CN-115399786-B - Cardiac rhythm recognition method and system, medical device, medical system, and storage medium

CN115399786BCN 115399786 BCN115399786 BCN 115399786BCN-115399786-B

Abstract

The invention is applied to the field of heart rhythm recognition and provides a heart rhythm recognition method and system, medical equipment, a medical system and a storage medium, wherein the method comprises the steps of acquiring first electrocardio characteristic data of a designated first user; based on a preset heart rhythm recognition algorithm and a rule model library of the medical equipment, carrying out heart rhythm recognition on the first electrocardio characteristic data to obtain a first heart rhythm recognition result, wherein the rule model library comprises heart rhythm recognition rules generated based on historical electrocardio event records of a designated first user, obtaining a first defibrillation recognition result according to the first heart rhythm recognition result, obtaining second electrocardio characteristic data of the designated first user if the first defibrillation recognition result is a defibrillation result, carrying out heart rhythm recognition on the second electrocardio characteristic data to obtain a second heart rhythm recognition result of the medical equipment, and obtaining a second defibrillation recognition result based on the heart rhythm recognition result. The invention greatly improves the accuracy of heart rhythm recognition.

Inventors

MA YIJIA

Assignees

苏州维伟思医疗科技有限公司

Dates

Publication Date: 20260508
Application Date: 20220930

Claims (14)

