32 results about "Electrodiagnosis" patented technology

The invention provides an ECG (electrocardiogram) diagnosis system which comprises an ECG acquisition system and an ECG analysis and diagnosis system that are connected with each other, wherein the ECG analysis and diagnosis system comprises a DLL (dynamic link library) system, an ECG feature extraction module, and an ECG feature statistical analysis module; and the ECG feature statistical analysis module comprises a plurality of analysis units corresponding to different ECG features; doctors choose the analysis units according to conditions of patients; the ECG feature extraction module takes the corresponding ECG features as ECG feature extraction objects, calls a corresponding dynamic database of the DLL system, to extract the ECG features from ECG data and transmits the ECG features to the ECG feature statistical analysis module; and the ECG feature statistical analysis module conducts statistical analysis on the ECG features for the doctors for diagnosis. The ECG diagnosis system facilitates the quick diagnosis of the doctors, the working efficiency of the doctors is improved, the interaction among the different ECG features is avoided, and the accuracy rate of the analysis is increased. The invention further provides an operating method of the ECG diagnosis system.

An electrode device for cardiological or neurological electrodiagnosis and / or electrotherapy comprises an elongated electrode body (12), at least one electrode (14, 16) in the vicinity of the distal end (24) of the electrode body (12), and an electrode conductor (44) for the electrical connection of the electrode (14, 16). The electrode conductor (44) has a fibrous structure (52) with anisotropic conductivity so that the specific conductivity of the electrode conductor (44) is significantly higher in its longitudinal direction than in its transverse direction.

The invention belongs to the technical field of electrocardiogram detection, and particularly relates to a wearable patient individual electrocardiogram detection method. According to the method, based on a multi-stream multi-scale convolutional neural networks (MM-CNN) model and a multi-lead comprehensive judgment algorithm, detection classifying is performed on an individual electrocardiogram (ECG). The invention proposes an MM-CNN-based single-lead classified detection algorithm to promote the clinical practice of ECG diagnosis; an algorithm that ECG signals of a few minutes are obtained from a specific patient to train a general model into a patient-specific model is proposed; the general model and the patient-specific model have a same network system, so that the efficiency of ECG detection is increased; the invention proposes the multi-lead comprehensive judgment algorithm to permanently classify the ECG signals from the specific patient, thus improving the robustness; and the method has high accuracy and high real-time performance, and is suitable for real-time detection of wearable equipment.

The invention discloses an electrocardiosignal classification model combining a deep learning model and medical field knowledge, achieving an effect of making compliant and reasonable medical interpretation for classification results while realizing accurate classification of arrhythmia. The method comprises data preprocessing, a deep neural network classification model, a domain knowledge model, a joint training model and an interpretable report model. According to the method, clinical diagnosis rules corresponding to medical pathological features are established, and a deep neural network is combined for joint training. The method has the beneficial effects that 1) for current electrocardiogram diagnosis, only a data driving technology is utilized, medical field knowledge is integrated, and parameters of the neural network are finely adjusted under the guidance of the field knowledge, so that the optimization direction of the deep neural network is more stably related to the field; and 2) an interpretable technology is adopted, visual anomaly positioning is formed through a CAM technology, and in combination with field knowledge, the pathological basis of each diagnosis result is interpreted on the semantic level, so that the medical diagnosis result is more credible.

Disclosed is an intelligent electrocardiogram diagnosis system. The intelligent electrocardiogram diagnosis system comprises a detection bed and an electrocardiogram diagnosis device; a support is arranged on the detection bed, and a mechanical arms, a three-dimensional vision system, a disinfection device and a system starting button are arranged on the support; limb conductive electrode mechanisms are arranged on the detection bed, and an electrical control cabinet is arranged at the lower part of the detection bed; the tail ends of the mechanical arms are connected with chest conductive electrode devices; the chest conductive electrode devices and the limb conductive electrode mechanisms are electrically connected with the electrocardiogram diagnosis device correspondingly; and the system starting button, the electrocardiogram diagnosis device, the mechanical arms, the three-dimensional visual system and the disinfection device are electrically connected with an electrical control cabinet. The system has the advantages that the automation, precision and intelligentization of the electrocardiogram diagnosis process are realized by utilizing the technologies of the three-dimensional visual system, the mechanical arms, machine learning and the like, the labor intensity of medical personnel is greatly reduced, and the effect and efficiency of electrocardiogram diagnosis are greatly improved; and in addition, the problems of cross infection between medical staff and a detected person and high disinfection work intensity of electrocardiogram detection equipment, instruments and the like are solved to a great extent; and the electrocardiogram diagnosis efficiency is improved.

The invention relates to a quality control system for an electrocardiogram diagnosis report. The system comprises the steps: obtaining electrocardiogram diagnosis terms contained in a plurality of clinical electrocardiogram conclusions, and constructing a training set and a test set of a recurrent neural network model through preprocessing; taking the kth electrocardiogram diagnosis term containedin each electrocardiogram conclusion in the training set and the test set as input, taking the (k+1)th electrocardiogram diagnosis term as output, and training a recurrent neural network; and utilizing the trained recurrent neural network model to predict the (k+1)th electrocardiogram diagnosis term of the electrocardiogram conclusion in the electrocardiogram diagnosis report to be subjected to quality control, and judging whether the corresponding electrocardiogram diagnosis report has a low-level error. According to the invention, some low-level errors when an electrocardiogram doctor givesa conclusion can be corrected, and intelligent prompts can be provided for clinical diagnosis.

The invention relates to an electrocardio diagnosis model, and the model is characterized by comprising the following steps: S1, collecting N pieces of resting 12-lead electrocardiogram data, and enabling the number of atrial fibrillation electrocardiogram data to be equal to that of non-atrial fibrillation electrocardiogram data; S2, performing preprocessing: if the signal sampling frequency is lower than 200Hz, re-sampling is carried out firstly, so that the sampling frequency reaches 200Hz or above, and then filtering is carried out; S3, training a deep learning network: the deep learning network comprises at least three convolutional layers as a feature extraction module, and at least comprises two full connection layers as a classification module; S4, optimizing parameters of the deep learning network through the loss value of the loss function under minimization, and obtaining all weights and offsets in the whole deep learning network. The invention provides a loss function, which not only reduces the error between the input and the tag, but also restrains the error between the outputs of the feature layers of different types of signals.

The invention relates to an automatic diagnosis method and system for an electrocardiogram diagnosis conclusion. An electrocardiosignal is input into a trained deep learning model to obtain an outputvector representing the diagnosis conclusion, an element in the output vector represents the probability that a corresponding electrocardio term is contained in the diagnosis conclusion. According tothe method, the final diagnosis conclusion of the to-be-diagnosed electrocardiosignal is given in combination with the element values in the output vector and the probability that the electrocardio terms can be combined with one another. By means of the method, automatic diagnosis can be achieved, meanwhile, the situation that mutually exclusive electrocardio terms appear in a diagnosis conclusionis avoided, and the accuracy of electrocardio diagnosis is improved.