A method and device for constructing an aortic dissection identification model and an electronic device

Abstract

The application provides a construction method and device of an aortic dissection identification model and electronic equipment, relates to the technical field of aortic dissection identification, and comprises the following steps: comparing the pulse oximetry waveforms of the extremities of a training object with standard pulse oximetry waveforms to obtain waveform difference comparison results; determining the amplitudes and blood flow arrival times of the pulse oximetry waveforms of the extremities of the training object based on the pulse oximetry waveforms of the extremities of the training object; obtaining correlation factors between the extremities of the training object based on the pulse oximetry waveforms of the extremities of the training object; performing time domain conversion on the pulse oximetry waveforms of the extremities of the training object to obtain periodic characteristic description indexes; and constructing an aortic dissection identification model based on the waveform difference comparison results, the amplitudes of the pulse oximetry waveforms of the extremities of the training object, the blood flow arrival times of the pulse oximetry waveforms of the extremities of the training object, the correlation factors between the extremities of the training object and the periodic characteristic description indexes. The application can provide a non-invasive and rapid aortic dissection identification model.

Description

Technical Field

[0001] This invention relates to the field of Internet technology, and in particular to a method, apparatus and electronic device for constructing an aortic dissection identification model. Background Technology

[0002] With the increasing aging population in my country, the incidence of acute cardiovascular diseases is rising, and the number of patients seeking medical attention for acute chest pain is also increasing year by year. For patients with acute chest pain, we often need to differentiate the cause, determining whether it is coronary artery disease or another condition. Among chest pain caused by non-coronary artery disease, the most critical is aortic dissection. Although its incidence is lower than that of coronary heart disease, it is extremely dangerous. These patients are at risk of dissection rupture at any time, and once ruptured, it is difficult to save them, resulting in a very high mortality rate. Timely surgical treatment is crucial to saving these patients. The diagnosis of aortic dissection mainly relies on CT angiography, which is invasive and costly in terms of time and money, making it difficult to perform this examination on every patient with chest pain. Furthermore, if aortic dissection is ultimately ruled out, performing CT angiography would consume time that would otherwise be spent addressing other causes. Therefore, a non-invasive and rapid tool for identifying aortic dissection is needed.

[0003] Therefore, a method, device, and electronic device for constructing an aortic dissection identification model are proposed. Summary of the Invention

[0004] This specification provides a method, apparatus, and electronic device for constructing an aortic dissection identification model, which can provide a non-invasive and rapid aortic dissection identification model.

[0005] This specification provides a method for constructing an aortic dissection identification model, including:

[0006] Obtain the pulse oxygenation waveforms of the extremities of the training subjects;

[0007] The pulse oxygenation waveforms of the extremities of the training subjects were compared with standard pulse oxygenation waveforms to obtain waveform difference comparison results.

[0008] The amplitude and blood flow arrival time of the pulse blood oxygen waveform of the extremities of the training subjects were determined respectively based on the pulse blood oxygen waveform of the extremities.

[0009] Based on the pulse oxygenation waveforms of the extremities of the training subjects, the correlation factors between the limbs were obtained;

[0010] The time-domain transformation of the pulse blood oxygen waveform of the limbs of the training subjects was performed to obtain the periodic feature description index.

[0011] Based on the waveform difference comparison results, the amplitude of the pulse blood oxygen waveform of the limbs, the blood flow arrival time of the pulse blood oxygen waveform of the limbs, the correlation factors between the four sites, and the periodic feature description index, an aortic dissection identification model is constructed.

[0012] Optionally, before acquiring the pulse oxygenation waveforms of the extremities of the training subject, the following steps are included:

[0013] Obtain the pulse oxygenation waveforms of the patient's extremities and the results of aortic dissection identification;

[0014] Determine whether the acquisition channels for the patient's peripheral pulse oxygenation waveforms and aortic dissection identification results meet the preset channels;

[0015] When the acquisition channel of the patient's peripheral pulse oximetry waveform and aortic dissection identification result meets the preset channel, the patient's peripheral pulse oximetry waveform and aortic dissection identification result that meets the preset channel will be used as the target research object;

[0016] The target research objects are divided according to a preset ratio to obtain training objects and verification objects.

