CN113925480A

CN113925480A - Coronary heart disease patient bleeding risk assessment method based on machine learning

Info

Publication number: CN113925480A
Application number: CN202111124787.9A
Authority: CN
Inventors: 王嵘; 叶卫华; 石俊山; 吴倩; 张华军; 肖颖彬
Original assignee: Beijing Hezhong Sizhuang Space Time Material Union Technology Co ltd; Beijing Runmai Technology Co ltd; Chinese PLA General Hospital
Current assignee: Beijing Hezhong Sizhuang Space Time Material Union Technology Co ltd; Beijing Runmai Technology Co ltd; Chinese PLA General Hospital
Priority date: 2021-09-25
Filing date: 2021-09-25
Publication date: 2022-01-14
Anticipated expiration: 2041-09-25
Also published as: CN113925480B

Abstract

Embodiments of the present disclosure provide a coronary heart disease patient bleeding risk assessment method, apparatus, device and computer-readable storage medium based on machine learning. The method comprises acquiring a PPG measurement signal of a coronary heart disease patient; carrying out segmentation processing on the PPG measurement signal to obtain M signal segments; m is a positive integer greater than or equal to 1; performing signal quality evaluation on the M signal segments through a preset algorithm to determine signal segments with qualified quality; extracting X characteristics from the signal segments with qualified quality, and inputting the characteristics into a bleeding risk evaluation model to obtain a bleeding risk score of a coronary heart disease patient; x is a positive integer of 1 or more. In this way, an assessment of the risk of bleeding in patients with coronary heart disease is achieved.

Description

Coronary heart disease patient bleeding risk assessment method based on machine learning

Technical Field

Embodiments of the present disclosure relate generally to the field of signal monitoring, and more particularly, to a coronary heart disease patient bleeding risk assessment method, apparatus, device and computer-readable storage medium based on machine learning.

Background

According to the report of the world health organization, the ratio of cardiovascular diseases in various diseases is 17.9%, and 100 ten thousand people die from cardiovascular diseases in 2016, wherein patients with Coronary Artery Disease (Coronary heart Disease) account for the main proportion. For patients with coronary heart disease, drug therapy (e.g., antiplatelet therapy) is the primary treatment modality. Bleeding events are a focus of attention during anti-thrombotic therapy in patients with coronary heart disease. The occurrence of bleeding episodes may lead to discontinuation of treatment, long-term disability, or even death of the patient. Therefore, it is of great significance to conduct bleeding risk assessment studies on patients with coronary heart disease to find sensitive factors relevant to prognosis.

Photoplethysmography (PPG) is a low-cost and non-invasive detection technique that can be applied to cardiovascular system assessment. Changes in the state of the cardiovascular system can be assessed by morphological features of the PPG waveform, such as aortic stiffness, blood volume detection, etc.

However, no study is currently available to assess the risk of bleeding in patients with coronary heart disease by PPG.

Disclosure of Invention

According to an embodiment of the present disclosure, a bleeding risk assessment scheme for coronary heart disease patients based on machine learning is provided.

In a first aspect of the disclosure, a method for assessing bleeding risk of a coronary heart disease patient based on machine learning is provided. The method comprises the following steps:

acquiring a PPG measurement signal of a coronary heart disease patient;

carrying out segmentation processing on the PPG measurement signal to obtain N signal segments; n is a positive integer greater than or equal to 1;

performing signal quality evaluation on the N signal segments through a preset algorithm to determine signal segments with qualified quality;

extracting X characteristics from the signal segments with qualified quality, and inputting the characteristics into a bleeding risk evaluation model to obtain a bleeding risk score of a coronary heart disease patient; x is a positive integer of 1 or more.

Further, the segmenting the PPG measurement signal to obtain N signal segments includes:

removing baseline drift and high-frequency noise of the PPG measurement signal through a Butterworth band-pass filter;

and based on the waveform of the PPG measuring signal, carrying out segmentation processing on the PPG measuring signal to obtain N signal segments.

Further, the performing signal quality evaluation on the N signal segments by using a preset algorithm, and determining a signal segment with qualified quality includes:

resampling each of the N signal segments; wherein the resampling length is a median of the N signal segment lengths;

and substituting the resampled segmented signals into a preset formula respectively, and if the calculation result is greater than a preset threshold, determining the current segmented signals to be qualified signals.

