Electrocardiogram lead clamp connection state monitoring method, system and equipment and medium

Abstract

The invention provides a method, a system and equipment for monitoring the connection state of an electrocardiogram lead clip and a medium. According to the method, after a multi-target lead clamp is taken out from a preset storage position by an operator, first movement data of the target lead clamp is collected, then a first movement track of the target lead clamp from the preset storage position to a limb of a patient is obtained based on the first movement data, and then after the target lead clamp completes clamping and is in electric contact with the limb of the patient, the first movement track of the target lead clamp is obtained. Determining first space pose information of the target lead clamp, and determining a first offset between the first motion track and a standard track model according to a standard track model and a standard space pose model which are pre-established according to a lead type corresponding to the target lead clamp, according to the first offset between the first spatial pose information and the standard spatial pose model and the second offset between the first spatial pose information and the standard spatial pose model, the lead connection state of the target lead clamp is determined according to the first offset and the second offset, so that the accuracy of electrocardiographic examination is improved.

Description

Technical Field

[0001] This application relates to data monitoring technology, and more particularly to a method, system, device, and medium for monitoring the connection status of electrocardiogram lead clips. Background Technology

[0002] During an electrocardiogram (ECG) examination, limb lead clips are typically held by the operator at specific locations on the patient's upper and lower limbs based on experience, in order to obtain standardized ECG signals.

[0003] In existing technologies, most lead clips rely solely on color and lead markings to distinguish different lead types. Whether the connection is correct depends mainly on the operator's subjective judgment and experience. There is a lack of an objective monitoring mechanism for the entire process of lead clips from storage to clamping completion.

[0004] If the lead clip is incorrectly connected, such as swapping the left and right limbs, swapping the upper and lower limbs, or deviating from the standard area, it can often only be discovered through subsequent abnormal electrocardiogram waveforms or manual re-examination. This not only increases the risk of misdiagnosis and missed diagnosis, but also prolongs the examination time and the workload of medical staff. Summary of the Invention

[0005] This application provides a method, system, device, and medium for monitoring the connection status of electrocardiogram (ECG) lead clips, in order to solve the technical problem of determining the connection status of the corresponding leads of the lead clip without relying on the operator's subjective experience or subsequent ECG waveform interpretation.

[0006] In a first aspect, this application provides a method for monitoring the connection status of electrocardiogram lead clips, including: After the multi-target lead clip is taken out by the operator from the preset storage position, the first motion data of the target lead clip is collected. The first motion data includes at least one of acceleration data and angular velocity data collected by the attitude monitor built into the target lead clip. Based on the first motion data, the first motion trajectory of the target lead clip from the preset storage position to the patient's limb is obtained; After the target lead clip completes clamping and forms electrical contact with the patient's limb, the first spatial pose information of the target lead clip is determined; Based on the standard trajectory model and standard spatial pose model pre-established according to the lead type corresponding to the target lead clip, the first offset between the first motion trajectory and the standard trajectory model, and the second offset between the first spatial pose information and the standard spatial pose model are determined respectively. The lead connection status of the target lead clip is determined based on the first offset and the second offset.

[0007] Secondly, this application provides a connection status monitoring system for electrocardiogram lead clips, comprising: The data acquisition module is used to acquire first motion data of the target lead clip after the multi-target lead clip is taken out by the operator from the preset storage position. The first motion data includes at least one of acceleration data and angular velocity data. The trajectory determination module is used to obtain the first motion trajectory of the target lead clip from the preset storage position to the patient's limb based on the first motion data; The pose determination module is used to determine the first spatial pose information of the target lead clip after the target lead clip has completed clamping and formed electrical contact with the patient's limb. The offset determination module is used to determine, based on a standard trajectory model and a standard spatial pose model pre-established according to the lead type corresponding to the target lead clip, a first offset between the first motion trajectory and the standard trajectory model, and a second offset between the first spatial pose information and the standard spatial pose model, respectively. The status determination module is used to determine the lead connection status of the target lead clip based on the first offset and the second offset.

[0008] Thirdly, this application provides an electronic device, comprising: Processor; and, Memory for storing the executable instructions of the processor; The processor is configured to perform any of the possible methods described in the first aspect by executing the executable instructions.

[0009] Fourthly, this application provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement any of the possible methods described in the first aspect.

[0010] The ECG lead clip connection status monitoring method, system, device, and medium provided in this application collect first motion data of the target lead clip after it is removed from a preset storage position by the operator. Based on the first motion data, the first motion trajectory of the target lead clip from the preset storage position to the patient's limb is obtained. Then, after the target lead clip completes clamping and forms electrical contact with the patient's limb, the first spatial pose information of the target lead clip is determined. Based on a pre-established standard trajectory model and a standard spatial pose model corresponding to the lead type of the target lead clip, a first offset between the first motion trajectory and the standard trajectory model, and a second offset between the first spatial pose information and the standard spatial pose model are determined. Based on the first and second offsets, the lead connection status of the target lead clip is determined, thereby improving the accuracy of ECG examination. Attached Figure Description

[0011] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0012] Figure 1 This is a schematic flowchart illustrating a method for monitoring the connection status of electrocardiogram lead clips according to an example embodiment of this application; Figure 2 This is a front view of the structure of an electrocardiogram lead clip according to an example embodiment of this application; Figure 3 This is an isometric view of the structure of an electrocardiogram lead clip according to an example embodiment of this application; Figure 4 yes Figure 1 A flowchart illustrating a specific implementation of S120 in the illustrated embodiment; Figure 5 This is a schematic diagram of the connection status monitoring system for electrocardiogram lead clips according to an example embodiment of this application; Figure 6 This is a schematic diagram of the structure of an electronic device according to an example embodiment of this application.