[0017] Optionally, comparing the pulse oximetry waveforms of the limbs of the training subject with standard pulse oximetry waveforms to obtain waveform difference comparison results includes:

[0018] A high-order polynomial fit was performed on the diastolic waveform of the pulse oxygenation waveform of the extremities of the training subjects to obtain the goodness of fit.

[0019] Determine whether the goodness of fit meets the preset goodness of fit;

[0020] When the goodness of fit meets the preset goodness of fit, waveform difference comparison results are obtained based on the pulse blood oxygen waveform of the limbs of the training object.

[0021] Optionally, when the goodness of fit meets the preset goodness of fit, obtaining waveform difference comparison results based on the pulse blood oxygen waveforms of the limbs of the training object includes:

[0022]

[0023] Where N is the notch coefficient, A is the peak value, and B is the trough value.

[0024] Optionally, after constructing the aortic dissection identification model based on the waveform difference comparison results, the amplitude of the pulse oxygenation waveforms of the limbs, the blood flow arrival time of the pulse oxygenation waveforms of the limbs, the correlation factors between the four sites, and the periodic feature descriptive index, the following steps are included:

[0025] Obtain the pulse oxygenation waveforms of the extremities of the verification object and the results of its aortic dissection identification;

[0026] The pulse oxygenation waveforms of the extremities of the verification object are input into the aortic dissection identification model to obtain the model identification results;

[0027] Determine whether the model identification result is consistent with the aortic dissection identification result of the verification object;

[0028] When the model recognition result is inconsistent with the aortic dissection recognition result of the verification object, return to obtaining the pulse oxygenation waveform of the patient's limbs and its aortic dissection recognition result, until the model recognition result is consistent with the aortic dissection recognition result of the verification object.

[0029] This specification provides a device for constructing an aortic dissection identification model, comprising:

[0030] The first acquisition module is used to acquire the pulse blood oxygen waveforms of the extremities of the training subject.

[0031] The comparison module is used to compare the pulse blood oxygen waveform of the extremities of the training subject with the standard pulse blood oxygen waveform to obtain the waveform difference comparison result;

[0032] The first determining module is used to determine the amplitude and blood flow arrival time of the pulse blood oxygen waveform of the extremities based on the pulse blood oxygen waveform of the training object.

[0033] The second determining module is used to obtain the correlation factors between the four limbs based on the pulse blood oxygen waveform of the limbs of the training object.

[0034] The conversion module is used to perform time-domain conversion on the pulse blood oxygen waveform of the extremities of the training object to obtain the periodic feature descriptive index.

[0035] A construction module is used to construct an aortic dissection identification model based on the waveform difference comparison results, the amplitude of the pulse blood oxygen waveform of the limbs, the blood flow arrival time of the pulse blood oxygen waveform of the limbs, the correlation factors between the four sites, and the periodic feature description index.

[0036] Optionally, before the first acquisition module, the following is included:

[0037] The second acquisition module is used to acquire the pulse oxygenation waveforms of the patient's limbs and the results of aortic dissection identification.

[0038] The first judgment module is used to determine whether the acquisition channels of the patient's limb pulse blood oxygen waveform and aortic dissection identification results meet the preset channels.

[0039] The third determining module is used to select the patient's limb pulse oxygen waveform and aortic dissection identification results as the target research object when the acquisition channel of the patient's limb pulse oxygen waveform and aortic dissection identification results meets the preset channel.

[0040] The partitioning module is used to partition the target research object based on a preset ratio to obtain training objects and validation objects.

[0041] Optionally, the comparison module includes:

[0042] The fitting unit is used to perform high-order polynomial fitting on the diastolic waveform of the pulse blood oxygen waveform of the limbs of the training object to obtain the goodness of fit.

[0043] A judgment unit is used to determine whether the goodness of fit meets a preset goodness of fit.

[0044] The determining unit is used to obtain waveform difference comparison results based on the pulse blood oxygen waveform of the limbs of the training object when the goodness of fit meets the preset goodness of fit.

[0045] Optionally, the determining unit includes:

[0046]

[0047] Where N is the notch coefficient, A is the peak value, and B is the trough value.