Further, the bleeding risk assessment model is obtained by training the following steps:

generating a training sample set, wherein the training sample comprises a feature vector corresponding to a PPG signal with labeled information, the labeled information is a bleeding condition, the bleeding label is 1, and the non-bleeding label is 0;

and training a bleeding risk assessment model by using samples in the training sample set, taking a feature vector corresponding to a PPG signal as input, taking a bleeding condition as output, and finishing training the bleeding risk assessment model when the unity rate of the output bleeding condition and the marked bleeding condition meets a preset threshold value.

Further, the feature vector corresponding to the PPG signal includes:

analyzing the collected PPG signal, and respectively extracting a feature vector corresponding to the PPG signal from a time domain, a frequency domain and a wavelet packet decomposition.

Further, the analyzing the acquired PPG signals comprises:

analyzing the PPG signal, a first derivative of the PPG signal, and a second derivative of the PPG signal.

Further, the XGboost algorithm is adopted to train the bleeding risk assessment model.

In a second aspect of the present disclosure, a coronary heart disease patient bleeding risk assessment device based on machine learning is provided. The device includes:

the acquisition module is used for acquiring a PPG measurement signal of a coronary heart disease patient;

the processing module is used for carrying out segmentation processing on the PPG measurement signal to obtain N signal segments; n is a positive integer greater than or equal to 1;

the evaluation module is used for evaluating the signal quality of the N signal segments through a preset algorithm and determining the signal segments with qualified quality;

the scoring module is used for extracting X characteristics from the signal segments with qualified quality and inputting the X characteristics into a bleeding risk evaluation model to obtain a bleeding risk score; x is a positive integer of 1 or more.

In a third aspect of the disclosure, an electronic device is provided. The electronic device includes: a memory having a computer program stored thereon and a processor implementing the method as described above when executing the program.

In a fourth aspect of the present disclosure, a computer readable storage medium is provided, having stored thereon a computer program, which when executed by a processor, implements a method as in accordance with the first aspect of the present disclosure.

The coronary heart disease patient bleeding risk assessment method based on machine learning provided by the embodiment of the application comprises the steps of obtaining a PPG measurement signal; carrying out segmentation processing on the PPG measurement signal to obtain N signal segments; n is a positive integer greater than or equal to 1; performing signal quality evaluation on the N signal segments through a preset algorithm to determine signal segments with qualified quality; extracting X time domain features from the signal segments with qualified quality, and inputting the time domain features into a bleeding risk evaluation model to obtain a bleeding risk score of a coronary heart disease patient; and X is a positive integer greater than or equal to 1, so that the bleeding risk assessment of the CAD patient is realized.

It should be understood that the statements herein reciting aspects are not intended to limit the critical or essential features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.

Drawings

The above and other features, advantages and aspects of various embodiments of the present disclosure will become more apparent by referring to the following detailed description when taken in conjunction with the accompanying drawings. In the drawings, like or similar reference characters designate like or similar elements, and wherein:

FIG. 1 illustrates a schematic diagram of an exemplary operating environment in which embodiments of the present disclosure can be implemented;

fig. 2 shows a flow chart of a machine learning based coronary heart disease patient bleeding risk assessment method according to an embodiment of the present disclosure;

figure 3 shows a PPG, VPG and APG signal schematic according to an embodiment of the present disclosure;

FIG. 4 shows a 10-fold cross-validation ROC curve, average ROC curve schematic for an XGboost model in accordance with an embodiment of the disclosure;

FIG. 5 shows a schematic diagram of a SHAP framework performing a feature analysis on an XGboost model, in accordance with an embodiment of the disclosure;

fig. 6 shows a block diagram of a coronary heart disease patient bleeding risk assessment device based on machine learning according to an embodiment of the present disclosure;

FIG. 7 illustrates a block diagram of an exemplary electronic device capable of implementing embodiments of the present disclosure.

Detailed Description

To make the objects, technical solutions and advantages of the embodiments of the present disclosure more clear, the technical solutions of the embodiments of the present disclosure will be described clearly and completely with reference to the drawings in the embodiments of the present disclosure, and it is obvious that the described embodiments are some, but not all embodiments of the present disclosure. All other embodiments, which can be derived by a person skilled in the art from the embodiments disclosed herein without making any creative effort, shall fall within the protection scope of the present disclosure.

