a single module with both the cardiac activity sensor and the motion sensor needs to be placed on the subject. Another benefit is that when the device is placed on the chest surface of the subject above the heart, this is a favorable position to monitor any significant movement in the chest area, which may cause displacement of the TEE probe.

[0029] Alternatively or additionally, the motion sensor may be an inertial sensor or a magnetometer included in the transesophageal echocardiography probe.Such an arrangement may be advantageous for detecting small amplitude movements (such as swallowing) which are local and have little effect on chest wall movement.

[0030] Alternatively or additionally, the motion sensor may be a ballistocardiography (BCG) sensor, a gyrocardiography (GCG) sensor and / or a seismocardiography (SCG) sensor, because motion information may be extracted from the BCG, GCG and / or SCG signals. This arrangement may be advantageous when the readings of the additional motion sensor are inaccessible (e.g., the motion sensor is detached, not working, or the data is corrupted). Another advantage is that the BCG, GCG and SCG sensors are also cardiac activity sensors, so they can be used as both motion sensors and cardiac activity sensors, thereby reducing the cost and complexity of the system performing the method.

[0031] More than one motion sensor can be used according to the method. In this case, a joint analysis of the motion data from the multiple motion sensors can be used to assess the reliability of the obtained cardiac parameters.

[0032] Assessing the reliability of the cardiac parameter means assessing whether the determined cardiac parameter is considered reliable, i.e., accurate and / or error-free. Assessing the reliability of the cardiac parameter may also include determining at least one of: whether the transesophageal echocardiography probe has been misaligned; whether the cardiac activity sensor has been displaced; whether a change in the cardiac parameter has been caused by motion of the subject; and whether a change in the cardiac parameter has been caused by a change in cardiac state.

[0033] As described above, the method further includes: determining a cardiac parameter trend; determining whether the cardiac parameter trend exceeds a trend threshold; detecting motion of the subject during a first time period based on data from a motion sensor; determining whether the cardiac parameter trend exceeds a trend threshold; and, assessing the reliability of the cardiac parameter based on whether the cardiac parameter trend exceeds the trend threshold and based on whether motion of the subject has been detected. These steps enable the method to provide additional information about the reliability of the cardiac parameter. Determining a cardiac parameter trend is used to assess whether there has been a significant change in the cardiac parameter.

[0034] Additionally, the method may involve comparing TEE cardiac parameters with cardiac activity cardiac parameters to detect correlated changes between them. Correlated changes between TEE cardiac parameters and cardiac activity cardiac parameters indicate that the measurements of the two modalities are consistent with each other. For example, if the TEE cardiac parameters show changes in the cardiac output of the subject, and the cardiac activity parameters show changes that are considered consistent with the TEE cardiac parameters, the TEE and cardiac activity cardiac parameters are determined to be correlated. In the case where a correlated change has not yet been detected, a first signal can be transmitted to an output device. The purpose of the first signal is to convey that the reliability of the cardiac parameters cannot be assessed due to the fact that there are differences between the cardiac parameters determined by different modalities, which is not as expected. The signal can convey that the reliability of the cardiac parameters cannot be assessed, and further information can also be provided, for example, there is no correlation between the data derived from the TEE probe and the cardiac activity monitor, and suggestions can also be provided to the user, for example, to check whether the cardiac activity sensor has been displaced, or whether there is a problem that prevents receiving data from the TEE probe or the cardiac activity sensor.

[0035] The method may also include determining at least one of the types of motion of the subject, wherein the type is physiological or pathological; and determining the effect of the motion of the subject on the cardiac parameter, and assessing the reliability of the cardiac parameter based on the type and / or effect of the motion of the subject. Motion sensors may also be used to account for certain physical conditions such as tremors, tremors, seizures, or movement of the subject's body due to position changes (all of which are common in ICU patients). Classifying the motion of the subject (i.e., type or effect) may enable the method to identify whether or how the motion affects the reliability of the cardiac parameter.

[0036] The method may also include: determining a TEE cardiac parameter change during a second time period; determining whether the TEE cardiac parameter change corresponds to a type and / or effect of motion of the subject; determining a cardiac activity cardiac parameter change during the second time period; determining whether the cardiac activity cardiac parameter change corresponds to a type and / or effect of motion of the subject; and, assessing the reliability of the cardiac parameter based on the TEE cardiac parameter change and whether the cardiac activity cardiac parameter change corresponds to a type and / or effect of motion of the subject. These additional steps enable the method to determine at least one of:

[0037] When the TEE cardiac parameter change and the cardiac activity cardiac parameter change correspond to the type and / or effect of the subject's motion, determining that the cardiac parameter change is caused by the subject's motion.

[0038] • Determining that the transesophageal echocardiography probe has been misaligned when the TEE cardiac parameter changes do not correspond to the type and / or effects of the subject's motion and the cardiac activity cardiac parameter changes correspond to the type and / or effects of the subject's motion.