[0048] Optionally, following the building module, the following is included:

[0049] The third acquisition module is used to acquire the pulse blood oxygen waveforms of the extremities of the verification object and the identification results of its aortic dissection.

[0050] The input module is used to input the pulse blood oxygen waveform of the extremities of the verification object into the aortic dissection identification model to obtain the model identification result;

[0051] The second judgment module is used to determine whether the model recognition result is consistent with the aortic dissection recognition result of the verification object;

[0052] The return module is used to return the obtained pulse oxygen waveform of the patient's limbs and its aortic dissection identification result when the model identification result is inconsistent with the aortic dissection identification result of the verification object, until the model identification result is consistent with the aortic dissection identification result of the verification object.

[0053] This specification also provides an electronic device, wherein the electronic device includes:

[0054] Processor; and,

[0055] A memory that stores computer-executable instructions, which, when executed, cause the processor to perform any of the methods described above.

[0056] This specification also provides a computer-readable storage medium that stores one or more programs that, when executed by a processor, implement any of the methods described above.

[0057] In this manual, the acquisition of pulse oximetry signals through the aortic dissection identification model is non-invasive and painless. The finger clip-type pulse oximetry sensor used can be reused after simple wiping and disinfection. The signal acquisition process is very fast and can provide timely dissection warning. Attached Figure Description

[0058] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0059] Figure 1 A schematic diagram illustrating the principle of a method for constructing an aortic dissection identification model provided in the embodiments of this specification;

[0060] Figure 2 A schematic diagram illustrating the principle of step S120 in a method for constructing an aortic dissection identification model provided in an embodiment of this specification;

[0061] Figure 3 A schematic diagram illustrating the principle of step S150 in a method for constructing an aortic dissection identification model provided in an embodiment of this specification;

[0062] Figure 4 A schematic diagram of a device for constructing an aortic dissection identification model provided in the embodiments of this specification;

[0063] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this specification;

[0064] Figure 6 This is a schematic diagram of a computer-readable medium provided for embodiments of this specification. Detailed Implementation

[0065] The following description is intended to disclose the present invention and enable those skilled in the art to implement it. The preferred embodiments described below are merely examples, and other obvious variations will occur to those skilled in the art. The basic principles of the invention defined in the following description can be applied to other embodiments, modifications, improvements, equivalents, and other technical solutions that do not depart from the spirit and scope of the invention.

[0066] The following is in conjunction with the appendix Figure 1-6 Exemplary embodiments of the invention will be described more fully here. However, exemplary embodiments can be implemented in many forms and should not be construed as limiting the invention to the embodiments set forth herein. Rather, these exemplary embodiments are provided to make the invention more comprehensive and complete, and to facilitate a full communication of the inventive concept to those skilled in the art. The same reference numerals in the figures denote the same or similar elements, components, or parts, and therefore repeated descriptions of them are omitted.

[0067] Subject to the technical concept of this invention, the features, structures, characteristics or other details described in a particular embodiment may be combined in one or more other embodiments in a suitable manner.

[0068] In the description of specific embodiments, the features, structures, characteristics, or other details described in this invention are intended to enable those skilled in the art to fully understand the embodiments. However, it is not excluded that those skilled in the art can practice the technical solutions of this invention without one or more of the specific features, structures, characteristics, or other details.

[0069] The flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations / steps, nor do they necessarily have to be performed in the described order. For example, some operations / steps can be broken down, while others can be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

[0070] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0071] The terms “and / or” or “and / or” include all combinations of any one or more of the listed items.

[0072] Figure 1 This is a schematic diagram illustrating the principle of a method for constructing an aortic dissection identification model provided in an embodiment of this specification. The method may include:

[0073] S110: Obtain the pulse oxygenation waveform of the extremities of the training subject;

[0074] In the specific implementation of this specification, four blood oxygen signal sensors are used to collect pulse blood oxygen signals from four parts of the training subject: the right hand, left hand, right foot, and left foot. These signals are then converted into pulse blood oxygen waveforms of the training subject's limbs by a data conversion module.