In addition, the term "and/or" herein is only one kind of association relationship describing an associated object, and means that there may be three kinds of relationships, for example, a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter related objects are in an "or" relationship.

Fig. 1 shows an exemplary system architecture 100 to which an embodiment of the machine learning based coronary heart disease patient bleeding risk assessment method apparatus of the present application may be applied.

As shown in fig. 1, the system architecture 100 may include

terminal devices

101, 102, 103, a network 104, and a server 105. The network 104 serves as a medium for providing communication links between the

terminal devices

101, 102, 103 and the server 105. Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.

The user may use the

terminal devices

101, 102, 103 to interact with the server 105 via the network 104 to receive or send messages or the like. Various communication client applications, such as a model training application, a video recognition application, a web browser application, social platform software, etc., may be installed on the

terminal devices

101, 102, 103.

The

terminal apparatuses

101, 102, and 103 may be hardware or software. When the

terminal devices

101, 102, 103 are hardware, they may be various electronic devices with a display screen, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III, mpeg compression standard Audio Layer 3), MP4 players (Moving Picture Experts Group Audio Layer IV, mpeg compression standard Audio Layer 4), PPG measuring devices, laptop portable computers, desktop computers, and so on. When the

terminal apparatuses

101, 102, 103 are software, they can be installed in the electronic apparatuses listed above. It may be implemented as multiple pieces of software or software modules (e.g., multiple pieces of software or software modules to provide distributed services) or as a single piece of software or software module. And is not particularly limited herein.

When the

terminals

101, 102, 103 are hardware, a video capture device may also be installed thereon. The video acquisition equipment can be various equipment capable of realizing the function of acquiring video, such as a camera, a sensor and the like. The user may capture video using a video capture device on the terminal 101, 102, 103.

The server 105 may be a server that provides various services, such as a background server that processes data displayed on the

terminal devices

101, 102, 103. The background server may perform processing such as analysis on the received data, and may feed back a processing result (e.g., an evaluation result) to the terminal device.

The server may be hardware or software. When the server is hardware, it may be implemented as a distributed server cluster formed by multiple servers, or may be implemented as a single server. When the server is software, it may be implemented as multiple pieces of software or software modules (e.g., multiple pieces of software or software modules used to provide distributed services), or as a single piece of software or software module. And is not particularly limited herein.

It should be understood that the number of terminal devices, networks, and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation. In particular, in the case where the target data does not need to be acquired from a remote place, the above system architecture may not include a network but only a terminal device or a server.

Fig. 2 is a flowchart of a coronary heart disease patient bleeding risk assessment method based on machine learning according to an embodiment of the present application. As can be seen from fig. 2, the method for assessing bleeding risk of patients with coronary heart disease based on machine learning of the present embodiment includes the following steps:

and S210, acquiring a PPG measurement signal of the patient with coronary heart disease.

In some embodiments, the performing subject (e.g., the server shown in fig. 1) for the machine learning-based coronary heart disease patient bleeding risk assessment method may acquire the PPG measurement signal by wired means or by wireless connection.

In some embodiments, the execution subject may obtain a PPG measurement signal transmitted by an electronic device (e.g. the terminal device shown in fig. 1) with which it is communicatively connected; the electronic device is provided with a PPG sensor for acquiring PPG data of a user (patient), for example, an optical heart rate sensor, etc.

In some embodiments, when the PPG measurement device alone is not able to upload data, e.g., a partial fingertip PPG measurement device, the PPG measurement device may also send the measurement to a mobile device (cell phone, etc.) connected to it, through which the relevant PPG measurement information is uploaded to a server as shown in fig. 1.

In some embodiments, for accuracy of measurement, PPG measurement data may be acquired by a variety of light intensities (luminous intensities); the collection time is usually 20s-60 s; the setting can be performed according to the actual application scenario, which is not further limited.

In some embodiments, the signal waveform of the PPG is as shown in fig. 3, VPG is the first derivative of the PPG, and APG is the second derivative of the PPG; t and Y represent the time ms and the amplitude of the corresponding point.

It should be noted that the PPG measurement device (electronic device) in the present disclosure is typically a portable device equipped with a PPG sensor, and can be used in a home environment.

S220, carrying out segmentation processing on the PPG measurement signal to obtain M signal segments; m is a positive integer greater than or equal to 1.