[0039] • It is determined that the electrocardiogram electrodes have shifted when the TEE cardiac parameter changes correspond to the type and / or influence of the subject's motion and the cardiac activity cardiac parameter changes do not correspond to the type and / or influence of the subject's motion.

[0040] In the case where neither the TEE cardiac parameter changes nor the cardiac activity cardiac parameter changes correspond to the type and / or effect of the subject's motion, the method may be unable to assess the reliability of the cardiac parameter due to a lack of sufficient information. In this case, the method transmits a second signal to an output device. The purpose of the second signal is to convey that the reliability of the cardiac parameter cannot be assessed. The signal can convey that the reliability of the cardiac parameter cannot be assessed, and can also provide further information, such as that the TEE cardiac parameter changes and the cardiac activity cardiac parameter changes do not correspond to the type and / or effect of the subject's motion, and can also provide suggestions to the user, such as checking whether the cardiac activity sensor or the motion sensor has been displaced or whether there is a problem that prevents receiving data from the TEE probe, the cardiac activity sensor or the motion sensor.

[0041] The method may also include: determining a TEE cardiac parameter change during a third time period; determining a cardiac activity cardiac parameter change during the third time period; determining that the cardiac parameter change is caused by a cardiac state change when the motion of the subject does not exceed the motion threshold during the first time period and the TEE cardiac parameter change is correlated with the cardiac activity cardiac parameter change; or, transmitting a third signal to the output device when the motion of the subject does not exceed the motion threshold during the first time period and the TEE cardiac parameter change is not correlated with the cardiac activity cardiac parameter change. This embodiment relates to an option for assessing the reliability of a cardiac parameter when the motion of the subject is considered to be low, non-existent, or of low consequence. In this case, the method may determine that the cardiac parameter measurement result is reliable, or that the reliability cannot be assessed. When the reliability cannot be assessed, the third signal is transmitted to the output device. Similar to the first signal and the second signal, the purpose of the third signal is to convey that the reliability of the cardiac parameter cannot be assessed. The signal can convey that the reliability of the cardiac parameter cannot be assessed, and can also provide further information, for example, that the TEE cardiac parameter changes are not correlated with the cardiac activity cardiac parameter changes, and can also provide suggestions to the user, for example, to check whether the cardiac activity sensor or motion sensor has been displaced or whether there are problems that prevent data from being received from the TEE probe, cardiac activity sensor or motion sensor.

[0042] In another aspect of the invention, there is provided a computer program for assessing the reliability of a cardiac parameter of a subject, enabling a processor to perform a method as described herein.

[0043] In another aspect of the present invention, a system for assessing the reliability of a subject's cardiac parameters is provided, the system comprising: a transesophageal echocardiography probe; a cardiac activity sensor; a motion sensor configured to detect motion of the subject; an output device; and a processor configured to execute the method described herein.

[0044] The advantages and technical effects already described for the method also apply to the corresponding computer program and system.

[0045] These and other aspects of the invention will be apparent from and elucidated with reference to the embodiments described hereinafter. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] For a better understanding of the invention, and to show more clearly how it may be put into practice, reference will now be made, by way of example only, to the accompanying drawings, in which:

[0047] Figure 1 A flow chart of a method for assessing reliability of a cardiac parameter of a subject is shown according to an example.

[0048] Figure 2 A flow chart of a method for assessing the reliability of a cardiac parameter of a subject according to an embodiment is shown.

[0049] Figure 3 A system for assessing reliability of cardiac parameter measurements of a subject according to an embodiment is schematically depicted. DETAILED DESCRIPTION

[0050] The present invention will be described with reference to the accompanying drawings. While indicating exemplary embodiments of the present invention, the detailed description and specific examples are intended only for illustrative purposes and are not intended to limit the scope of the present invention. These and other features, aspects and advantages of the present invention will be better understood through the following description, the appended claims and the accompanying drawings. The accompanying drawings are merely schematic and are not drawn to scale. It should also be understood that the same reference numerals are used throughout the drawings to indicate the same or similar parts.

[0051] According to an example, the present invention provides a method 100 for evaluating the reliability of a cardiac parameter of a subject using a TEE (transesophageal echocardiography) probe, a cardiac activity sensor, and a motion sensor. Figure 1 A flow chart of the method 100 is shown. In a first step 101, the method comprises receiving data from a TEE probe, a cardiac activity sensor and a motion sensor.

[0052] The TEE probe is positioned in the object accordingly. The cardiac activity sensor can be any sensor capable of sensing cardiac activity, for example, a photoplethysmography (PPG) sensor, a camera sensor, an acoustic sensor, an ultrasound sensor, an electrocardiogram (ECG) sensor, a ballistocardiography (BCG) sensor, a gyrocardiography (GCG) sensor, or a shockcardiography (SCG) sensor. Preferably, the cardiac activity sensor is an ECG or BCG sensor, because these sensors can be used to estimate a wide range of cardiac parameters and can also provide reliable measurements in continuous cardiac monitoring. In addition, more than one cardiac activity sensor can be used, such as a combination of any one of ECG, BCG and PPG, camera, acoustic or ultrasound sensors.