[0075] Optionally, before S110, the following steps are included:

[0076] Obtain the pulse oxygenation waveforms of the patient's extremities and the results of aortic dissection identification;

[0077] Determine whether the acquisition channels for the patient's peripheral pulse oxygenation waveforms and aortic dissection identification results meet the preset channels;

[0078] When the acquisition channel of the patient's peripheral pulse oximetry waveform and aortic dissection identification result meets the preset channel, the patient's peripheral pulse oximetry waveform and aortic dissection identification result that meets the preset channel will be used as the target research object;

[0079] The target research objects are divided according to a preset ratio to obtain training objects and verification objects.

[0080] In the specific implementation of this specification, pulse oximetry signals from four locations—the patient's right hand, left hand, right foot, and left foot—are collected using four pulse oximetry sensors. These signals are then converted into pulse oximetry waveforms of the extremities of the training subjects using a data conversion module. The patient's aortic dissection identification result is obtained from their follow-up records. Simultaneously, the acquisition channels for the patient's extremity pulse oximetry waveforms and aortic dissection identification results are assessed to determine if they meet preset criteria. These criteria include, but are not limited to, the absence of equipment malfunction and compliance with acquisition procedures. When the acquisition channels meet the preset criteria, the patient's extremity pulse oximetry waveforms and aortic dissection identification results that meet these criteria are used as the target research objects for model construction. The target research objects are divided according to a preset ratio, such as 7:3, to obtain training and validation subjects.

[0081] S120: Compare the pulse oxygenation waveforms of the extremities of the training subject with the standard pulse oxygenation waveforms to obtain waveform difference comparison results;

[0082] Reference Figure 2 Optionally, S120 includes:

[0083] A high-order polynomial fit was performed on the diastolic waveform of the pulse oxygenation waveform of the extremities of the training subjects to obtain the goodness of fit.

[0084] Determine whether the goodness of fit meets the preset goodness of fit;

[0085] When the goodness of fit meets the preset goodness of fit, waveform difference comparison results are obtained based on the pulse blood oxygen waveform of the limbs of the training object.

[0086] In the specific implementation of this specification, high-order polynomial fitting involves constructing a polynomial approximation function from piecewise discrete data. The function expression replaces the discrete data, and within the segmented intervals, the fitted function curve is smooth and continuous, thus "smoothing" the discrete data. High-order polynomial fitting is applied to the diastolic waveform of the pulse oxygenation waveform of the extremities of the training subject to obtain the goodness-of-fit R. 2 Determine R 2 Is R greater than 0.99? 2 If the value is greater than 0.99, the pulse oxygenation waveforms of the extremities of the training subjects are compared with those of the standard extremities to obtain the waveform difference results.

[0087] Optionally, when the goodness of fit meets the preset goodness of fit, obtaining waveform difference comparison results based on the pulse blood oxygen waveforms of the limbs of the training object includes:

[0088]

[0089] Where N is the notch coefficient, A is the peak value, and B is the trough value.

[0090] In the specific implementation of this specification, the peak value and trough value of the pulse blood oxygen waveform of the limbs of the training subject are read. Based on the conversion of the peak value (corresponding to the beginning of diastole) and the trough value (corresponding to the beginning of the systole of the next cycle), the notch coefficient is obtained. The notch coefficient is an indicator that reflects the degree of waveform difference, that is, the waveform difference comparison result.

[0091] S130: Determine the amplitude and blood flow arrival time of the pulse blood oxygen waveform of the extremities based on the pulse blood oxygen waveform of the training object.

[0092] In the specific implementation of this specification, the amplitude is the difference between the peak value and the trough value, which is used to reflect the intensity of blood flow reaching each part; the trough value of each waveform is used as the time calculation base point, and the right hand signal is used as the calibration, and its T1=0 is set, and then the arrival times T2, T3 and T4 corresponding to the left hand, left foot and right foot are calculated to reflect the order of blood flow reaching each part.

[0093] S140: Based on the pulse oxygenation waveforms of the extremities of the training subjects, obtain the correlation factors between the limbs;

[0094] In the specific implementation of this specification, the consistency between the signals from the four parts of the right hand (ra), left hand (la), left foot (lf), and right foot (rf) can be calculated to generate six Pearson correlation coefficients.

