27 results about "ECG analysis" patented technology

A system and method for determining whether to modify a diagnostic interpretation of a rule-based ECG analysis model using an AI model is provided. Information identifying a feature set of the ECG determined by a rule-based ECG analysis model may be received. Information identifying a diagnostic interpretation of the ECG determined by a rule-based ECG analysis model may be received. The feature set of the ECG and the diagnostic interpretation results may be input to the AI model. Whether the diagnostic interpretation should be modified may be determined based on the output of the AI model. A diagnostic interpretation of the ECG may be transmitted based on determining whether the diagnostic interpretation should be modified.

Systems, devices, and methods provide up-to-date defibrillation shock recommendations. In an example method, multiple segments of an electrocardiogram (ECG) of an individual are detected from an individual receiving chest compressions. The multiple segments are evaluated to determine whether the individual is exhibiting a shockable heart rhythm. A medical device outputs a recommendation indicating whether a defibrillation shock is advised based on the most recent determination of the individual's heart rhythm. For example, the medical device outputs an up-to-date recommendation on-demand in response to an input signal from a user. In some examples, the medical device updates the recommendation based on ongoing analysis of the ECG.

The invention provides an electrocardio physiological signal feature extraction method for heart conduction block classification, and belongs to the technical field of electrocardio physiological signals. 12-lead electrocardiosignals and auxiliary signals of a patient are collected, a wave equation is established through a water-wave-imitating interference multi-signal fusion algorithm, and a multi-lead signal interference mode is simulated; the method comprises the following steps: extracting time domain characteristic parameters including a PR interval, a QRS wave width, a QT interval and the like from a fusion signal, and calculating frequency domain characteristic parameters including power density distribution and a heart rate variability index; nonlinear dynamic characteristic parameters including a sample entropy value, a fractal dimension and the like are extracted, the conduction block type is judged according to the PR interval length and a QRS wave falling mode, and the technical problem that a weak heart conduction block characteristic signal cannot be accurately recognized through single-lead electrocardio analysis is solved.

An electrocardiogram (ECG) acquisition system comprises a processor configured to process an ECG signal from a patient, a plurality of ECG electrodes configured to be coupled to the patient to obtain the ECG signal from the patient, and an analog-to-digital (A / D) converter configured to acquire the ECG signal from the plurality of ECG electrodes, and to provide the ECG signal to the processor as ECG data representative of the ECG signal. The A / D converter is configured to acquire the ECG signal at a first resolution and the processor is configured to process the ECG data at a second resolution, and the first resolution is higher than the second resolution.

The invention provides a multi-domain electrocardio intelligent analysis method of a mixed Fourier and wavelet convolutional neural network, belongs to the technical field of artificial intelligence and medical health crossing, and solves the technical problems that global spectrum features and local transient features are difficult to consider and task generalization is poor in traditional single-domain ECG analysis. According to the technical scheme, the method comprises the following steps: S1, preprocessing an ECG signal, filtering, segmenting, normalizing and enhancing data; s2, constructing a three-branch model; s3, fusing the attention mechanism with multi-domain features; s4, setting a task classification head; s5, using Adam optimization and an early stop strategy to prevent overfitting; and S6, inputting data, and outputting arrhythmia classification, biological recognition and sleep apnea detection results. According to the method, generalization and accuracy are improved through multi-domain fusion, multiple tasks are supported, and clinical and biological recognition scenes are adapted.

The present disclosure describes an intelligent, cloud-based, wearable IoT-enabled device for real-time ECG monitoring and cardiovascular health assessment. It tracks ECG, heart rate, respiration, SpO2, skin temperature, and activity using integrated biosensors, a central microprocessor, and wireless transceivers (Wi-Fi, Bluetooth, 3G–6G). The device supports GPS tracking and local ECG analysis, including noise filtering, R-peak detection, and arrhythmia identification. An AI module detects cardiac events such as AFib and PVCs, with data visualized through a personalized dashboard. Additional features include fall detection, pacemaker signal filtering, voice messaging, and modular support for external biosensors. Data is securely transmitted to a cloud-based platform for AI-driven analytics, remote access, and proactive medical alerts. The ergonomic, standalone design suits both clinical monitoring and everyday wellness tracking.

A defibrillator using an ECG analyzer and a shock impedance advisor for improving defibrillation of a patient's heart by a defibrillation discharge circuit associated with the defibrillator. In operation, the ECG analyzer derives a shock delivery decision from detecting a shockable rhythm in the patient's ECG waveform in response to a shock delivery decision, and the shock impedance advisor measures the non-shock impedance of the defibrillation discharge circuit, estimates a pre-shock impedance of the defibrillation discharge circuit from the measured non-shock impedance of the defibrillation discharge circuit, and communicates a lower shock impedance advisory to a responder operating the defibrillator when the pre-shock impedance of the defibrillation discharge circuit exceeds a shock impedance threshold.