[0053] The determined cardiac parameter may be at least one of: cardiac output, stroke volume, left ventricular filling pressure, ejection fraction, blood flow, heart rate, heart rhythm, heart rate variability, left and right ventricular volumes, left and right atrial volumes, pulmonary artery pressure. Preferably, the determined parameter is at least one of: cardiac output, heart rate, heart rhythm and heart rate variability. All of the above parameters may be determined or derived using a TEE probe and an ECG. Most of these parameters may also be measured directly or indirectly using a BCG. Other cardiac activity sensors may not be able to determine all of the mentioned cardiac parameters, and the determination of the cardiac parameters whose reliability is assessed by the method depends on the cardiac activity sensor to be used. Those skilled in the art are familiar with which cardiac parameters may be determined by each cardiac activity sensor.

[0054] In one example, the method is used to assess the reliability of a cardiac parameter of a continuously monitored subject. Continuous monitoring of cardiac parameters is preferred or required in certain wards in a hospital (e.g., in an ICU). In one example, the method can be used to assess the reliability of cardiac output (CO) measurements over a period of time ranging from a few minutes to a few hours or days.

[0055] In step 102, TEE cardiac parameters and cardiac activity cardiac parameters are determined. TEE cardiac parameters relate to cardiac parameters determined using a TEE probe. Thus, the TEE cardiac parameters may be cardiac parameters determined by using a TEE probe, or alternatively a TEE cardiac parameter signal related to the TEE cardiac parameters, i.e., a signal that provides cardiac parameters when processed. Similarly, cardiac activity cardiac parameters relate to cardiac parameters determined by using a cardiac activity sensor. Thus, cardiac activity cardiac parameters may be cardiac parameters determined by using a cardiac activity sensor, or alternatively a cardiac activity cardiac parameter signal related to the cardiac activity cardiac parameters, i.e., a signal that provides cardiac parameters when processed. Both TEE cardiac parameters and cardiac activity cardiac parameters relate to the same cardiac parameters, e.g., cardiac output, heart rate, heart rhythm, heart rate variability, stroke volume, left ventricular filling pressure, ejection fraction, etc.

[0056] In step 103, the cardiac parameters to be evaluated are determined. In one embodiment, the measurement results of the cardiac parameters are based only on the TEE cardiac parameters, i.e., the cardiac parameters to be evaluated are measured using a TEE probe. In another embodiment, the measurement results of the cardiac parameters are based only on the cardiac activity cardiac parameters, i.e., the cardiac parameters to be evaluated are measured using a cardiac activity sensor. In a third embodiment, the measurement results of the cardiac parameters are based on both the TEE cardiac parameters and the cardiac activity cardiac parameters.

[0057] In an example, the method includes the following step 104: comparing the TEE cardiac parameters with the cardiac activity cardiac parameters to detect expected relevant changes or differences therebetween. Determining whether the changes are relevant can be achieved by using any suitable statistical analysis, such as disclosed by the above-mentioned article from Hosein-Nejad et al. (2018).

[0058] In case a correlation between the TEE cardiac parameter and the heart activity cardiac parameter is established, in optional step 105 a first signal is transmitted, communicating that the reliability of the cardiac parameter cannot be assessed.

[0059] After the cardiac parameters have been determined in step 103, their reliability is assessed in step 130. In this step, the TEE cardiac parameters and the cardiac activity cardiac parameters already determined in step 102 and the data from the motion sensor are used to assess the reliability of the cardiac parameters.

[0060] There are different options for determining the reliability of the cardiac parameters in step 130. In an example, rules are defined using TEE cardiac parameters, cardiac activity cardiac parameters and data from a motion sensor. Such rules may be defined by the user or may be imported from historical data annotated by the user. For example, such a rule may be that if the data from the motion sensor shows the absence of any significant movement, the TEE cardiac parameters and the cardiac activity parameters will be considered reliable and therefore also the determined cardiac parameters. Another rule is that if significant motion is detected, followed by a change in the cardiac parameters that is proportional to the detected motion and lasts only for the time expected due to the motion, then the determined cardiac parameters will also be considered reliable.

[0061] Additionally or alternatively, in order to determine the cardiac parameters in step 130, the annotation vector can be used to train a machine learning classifier. In this case, the measurement input vector includes TEE, cardiac activity and motion data, and each vector is annotated by the user in terms of reliability. In the case of binary classification, "reliable" and "unreliable" labels can be used. Using the annotation vector, a classifier can be trained. Example methods used are neural networks, support vector machines, decision trees, naive Bayes, logistic regression, etc. In order to train the machine learning classifier, the collected past data can be used. Once the classifier is trained, it can receive TEE, cardiac activity and motion data as input, and then generate an output indicating the reliability of these measurements.