[0095] left hand <![CDATA[R 2 _day_day]]> <![CDATA[R 2 _la_fr]]> <![CDATA[R 2 _la_lf]]> left foot <![CDATA[R 2 _lf_ra]]> <![CDATA[R 2 _lf_rf]]> right foot <![CDATA[R 2 _rf_ra]]>

[0096] Reference Figure 3 S150: Perform time-domain transformation on the pulse blood oxygen waveform of the extremities of the training object to obtain the periodic feature description index;

[0097] In the specific implementation of this specification, all waveforms are subjected to Fourier transform, converted into Fourier series, and the time-domain features are transformed into frequency-domain features. The formula for Fourier series fitting is:

[0098] y=a0+a1 cos(xw)+b1sin(xw)+a2cos(2xw)+b2sin(2xw)+a3cos(4xw)+b3sin(3xw)+a4cos(4xw)+b4sin(4xw)

[0099] Through fourth-order decomposition, each part of the signal generates 10 coefficients: a0, a1, a2, a3, a4, b1, b2, b3, b4, and w10, which are used to describe the periodic characteristics.

[0100] S160: Based on the waveform difference comparison results, the amplitude of the pulse blood oxygen waveform of the limbs, the blood flow arrival time of the pulse blood oxygen waveform of the limbs, the correlation factors between the four sites, and the periodic feature description index, an aortic dissection identification model is constructed.

[0101] In the specific implementation of this specification, the waveform difference comparison results, the amplitude of the pulse oxygenation waveforms of the extremities, the blood flow arrival time of the pulse oxygenation waveforms of the extremities, the correlation factors between the limbs and the periodic feature descriptor index are used to evaluate the importance of variables using the ex post facto interpretation framework—Shapley Additive exPlanations (SHAP) value. The recursive feature elimination (RFE) algorithm is used to select key features. The hyperparameters are optimized using open-source deep learning frameworks such as CatBoost (github.com / catboost) and other automated deep learning toolkits to obtain the aortic dissection identification model.

[0102] Optionally, after S160, the following steps are included:

[0103] Obtain the pulse oxygenation waveforms of the extremities of the verification object and the results of its aortic dissection identification;

[0104] The pulse oxygenation waveforms of the extremities of the verification object are input into the aortic dissection identification model to obtain the model identification results;

[0105] Determine whether the model identification result is consistent with the aortic dissection identification result of the verification object;

[0106] When the model recognition result is inconsistent with the aortic dissection recognition result of the verification object, return to obtaining the pulse oxygenation waveform of the patient's limbs and its aortic dissection recognition result, until the model recognition result is consistent with the aortic dissection recognition result of the verification object.

[0107] In the specific implementation of this specification, the pulse blood oxygen waveforms of the extremities of the verification subject and the aortic dissection identification results are used for the verification of the aortic dissection identification model. If the verification results are not ideal, the pulse blood oxygen waveforms of the extremities of the patient and the aortic dissection identification results are re-acquired, and the aortic dissection identification model is reconstructed.

[0108] In this manual, the acquisition of pulse oximetry signals through the aortic dissection identification model is non-invasive and painless. The finger clip-type pulse oximetry sensor used can be reused after simple wiping and disinfection. The signal acquisition process is very fast and can provide timely dissection warning.

[0109] Figure 4 This is a schematic diagram of a device for constructing an aortic dissection identification model provided in an embodiment of this specification. The device may include:

[0110] The first acquisition module 10 is used to acquire the pulse blood oxygen waveform of the extremities of the training object;

[0111] The comparison module 20 is used to compare the pulse blood oxygen waveform of the extremities of the training subject with the standard pulse blood oxygen waveform to obtain the waveform difference comparison result;

[0112] The first determining module 30 is used to determine the amplitude and blood flow arrival time of the pulse blood oxygen waveform of the extremities based on the pulse blood oxygen waveform of the training object.

[0113] The second determining module 40 is used to obtain the correlation factors between the four limbs based on the pulse blood oxygen waveform of the limbs of the training object.

[0114] The conversion module 50 is used to perform time-domain conversion on the pulse blood oxygen waveform of the limbs of the training object to obtain the periodic feature description index.