[0013] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0014] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0015] Figure 1 This is a schematic flowchart illustrating a method for monitoring the connection status of electrocardiogram lead clips according to an example embodiment of this application. Figure 1 As shown, the ECG lead clip connection status monitoring method provided in this embodiment includes: S110. After the multi-target lead clip is taken out by the operator from the preset storage position, the first motion data of the target lead clip is collected.

[0016] In this step, after the multi-target lead clip is taken out by the operator from the preset storage position, the first motion data of the target lead clip is collected. The first motion data includes at least one of acceleration data and angular velocity data collected by the attitude monitor built into the target lead clip.

[0017] It is worth noting that Figure 2 This is a front view of the structure of an electrocardiogram lead clip according to an example embodiment of this application. Figure 3 This is an isometric view of the structure of an electrocardiogram lead clip according to an example embodiment of this application. For example... Figures 2-3 As shown, the ECG lead clip used in this embodiment includes a lead clip body 201, an electrode pad 202 disposed at one end of the lead clip body 201, and an attitude monitor 203 disposed at the other end of the lead clip body 201.

[0018] Optionally, the attitude monitor 203 can be an integrated IM948 positioning module, which contains sensors such as gyroscope, accelerometer, magnetometer, barometer, and altitude. It connects to the computing module via Bluetooth to draw angle and trajectory diagrams in real time, enabling precise navigation at close range.

[0019] Specifically, before the electrocardiogram (ECG) examination begins, a unique identifier is assigned to each target lead clip, and a correspondence is established between the identifier and the corresponding lead type. Then, at the preset storage position, the attitude monitor built into the target lead clip is put into standby mode, and the amplitude changes of the acceleration and angular velocity data collected by the attitude monitor are periodically detected.

[0020] When the amplitude change of acceleration data and / or angular velocity data exceeds the preset activation threshold, it is determined that the target lead clip has been removed from the preset storage position by the operator, and a motion data acquisition command is triggered.

[0021] Under the control of the motion data acquisition command, the attitude monitor continuously acquires acceleration data and / or angular velocity data at a first sampling frequency, and timestamps the acceleration data and / or angular velocity data during the acquisition process as the first motion data of the target lead clip.

[0022] Optionally, during the acquisition of the first motion data, the first motion data is transmitted to the host computer terminal and / or the electrocardiogram host via wired or wireless communication for subsequent motion trajectory calculation and processing.

[0023] S120. Based on the first motion data, the first motion trajectory of the target lead clip from the preset storage position to the patient's limb is obtained.

[0024] Figure 4 yes Figure 1 The illustrated embodiment shows a flowchart of a specific implementation of S120. Figure 4 As shown, the above-mentioned S120 includes: S121. Perform filtering preprocessing on the acceleration data and angular velocity data to obtain preprocessed acceleration data and preprocessed angular velocity data.

[0025] In this step, raw acceleration and angular velocity data output by the attitude monitor in a stationary state are first acquired. Then, based on the raw acceleration and angular velocity data, the bias parameter and noise statistical characteristic parameter are determined. Next, based on the bias parameter, the subsequently acquired acceleration and angular velocity data are corrected for bias, resulting in bias-corrected acceleration and angular velocity data.

[0026] Next, based on the noise statistical characteristic parameters, a one-dimensional or multi-dimensional digital filter is selected to filter the zero-bias-corrected acceleration data and the zero-bias-corrected angular velocity data. The filtering process includes at least one of low-pass filtering, band-pass filtering, or Kalman filtering to suppress high-frequency noise and / or power frequency interference.

[0027] Finally, the filtered acceleration data is used as the preprocessed acceleration data, and the filtered angular velocity data is used as the preprocessed angular velocity data.

[0028] S122. Based on the preprocessed acceleration data and preprocessed angular velocity data, the first attitude information of the target lead clip is determined by the attitude calculation algorithm.

[0029] Optionally, the preprocessed acceleration data and preprocessed angular velocity data can be fused based on at least one of the extended Kalman filter algorithm, complementary filter algorithm, or quaternion attitude calculation algorithm to obtain the first attitude information of the target lead clip.

[0030] Specifically, the preprocessed acceleration data and preprocessed angular velocity data are synchronized according to the sampling time, and the data collected at different times are time-aligned to obtain the time-synchronized acceleration data sequence and angular velocity data sequence.

[0031] Then, an attitude prediction model is constructed based on the angular velocity data sequence. The attitude of the target lead clip is modeled in the form of quaternions or Euler angles to obtain the attitude prediction state variables. An attitude observation model is constructed based on the acceleration data sequence. The gravity direction calculated from the acceleration data is used as the observation to correct the attitude prediction state variables.

[0032] When using the extended Kalman filter algorithm, based on the attitude prediction model and attitude observation model, the time update and observation update steps are executed iteratively to perform nonlinear filtering on the quaternion attitude state variables, and the filtered attitude quaternion is obtained as the first attitude information.

[0033] When the complementary filtering algorithm is used, the high-frequency attitude change information obtained by integrating the angular velocity data and the low-frequency attitude reference information calculated by the acceleration data are weighted and fused according to the preset high-frequency gain and low-frequency gain to obtain the fused attitude information, which is used as the first attitude information.

[0034] When using the quaternion attitude calculation algorithm, the attitude quaternion of the previous moment is updated by integrating the angular velocity data, and the updated attitude quaternion is normalized and error compensated by combining the gravity reference quaternion obtained from the acceleration data to obtain a stable attitude quaternion, which serves as the first attitude information.

[0035] Optionally, during the attitude calculation process of any of the above algorithms, the filtering parameters and / or fusion weights are adaptively adjusted based on a preset motion condition threshold to improve the accuracy and stability of the first attitude information under different operating speeds and different jitter intensities.

[0036] S123. Based on the first attitude information, perform coordinate system transformation and gravity component compensation on the preprocessed acceleration data to obtain linear acceleration data.