[0062] Additionally or alternatively, a physiological digital twin of the heart or cardiovascular system can be used to run simulations, as explained in Niederer SA, Sacks MS, Girolami M, et al. Scaling digital twins from theartisanal to the industrial. Nat Comput Sci 1, 313–320 (2021). https: / / doi.org / 10.1038 / s43588-021-00072-5 and Baillargeon B, Rebelo N, Fox DD, Taylor RL, KuhlE. The Living Heart Project: A robust and integrative simulator for human heartfunction. Eur JMech A Solids. 2014 Nov; 48: 38-47. doi: 10.1016 / j.euromechsol.2014.04.001. PMID: 25267880; PMCID: PMC4175454. Using the measured TEE, cardiac activity and motion data as input to the digital twin, the reliability of the cardiac parameters can be determined. The digital twin can be considered as a verified copy of the physical object, and the digital twin can be used to synthesize different signals and parameters. In an example, a synthesizer can be used with a digital twin, where two signals such as TEE cardiac parameters and data from a motion sensor will be used as inputs, and a simulated signal (e.g., a simulated cardiac activity parameter) will be generated by the digital twin. Then, the simulated signal (e.g., a simulated cardiac activity parameter) can be compared with the measured signal (e.g., a measured cardiac activity parameter), and if there is a difference between the simulated signal and the measured signal, the cardiac parameter is assessed to be unreliable. Due to the motion sensor data, the digital twin can also be used to estimate the type and timing of the artifacts expected in the TEE cardiac parameters and the cardiac activity cardiac parameters, which can then be compared with the type and timing of the artifacts measured. If they are found to be different, it can be inferred that any one of the TEE cardiac parameters, cardiac activity parameters, or motion data is unreliable, and therefore the determined cardiac parameters are unreliable.

[0063] Additionally or alternatively, in step 104, the TEE cardiac parameters are compared with the cardiac activity cardiac parameters to detect relevant changes between them, and the reliability of the cardiac parameters is evaluated based on whether relevant changes and motion of the object have been detected. If the data from the motion sensor shows that the object has no motion or has insignificant motion, and the TEE cardiac parameters are consistent with the cardiac activity cardiac parameters, the cardiac parameters are considered reliable. If the data from the motion sensor shows significant motion of the object, and the TEE cardiac parameters are not consistent with the cardiac activity cardiac parameters, the reliability of the cardiac parameters cannot be determined. For example, if the TEE cardiac parameters and the cardiac activity parameter values ​​differ by less than + / -5%, they are considered to be consistent with each other. Digital twins can also be used by setting up a simulated digital twin using patient data or representative inputs to generate simulated TEE and cardiac activity parameters. The correlation between the simulated TEE and the cardiac activity parameters can then be calculated. The calculated correlation can then be compared with the correlation between the measured TEE and the cardiac activity parameters. For example, if the correlation between the simulated parameters and the measured parameters is different and the motion sensor shows that the object has no motion or has insignificant motion, it can be inferred that the determined cardiac parameters are unreliable. Furthermore, if the correlation between the simulated and measured parameters does not differ, it can be concluded that the determined cardiac parameters are reliable.

[0064] In one embodiment, data collected from the TEE probe, cardiac activity sensor, and motion sensor may be synchronized.

[0065] Assessing the reliability of a cardiac parameter involves one or more of the following: determining whether a cardiac parameter is considered or is not reliable; determining whether the TEE probe has been misaligned; determining whether the cardiac activity sensor has been displaced; determining whether a change in the cardiac parameter has been caused by the subject's motion; and, determining whether a change in the cardiac parameter has been caused by a change in the cardiac state. There are also situations where reliability cannot be determined as described above.

[0066] Not all of the above options for assessing the reliability of cardiac parameters need to be determined by the method. In one embodiment, the method may only be able to determine that cardiac parameters are considered reliable, in another embodiment, may only be able to determine whether the TEE probe has been misaligned, and in another embodiment, may only be able to determine whether the cardiac activity sensor has been displaced, etc. In another embodiment, the method is able to determine all of the above.

[0067] In step 140, after evaluating the reliability of the cardiac parameter, a feedback signal is transmitted to an output device based on the reliability of the cardiac parameter. The output device can be a screen, a handheld device such as a tablet, an indicator light, a database, or a speaker. For example, in various embodiments, the feedback signal can relate to the following communications: the cardiac parameter measurement is considered or is not reliable; the TEE probe has been misaligned; the cardiac activity sensor has shifted; the cardiac parameter has been changed by the movement of the object, caused by a change in the cardiac state, or the reliability cannot be determined. In another embodiment, the feedback signal can also transmit the measured cardiac parameters. In this case, the transmitted cardiac parameters can be cardiac parameters determined only by the TEE probe, cardiac parameters determined only by the cardiac activity sensor, or cardiac parameters determined by combining the TEE probe and cardiac activity sensor signals. In yet another embodiment, the feedback signal can also transmit TEE cardiac parameters and / or cardiac activity cardiac parameters.