1. A method of heart rhythm recognition comprising the steps of: Acquiring first electrocardiographic feature data of a designated first user; Performing heart rhythm recognition on the first electrocardio characteristic data based on a preset heart rhythm recognition algorithm of medical equipment and a rule model library to obtain a first heart rhythm recognition result, wherein the rule model library comprises heart rhythm recognition rules generated based on historical electrocardio event records of the appointed first user, and the first user is a user wearing the medical equipment; Obtaining a first defibrillation recognition result according to the first heart rhythm recognition result; if the first defibrillation identification result is a defibrillation result, acquiring second electrocardio characteristic data of the appointed first user; based on a preset heart rhythm recognition algorithm of the medical equipment, carrying out heart rhythm recognition on the second electrocardio characteristic data to obtain a second heart rhythm recognition result of the medical equipment; Obtaining a second defibrillation recognition result based on the first and second heart rhythm recognition results, wherein the second defibrillation recognition result comprises a first weight of the first heart rhythm recognition result and a second weight of the second heart rhythm recognition result, a final heart rhythm recognition result obtained by weighting and averaging the first and second heart rhythm recognition results, and a second defibrillation recognition result obtained based on the final heart rhythm recognition result; Wherein, the rule model library is formed by the following modes: Acquiring historical electrocardiographic event records of medical equipment, wherein each historical electrocardiographic event record comprises historical electrocardiographic feature data of the appointed first user and a second defibrillation recognition result of the medical equipment, the second defibrillation recognition result is obtained after heart rhythm recognition is carried out based on a preset heart rhythm recognition algorithm and second electrocardiographic feature data, and the historical electrocardiographic feature data comprises electrocardiographic feature data of the first user at the occurrence time of a historical electrocardiographic event, and electrocardiographic feature data of the first user in a first time period before the occurrence time of the historical electrocardiographic event and in a second time period after the occurrence time of the historical electrocardiographic event; Transmitting the historical electrocardiographic event record to a processing device; receiving heart rhythm recognition rules from the processing device, each heart rhythm recognition rule including an electrocardiographic feature condition and a standard defibrillation recognition result, the electrocardiographic feature condition being generated based on historical electrocardiographic feature data of the designated first user; The heart rhythm recognition rules are stored in a rule model library in the medical device.
2. The method of claim 1, wherein the processing device is configured to form or automatically update the rhythm recognition rules using the steps of: Receiving the historical electrocardiographic event record; Obtaining a standard defibrillation recognition result corresponding to the historical electrocardiographic event record; Acquiring the rhythm recognition rule according to the historical electrocardiographic event record and the corresponding standard defibrillation recognition result; And automatically updating the rhythm recognition rule when a preset condition is met each time, wherein the preset condition is one of reaching a specific time, reaching a specific amount of data and receiving a specific instruction.
3. The method for recognizing cardiac rhythm according to claim 2, wherein the processing device comprises a processing terminal and a processing server, and the processing device obtains the standard defibrillation recognition result corresponding to the historical electrocardiographic event record by: The processing terminal displays the received historical electrocardio event record, receives a plurality of defibrillation recognition results input by a plurality of second users, generates standard defibrillation recognition results based on the plurality of defibrillation recognition results, and sends the historical electrocardio event record and the standard defibrillation recognition results to the processing server, or The processing terminal sends the received historical electrocardio event record to the processing server, the processing server pushes the received historical electrocardio event record to a plurality of second users, receives a plurality of defibrillation recognition results input by the plurality of second users, generates standard defibrillation recognition results based on the plurality of defibrillation recognition results, and stores the historical electrocardio event record and the standard defibrillation recognition results.
4. The method of claim 3, wherein generating a standard defibrillation recognition result based on a number of defibrillation recognition results comprises determining a defibrillation recognition result having a result ratio greater than a preset ratio threshold as the standard defibrillation recognition result.
5. A method of heart rhythm recognition according to claim 3 wherein the processing device is configured to obtain the heart rhythm recognition rules by: The processing server filters the historical electrocardiographic event records to obtain misjudgment records of inconsistent second defibrillation recognition results and standard defibrillation recognition results of the medical equipment; The processing server pushes the misjudgment record of the appointed first user to a second user; the processing server obtains the rhythm recognition rule added by the second user.
6. The method of claim 4, wherein the processing device is configured to obtain the rhythm recognition rule using the steps of: The processing server obtains the historical electrocardio event record and the standard defibrillation identification result of the appointed first user; The processing server filters and obtains misjudgment records of inconsistent second sub-defibrillation identification results and standard defibrillation identification results of the medical equipment; the processing server determines whether to generate a pre-added rhythm recognition rule based on the historical electrocardio characteristic data corresponding to the erroneous judgment record; the processing server pushes the generated pre-added rhythm recognition rule to a second user, and takes the pre-added rhythm recognition rule as a confirmed added rhythm recognition rule when receiving a confirmation instruction of the second user, or takes the modified pre-added rhythm recognition rule as a confirmed added rhythm recognition rule when receiving a modification instruction of the second user.