[0037] Specifically, a calibration transformation relationship between the sensor coordinate system and the target lead clip's body coordinate system can be pre-established within the target lead clip. Then, based on the first attitude information, the preprocessed acceleration data is transformed from the sensor coordinate system to the target lead clip's body coordinate system, obtaining acceleration data in the body coordinate system. Next, the standard gravitational acceleration vector is projected onto the target lead clip's body coordinate system according to the first attitude information, obtaining gravity component data in the body coordinate system. Finally, vector operations are performed between the acceleration data and gravity component data in the body coordinate system to eliminate the gravitational acceleration component, obtaining linear acceleration data in the target lead clip's body coordinate system.

[0038] S124. Integrate the linear acceleration data to obtain the displacement data of the target lead clamp.

[0039] Specifically, based on a preset integration time step, the linear acceleration data is discretely sampled to obtain discrete linear acceleration data arranged in a time series. Then, the discrete linear acceleration data is numerically integrated to obtain the corresponding discrete velocity data. Velocity constraints and / or a zero-velocity update strategy are introduced during the integration process to suppress cumulative integration errors. Next, the discrete velocity data is numerically integrated a second time to obtain the discrete displacement data of the target lead clamp at each discrete time point. Finally, based on the preset initial position and the discrete displacement data, the displacement data of the target lead clamp is obtained.

[0040] S125. Based on the displacement data and the first attitude information, the first motion trajectory of the target lead clip is reconstructed.

[0041] Specifically, the displacement data can be arranged in the order of sampling time to obtain displacement time series data, and the first attitude information corresponding to the displacement time series data can be synchronously registered to obtain attitude time series data.

[0042] Then, based on the preset global reference coordinate system, the displacement vector corresponding to each moment in the displacement time series data is transformed from the target lead clip body coordinate system to the global reference coordinate system to obtain global displacement time series data.

[0043] Next, based on the preset initial position coordinates, the global displacement time series data is accumulated and calculated to obtain the trajectory point sequence of the target lead clamp in the global reference coordinate system. Each trajectory point in the trajectory point sequence includes spatial position coordinates and corresponding attitude information.

[0044] Finally, the trajectory point sequence is smoothed and / or interpolated to obtain a smoothed trajectory point sequence. The smoothing process includes at least one of the following methods: sliding window filtering, spline interpolation, or polynomial fitting. The smoothed trajectory point sequence is then used as the first motion trajectory of the target lead clip.

[0045] S130. After the target lead clip has completed clamping and formed electrical contact with the patient's limb, determine the first spatial pose information of the target lead clip.

[0046] Specifically, when the clamping state of the target lead clip changes from open to closed and the contact impedance between the lead electrode and the patient's skin is less than a preset impedance threshold, the current moment is determined as the clamping completion moment.

[0047] At the moment of clamping completion, the attitude monitor is triggered to output the attitude data and / or displacement reference data of the current moment. The attitude data includes acceleration data, angular velocity data and / or attitude angles or attitude quaternions obtained by the attitude calculation algorithm.

[0048] Based on the preprocessed acceleration data and preprocessed angular velocity data collected within a preset time window before the clamping completion time, the attitude calculation algorithm in S122 above is used to filter, smooth and correct the time consistency of the target lead clamp attitude to obtain the attitude calculation result after clamping stabilization, which is used as the current attitude angle or attitude quaternion of the target lead clamp.

[0049] The calibration relationship between the target lead clip body coordinate system and the patient's body surface reference coordinate system is pre-established inside the target lead clip, and / or a reference positioning mark is pre-placed on the patient's body surface. The current position coordinates of the target lead clip in the patient's body surface reference coordinate system are calculated by the relative position relationship between the attitude monitor and the reference positioning mark.

[0050] Finally, based on the current position coordinates of the target lead clip in the patient's body surface reference coordinate system and the current posture angle or posture quaternion, the first spatial pose information containing spatial position parameters and posture parameters is obtained. The spatial position parameters are used to characterize the three-dimensional position of the target lead clip on the patient's limb, and the posture parameters are used to characterize the rotation direction of the target lead clip relative to the patient's limb.

[0051] It is worth noting that existing ECG systems lack the ability to continuously sense the movement of the lead clip after it has been clamped. Therefore, they cannot construct quantifiable micro-motion characteristic parameters to describe the subtle shaking, slippage, or intermittent jitter of the lead clip within a preset time period. Secondly, existing technologies typically assess lead connection quality solely from an electrical or waveform perspective, such as through impedance detection, noise levels, or waveform distortion to roughly determine whether there is poor contact or detachment. This lack of correlation analysis with the mechanical movement information of the lead clip itself makes it difficult to determine whether the decline in ECG signal quality stems from unstable clamping, lead traction, patient voluntary activity, or other interfering factors.

[0052] To address this, after the target lead clip has been clamped and made electrical contact with the patient's limb, second motion data of the target lead clip can be acquired within a preset time period. Based on this second motion data, the micromotion characteristic parameters of the target lead clip relative to the patient's limb can be determined. Then, the electrocardiogram (ECG) signal corresponding to the target lead clip can be acquired within the preset time period. The ECG signal quality is then assessed to obtain signal quality parameters. Finally, based on the micromotion characteristic parameters and the signal quality parameters, the fixation stability of the target lead clip can be determined.

[0053] Optionally, the determination of the aforementioned micro-motion characteristic parameters can be achieved by first filtering and preprocessing the second motion data to obtain preprocessed second motion data, which includes acceleration data and / or angular velocity data collected by the attitude monitor. Then, based on the preprocessed second motion data, the data is segmented within a preset time window over a preset duration to obtain multiple second motion data segments within that time window. Next, for each second motion data segment within that time window, at least one statistical characteristic parameter is calculated, including acceleration variance, angular velocity variance, root mean square value of acceleration, and root mean square value of angular velocity. Then, based on the preprocessed second motion data, abrupt changes in the rate of change of acceleration and / or the rate of change of angular velocity between adjacent sampling times are detected to obtain abrupt change characteristic parameters characterizing short-term intense motion. Finally, the statistical characteristic parameters and the abrupt change characteristic parameters are combined to obtain the micro-motion characteristic parameters of the target lead clip relative to the patient's limb.

