CN116671887A - Device for screening sudden cardiac death high risk group based on photoelectric volume pulse wave signals - Google Patents
Device for screening sudden cardiac death high risk group based on photoelectric volume pulse wave signals Download PDFInfo
- Publication number
- CN116671887A CN116671887A CN202310950299.6A CN202310950299A CN116671887A CN 116671887 A CN116671887 A CN 116671887A CN 202310950299 A CN202310950299 A CN 202310950299A CN 116671887 A CN116671887 A CN 116671887A
- Authority
- CN
- China
- Prior art keywords
- module
- screening
- feature
- high risk
- risk group
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012216 screening Methods 0.000 title claims abstract description 45
- 206010049418 Sudden Cardiac Death Diseases 0.000 title claims abstract description 30
- 238000012545 processing Methods 0.000 claims abstract description 46
- 238000000605 extraction Methods 0.000 claims abstract description 19
- 238000000034 method Methods 0.000 claims abstract description 9
- 238000001914 filtration Methods 0.000 claims description 28
- 239000013598 vector Substances 0.000 claims description 17
- 238000005070 sampling Methods 0.000 claims description 8
- 230000009466 transformation Effects 0.000 claims description 6
- 230000036541 health Effects 0.000 abstract description 6
- 238000012544 monitoring process Methods 0.000 abstract description 6
- 238000007405 data analysis Methods 0.000 abstract description 2
- 238000013186 photoplethysmography Methods 0.000 description 33
- 201000004224 Schnyder corneal dystrophy Diseases 0.000 description 6
- 230000005540 biological transmission Effects 0.000 description 6
- 238000012549 training Methods 0.000 description 6
- KJONHKAYOJNZEC-UHFFFAOYSA-N nitrazepam Chemical compound C12=CC([N+](=O)[O-])=CC=C2NC(=O)CN=C1C1=CC=CC=C1 KJONHKAYOJNZEC-UHFFFAOYSA-N 0.000 description 4
- 238000010606 normalization Methods 0.000 description 4
- 210000000707 wrist Anatomy 0.000 description 3
- 239000008280 blood Substances 0.000 description 2
- 210000004369 blood Anatomy 0.000 description 2
- 210000004204 blood vessel Anatomy 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000002792 vascular Effects 0.000 description 2
- 206010003658 Atrial Fibrillation Diseases 0.000 description 1
- 230000001154 acute effect Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 206010003119 arrhythmia Diseases 0.000 description 1
- 230000006793 arrhythmia Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000036772 blood pressure Effects 0.000 description 1
- 230000003840 blood vessel health Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000000747 cardiac effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 208000029078 coronary artery disease Diseases 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 210000000624 ear auricle Anatomy 0.000 description 1
- 238000002592 echocardiography Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000002565 electrocardiography Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 229910052760 oxygen Inorganic materials 0.000 description 1
- 239000001301 oxygen Substances 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000002250 progressing effect Effects 0.000 description 1
- 230000010349 pulsation Effects 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/024—Detecting, measuring or recording pulse rate or heart rate
- A61B5/02416—Detecting, measuring or recording pulse rate or heart rate using photoplethysmograph signals, e.g. generated by infrared radiation
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/725—Details of waveform analysis using specific filters therefor, e.g. Kalman or adaptive filters
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Surgery (AREA)
- Public Health (AREA)
- Pathology (AREA)
- Physiology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Veterinary Medicine (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Cardiology (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Psychiatry (AREA)
- Signal Processing (AREA)
- Evolutionary Computation (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Measuring Pulse, Heart Rate, Blood Pressure Or Blood Flow (AREA)
Abstract
The invention provides a screening device for a sudden cardiac death high risk group based on photoelectric volume pulse wave signals, which comprises a data acquisition part and a processing part, wherein the data acquisition part comprises a data acquisition module, a signal processing module and a data uploading module, and the data processing part comprises a feature extraction module and a classification screening module, and the signal acquisition module is used for acquiring PPG signals; the data uploading module is used for uploading the PPG signal processed by the signal processing module to the processing part; the feature extraction module is used for carrying out feature extraction and feature screening processing according to the PPG signal and the basic data of the acquisition object; and the classification screening module classifies the cardiac sudden death risk of the acquisition object according to the feature after the dimension reduction output by the feature extraction module. The method is based on big data analysis and prediction, realizes screening of the sudden cardiac death high risk group, can realize early identification and early warning for the high risk group, and is suitable for all-weather health monitoring at home.