[0115] The construction module 60 is used to construct an aortic dissection identification model based on the waveform difference comparison results, the amplitude of the pulse blood oxygen waveform of the limbs, the blood flow arrival time of the pulse blood oxygen waveform of the limbs, the correlation factors between the four parts, and the periodic feature description index.

[0116] Optionally, before the first acquisition module 10, the following are included:

[0117] The second acquisition module is used to acquire the pulse oxygenation waveforms of the patient's limbs and the results of aortic dissection identification.

[0118] The first judgment module is used to determine whether the acquisition channels of the patient's limb pulse blood oxygen waveform and aortic dissection identification results meet the preset channels.

[0119] The third determining module is used to select the patient's limb pulse oxygen waveform and aortic dissection identification results as the target research object when the acquisition channel of the patient's limb pulse oxygen waveform and aortic dissection identification results meets the preset channel.

[0120] The partitioning module is used to partition the target research object based on a preset ratio to obtain training objects and validation objects.

[0121] Optionally, the comparison module 20 includes:

[0122] The fitting unit is used to perform high-order polynomial fitting on the diastolic waveform of the pulse blood oxygen waveform of the limbs of the training object to obtain the goodness of fit.

[0123] A judgment unit is used to determine whether the goodness of fit meets a preset goodness of fit.

[0124] The determining unit is used to obtain waveform difference comparison results based on the pulse blood oxygen waveform of the limbs of the training object when the goodness of fit meets the preset goodness of fit.

[0125] Optionally, the determining unit includes:

[0126]

[0127] Where N is the notch coefficient, A is the peak value, and B is the trough value.

[0128] Optionally, after the building module 60, it includes:

[0129] The third acquisition module is used to acquire the pulse blood oxygen waveforms of the extremities of the verification object and the identification results of its aortic dissection.

[0130] The input module is used to input the pulse blood oxygen waveform of the extremities of the verification object into the aortic dissection identification model to obtain the model identification result;

[0131] The second judgment module is used to determine whether the model recognition result is consistent with the aortic dissection recognition result of the verification object;

[0132] The return module is used to return the obtained pulse oxygen waveform of the patient's limbs and its aortic dissection identification result when the model identification result is inconsistent with the aortic dissection identification result of the verification object, until the model identification result is consistent with the aortic dissection identification result of the verification object.

[0133] The functions of the apparatus in this embodiment have been described in the above method embodiments. Therefore, for any parts not detailed in this embodiment, please refer to the relevant descriptions in the foregoing embodiments, which will not be repeated here.

[0134] Based on the same inventive concept, embodiments of this specification also provide an electronic device.

[0135] The following describes embodiments of the electronic device of the present invention, which can be considered as specific implementations of the methods and apparatus embodiments of the present invention described above. Details described in the embodiments of the electronic device of the present invention should be considered as supplements to the methods or apparatus embodiments described above; details not disclosed in the embodiments of the electronic device of the present invention can be implemented with reference to the methods or apparatus embodiments described above.

[0136] Figure 5 This is a schematic diagram of an electronic device provided as an embodiment of this specification. Refer to the following... Figure 3 The electronic device 300 according to this embodiment of the present invention will be described. Figure 5 The electronic device 300 shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of the present invention.

[0137] like Figure 5 As shown, the electronic device 300 is presented in the form of a general-purpose computing device. The components of the electronic device 300 may include, but are not limited to: at least one processing unit 310, at least one storage unit 320, a bus 330 connecting different system components (including storage unit 320 and processing unit 310), a display unit 340, etc.

[0138] The storage unit stores program code that can be executed by the processing unit 310, causing the processing unit 310 to perform the steps described in the processing method section of this specification according to various exemplary embodiments of the present invention. For example, the processing unit 310 can perform, for example... Figure 1 The steps are shown.

[0139] The storage unit 320 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 3201 and / or a cache storage unit 3202, and may further include a read-only memory unit (ROM) 3203.

[0140] The storage unit 320 may also include a program / utility 3204 having a set (at least one) program module 3205, such program module 3205 including but not limited to: an operating system, one or more application programs, other program modules and program data, each or some combination of these examples may include an implementation of a network environment.

[0141] Bus 330 can represent one or more of several types of bus structures, including a memory cell bus or memory cell controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the various bus structures.