A cordless, wireless system for providing the long-term collection of medical data that may be used in digital ECG analysis, that includes a retaining element that retains a sensor in close proximity or adjacent to a user's skin and an intelligent measuring head that obtains the information provided by the sensor and transmits the obtained information to a processing system. The processing system collates the obtained information and determines from the collated data a digital ECG response and further a blood pressure based on blood oxygenation level.

An automatic external defibrillator is used for conducting electrocardiogram analysis and discharge processing on a detected person. The automated external defibrillator includes a detection unit configured to detect a body movement of a subject during a cardio-pulmonary resuscitation period after electrocardiogram analysis and discharge processing, and an output controller configured to output an instruction regarding chest compression on the subject to a rescuer based on the presence or absence of the body movement of the subject during the cardio-pulmonary resuscitation period. An output controller configured to output a continuation instruction for instructing continuation of the chest compression, and to output the continuation instruction again in a case where a first time has elapsed from the last output of the continuation instruction; a start command output unit that outputs a start command for instructing the start of chest compression over the continuation command when the body movement of the subject is not detected continuously for a second time or longer shorter than the first time; and outputting the start command again when a second time has elapsed from the last output of the start command.

Effective utilization is provided in a cloud computing environment in which a master plane executing on a master node controls startup and shutdown of working nodes in which a working node that outputs necessary for operation of other working nodes is started prior to the working node that requires that output. By specifying available computing resources to earlier launched working nodes, these working nodes can process a larger amount of monitoring data. Once the outputs of these working nodes are ready, available resources will be reallocated to working nodes that use earlier launched working node outputs. Additional control of heart monitoring may be provided by communicating with the monitor to increase the rate at which the monitor transmits the collected data and suspend alarm generation based on the monitored data if such alarms may be inaccurate.

The invention relates to the technical field of medical treatment and health data processing, and discloses a method for identifying heart risks by utilizing night vital sign data mutation, which comprises the following steps: carrying out scene classification on respiratory signals, and when the classification result is an ambiguous fluctuation artifact state, further acquiring a signal quality index of an ECG signal; the method comprises the following steps: acquiring a signal quality index, performing cross validation on a fluctuation artifact state by using the signal quality index, correcting the fluctuation artifact state into a physiological wave state or a signal artifact state, and adaptively selecting an ECG analysis model according to a final classification result. According to the method, the inherent ambiguity problem of the fluctuation artifact state is solved, and the method can effectively distinguish the real physiological fluctuation from the technical artifact, so that a targeted analysis model is scheduled for the two scenes with different properties, and the accuracy of risk identification is improved.

The present application relates to the technical field of medical health data processing, and discloses a method for identifying heart risk by using night vital sign data mutation, comprising: performing scene classification on a breathing signal, and when the classification result is a fluctuation artifact state with ambiguity, further acquiring a signal quality index of an electrocardiogram (ECG) signal; cross-verification is performed on the fluctuation artifact state by using the signal quality index, the fluctuation artifact state is corrected to a physiological fluctuation state or a signal artifact state, and an ECG analysis model is adaptively selected according to the final classification result. The present application cross-verification is performed on the breathing scene classification by introducing the electrocardiogram signal quality index, the inherent ambiguity problem of the fluctuation artifact state is solved, the method can effectively distinguish the real physiological fluctuation from the technical artifact, thereby the analysis model of the two different nature scenes is targeted, and the accuracy of risk identification is improved.

Systems and methods for adding interpretability to and assessing bias of an ECG analysis model are herein provided. In one example, a method comprises: obtaining a diagnostic output from an AI-based ECG analysis model on an ECG dataset; extracting interpretable criteria from the ECG dataset for a target of the diagnostic output of the AI-based ECG analysis model to predict an output for the ECG dataset based on the extracted criteria; determining one or more characteristics of the extracted criteria; assessing the output from the ECG analysis model for bias based on a comparison between the output of the ECG analysis model and the predicted output; and outputting the one or more characteristics and the bias assessment to a user device.