7. The method of claim 6, wherein the processing server determines whether to generate a pre-added rhythm recognition rule based on historical electrocardiographic feature data corresponding to the erroneous determination record, comprising the steps of: The processing server classifies the misjudgment records according to the standard defibrillation recognition result to obtain a first misjudgment record capable of defibrillation and a second misjudgment record not capable of defibrillation; for the first misjudgment record and the second misjudgment record, respectively arranging and combining all characteristic values in the historical electrocardio characteristic data; Calculating the correlation coefficient of each combination and the erroneous judgment result respectively; If the correlation coefficient of at least one combination is larger than a preset correlation threshold, determining to generate a pre-added rhythm recognition rule, taking the characteristic value of the combination as an electrocardio characteristic condition, and determining the category of the standard defibrillation recognition result according to whether the historical electrocardio characteristic data belongs to a first misjudgment record or a second misjudgment record.
8. The method of claim 6, further comprising the step of, after said pre-added rhythm recognition rule is used as a confirmation added rhythm recognition rule: The processing server calculates the probability of misjudgment of the historical electrocardio characteristic data conforming to the rhythm recognition rule added by confirmation based on the historical electrocardio characteristic data of the appointed first user, the second defibrillation recognition result of the medical equipment and the standard defibrillation recognition result; and the processing server sets a third weight value of the rhythm recognition rule according to the probability of misjudgment.
9. The method for recognizing cardiac rhythm according to claim 8, wherein the performing cardiac rhythm recognition on the first cardiac electrical feature data based on the preset cardiac rhythm recognition algorithm and rule model library of the medical device to obtain a first cardiac rhythm recognition result of the medical device comprises the following steps: Acquiring a first sub-heart rhythm recognition result based on the first electrocardio characteristic data and a preset heart rhythm recognition algorithm; determining whether the first electrocardio characteristic data is matched with a certain rhythm recognition rule in the rule model library, if so, determining a second sub-rhythm recognition result according to a standard defibrillation recognition result of the matched rhythm recognition rule; Acquiring a third weight value of the matched rhythm recognition rule, taking the third weight value as a third weight value of a second sub-rhythm recognition result, and calculating a fourth weight value of the first sub-rhythm recognition result based on the third weight value; And weighting and averaging the first sub-rhythm recognition result and the second sub-rhythm recognition result to obtain a first rhythm recognition result.
10. The method of claim 1, wherein the first electrocardiographic feature data comprises at least one of an electrocardiographic signal map acquired in real-time and an electrocardiographic feature parameter, and the second electrocardiographic feature data comprises at least one of an electrocardiographic signal map acquired in real-time and an electrocardiographic feature parameter.
11. A heart rhythm recognition system, the system comprising: the first acquisition module is used for acquiring first electrocardio characteristic data of a designated first user; The first judging module is used for carrying out heart rhythm recognition on the first electrocardio characteristic data based on a preset heart rhythm recognition algorithm of the medical equipment and a rule model library to obtain a first heart rhythm recognition result and obtain a first defibrillation recognition result according to the first heart rhythm recognition result, wherein the rule model library comprises heart rhythm recognition rules generated based on the historical electrocardio event records of the appointed first user, and the first user is a user wearing the medical equipment; the second acquisition module is used for acquiring second electrocardio characteristic data of the appointed first user if the first defibrillation identification result is a defibrillation result; The second judging module is used for carrying out heart rhythm recognition on the second electrocardio characteristic data based on a preset heart rhythm recognition algorithm of the medical equipment to obtain a second heart rhythm recognition result of the medical equipment and obtaining a second defibrillation recognition result based on the first heart rhythm recognition result and the second heart rhythm recognition result, and comprises the steps of obtaining a first weight of the first heart rhythm recognition result and a second weight of the second heart rhythm recognition result, carrying out weighted averaging on the first heart rhythm recognition result and the second heart rhythm recognition result to obtain a final heart rhythm recognition result, and obtaining a second defibrillation recognition result based on the final heart rhythm recognition result; Wherein, the rule model library is formed by the following modes: Acquiring historical electrocardiographic event records of medical equipment, wherein each historical electrocardiographic event record comprises historical electrocardiographic feature data of the appointed first user and a second defibrillation recognition result of the medical equipment, the second defibrillation recognition result is obtained after heart rhythm recognition is carried out based on a preset heart rhythm recognition algorithm and second electrocardiographic feature data, and the historical electrocardiographic feature data comprises electrocardiographic feature data of the first user at the occurrence time of a historical electrocardiographic event, and electrocardiographic feature data of the first user in a first time period before the occurrence time of the historical electrocardiographic event and in a second time period after the occurrence time of the historical electrocardiographic event; Transmitting the historical electrocardiographic event record to a processing device; receiving heart rhythm recognition rules from the processing device, each heart rhythm recognition rule including an electrocardiographic feature condition and a standard defibrillation recognition result, the electrocardiographic feature condition being generated based on historical electrocardiographic feature data of the designated first user; The heart rhythm recognition rules are stored in a rule model library in the medical device.
12. A medical device, comprising: A processor; a memory in which a preset heart rhythm recognition algorithm, a rule model library, and executable instructions of the processor are stored; a communication module for communicating with the processing device; wherein the processor is configured to perform the steps of the heart rhythm recognition method of any one of claims 1 to 10 via execution of the executable instructions.
13. A medical system, comprising: The processing device is used for receiving the historical electrocardio event record of the medical device, acquiring the standard defibrillation recognition result corresponding to the historical electrocardio event record, acquiring the rhythm recognition rule according to the historical electrocardio event record and the corresponding standard defibrillation recognition result, and The medical device of claim 12.
14. A computer-readable storage medium storing a program, characterized in that the program when executed by a processor implements the steps of the heart rhythm recognition method according to any one of claims 1 to 10.