[0142] Electronic device 300 can also communicate with one or more external devices 400 (e.g., keyboard, pointing device, Bluetooth device, etc.), and with one or more devices that enable a user to interact with the electronic device 300, and / or with any device that enables the electronic device 300 to communicate with one or more other computing devices (e.g., router, modem, etc.). This communication can be performed via input / output (I / O) interface 350. Furthermore, electronic device 300 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 360. Network adapter 360 can communicate with other modules of electronic device 300 via bus 330. It should be understood that, although... Figure 5 As not shown, other hardware and / or software modules may be used in conjunction with electronic device 300, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0143] Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described in this invention can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this invention can be embodied in the form of a software product, which can be stored in a computer-readable storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, or network device, etc.) to execute the above-described method according to this invention. When the computer program is executed by a data processing device, it enables the computer-readable medium to implement the above-described method of this invention, i.e.: as... Figure 1 The method shown.

[0144] Figure 6 This is a schematic diagram of a computer-readable medium provided for embodiments of this specification.

[0145] accomplish Figure 1 The computer program of the method shown can be stored on one or more computer-readable media. A computer-readable medium can be a readable signal medium or a readable storage medium. A readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof.

[0146] The computer-readable storage medium may include data signals propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The readable storage medium may also be any readable medium other than a readable storage medium, capable of transmitting, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0147] Program code for performing the operations of this invention can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0148] In summary, this invention can be implemented in hardware, or as software modules running on one or more processors, or a combination thereof. Those skilled in the art will understand that in practice, general-purpose data processing devices such as microprocessors or digital signal processors (DSPs) can be used to implement some or all of the functions of some or all of the components according to the embodiments of the invention. The invention can also be implemented as a device or apparatus program (e.g., a computer program and computer program product) for performing part or all of the methods described herein. Such programs implementing the invention can be stored on a computer-readable medium or can take the form of one or more signals. Such signals can be downloaded from an Internet website, provided on a carrier signal, or provided in any other form.

[0149] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the present invention is not inherently related to any specific computer, virtual device, or electronic device, and various general-purpose devices can also implement the present invention. The above descriptions are merely specific embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

[0150] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

[0151] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for constructing an aortic dissection identification model, characterized in that, include: Obtain the pulse oxygenation waveforms of the extremities of the training subjects; The pulse oxygenation waveforms of the extremities of the training subjects were compared with standard pulse oxygenation waveforms to obtain waveform difference comparison results. The amplitude and blood flow arrival time of the pulse blood oxygen waveform of the extremities of the training subjects were determined respectively based on the pulse blood oxygen waveform of the extremities. Based on the pulse blood oxygen waveform of the limbs of the training object, the Pearson correlation coefficient between each pair of signals in the limbs is calculated, and the Pearson correlation coefficient is used as the correlation factor between the four parts. The time-domain transformation of the pulse blood oxygen waveform of the limbs of the training subjects was performed to obtain the periodic feature description index. Based on the waveform difference comparison results, the amplitude of the pulse blood oxygen waveform of the limbs, the blood flow arrival time of the pulse blood oxygen waveform of the limbs, the correlation factors between the four sites, and the periodic feature description index, an aortic dissection identification model is constructed.

2. The method for constructing the aortic dissection identification model as described in claim 1, characterized in that, Before acquiring the pulse oxygenation waveforms of the extremities of the training subject, the following steps are included: Obtain the pulse oxygenation waveforms of the patient's extremities and the results of aortic dissection identification; Determine whether the acquisition channels for the patient's peripheral pulse oxygenation waveforms and aortic dissection identification results meet the preset channels; When the acquisition channel of the patient's peripheral pulse oximetry waveform and aortic dissection identification result meets the preset channel, the patient's peripheral pulse oximetry waveform and aortic dissection identification result that meets the preset channel will be used as the target research object; The target research objects are divided according to a preset ratio to obtain training objects and verification objects.