In some embodiments, the PPG measurement signal needs to be pre-processed before being segmented;

specifically, the baseline drift and high frequency noise of the PPG measurement signal can be removed by setting the cut-off frequency to 0.2 and 20Hz by means of a butterworth band-pass filter.

In some embodiments, the preprocessed PPG measurement signal is sliced according to a waveform period of the PPG measurement signal, resulting in M signal segments, which may be denoted as S ═ S1, S2.., SM }; wherein M is a positive integer greater than or equal to 1; s represents a set of signal segments.

And S230, performing signal quality evaluation on the M signal segments through a preset algorithm, and determining the signal segments with qualified quality.

Some segments in S may be damaged in consideration of noise that a user may generate during measurement, and thus, signal quality of each segment needs to be detected, i.e., evaluated.

In some embodiments, each of the M signal segments is resampled, i.e., each segment in set S is resampled to the same length, which may be denoted as RS ═ { RS ═ RS₁,RS₂,…,RS_M}; wherein, the sampling length is the median of all segment lengths;

respectively substituting the segmented signals in the S into the following formulas, and if the calculation conditions are met, determining the segmented signals to be qualified;

S_valid＝{S_i∣S_i∈S,RS_i∈RS,r(RS_i,RS_T)>0.9}

wherein, the RS_TIs, the average of the RS;

the r is a Pearson correlation coefficient, and the value range is-1;

the 0.9 is a preset threshold value and is obtained according to a large number of experiments; the preset threshold value can also be set according to manual experience, big data analysis and/or practical application scenes.

S240, extracting X characteristics from the signal segments with qualified quality, and inputting the characteristics into a bleeding risk evaluation model to obtain a bleeding risk score of a coronary heart disease patient; x is a positive integer of 1 or more.

In some embodiments, from the qualified signal segments, X features are extracted, e.g., 30 features are extracted, see table 1; t and Y represent the time ms and the amplitude of the corresponding point, see fig. 3.

TABLE 1

In some embodiments, for the accuracy of the measurement, each waveform (signal segment) needs to be normalized to be in the range of 0-1 before extracting features.

In some embodiments, the bleeding risk assessment model may be trained by:

training a bleeding risk assessment model by using samples in the training sample set, taking a feature vector corresponding to a PPG signal as input, taking a bleeding condition as output, and finishing training the bleeding risk assessment model when the unity rate of the output bleeding condition and the marked bleeding condition meets a preset threshold; the threshold value can be set with an actual application scene;

further, based on the output, a bleeding risk score of the patient with coronary heart disease can be calculated through manual experience, big data analysis and/or a threshold setting method, wherein the higher the score is, the greater the bleeding risk is;

wherein, the feature vector corresponding to the PPG signal further comprises feature vectors of a first derivative (VPG) and a second derivative (APG) of the PPG; the synchronized PPG, VPG, APG signals are shown in fig. 3;

the PPG signal may be a PPG signal acquired over large data, e.g., a PPG signal acquired over a large scale over two years;

analyzing the collected PPG signal to obtain a feature vector corresponding to the PPG signal, namely analyzing the PPG signal, a first derivative of the PPG signal and a second derivative of the PPG signal, extracting a 30-dimensional feature vector (which can be set according to an actual application scene) from time domain, frequency domain and wavelet packet decomposition (energy feature), and referring to Table 1;

wherein the frequency domain may be determined by:

the PPG signal is composed of abundant frequency components, the power spectral density of the PPG signal can be calculated by adopting a Welch algorithm, the position of each harmonic is determined by detecting an extreme point, and the power normalization processing of dividing the second harmonic to the sixth harmonic by the fundamental frequency (first harmonic) is carried out to determine the frequency domain characteristics, namely frequency domains H1-H5 in the table 1;

through a large number of research experiments, 99% of energy in the PPG signal is concentrated within the range of 1-10 Hz, and therefore, in the present disclosure, only frequency components within 10Hz are studied and extracted;

specifically, the sampling rate of the PPG signal is 500Hz, after 8 wavelet packet decompositions, the bandwidth of each sub-band is 0.977Hz, 10 components are reserved as E1 to E10, and the total energy of the PPG signal is represented as early.