Description
Technical Field
The invention belongs to the field of health monitoring equipment, and particularly relates to a screening device for cardiac sudden death high risk groups based on photoelectric volume pulse wave signals.
Background
Sudden cardiac death (sudden cardiac death, SCD) refers to an unexpected, rapidly progressing natural death due to various cardiac causes, which usually occurs within 1h after the onset of acute symptoms. It is estimated that 54.4 thousands of acquisition objects in China generate SCD every year. At present, a means for screening SCD risks in general population is lacking, and long-time electrocardiography, echocardiography and the like are not suitable for home observation and large-scale risk screening.
Photoplethysmography (PPG) can obtain periodic changes in blood pulsation by a photoelectric sensor, and pulse wave signals can reflect the trend of changes in human heart and blood vessels to a certain extent. The method is commonly used for manufacturing noninvasive monitoring equipment for blood pressure, blood oxygen saturation and heart rate, and meanwhile, because the PPG signal can reflect the health state of the heart vessels, the early recognition early warning of the heart vessels diseases such as arrhythmia, atrial fibrillation, coronary heart disease and the like and the blood vessel health evaluation of the PPG have related applications at present. The PPG can be used for constructing various wearable sensors such as an intelligent wrist watch, a pulse oximeter and the like, and can realize linkage with intelligent equipment by matching with a wireless transmission technology due to the simple structure and low power consumption, so that the intelligent wrist watch is suitable for all-weather health monitoring at home.
Disclosure of Invention
Aiming at the screening requirement of SCD risks in large-scale people, the invention provides a screening device for cardiac sudden death high risk people, which is suitable for all-weather health monitoring at home. This device is implemented based on PPG technology. The technical scheme of the invention is as follows:
the device comprises a data acquisition part and a processing part, wherein the data acquisition part comprises a data acquisition module, a signal processing module and a data uploading module, the data processing part comprises a feature extraction module and a classification screening module,
the signal acquisition module is used for acquiring PPG signals and comprises an LED emitter and a photoelectric sensor;
the signal processing module is used for processing the PPG signals acquired by the photoelectric sensor;
the data uploading module is used for uploading the PPG signal processed by the signal processing module to the processing part;
the feature extraction module is used for carrying out feature extraction and feature screening processing according to PPG signals and basic data of an acquisition object, evaluating the correlation between features and between the features and labels, calculating Pelson correlation coefficients between different feature values, wherein the absolute value of the Pelson correlation coefficient between two feature values is closer to 1 to represent that the linear correlation between the two feature values is stronger, and calculating the Pelson correlation coefficient between each pair of feature values, limiting the threshold value of the Pelson correlation coefficient, reserving one of the two feature values, and further screening to obtain feature vectors with reduced dimensions; based on the feature vectors after dimension reduction, carrying out importance ranking on the feature values, and selecting important features with top ranking;
the classification screening module is used for classifying the cardiac sudden death risk of the acquisition object according to the important features output by the feature extraction module to obtain a cardiac sudden death risk classification screening model.
Further, the processing of the acquired PPG signal includes filtering processing.
Further, the feature extraction module performs feature extraction according to the PPG signal to obtain heart rate, heart rate variability and mathematical features.
Further, heart rate variability includes SDNN; RMSSD; NN50; PNN50.
Further, the signal processing module comprises filtering processing, and the filtering processing link comprises one or more of power frequency filtering, IIR filtering, FIR filtering, wavelet filtering, wiener filtering, zero-phase filtering, integral transformation and differential transformation.
Further, the signal processing module samples at a frequency of 100HZ.
Further, the basic data of the collected subject includes height, weight, age and sex.
Further, the pearson correlation coefficient is adopted to evaluate the linear correlation between the features and the labels, the pearson correlation coefficient between different feature values is calculated, the absolute value of the pearson correlation coefficient between the two feature values is closer to 1 to represent the stronger linear correlation between the two feature values, the pearson correlation coefficient between each pair of feature values is calculated to limit the threshold value of the pearson correlation coefficient, and if the pearson correlation coefficient between the two feature values is higher than the set threshold value, one of the two feature values is reserved, and then the feature vector after dimension reduction is obtained through screening.