[0054] Optionally, the determination of the aforementioned signal quality parameters can be achieved by preprocessing the ECG signals acquired within a preset time period using bandpass filtering and / or notch filtering to suppress baseline drift, power line interference, and high-frequency noise, resulting in a preprocessed ECG signal. Then, based on the preprocessed ECG signal, it is segmented according to a preset time window to obtain multiple ECG signal segments. Next, for each ECG signal segment, at least one ECG quality characteristic parameter is extracted from the following: signal-to-noise ratio, baseline drift amplitude, power line interference energy, electromyographic noise energy, and waveform integrity parameter. The waveform integrity parameter characterizes whether at least one of the P wave, QRS complex, and T wave waveforms is continuous, complete, and its amplitude is within a preset reasonable range. Then, according to a preset ECG quality assessment model, each ECG quality characteristic parameter is weighted and fused to obtain the corresponding segment quality score. Finally, based on the segment quality scores, a comprehensive quality score for the entire ECG signal is calculated according to preset rules. This comprehensive quality score serves as a signal quality parameter, characterizing the overall quality level of the ECG signal corresponding to the target lead clip within a preset time period.

[0055] Furthermore, the determination of the above-mentioned fixed stability assessment result can be as follows: when the micro-motion characteristic parameter is greater than the first stability threshold and the signal quality parameter is less than the second stability threshold, the fixed stability assessment result is determined to be clamp instability. When the micro-motion characteristic parameter is characterized by a sudden change and the ECG signal changes from a valid waveform to noise or baseline, the fixed stability assessment result is determined to be lead detachment. When both the micro-motion characteristic parameter and the signal quality parameter are within the preset normal range, the fixed stability assessment result is determined to be fixed and stable.

[0056] The aforementioned micro-motion characteristic parameter being characterized as a mutation refers to: within a preset time period, calculating at least one motion characteristic quantity of the target lead clip relative to the patient's limb based on the second motion data. This motion characteristic quantity includes at least one of acceleration magnitude, angular velocity magnitude, displacement increment, and attitude angle change. Time series analysis is performed on the motion characteristic quantity to obtain statistical characteristic parameters of the motion characteristic quantity within a sliding time window. These statistical characteristic parameters include mean, variance, maximum, minimum, root mean square value, and / or peak-to-peak value. The statistical characteristic parameter corresponding to any current moment is compared with its reference statistical characteristic parameter within the target historical time window to obtain a first rate of change parameter and / or a first amplitude of change parameter. When the first rate of change parameter is greater than a third preset threshold and / or the first amplitude of change parameter is greater than a fourth preset threshold, and these conditions remain met within a preset duration, the micro-motion characteristic parameter is characterized as a mutation.

[0057] Furthermore, the abrupt change of the aforementioned ECG signal from a valid waveform to noise or baseline refers to the following: Continuous temporal analysis is performed on the ECG signal acquired within a preset time period corresponding to the target lead clip. Based on an ECG waveform detection algorithm, valid waveform feature parameters of the ECG signal within a first time period are identified. Valid waveform feature parameters include at least one of the following: R-wave detection rate, valid heart rate, RR interval stability parameter, QRS waveform morphology similarity parameter, and heartbeat waveform energy parameter. In a second time period adjacent to the first time period, noise feature analysis and baseline feature analysis are performed on the ECG signal to obtain noise feature parameters and / or baseline feature parameters. Noise feature parameters include at least one of the following: high-frequency noise energy, power line interference energy, electromyographic interference energy, and signal-to-noise ratio parameter. Baseline feature parameters include at least one of the following: baseline drift amplitude, low-frequency energy ratio, and heartbeat detection rate. The valid waveform feature parameters in the second time period are compared with the corresponding reference valid waveform feature parameters in the first time period to obtain a second rate of change parameter and / or a second amplitude of change parameter. Simultaneously, the noise feature parameters and / or baseline feature parameters in the second time period are compared with preset noise thresholds and / or preset baseline thresholds. When the second rate of change parameter is greater than the fifth preset threshold and / or the second amplitude of change parameter is greater than the sixth preset threshold, and the noise characteristic parameter is greater than the corresponding preset noise threshold and / or the baseline characteristic parameter is greater than the corresponding preset baseline threshold, and the above conditions are maintained within a preset duration, the ECG signal is determined to change from a valid waveform to noise or baseline, which is one of the triggering conditions for lead dropout determination.

[0058] S140. Determine the first offset between the first motion trajectory and the standard trajectory model, and the second offset between the first spatial pose information and the standard spatial pose model.

[0059] In this step, based on the standard trajectory model and standard spatial pose model pre-established according to the lead type corresponding to the target lead clip, the first offset between the first motion trajectory and the standard trajectory model, and the second offset between the first spatial pose information and the standard spatial pose model are determined respectively.

[0060] It is worth noting that the existing routine 12-lead electrocardiogram examination cannot distinguish more subtle errors such as left and right limb swapping, upper and lower limb swapping, and positional deviation but still good electrical contact.

[0061] Especially in primary healthcare institutions with high ECG volume and staff turnover, incorrect lead clip placement often doesn't lead to complete signal loss, but it can introduce systemic lead waveform reversals, amplitude abnormalities, or electrical axis deviations, posing a risk of misdiagnosis. However, these changes are difficult for on-site equipment to automatically identify and locate. Therefore, it is necessary to further address how to automatically identify and differentiate various fine-grained positional abnormalities, such as left-right swapping, up-down swapping, and deviations from the standard position but still maintaining electrical contact, while ensuring electrical contact with the lead clips and the availability of ECG signals.