In the present disclosure, data collected 1683 for patients with coronary heart disease was collected and analyzed, where 114 were patients with at least one positive event (bleeding), and non-demographic records and records with poor signal quality were deleted, resulting in patient demographic characteristics as shown in table 2;

TABLE 2

Of these, 10 features were statistically significantly different between the negative and positive groups, see table 3:

TABLE 3

Referring to table 3, the positive group Td is smaller than the negative group, and the RI is larger, and analysis from the geometric feature of the PPG waveform, it is likely that the diastolic wave delay of the positive group is increased, resulting in increased diastolic wave width, and Td, Rarea tend to become smaller; the frequency domain H1-H5 has statistical difference between the negative group and the positive group, and 5 normalized harmonics are gradually reduced; the total energy early calculated by wavelet packet decomposition was smaller in the positive group.

In some embodiments, based on collected PPG data of coronary heart disease patients, a hemorrhage analysis assessment model is trained using lr (logistic regression), svr (support Vector regression), rf (random forest), XGBoost algorithms, respectively. 90% of the data is used for training the classification model (training set), the rest 10% of the data is used for testing (test set), training and evaluation are carried out through 10-fold cross validation and grid search, the optimal hyper-parameter obtained through grid search is used for 10-fold cross validation, and the average AUC (model evaluation index) of each model is obtained, and is shown in Table 4. The sensitivity and specificity of each model are shown in table 5. By comparison, the XGboost performance in a plurality of algorithm models is optimal, the average AUC is 0.762, the sensitivity and the specificity are 0.679 and 0.714 respectively, and the XGboost performance is obviously higher than that of other models. The 10-fold cross-validation ROC curve, the average ROC curve, and AUC for the XGBoost model are shown in fig. 4.

TABLE 4

TABLE 5

Further, characteristics of the XGBoost model are analyzed using a shap (adaptive interpretation) framework, as shown in fig. 5, which shows 20 features thereof; the SHAP value represents the contribution of the feature to the target (negative: 0, positive: 1). The feature values are represented by different colors, that is, the larger the feature value is, the more red the color is, whereas the smaller the feature value is, the more blue the color is (in fig. 5, the lower the gray value is, the blue is, and the higher the gray value is, the red is); for example, as the eigenvalues of H4, E10, SI, etc. increase, the SHAP value tends to be less than 0; that is, the model is more inclined to determine the current sample as target 0; conversely, as the RI, VDae values decrease, the SHAP value tends to be greater than 0.

Furthermore, the sum of the absolute values of the SHAP values reflects the importance of the feature, and therefore, according to this criterion, H4 can be considered to be the most important feature. The above observations are also in good agreement with the results in table 3; for example, for the negative group, Td, Rarea, H4, H1, H5, H2, all are consistent, i.e. as the eigenvalues increase, the SHAP values tend to be negative, while RI values behave the exact opposite.

To sum up, the XGBoost model may be employed in the present disclosure to train the bleeding risk assessment model; the bleeding risk assessment model is described using the SHAP framework.

In some embodiments, the extracted features are input into a trained bleeding risk assessment model, and a bleeding risk score of the current patient is determined;

further, the bleeding risk score is sent to the PPG measurement device and/or the terminal device as shown in fig. 1, forming a closed loop, helping the patient to achieve self-health management.

According to the embodiment of the disclosure, the following technical effects are achieved:

the invention is different from other coronary heart disease patient bleeding risk assessment researches, and by using the portable PPG equipment, the device can be used by a user to assess possible bleeding events in a home environment without depending on clinical environment. The system may help remotely alert the CAD patient to give sufficient attention or assist the physician in selecting a treatment plan.

It is noted that while for simplicity of explanation, the foregoing method embodiments have been described as a series of acts or combination of acts, it will be appreciated by those skilled in the art that the present disclosure is not limited by the order of acts, as some steps may, in accordance with the present disclosure, occur in other orders and concurrently. Further, those skilled in the art should also appreciate that the embodiments described in the specification are exemplary embodiments and that acts and modules referred to are not necessarily required by the disclosure.

The above is a description of embodiments of the method, and the embodiments of the apparatus are further described below.

Fig. 6 illustrates a block diagram of a machine learning based coronary heart disease patient bleeding risk assessment apparatus 600, according to an embodiment of the present disclosure. As shown in fig. 6, the apparatus 600 includes:

an obtaining module 610, configured to obtain a PPG measurement signal of a coronary heart disease patient;

a processing module 620, configured to perform segmentation processing on the PPG measurement signal to obtain M signal segments; m is a positive integer greater than or equal to 1;

an evaluation module 630, configured to perform signal quality evaluation on the M signal segments through a preset algorithm, and determine a signal segment with qualified quality;

a scoring module 640, configured to extract X features from the signal segments with qualified quality, and input the X features into a bleeding risk assessment model to obtain a bleeding risk score; x is a positive integer of 1 or more.