[0068] Figure 2 A flow chart of method 200 is depicted. Steps 201-205 correspond to steps 101-105 of method 100 already described and for the sake of brevity these steps will not be described again.

[0069] In step 206, the trend of the cardiac parameter is determined. The trend may be determined according to known trend analysis methods. The cardiac parameter trend is determined in order to assess whether any significant changes in the cardiac parameter have occurred. It is then checked whether the cardiac parameter trend exceeds a trend threshold. For this purpose, thresholds as defined in the literature or empirical thresholds may be used. For example, a 10% change in an initial or baseline cardiac parameter may be used to determine the trend threshold. The trend threshold may not be constant, because the initial or baseline cardiac parameter may also not be constant. For example, if the cardiac parameter has changed in a previous measurement, the previously measured cardiac parameter may be used as a baseline cardiac parameter to calculate the trend threshold for the following cardiac parameter trend assessment.

[0070] In case the cardiac parameter trend does not exceed the trend threshold, then the method may return to step 202 where the TEE cardiac parameter and the cardiac activity cardiac parameter are determined. In case the trend of the cardiac parameter exceeds the threshold, then the method proceeds to step 220.

[0071] In step 220, the movement data of the subject's body is checked to detect the movement of the subject's body within a first time period T1. The first time period may have a duration of several seconds (e.g., 1-10 seconds and preferably 1-5 seconds) before the cardiac parameter changes. In one example, considering that the cardiac parameter may exceed the trend threshold multiple times after significant movement, the first time period has a starting point several seconds before the cardiac parameter trend exceeds the trend threshold in the first instance.

[0072] The use of motion sensors for detecting body movement is widely demonstrated in the literature, for example: Jarvis L, Moninger S, Pavon J, Throckmorton C, Caves K. Accelerometer-Based Machine Learning Categorization of Body Position in Adult Populations. Comput Help People Spec Needs. 2020; 12377: 242–249. Doi: 10.1007 / 978-3-030-58805-2_29. Using a proven processing method, the motion sensor data is processed to detect body movement within a first time period. For example, if the detected movement of the object does not exceed a motion threshold, for example, a 10% change in the motion data over the initial / baseline motion data, it is determined that no movement has occurred or no significant movement has occurred. Additionally or alternatively, if the detected movement of the object does not exceed an angular change of up to 15 degrees, for example, an angle of up to 10 degrees on the initial orientation of the object detected by the sensor on any axis, it is determined that no movement has occurred or no significant movement has occurred.

[0073] The reliability of the cardiac parameter can be evaluated by considering whether the cardiac parameter trend has exceeded a trend threshold and whether movement of the object has been detected. In the case where the cardiac parameter trend does not exceed the trend threshold, the method may not proceed with determining the reliability of the cardiac parameter until a change occurs. If the cardiac parameter trend exceeds the trend threshold, and therefore a significant change in the cardiac parameter has occurred, it is checked whether the change has occurred while the object is moving. In one example, if it is determined that there is no significant movement, if the TEE cardiac parameters are consistent with the cardiac activity cardiac parameters and the cardiac parameter trend exceeds the trend threshold, it can be determined that the change in the cardiac parameters is caused by a change in the cardiac state. In another example, if movement is determined, if the TEE cardiac parameters are not consistent with the cardiac activity cardiac parameters and the cardiac parameter trend exceeds the trend threshold, the reliability of the cardiac parameters cannot be determined.

[0074] Different types of body movements may have different effects on cardiac parameters. Therefore, in optional step 221, body movements are classified. Body movements can be divided into two major categories: physiological body movements, such as lying down, leaning, sitting, standing, walking; and pathological body movements, such as shaking, tremors, seizures. Physiological body movements usually have a transient, predictable and small effect on the measured cardiac parameters, while pathological body movements can significantly reduce or obscure cardiac parameters. Based on information from the literature or empirical data on TEE and cardiac activity sensor patterns and changes in different body movements, a database / lookup table can be constructed to link body movements with expected changes derived by the TEE probe and cardiac activity sensor. Examples of literature from which such information can be derived are: M,García J,Laguna P,Pahlm O, L.Detection of body position changes using the surfaceelectrocardiogram.Med Biol Eng Comput.2003Mar;41(2):164-71.Doi:10.1007 / BF02344884.PMID:12691436,Brigo F,Storti M,Bongiovanni LG,Fiaschi A.ECGmyogenic artifacts during clonic seizures:a disturbing(and interesting)finding.J Clin Monit Comput.2011Apr;25(2):151-3.Doi:10.1007 / s10877-011-9279-z.Epub 2011Apr 22.PMID:21512778,Matsumoto M,Hanrath P,Kremer P,BleifeldW.Transesophageal echocardiographic evaluation of left ventricular functionat rest and during dynamic exercise in aortic insufficiency.JCardiogr.1981Dec;11(4):1147-57.PMID:7345121,Shin S,Mousavi A,Lyle S,Jang E,Yousefian P,Mukkamala R,Jang DG,Kwon UK,Kim YH,Hahn JO.Posture-DependentVariability in Wrist Ballistocardiogram-Photoplethysmogram Pulse TransitTime:Implication to Cuff-Less Blood Pressure Tracking.IEEE Trans BiomedEng.2022Jan;69(1):347-355.doi:10.1109 / TBME.2021.3094200.Epub 2021Dec 23.PMID:34197317,M.Takano and A.Ueno, "Noncontact In-Bed Measurements of Physiological and Behavioral Signals Using an Integrated Fabric-Sheet Sensing Scheme," inIEEE Journal of Biomedical and Health Informatics, vol.23, no.2, pp.618-630, March 2019, doi:10.1109 / JBHI.2018.2825020. .