The present invention discloses a method, apparatus, terminal device and storage medium for processing ECG data for heart failure assessment, which obtains ECG data of a patient; performs peak screening processing on an ECG in the ECG data to obtain a plurality of ECG waves; determines R waves, P waves, Q waves, S waves and T waves in the plurality of ECG waves; extracts ECG acquisition parameters and ECG waveform parameters corresponding to each ECG wave in the ECG data based on generation time; establishes a coordinate system for each ECG wave with the ECG waveform parameter type of the ECG wave as the horizontal coordinate and the ECG waveform parameter value as the vertical coordinate, determines the ECG waveform type of the ECG wave based on the parameter value range of historical ECG waveform types, and summarizes the ECG waveform type and the ECG acquisition parameters to generate ECG analysis data of the patient; performs heart failure assessment based on the obtained accurate ECG analysis data in combination with the user's body impedance, which is beneficial to improving the accuracy of heart failure assessment.

Systems and methods for adding interpretability to and evaluating the bias of an ECG analysis model are provided herein. In one example, a method includes obtaining a diagnostic output on an ECG data set from an AI-based ECG analysis model (302); extracting an interpretable criterion from the ECG dataset for a target of a diagnostic output of the AI-based ECG analysis model to predict an output of the ECG dataset based on the extracted criterion; determining one or more characteristics of the extracted criteria (304); evaluating a bias from the output of the ECG analysis model based on a comparison between the output of the ECG analysis model and the predicted output (404); and outputting the one or more characteristics and bias evaluations to the user equipment (362).

A system and method for determining, by a rule-based ECG analysis model, a diagnosis of an ECG using criteria extracted by an AI model are provided. An ECG may be received by the rule-based ECG analysis model. Features of the ECG may be determined by the rule-based ECG analysis model. The diagnosis may be determined by the rule-based ECG analysis model using the features of the ECG and the criteria extracted by the AI model. The diagnosis may be transmitted.

A method for reviewing ECG studies, comprising: selecting one or more ECG studies from a database of ECG studies, wherein the one or more ECG studies have been subjected to a first review by a first clinician; storing the selected one or more ECG studies in a review database; presenting the one or more selected ECG studies to a second clinician for a second review; storing the second review in the review database; comparing the first review and the second review for each of the one or more selected ECG studies to: (i) identify one or more differences between the first review and the second review, and / or (ii) identify a degree of difference of each of the identified one or more differences between the first review and the second review; generating a report summarizing the differences and / or degree of differences for the one or more selected ECG studies.

This application relates to a supervised pre-training-based multimodal electrocardiogram (ECG) signal representation learning method. The method includes: entity extraction and standardized mapping of clinical text reports to obtain structured diagnostic labels; extraction of ECG features from raw ECG data through cross-channel slicing and routing aggregation using a multi-granularity ECG encoder; inputting the structured diagnostic labels and ECG features into a multimodal fusion network to complete text semantic extraction and cross-modal interaction, obtaining fused features; constructing modality consistency loss and classification loss to jointly optimize model parameters; and inputting the ECG data to be tested into the optimized model to complete diagnostic prediction. This method can fully exploit the value of clinical text, achieve fine-grained alignment of cross-modal features, reduce the computational complexity of long sequences, and take into account the multi-scale features of ECG signals, effectively improving the accuracy, robustness, and generalization ability of ECG analysis models.

The invention provides an electrocardiosignal analysis processing method and system, a medium and equipment. The method comprises the following steps: S1, acquiring electrocardiosignal data to be analyzed; s2, preprocessing the electrocardiogram data to be analyzed to obtain preprocessed electrocardiogram data to be analyzed; s3, performing recognition processing on the to-be-analyzed electrocardiogram data by using a deep learning model to obtain a first recognition result and semantic features generated by the deep learning model in a reasoning process; and S4, analyzing the first recognition result and the semantic features by using an explanatory analysis model, obtaining an extraction result of the fibrillation wave and interval irregular features of the atrial fibrillation in the electrocardiogram data by the deep learning model, and generating an explanation report. The invention provides an electrocardiosignal analysis method capable of automatically identifying atrial fibrillation and giving a result explanation report at the same time, an electrocardiogram feature shielding method is adopted, the problem that electrocardiogram analysis is unreasonable in a conventional mask shielding method is solved, and the effect of shielding any semantic feature of the electrocardiogram is achieved.

Methods and systems for electrocardiogram (ECG) interpretation based on longitudinal medical data are here presented. In one example, a method, comprises, during a development phase of an ECG analysis model, generating a bank of longitudinal electrocardiogram (ECG) features from a plurality of ECGs with known diagnoses; extracting longitudinal criteria from the plurality of ECGs; during a deployment phase of the ECG analysis model, obtaining a plurality of ECGs of a patient, wherein the plurality of ECGs includes a current ECG and one or more historical ECGs; determining, based on the longitudinal criteria, a diagnosis; and transmitting the diagnosis to a user device.