[0062] In response, this step can be achieved by quantitatively modeling and comparing the first motion trajectory and the final first spatial pose information of the entire lead clip operation process, calculating the first offset reflecting the degree of deviation of the operation path and the second offset reflecting the degree of deviation of the final spatial pose, and classifying the lead connection status based on these two offsets. This enables the automatic identification and differentiation of various fine-grained positional abnormalities, such as left-right swapping, up-down swapping, and deviation from the standard position but still having electrical contact, without relying on the operator's subjective experience or solely on the characteristics of the ECG waveform results.

[0063] To achieve the above objectives, in one specific implementation, the determination of the first offset can be achieved by first determining the lead type corresponding to the target lead clip based on its identification. Then, a standard trajectory model corresponding to the lead type is invoked, where the standard trajectory model is trained based on trajectory data from multiple historical correctly connected samples. Next, the first motion trajectory is compared with the standard trajectory model to obtain a first trajectory similarity parameter. Finally, the first offset is determined based on the first trajectory similarity parameter.

[0064] Optionally, the aforementioned standard trajectory model is a probabilistic trajectory distribution model constructed based on at least one of the dynamic time warping algorithm, trajectory distance metric algorithm, or cluster analysis algorithm, and the first offset is used to characterize the degree of deviation of the first motion trajectory from the probabilistic trajectory distribution model.

[0065] Furthermore, for multiple historical correct connection samples corresponding to each lead type, the sample trajectory data of each historical correct connection sample from the preset storage position to the corresponding patient limb position can be obtained, and the sample trajectory data can be processed by time normalization and spatial coordinate normalization to obtain a standardized sample trajectory sequence set.

[0066] When constructing a probabilistic trajectory distribution model using the dynamic time warping algorithm, dynamic time warping matching is performed on any two sample trajectory sequences in the standardized sample trajectory sequence set to calculate the time warping distance of the paired trajectories. Based on the time warping distance, the standardized sample trajectory sequence set is aggregated and statistically analyzed to obtain the mean and / or covariance parameters of the trajectory point distribution at each discrete time alignment position. Based on this, a probabilistic trajectory distribution model based on dynamic time warping is established.

[0067] When constructing a probabilistic trajectory distribution model using a trajectory distance metric algorithm, distance calculation and similar trajectory aggregation are performed on a standardized set of sample trajectory sequences based on at least one of the following trajectory distance metrics: Fraser distance, Hausdorff distance, or Euclidean sequence distance. Sample trajectories with a distance less than a preset clustering threshold are grouped into the same trajectory cluster. The trajectory point sequences within each trajectory cluster are statistically analyzed to obtain the central trajectory of the trajectory cluster and the variance or covariance parameters at each trajectory point position. Based on this, a probabilistic trajectory distribution model based on trajectory distance metrics is established.

[0068] When constructing a probabilistic trajectory distribution model using clustering analysis algorithms, the standardized sample trajectory sequence is regarded as a high-dimensional feature vector. Based on at least one of the K-means algorithm, hierarchical clustering algorithm, or Gaussian mixture model clustering algorithm, cluster analysis is performed on the set of standardized sample trajectory sequences to obtain multiple trajectory cluster centers and the trajectory distribution parameters corresponding to each cluster center. Each cluster center and its distribution parameters are then used as components of the probabilistic trajectory distribution model.

[0069] When determining the first offset, the first motion trajectory is first normalized by the same time and spatial coordinate normalization process as when constructing the probability trajectory distribution model, to obtain the normalized first motion trajectory.

[0070] When the probability trajectory distribution model is a probability trajectory distribution model based on dynamic time warping, the dynamic time warping distance between the normalized first motion trajectory and the mean trajectory of the probability trajectory distribution model is calculated. Based on the variance or covariance parameter of the dynamic time warping distance and the probability trajectory distribution model on the aligned time axis, the deviation score of the normalized first motion trajectory relative to the probability trajectory distribution model is calculated. The deviation score is used as the first offset or used to generate the first offset.

[0071] When the probability trajectory distribution model is a probability trajectory distribution model based on trajectory distance metric, the trajectory distance between the normalized first motion trajectory and the center trajectory of each trajectory cluster is calculated. Combined with the distribution variance or covariance parameter of the corresponding trajectory cluster, the nearest trajectory cluster to which the normalized first motion trajectory belongs and its standardized distance are determined. The standardized distance is used as the first offset or used to generate the first offset.

[0072] When the probability trajectory distribution model is a probability trajectory distribution model based on cluster analysis, the normalized first motion trajectory is mapped to the trajectory feature space obtained by cluster analysis. The Mahalanobis distance or Euclidean distance between the normalized first motion trajectory and the cluster centers of each trajectory is calculated. Based on the corresponding Gaussian mixture distribution or cluster radius, the confidence or likelihood of the normalized first motion trajectory relative to the nearest cluster center is obtained. The confidence or likelihood is converted into a first offset through a preset function to characterize the degree to which the first motion trajectory deviates from the probability trajectory distribution model.

[0073] Furthermore, the determination of the aforementioned second offset can be achieved by determining the current position coordinates and current attitude angle of the target lead clip based on the attitude information from the attitude monitor after the target lead clip has been clamped, serving as the first spatial pose information. Then, the standard spatial pose model corresponding to the lead type is invoked, where the standard spatial pose model represents the spatial position and attitude range of the lead type on a standard patient's body surface. Next, the first spatial pose information is compared with the standard spatial pose model to obtain the first spatial position deviation parameter and the first attitude deviation parameter. Finally, the second offset is determined based on the first spatial position deviation parameter and the first attitude deviation parameter.

[0074] The aforementioned standard spatial pose model is a pre-established spatial reference model for the spatial position and posture range of different lead types on the standard patient's body surface. The standard spatial pose model includes a set of standard spatial position parameters and a set of standard posture range parameters that correspond one-to-one with each lead type.