[0075] Additionally or alternatively, the subject's body motion can be classified based on the expected effect of the motion on the cardiac parameters. For example, body motion can be classified into three categories: (1) low-level cardiac-affecting motion, such as swallowing; (2) intermediate-level cardiac-affecting motion, such as changing position from sitting to lying; and (3) high-level cardiac-affecting motion, such as an epileptic seizure.

[0076] Additionally or alternatively, machine learning based methods and annotated datasets may be used to correlate different types of body motion with expected changes in TEE and cardiac activity sensor cardiac parameters and / or their raw signals.

[0077] In step 233, it is checked whether the change in the TEE cardiac parameter and the change in the cardiac activity cardiac parameter corresponds to the type or influence of the object's motion. That is, it is checked whether such a change is expected according to the type or influence of the object's motion determined in step 221. To this end, the change in the TEE cardiac parameter is determined in the second time period T2, and then it is evaluated whether the TEE cardiac parameter change corresponds to the determined type or influence of the object's motion. The second time period T2 is calculated as the first time period T1 plus a few seconds. For example, the second time period T2 can be T1+(1 to 30) seconds, preferably T1+(1 to 10) seconds, and more preferably T1+(2 to 4) seconds.

[0078] In step 233, a change in the cardiac activity cardiac parameter is also determined during the second time period T2. It is then evaluated whether the change in the cardiac activity cardiac parameter corresponds to the determined type or influence of a movement of the subject.

[0079] In the case where both the TEE cardiac parameter change and the cardiac activity cardiac parameter change correspond to the type or effect of the subject's motion, in step 241, it is determined that the cardiac parameter change is caused by the subject's motion, indicating that the obtained cardiac parameter reliably reflects the change in cardiac state due to motion. Based on this result, a feedback signal is then transmitted to an output device.

[0080] In the event that the TEE cardiac parameter changes do not correspond to the determined type or effect of the subject's motion, but the cardiac activity cardiac parameter changes do correspond to the determined type or effect of the subject's motion, it is determined that the TEE probe has been misaligned in step 242. A feedback signal is then transmitted to an output device based on this result.

[0081] In the event that the TEE cardiac parameter changes correspond to the determined type or effect of the subject's motion, but the cardiac activity cardiac parameter changes do not correspond to the determined type or effect of the subject's motion, it is determined in step 243 that the cardiac activity sensor has been displaced. For example, depending on what type of cardiac activity sensor is used, it may be determined that an ECG, PPG, BCG, or EMG sensor has been misplaced. A feedback signal is then transmitted to an output device based on the result.

[0082] In the case where neither the TEE cardiac parameter changes nor the cardiac activity cardiac parameter changes correspond to the type or effect of the determined subject's motion, the reliability of the cardiac parameter cannot be assessed. In this case, in step 244, a second signal is transmitted to the output device, conveying that the reliability of the cardiac parameter cannot be assessed.

[0083] Step 232 may follow step 220, wherein the movement data of the subject's body has been checked and as a result no movement or significant movement of the subject within the first time period T1 is detected. In step 232, similarly to step 233, TEE cardiac parameter changes are determined for a third time period T3. The third time period T3 is calculated as the first time period T1 plus a few seconds. For example, the third time period T3 may be T1+(1 to 100) seconds, preferably T1+(1 to 30) seconds, and more preferably T1+(1 to 10) seconds. In step 232, similarly to step 233, cardiac activity cardiac parameter changes are also determined.

[0084] Afterwards, determine whether there is a correlation between the TEE cardiac parameter changes and the cardiac activity cardiac parameter changes. The purpose of this correlation is to detect whether the cardiac parameter changes detected by the TEE probe and the cardiac activity sensor are consistent with each other. The determination of whether the changes are related can be achieved by using any suitable statistical analysis, such as that disclosed by Hosein-Nejad et al. (2018). In one example, if the TEE cardiac parameter has changed, such as an increase or decrease of 10%, and the cardiac activity cardiac parameter has a similar type of change, for example, if the TEE cardiac parameter increases, the cardiac activity parameter also increases and changes by 10%, or changes by 9% to 11%, or changes by 8% to 12%, then the TEE cardiac parameter is considered to be correlated with the cardiac activity cardiac parameter.