3. The method for constructing the aortic dissection identification model as described in claim 1, characterized in that, The step of comparing the pulse oximetry waveforms of the extremities of the training subject with standard pulse oximetry waveforms to obtain waveform difference comparison results includes: A high-order polynomial fit was performed on the diastolic waveform of the pulse oxygenation waveform of the extremities of the training subjects to obtain the goodness of fit. Determine whether the goodness of fit meets the preset goodness of fit; When the goodness of fit meets the preset goodness of fit, waveform difference comparison results are obtained based on the pulse blood oxygen waveform of the limbs of the training object.

4. The method for constructing the aortic dissection identification model as described in claim 3, characterized in that, When the goodness of fit meets the preset goodness of fit, the waveform difference comparison result is obtained based on the pulse blood oxygen waveform of the extremities of the training object, including: Where N is the notch coefficient, A is the peak value, and B is the trough value.

5. The method for constructing the aortic dissection identification model as described in claim 2, characterized in that, After constructing the aortic dissection identification model based on the waveform difference comparison results, the amplitude of the pulse oxygenation waveforms of the extremities, the blood flow arrival time of the pulse oxygenation waveforms of the extremities, the correlation factors between the four sites, and the periodic feature descriptive index, the following steps are included: Obtain the pulse oxygenation waveforms of the extremities of the verification object and the results of its aortic dissection identification; The pulse oxygenation waveforms of the extremities of the verification object are input into the aortic dissection identification model to obtain the model identification results; Determine whether the model identification result is consistent with the aortic dissection identification result of the verification object; When the model recognition result is inconsistent with the aortic dissection recognition result of the verification object, return to obtaining the pulse oxygenation waveform of the patient's limbs and the aortic dissection recognition result, until the model recognition result is consistent with the aortic dissection recognition result of the verification object.

6. A device for constructing an aortic dissection identification model, characterized in that, include: The first acquisition module is used to acquire the pulse blood oxygen waveforms of the extremities of the training subject. The comparison module is used to compare the pulse blood oxygen waveform of the extremities of the training subject with the standard pulse blood oxygen waveform to obtain the waveform difference comparison result; The first determining module is used to determine the amplitude and blood flow arrival time of the pulse blood oxygen waveform of the extremities based on the pulse blood oxygen waveform of the training object. The second determining module is used to calculate the Pearson correlation coefficient between pairs of signals in the limbs based on the pulse blood oxygen waveform of the limbs of the training object, and to use the Pearson correlation coefficient as the correlation factor between the limbs. The conversion module is used to perform time-domain conversion on the pulse blood oxygen waveform of the extremities of the training object to obtain the periodic feature descriptive index. A construction module is used to construct an aortic dissection identification model based on the waveform difference comparison results, the amplitude of the pulse blood oxygen waveform of the limbs, the blood flow arrival time of the pulse blood oxygen waveform of the limbs, the correlation factors between the four sites, and the periodic feature description index.

7. The apparatus for constructing an aortic dissection identification model as described in claim 6, characterized in that, Prior to the first acquisition module, it includes: The second acquisition module is used to acquire the pulse oxygenation waveforms of the patient's limbs and the results of aortic dissection identification. The first judgment module is used to determine whether the acquisition channels of the patient's limb pulse blood oxygen waveform and aortic dissection identification results meet the preset channels. The third determining module is used to select the patient's limb pulse oxygen waveform and aortic dissection identification results as the target research object when the acquisition channel of the patient's limb pulse oxygen waveform and aortic dissection identification results meets the preset channel. The partitioning module is used to partition the target research object based on a preset ratio to obtain training objects and validation objects.

8. The apparatus for constructing an aortic dissection identification model as described in claim 6, characterized in that, The comparison module includes: The fitting unit is used to perform high-order polynomial fitting on the diastolic waveform of the pulse blood oxygen waveform of the limbs of the training object to obtain the goodness of fit. A judgment unit is used to determine whether the goodness of fit meets a preset goodness of fit. The determining unit is used to obtain waveform difference comparison results based on the pulse blood oxygen waveform of the limbs of the training object when the goodness of fit meets the preset goodness of fit.

9. An electronic device, wherein, The electronic device includes: Processor; and, A memory storing computer-executable instructions, which, when executed, cause the processor to perform the method according to any one of claims 1-5.

10. A computer-readable storage medium, wherein, The computer-readable storage medium stores one or more programs that, when executed by a processor, implement the method of any one of claims 1-5.

Images