A system and method for determining a diagnosis of an ECG by a rule-based ECG analysis model using criteria extracted by an AI model is provided. The ECG may be received by the rule-based ECG analysis model. Features of the ECG may be determined by a rule-based ECG analysis model. The diagnosis may be determined by the rule-based ECG analysis model using characteristics of the ECG and the criteria extracted by the AI model. The diagnosis may be transmitted.

A system and method for determining, by a rule-based ECG analysis model, a diagnosis of an ECG using criteria extracted by an AI model are provided. An ECG may be received by the rule-based ECG analysis model. Features of the ECG may be determined by the rule-based ECG analysis model. The diagnosis may be determined by the rule-based ECG analysis model using the features of the ECG and the criteria extracted by the AI model. The diagnosis may be transmitted.

Methods and systems for electrocardiogram (ECG) interpretation based on longitudinal medical data are presented herein. In one example, a method includes, during a development phase of an ECG analysis model, generating a set of longitudinal ECG features (306) from a plurality of electrocardiograms (ECGs) with known diagnostics; extracting a longitudinal criterion from the plurality of ECGs (410); during a deployment phase of the ECG analysis model, obtaining a plurality of ECGs (502, 506) of the patient, where the plurality of ECGs includes a current ECG and one or more historical ECGs; determining a diagnosis (510) based on the longitudinal criterion; and sending the diagnosis to the user device (514).

A defibrillator (AED) that uses an ECG analysis model or algorithm that is capable of operating in two different modes. The ECG analysis model is particularly suited for analysis during the period of CPR. Both modes of operation arrive at a shock decision in substantially the same manner, wherein one or more segments of ECG data indicate a shockable cardiac condition. In one mode of operation, once a shock decision is made, the shock decision is irrevocable. In another mode of operation, the shock decision is revocable if one or more subsequent segments of ECG data indicate a no-shock decision. Improved specificity of the model is obtained without over-rejecting shockable ECGs.

The invention relates to the technical field of electrocardiogram analysis, in particular to a method and system for predicting ventricular fibrillation, and the method comprises the steps: obtaining long-time electrocardiogram data of a first preset time length, calculating characteristic parameters and average heart rate of the long-time electrocardiogram data, fitting each characteristic parameter and the average heart rate, and obtaining a characteristic curve corresponding to each characteristic parameter; the method comprises the following steps: acquiring short-time electrocardiogram data of a preset monitoring time length, calculating characteristic parameters and an average heart rate of the short-time electrocardiogram data, calling a characteristic curve of each characteristic parameter, correcting the characteristic parameters of the short-time electrocardiogram data in combination with the average heart rate of the short-time electrocardiogram data, and acquiring standardized characteristic parameters; and inputting the standardized characteristic parameters into the constructed prediction model, and predicting the risk probability of the occurrence of the ventricular fibrillation. According to the scheme, the accuracy of ventricular fibrillation prediction can be improved, and high-risk groups can be helped to carry out early warning on the sudden cardiac arrest risk of the high-risk groups.

An external defibrillator includes therapy delivery circuitry configured to discharge electrotherapy to a patient, a chest compression sensor configured to acquire motion signals during and after administration of CPR to the patient, an ECG sensor configured to acquire ECG signals from the patient, and a processor coupled to the therapy delivery circuitry, the chest compression sensor, and the ECG sensor. The processor is configured to generate first ECG data from ECG signals acquired during a cycle of CPR, generate second ECG data from ECG signals acquired after the cycle of CPR, identify a plurality of temporally overlapping segments in the first ECG data, determine shock / no-shock guidance based on the plurality of temporally overlapping segments, confirm the shock / no-shock guidance based on the second ECG data, and control the therapy delivery circuitry to discharge the electrotherapy where the shock / no-shock guidance is confirmed to specify electrotherapy.

The invention discloses an electrocardiosignal atrial fibrillation detection system and method and electronic equipment, and belongs to the technical field of electrocardiogram analysis. The invention provides a Y-type detection network combining a double-lead coding module and an attention mechanism, which is characterized in that based on a UNet structure, two codes at the same level are respectively connected with decoders at corresponding levels through a space channel mixed attention module; the first lead coding module and the second lead coding module decode step by step after the deep features obtained at the last stage are fused, and a classification result of whether each sampling point in the multi-lead electrocardiosignal to be detected belongs to an atrial fibrillation signal or not can be obtained after the deep features pass through a classifier; on the premise of ensuring the stability and accuracy of atrial fibrillation detection, the time resolution of atrial fibrillation detection is improved, the accurate calibration of the atrial fibrillation starting and ending moments is realized, and the generalization ability of the atrial fibrillation detection on different lead numbers is improved, so that the clinical requirements are better met.