[0075] Specifically, the establishment of a standard spatial pose model can include: Based on multiple standard subjects who meet the preset body shape conditions, lead clips of the corresponding lead types are manually and accurately placed on the body surface of each standard subject in accordance with the electrocardiogram lead specifications. The actual spatial position coordinates and actual posture angles of each lead clip in the reference coordinate system on the patient's body surface are obtained through a reference positioning device and / or three-dimensional positioning equipment, which serve as standard sampling posture data.

[0076] The standard sampling pose data of each standard subject were normalized and mapped to a unified patient body surface reference coordinate system. The data were then normalized in size according to at least one human body parameter, such as height, limb length, or distance between body surface markers, to eliminate the influence of differences in body shape among different subjects, thus obtaining a set of normalized standard sampling pose data.

[0077] For each lead type, statistical analysis is performed on the spatial coordinates of each standard sampling point in the normalized standard sampling pose data set to calculate the mean, variance, and / or covariance matrix of the lead type in the patient's body surface reference coordinate system. Based on the mean position and the variance and / or covariance matrix, the standard spatial position range of the lead type is determined, which serves as the standard spatial position parameter set for the lead type.

[0078] For each lead type, statistical analysis is performed on the posture angles of each standard sampling point in the normalized standard sampling posture data set to calculate the posture mean, posture variance, and / or covariance matrix of that lead type in the patient's body surface reference coordinate system. Based on the posture mean, the standard posture angle range of that lead type is determined by combining the posture variance and / or covariance matrix, which serves as the standard posture range parameter set for that lead type.

[0079] The standard spatial position parameter set and standard attitude range parameter set obtained for each lead type are bound and stored to form a standard spatial pose model corresponding to the lead type. According to the preset spatial confidence level, the standard spatial position parameter set and standard attitude range parameter set are divided into core standard range and extended standard range, respectively, which are used to distinguish the degree of deviation of different levels when determining the first spatial position deviation parameter and the first attitude deviation parameter.

[0080] Furthermore, the determination of the first spatial position deviation parameter and the first posture deviation parameter can be specifically achieved by using the standard spatial position parameters pre-stored in the standard spatial pose model for the lead type corresponding to the target lead clip, to obtain the standard target position coordinates of the lead type in the patient's body surface reference coordinate system. The standard target position coordinates are used to characterize the reference spatial position of the lead type in the standard patient's body surface position.

[0081] Based on the current position coordinates and the standard target position coordinates in the first spatial pose information, the three-dimensional spatial distance and / or the component deviations in each coordinate axis direction between the current position coordinates and the standard target position coordinates are calculated. The three-dimensional spatial distance and / or component deviations are used as the first spatial position deviation parameter or used to generate the first spatial position deviation parameter to characterize the degree of deviation of the current position of the target lead clip from the standard spatial position.

[0082] Then, using the standard posture range parameters pre-stored in the standard spatial pose model for the lead type corresponding to the target lead clip, the standard target posture angle or posture angle range of the lead type in the patient's body surface reference coordinate system is obtained. The standard target posture angle or posture angle range is used to characterize the reference posture direction of the lead type at the standard patient's body surface position.

[0083] Next, based on the current attitude angle and the standard target attitude angle or attitude angle range in the first spatial pose information, the attitude angle difference between the current attitude angle and the standard target attitude angle and / or the rotational deviation around each attitude degree of freedom axis are calculated. The attitude angle difference and / or rotational deviation are used as the first attitude deviation parameter or used to generate the first attitude deviation parameter to characterize the degree of deviation of the current attitude of the target lead clip from the standard attitude range.

[0084] Specifically, when the standard spatial pose model divides the standard spatial position parameters and standard attitude range parameters into a core standard range and an extended standard range, it further includes: determining whether the current position coordinates fall within the core standard position range, the extended standard position range, or exceed the extended standard position range based on the deviation relationship between the current position coordinates and the standard target position coordinates, and classifying and labeling the first spatial position deviation parameter; determining whether the current attitude angle falls within the core standard attitude range, the extended standard attitude range, or exceeds the extended standard attitude range based on the deviation relationship between the current attitude angle and the standard target attitude angle or attitude angle range, and classifying and labeling the first attitude deviation parameter so as to distinguish different levels of deviation when determining the second offset based on the first spatial position deviation parameter and the first attitude deviation parameter.

[0085] Furthermore, the specific method for determining the aforementioned second offset can be to first normalize the first spatial position deviation parameter to obtain the first normalized spatial position deviation parameter, wherein the first normalized spatial position deviation parameter is used to characterize the relative deviation of the target lead clip from the spatial position range in the standard spatial pose model.

[0086] The first attitude deviation parameter is then normalized to obtain the first normalized attitude deviation parameter, which is used to characterize the degree of relative deviation of the target lead clip from the attitude range in the standard spatial pose model.

[0087] Next, based on the preset weighting coefficients, the first normalized spatial position deviation parameter and the first normalized attitude deviation parameter are weighted to obtain the initial spatial pose comprehensive deviation parameter. The weighting coefficients are used to differentiate the weighting of the first normalized spatial position deviation parameter and the first normalized attitude deviation parameter according to the degree of influence of spatial position deviation and attitude deviation on the accuracy of lead connection under different lead types and / or different application scenarios.

[0088] Then, based on the magnitude and / or deviation level of the first spatial position deviation parameter and the first attitude deviation parameter, the initial spatial pose comprehensive deviation parameter is subjected to nonlinear mapping or piecewise function transformation to obtain the corrected spatial pose comprehensive deviation parameter. The nonlinear mapping or piecewise function transformation is used to improve the sensitivity of characterization of abnormal deviations when the first spatial position deviation parameter and / or the first attitude deviation parameter are close to or exceed the upper limit of the preset allowable range.

[0089] Finally, the corrected spatial pose comprehensive deviation parameter is used as the second offset or used to generate the second offset. The second offset is used to comprehensively characterize the overall deviation of the target lead clip from the standard spatial pose model in both spatial position and attitude dimensions, so as to determine the lead connection state of the target lead clip in the subsequent joint determination of the first offset and the second offset.