It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working process of the described module may refer to the corresponding process in the foregoing method embodiment, and is not described herein again.

FIG. 7 illustrates a schematic block diagram of an electronic device 700 that may be used to implement embodiments of the present disclosure. Device 700 can be used to implement at least one of message system 104 and message arrival rate determination system 106 of fig. 1. As shown, device 700 includes a Central Processing Unit (CPU)701 that may perform various appropriate actions and processes in accordance with computer program instructions stored in a Read Only Memory (ROM)702 or computer program instructions loaded from a storage unit 708 into a Random Access Memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the device 700 can also be stored. The CPU 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An input/output (I/O) interface 705 is also connected to bus 704.

Various components in the device 700 are connected to the I/O interface 705, including: an input unit 706 such as a keyboard, a mouse, or the like; an output unit 707 such as various types of displays, speakers, and the like; a storage unit 708 such as a magnetic disk, optical disk, or the like; and a communication unit 709 such as a network card, modem, wireless communication transceiver, etc. The communication unit 709 allows the device 700 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.

The processing unit 701 performs the various methods and processes described above. For example, in some embodiments, the methods may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as storage unit 708. In some embodiments, part or all of a computer program may be loaded onto and/or installed onto device 700 via ROM 702 and/or communications unit 709. When the computer program is loaded into the RAM 703 and executed by the CPU 701, one or more steps of the methods described above may be performed. Alternatively, in other embodiments, CPU 701 may be configured to perform the method by any other suitable means (e.g., by way of firmware).

The functions described herein above may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: a Field Programmable Gate Array (FPGA), an Application Specific Integrated Circuit (ASIC), an Application Specific Standard Product (ASSP), a system on a chip (SOC), a load programmable logic device (CPLD), and the like.

Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

Further, while operations are depicted in a particular order, this should be understood as requiring that such operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed, to achieve desirable results. Under certain circumstances, multitasking and parallel processing may be advantageous. Likewise, while several specific implementation details are included in the above discussion, these should not be construed as limitations on the scope of the disclosure. Certain features that are described in the context of separate embodiments can also be implemented in combination in a single implementation. Conversely, various features that are described in the context of a single implementation can also be implemented in multiple implementations separately or in any suitable subcombination.

Although the subject matter has been described in language specific to structural features and/or methodological acts, it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the claims.

Claims

1. A coronary heart disease patient bleeding risk assessment method based on machine learning is characterized by comprising the following steps:

acquiring a PPG measurement signal of a coronary heart disease patient;

carrying out segmentation processing on the PPG measurement signal to obtain M signal segments; m is a positive integer greater than or equal to 1;

performing signal quality evaluation on the M signal segments through a preset algorithm to determine signal segments with qualified quality;

2. The method of claim 1, wherein the segmenting the PPG measurement signals into M signal segments comprises:

and carrying out segmentation processing on the PPG measuring signal based on the waveform of the PPG measuring signal to obtain M signal segments.

3. The method of claim 2, wherein the evaluating the signal quality of the M signal segments by a predetermined algorithm, and wherein determining a signal segment that is qualified for quality comprises:

resampling each of the M signal segments; wherein the resampling length is a median of the M signal segment lengths;

4. The method according to claim 3, wherein the bleeding risk assessment model is trained by:

5. The method of claim 4, wherein the feature vector corresponding to the PPG signal comprises:

6. The method of claim 5, wherein the analyzing the acquired PPG signal comprises:

7. The method of claim 6, wherein the bleeding risk assessment model is trained using an XGboost algorithm.

8. A coronary heart disease patient bleeding risk assessment device based on machine learning, comprising:

the processing module is used for carrying out segmentation processing on the PPG measurement signal to obtain M signal segments; m is a positive integer greater than or equal to 1;

the evaluation module is used for evaluating the signal quality of the M signal segments through a preset algorithm and determining the signal segments with qualified quality;

9. An electronic device comprising a memory and a processor, the memory having stored thereon a computer program, wherein the processor, when executing the program, implements the method of any of claims 1-7.

10. A computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, carries out the method according to any one of claims 1 to 7.