[0085] If the TEE cardiac parameter change and the cardiac activity cardiac parameter change are assessed to be correlated, then it is determined that there is a change in the subject's cardiac state and that the measured cardiac parameter is reliable in step 245. The result is then transmitted to an output device.

[0086] On the other hand, in case the TEE cardiac parameters are not correlated with the cardiac activity cardiac parameters, the reliability of the cardiac parameters cannot be assessed and in this case, in step 246, a third signal associated with this result is transmitted to the output device.

[0087] In a second aspect of the invention, a computer program for assessing the reliability of a cardiac parameter of a subject is proposed, enabling a processor to perform a method as described herein.

[0088] The computer program may be stored / distributed on suitable non-transitory computer-readable media, such as optical storage media or solid-state media supplied with or as part of other hardware, but may also be distributed in other forms, such as via the Internet or other wired or wireless telecommunications systems.

[0089] Figure 3 Schematically depicted is an apparatus for assessing the reliability of cardiac parameters of subject 1 by system 3. System 3 typically comprises a TEE probe 10, a cardiac activity sensor 11 and a motion sensor 12. The cardiac activity sensor 11 may be an electrocardiogram (ECG) sensor, a photoplethysmography (PPG) sensor, a camera sensor, an acoustic sensor, an ultrasound sensor or a ballistocardiography (BCG) sensor. More than one cardiac activity sensor may be used, such as a combination of ECG, BCG and any of PPG, camera, acoustic or ultrasound sensors.

[0090] The motion sensor 12 may be an inertial sensor (e.g., an accelerometer or a gyroscope), a magnetometer, an optical sensor (e.g., a camera), a radar, an EMG sensor, a BCG sensor, a GCG sensor, an SCG sensor, a pressure sensor, or a mattress. Figure 3 , the motion sensor 12 is shown as being positioned on the chest surface of the subject. However, it may be placed in any suitable place where the motion of the subject can be detected, or in the case of a camera or radar, it may not be placed on the subject. Additionally or alternatively, the motion sensor 12 and the cardiac activity sensor 11 may be housed in the same device. For example, a device (e.g., an inertial sensor) including a cardiac activity sensor (e.g., an ECG sensor and a motion sensor) is attached to the subject, and the device is capable of collecting data for both the cardiac activity and motion of the subject. Additionally or alternatively, the TEE probe 10 may include one or more motion sensors 12.

[0091] The TEE probe 10, the cardiac activity sensor 11, and the motion sensor 12 collect data that is transmitted using a wired and / or wireless interface to a processor 20. The processor 20 may include one or more processing elements arranged to process the data provided by the TEE probe 10, the cardiac activity sensor 11, and the motion sensor 12, such as one or more processors, processor cores, etc.

[0092] The TEE probe 10 and the cardiac activity sensor 11 are generally arranged to provide signals related to the cardiac parameters of the subject to the processor 20. In addition, the motion sensor 12 is arranged to provide data related to the motion of the subject to the processor 20. The processor 20 has received the signals from the TEE probe 10, the cardiac activity sensor 11 and the motion sensor 12, and then processes these data according to the methods already described herein. The processor 20 then determines the cardiac parameters derived from the TEE probe 10 and / or the cardiac activity sensor 11, and also evaluates the reliability of the determined cardiac parameters.

[0093] Based on the reliability of the cardiac parameters, the processor 20 transmits a feedback signal to an output device 40 by wire or wirelessly. The output device 40 can be one or more of the following: a monitor, a handheld device (e.g., a smart phone), a database, and a speaker. The signal transmitted from the processor 20 makes it compatible with the signal that the output device can receive. For example, the processor sends a video signal to the monitor and / or sends an audio signal to the speaker.

[0094] It should be noted that the above embodiments illustrate rather than limit the present invention, and that a person skilled in the art will be able to design many alternative embodiments without departing from the scope of the appended claims. In the claims, any reference numerals placed between brackets should not be interpreted as limiting the claims. The word "comprising" does not exclude the presence of elements or steps other than those listed in the claims. The word "one" or "an" before an element does not exclude the presence of multiple such elements. The present invention can be implemented by means of hardware comprising several different elements and / or by means of a suitably programmed processor. In a device claim enumerating several means, several of these devices may be embodied by the same hardware item. Measures recorded in mutually different dependent claims can be advantageously used in combination.