[0090] S150. Determine the lead connection status of the target lead clip based on the first offset and the second offset.

[0091] In this step, the first offset can be compared with the first preset threshold, and the second offset can be compared with the second preset threshold.

[0092] If both the first offset and the second offset are less than the corresponding preset threshold, the determination result will be that the position is correct.

[0093] If the first offset is greater than the first preset threshold and / or the second offset is greater than the second preset threshold, the determination result will be determined as a positional abnormality. The positional abnormality includes at least one of the following abnormal types: left and right limb swapping, upper and lower limb swapping, and exceeding the standard position range.

[0094] Furthermore, when the determination result is that the position is correct, the lead connection status information is set to a qualified state. When the determination result is that the position is abnormal, the lead connection status information is set to the corresponding error type according to the type of abnormality, and visual and / or audible prompts are generated.

[0095] In this embodiment, after the multi-target lead clip is removed from the preset storage position by the operator, the first motion data of the target lead clip is collected. Based on the first motion data, the first motion trajectory of the target lead clip from the preset storage position to the patient's limb is obtained. Then, after the target lead clip completes clamping and forms electrical contact with the patient's limb, the first spatial pose information of the target lead clip is determined. According to the standard trajectory model and standard spatial pose model pre-established for the lead type corresponding to the target lead clip, the first offset between the first motion trajectory and the standard trajectory model, and the second offset between the first spatial pose information and the standard spatial pose model are determined respectively. Based on the first offset and the second offset, the lead connection status of the target lead clip is determined. Then, based on these two offsets, the lead connection status is comprehensively judged. It can automatically output whether the lead connection is correct, whether there is a mismatch between the lead type and the limb position, and whether the clamping position exceeds the standard body surface range when the lead clip just forms electrical contact with the patient's limb, thereby improving the accuracy of electrocardiogram examination.

[0096] Specifically, an attitude monitor can be integrated into each target lead clip to continuously collect at least one of acceleration and angular velocity data from the moment the lead clip is removed from the preset storage position, forming first motion data. This data is then processed and kinematically deduced in a preset algorithm environment to obtain the first motion trajectory of the lead clip from the storage position to the patient's limb.

[0097] Simultaneously, when the lead clip completes clamping and establishes electrical contact with the patient's limb, the posture data and position information currently output by the posture monitor constitute the first spatial pose information of the lead clip. Based on the lead clip's identification, the system determines its corresponding lead type and invokes a pre-established standard trajectory model and standard spatial pose model for that lead type. The standard trajectory model depicts the typical motion path distribution from the storage position to the target limb when correctly connected, while the standard spatial pose model depicts the reasonable spatial position and pose range of that lead type on a standard body surface location.

[0098] By performing similarity or deviation calculations between the actual motion trajectory and the standard trajectory model in a unified reference coordinate system, a first offset reflecting the degree of deviation in the operation path is obtained. Then, by calculating the position and attitude deviations between the actual spatial pose information and the standard spatial pose model, a second offset reflecting the degree of deviation in the final clamping position and attitude is obtained.

[0099] Based on the judgment rules or threshold logic corresponding to these two offsets, the lead connection status is automatically output, thereby achieving objective and real-time monitoring of the correctness of the lead connection.

[0100] In other words, each ECG lead clip is equipped with sensors such as gravity sensors and gyroscopes. When medical staff pick up the clip to clamp the patient's hands or feet, the system records the entire movement process and the final position and direction of the clip.

[0101] The system needs to learn in advance how each type of contact clip should be operated correctly, roughly following the path from the tray to which hand / leg, and ultimately clamped in which area of ​​the body and in what orientation.

[0102] Then, during actual operation, the system compares the trajectory and final position / attitude of this operation with the standard model established based on correct operation, and calculates two deviation values. Based on these two deviation values, the system automatically determines whether the clamp is clamped on the correct limb and the correct approximate position, thereby providing the lead connection status in real time.

[0103] In this way, even if the operator is inexperienced or makes a momentary oversight, the system can proactively detect the problem of incorrect lead clip placement, rather than passively discovering it only after the electrocardiogram is drawn.

[0104] Figure 5 This is a schematic diagram of the connection status monitoring system for electrocardiogram lead clips according to an example embodiment of this application. Figure 5 As shown, the ECG lead clip connection status monitoring system 300 provided in this embodiment includes: The data acquisition module 310 is used to acquire first motion data of the target lead clip after the multi-target lead clip is taken out from the preset storage position by the operator. The first motion data includes at least one of acceleration data and angular velocity data. The trajectory determination module 320 is used to obtain the first motion trajectory of the target lead clip from the preset storage position to the patient's limb based on the first motion data; The pose determination module 330 is used to determine the first spatial pose information of the target lead clip after the target lead clip has completed clamping and formed electrical contact with the patient's limb. The offset determination module 340 is used to determine, respectively, a first offset between the first motion trajectory and the standard trajectory model, and a second offset between the first spatial pose information and the standard spatial pose model, based on a standard trajectory model and a standard spatial pose model pre-established according to the lead type corresponding to the target lead clip. The status determination module 350 is used to determine the lead connection status of the target lead clip based on the first offset and the second offset.

[0105] Figure 6 This is a schematic diagram of the structure of an electronic device according to an example embodiment of this application. For example... Figure 6As shown, the electronic device 400 provided in this embodiment includes: a processor 401 and a memory 402; wherein: Memory 402 is used to store computer programs, and the memory may also be flash memory.

[0106] Processor 401 is used to execute the execution instructions stored in the memory to implement the various steps in the above method. For details, please refer to the relevant descriptions in the preceding method embodiments.

[0107] Alternatively, the memory 402 can be either standalone or integrated with the processor 401.

[0108] When the memory 402 is a device independent of the processor 401, the electronic device 400 may further include: Bus 403 is used to connect the memory 402 and the processor 401.