Description

Cardiac rhythm recognition method and system, medical device, medical system, and storage medium Technical Field The present invention relates to the field of data processing technologies, and in particular, to a method and system for identifying a heart rhythm, a medical device, a medical system, and a storage medium. Background Sudden cardiac arrest is a life threatening emergency that may occur to all ages. Many defibrillation devices are currently available for timely treatment of patients. The cardiac defibrillation device performs cardiac rhythm recognition by collecting cardiac electrical data of the patient and determines whether electrical defibrillation therapy needs to be performed according to the cardiac rhythm recognition result. The existing heart rhythm recognition flow comprises the steps of monitoring an electrocardiosignal of a patient, judging whether a malignant heart rhythm event occurs for the first time, if not, continuing to monitor the electrocardiosignal, and if the malignant heart rhythm event occurs, starting to precharge a high-voltage capacitor. After the precharge is completed, the algorithm determines a second time whether a malignant cardiac rhythm event persists. If the malignant cardiac rhythm event persists, the patient is subjected to electrical defibrillation therapy, and if the malignant cardiac rhythm event spontaneously ceases, the electrical defibrillation therapy is abandoned and the monitoring of the electrocardiographic signal is continued. Although current heart rhythm recognition algorithms already possess a high recognition accuracy, the development and optimization of existing heart rhythm recognition algorithms is realized based on a common data set. Due to the data integrity of the generic data set, the accuracy of the heart rhythm recognition algorithm may have some impact. The conventional solution is to enhance the robustness of the algorithm through continuous iteration and upgrading of the algorithm. However, once some medical devices are put into use, the upgrades to the algorithms are often directed only to subsequently released products for various security considerations. The existing algorithm is solidified in the host when the implantable cardioverter-defibrillator leaves the factory, the algorithm can not be upgraded and optimized after the host is implanted into the body, only a small part of parameters can be finely adjusted through the program control instrument, and no better solution exists for the algorithm upgrading requirement after the product is marketed. In addition, different individuals of patients may have specific heart rhythm characteristics, and may have certain differences from the general data set. If the existing rhythm recognition algorithm is uniformly adopted, misjudgment can be generated for some special rhythm characteristics of a patient, and the situation of false defibrillation and missed defibrillation can be caused. In particular, the erroneous judgment of the first heart rhythm recognition brings inconvenience to the user on the one hand, and on the other hand, repeated precharge is caused, electric energy loss in the precharge process is caused, and the service life of medical equipment with limited electric energy is greatly shortened. It should be noted that the information disclosed in the foregoing background section is only for enhancement of understanding of the background of the invention and thus may include information that does not form the prior art that is already known to those of ordinary skill in the art. Disclosure of Invention Aiming at the problems in the prior art, the invention aims to provide a heart rhythm recognition method and system, medical equipment, a medical system and a storage medium, and the heart rhythm recognition accuracy is greatly improved by combining a specific rule model library aiming at a specified user and a preset heart rhythm recognition algorithm. The embodiment of the invention provides a heart rhythm recognition method, which comprises the following steps: Acquiring first electrocardiographic feature data of a designated first user; Based on a preset heart rhythm recognition algorithm of medical equipment and a rule model library, carrying out heart rhythm recognition on the first electrocardio characteristic data to obtain a first heart rhythm recognition result, wherein the rule model library comprises heart rhythm recognition rules generated based on the historical electrocardio event records of the appointed first user; Obtaining a first defibrillation recognition result according to the first heart rhythm recognition result; if the first defibrillation identification result is a defibrillation result, acquiring second electrocardio characteristic data of the appointed first user; based on a preset heart rhythm recognition algorithm of the medical equipment and/or the rule model library, carrying out heart rhythm recognition on the second electrocardio character