Claims

1. A computer-implemented method (100, 200) for assessing the reliability of a cardiac parameter of a subject, the method comprising: receiving (101, 201) data from a transesophageal echocardiography probe, receiving (101, 201) data from a cardiac activity sensor, receiving (101, 201) data from a motion sensor, determining (102, 202) a TEE cardiac parameter that is correlated with the cardiac parameter estimated using data from the transesophageal echocardiography probe, determining (102, 202) a cardiac activity cardiac parameter related to the cardiac parameter estimated using data from the cardiac activity sensor, determining (103, 203) the cardiac parameter based on at least one of the TEE cardiac parameter and the cardiac activity cardiac parameter, determining (206) a cardiac parameter trend and whether the cardiac parameter trend exceeds a trend threshold, detecting (220) motion of the object during a first time period based on the data from the motion sensor, evaluating (130) the reliability of the cardiac parameter based on the TEE cardiac parameter and the cardiac activity cardiac parameter, the data from the motion sensor and based on whether a trend of the cardiac parameter exceeds the trend threshold and based on whether motion of the subject has been detected; as well as A feedback signal is transmitted (140) to an output device based on the reliability of the cardiac parameter.

2. The method according to claim 1, wherein: The method further comprises: comparing (104, 204) the TEE cardiac parameter with the cardiac activity cardiac parameter to detect correlated changes therebetween, and preferably If no relevant change has been detected, a first signal is transmitted (105, 205) to the output device.

3. The method according to claim 1 or 2, wherein: Assessing the reliability of the cardiac parameter includes determining at least one of: whether the transesophageal echocardiography probe has been misaligned, whether the cardiac activity sensor has been displaced, whether a cardiac parameter change has been caused by the movement of the object, whether the cardiac parameter change has been caused by a change in cardiac state, and whether the cardiac parameter is considered to be reliable.

4. A method according to any one of the preceding claims, wherein: The method further comprises: determining (221) at least one of: a type of the motion of the subject, wherein the type is physiological or pathological; and an effect of the motion of the subject on the cardiac parameter, and The reliability of the cardiac parameter is assessed based on the type and / or effect of the motion of the subject.

5. The method according to claim 4, wherein: The method further comprises: determining (233) a TEE cardiac parameter change during a second time period, determining (233) whether the TEE cardiac parameter change corresponds to the type and / or effect of the motion of the subject, determining (233) a cardiac activity cardiac parameter change during said second time period, determining (233) whether the cardiac activity cardiac parameter change corresponds to the type and / or effect of the motion of the subject, and The reliability of the cardiac parameter is assessed based on whether the TEE cardiac parameter change and the cardiac activity cardiac parameter change correspond to the type and / or effect of the motion of the subject.

6. The method according to claim 5, wherein: The method further comprises: When the TEE cardiac parameter change and the cardiac activity cardiac parameter change correspond to the type and / or effect of the motion of the subject, it is determined (241) that the cardiac parameter change is caused by the motion of the subject.

7. The method according to claim 5 or 6, wherein: The method further comprises: When the TEE cardiac parameter changes do not correspond to the type and / or effect of the motion of the subject and the cardiac activity cardiac parameter changes correspond to the type and / or effect of the motion of the subject, it is determined (242) that the transesophageal echocardiography probe has been misaligned.

8. The method according to any one of claims 5 to 7, wherein: The method further comprises: When the TEE cardiac parameter change corresponds to the type and / or influence of the movement of the subject and the cardiac activity cardiac parameter change does not correspond to the type and / or influence of the movement of the subject, it is determined (243) that the electrocardiogram electrodes have shifted.

9. The method according to any one of claims 5 to 8, wherein: The method further comprises: When the TEE cardiac parameter change and the cardiac activity cardiac parameter change do not correspond to the type and / or effect of the motion of the subject, a second signal is transmitted (244) to the output device.

10. The method according to any one of the preceding claims, wherein: The method further comprises: determining (232) a TEE cardiac parameter change during a third time period, determining (232) a change in a cardiac parameter of cardiac activity during said third time period, determining (244) that the cardiac parameter change is caused by a change in cardiac state when the motion of the subject during the first time period does not exceed a motion threshold and the TEE cardiac parameter change is correlated with the cardiac activity cardiac parameter change, or When the motion of the subject during the first time period does not exceed the motion threshold and the TEE cardiac parameter changes are uncorrelated with the cardiac activity cardiac parameter changes, a third signal is transmitted (246) to the output device.

11. A method according to any one of the preceding claims, wherein: The motion sensor is at least one of: Inertial sensors, magnetometers, optical sensors, radars, electromyography sensors, pressure sensors or mattresses, an inertial sensor or a magnetometer included in a device comprising said cardiac activity sensor (11), an inertial sensor or a magnetometer included in the transesophageal echocardiographic probe (10), and A ballistocardiograph sensor, a gyrocardiograph sensor, or a seismocardiograph sensor.

12. A computer program for assessing the reliability of a cardiac parameter of a subject, the computer program enabling a processor (20) to perform the method according to any one of claims 1 to 11.

13. A system (3) for assessing the reliability of a cardiac parameter of a subject, the system comprising: Transesophageal echocardiography probe (10), Heart activity sensor (11), a motion sensor (12) configured to detect the motion of the object, an output device (40), and A processor (20) configured to execute the method according to any one of claims 1 to 11.

Images