[0109] This embodiment also provides a readable storage medium storing a computer program, which, when executed by at least one processor of an electronic device, enables the electronic device to perform the methods provided in the various embodiments described above.

[0110] This embodiment also provides a program product including a computer program stored in a readable storage medium. At least one processor of an electronic device can read the computer program from the readable storage medium, and the at least one processor executes the computer program to cause the electronic device to perform the methods provided in the various embodiments described above.

[0111] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this application are indicated by the claims.

[0112] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A method for monitoring the connection status of electrocardiogram lead clips, characterized in that, include: After the multi-target lead clip is taken out by the operator from the preset storage position, the first motion data of the target lead clip is collected. The first motion data includes at least one of acceleration data and angular velocity data collected by the attitude monitor built into the target lead clip. Based on the first motion data, the first motion trajectory of the target lead clip from the preset storage position to the patient's limb is obtained; After the target lead clip completes clamping and forms electrical contact with the patient's limb, the first spatial pose information of the target lead clip is determined; Based on the standard trajectory model and standard spatial pose model pre-established according to the lead type corresponding to the target lead clip, the first offset between the first motion trajectory and the standard trajectory model, and the second offset between the first spatial pose information and the standard spatial pose model are determined respectively. The lead connection status of the target lead clip is determined based on the first offset and the second offset.

2. The method for monitoring the connection status of ECG lead clips according to claim 1, characterized in that, The step of obtaining the first motion trajectory of the target lead clip from the preset storage position to the patient's limb based on the first motion data includes: The acceleration data and the angular velocity data are filtered and preprocessed to obtain preprocessed acceleration data and preprocessed angular velocity data; Based on the preprocessed acceleration data and the preprocessed angular velocity data, an attitude calculation algorithm is used to determine the first attitude information of the target lead clip; Based on the first attitude information, coordinate system transformation and gravity component compensation are performed on the preprocessed acceleration data to obtain linear acceleration data. The displacement data of the target lead clip is obtained by integrating the linear acceleration data. Based on the displacement data and the first attitude information, the first motion trajectory of the target lead clip is reconstructed.

3. The method for monitoring the connection status of electrocardiogram lead clips according to claim 2, characterized in that, The process of determining the first attitude information of the target lead clip using an attitude calculation algorithm includes: The preprocessed acceleration data and the preprocessed angular velocity data are fused based on at least one of the extended Kalman filter algorithm, complementary filter algorithm, or quaternion attitude calculation algorithm to obtain the first attitude information of the target lead clip.

4. The method for monitoring the connection status of electrocardiogram lead clips according to claim 1, characterized in that, Determining the first offset between the first motion trajectory and the standard trajectory model includes: The lead type corresponding to the target lead clip is determined based on the identification of the target lead clip; Invoke the standard trajectory model corresponding to the lead type, which is trained based on trajectory data of multiple historical correct connection samples; The first motion trajectory is compared with the standard trajectory model to obtain the first trajectory similarity parameter; The first offset is determined based on the first trajectory similarity parameter.

5. The method for monitoring the connection status of ECG lead clips according to claim 4, characterized in that, The standard trajectory model is a probabilistic trajectory distribution model constructed based on at least one of the dynamic time warping algorithm, trajectory distance metric algorithm, or clustering analysis algorithm. The first offset is used to characterize the degree of deviation of the first motion trajectory from the probabilistic trajectory distribution model.

6. The method for monitoring the connection status of electrocardiogram lead clips according to claim 4, characterized in that, Determining the second offset between the first spatial pose information and the standard spatial pose model includes: After the target lead clip completes clamping, the current position coordinates and current attitude angle of the target lead clip are determined based on the attitude information of the attitude monitor, and used as the first spatial pose information; Invoke the standard spatial pose model corresponding to the lead type, wherein the standard spatial pose model is the spatial position and pose range of the lead type on the standard patient body surface position; The first spatial pose information is compared with the standard spatial pose model to obtain the first spatial position deviation parameter and the first attitude deviation parameter. The second offset is determined based on the first spatial position deviation parameter and the first attitude deviation parameter.

7. The method for monitoring the connection status of electrocardiogram lead clips according to claim 1, characterized in that, Determining the lead connection status of the target lead clip based on the first offset and the second offset includes: The first offset is compared with the first preset threshold, and the second offset is compared with the second preset threshold. If both the first offset and the second offset are less than the corresponding preset threshold, the determination result will be that the position is correct. If the first offset is greater than the first preset threshold and / or the second offset is greater than the second preset threshold, the determination result is determined to be a positional abnormality, wherein the positional abnormality includes at least one of the following abnormal types: left and right limb swapping, upper and lower limb swapping, and exceeding the standard position range. When the determination result is that the position is correct, the lead connection status information is set to qualified status; When the determination result is a positional abnormality, the lead connection status information is set to the corresponding error type according to the abnormality type, and visual and / or audible prompts are generated.

8. A connection status monitoring system for electrocardiogram lead clips, characterized in that, include: The data acquisition module is used to acquire first motion data of the target lead clip after the multi-target lead clip is taken out by the operator from the preset storage position. The first motion data includes at least one of acceleration data and angular velocity data. The trajectory determination module is used to obtain the first motion trajectory of the target lead clip from the preset storage position to the patient's limb based on the first motion data; The pose determination module is used to determine the first spatial pose information of the target lead clip after the target lead clip has completed clamping and formed electrical contact with the patient's limb. The offset determination module is used to determine, based on a standard trajectory model and a standard spatial pose model pre-established according to the lead type corresponding to the target lead clip, a first offset between the first motion trajectory and the standard trajectory model, and a second offset between the first spatial pose information and the standard spatial pose model, respectively. The status determination module is used to determine the lead connection status of the target lead clip based on the first offset and the second offset.

9. An electronic device, characterized in that, include: processor; as well as, Memory for storing the executable instructions of the processor; The processor is configured to execute the method of any one of claims 1 to 7 by executing the executable instructions.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1 to 7.

Images