Further, based on the feature vectors after dimension reduction, the pearson correlation coefficients of different feature values and the labels are calculated to sort the importance of the feature values, and important features with top ranking are selected.
Further, the classification screening module classifies the cardiac sudden death risk of the acquired object by using a Gaussian naive Bayes classifier.
The beneficial effects of the invention are as follows: based on big data analysis and prediction, the invention adopts a non-invasive, portable and wearable PPG measurement method, and realizes screening of the sudden cardiac death high risk group, thereby realizing early recognition and early warning for the high risk group and being suitable for all-weather health monitoring at home.
Drawings
FIG. 1 is a system block diagram of the present invention;
fig. 2 is a diagnostic flow chart of the present invention.
Detailed Description
Based on the characteristics of PPG signals, the invention utilizes the heart and blood vessel quality information carried by the PPG signals to learn the classified data through artificial intelligence, and establishes a classification model. The screening device for the sudden cardiac death high risk group comprises two parts, wherein the acquisition part can be a customized fingertip oximeter, and the acquisition part can comprise a data acquisition module, a signal processing module and a data uploading module; the processing part can be customized special analysis equipment or special software developed by using a smart phone, and comprises a feature extraction module and a classification screening module.
The method comprises the steps of collecting data from the places such as fingertips, earlobes or wrists of a collection object through a signal collecting module, processing the collected original data through a signal processing module, including filtering and the like, uploading signals to a processing part through a data uploading module, extracting required characteristics through a characteristic extracting module, and classifying the risk of the collection object through a classifying and screening module. In particular, the method comprises the steps of,
the signal acquisition module comprises an LED emitter and a photoelectric sensor, the specific wavelength light emitted by the LED irradiates the skin and then changes due to vascular changes, and the photoelectric sensor is used for converting the optical signals containing vascular changes into electric signals to obtain the required PPG signals;
the signal processing module comprises two links of sampling and filtering PPG signals; firstly, analog signals acquired by a photoelectric sensor are converted into digital signals of a PPG sequence through AD conversion, the optional sampling frequency is 100HZ, the data volume is reduced on the premise of not losing the characteristics, and the subsequent processing difficulty is reduced; the filtering link comprises one or more of power frequency filtering, IIR filtering, FIR filtering, wavelet filtering, wiener filtering, zero-phase filtering, integral transformation and differential transformation.
The data uploading module can upload the PPG sequence signal subjected to filtering treatment to the processing part, and optional transmission modes comprise Bluetooth transmission, 4G transmission, wired transmission and the like, and Bluetooth transmission is preferred for realizing portability due to small data volume;
the processing part can be software on the smart phone, basic data of the acquisition object including height, weight, age, gender and the like can be collected through the software, and the basic data can be used as part of characteristics of the acquisition object for screening;
in this embodiment, the implementation of the processing portion is based on a smart phone APP implementation, and the acquisition object acquires the PPG signal through smart phone operation.
The PPG data is acquired for a certain time by the acquisition part and uploaded to the processing part and the PPG signal is further processed and analyzed. 30s may be selected as the duration of one acquisition.
The feature extraction module performs normalization processing on the PPG signal, and a normalization processing formula is shown as follows.
Wherein Xnorm is the value of the sampling point after normalization, X is the original value of the sampling point, xmin is the minimum value of the sequence PPG signal, and Xmax is the maximum value of the PPG signal.
Obtaining a PPG signal after normalization processing; extracting characteristic values, extracting waveform characteristics to obtain heart rate, heart rate variability, mathematical characteristics and other characteristics, wherein the specific steps are as follows:
1 calculating RR interval sequence: the heartbeat interval represents the interval time between two consecutive heartbeats, which may be referred to as RR interval, in ms; the sequence consisting of consecutive heart beat intervals is called heart beat interval sequence, i.e. RR interval sequence. Since PPG may represent heart activity, the interval time of adjacent PPG peaks may be used as the heartbeat interval, i.e. RR interval. Forming RR interval sequences by extracting PPG signal peak values and all RR interval values of the sampling signals;
2, calculating heart rate and heart rate variability related characteristic values:
heart rate: mean heart rate over sampling time, denoted HR; hr=60/mean (RR) ×1000, wherein mean (RR) represents RR interval sequence mean;
SDNN is standard deviation of RR interval sequences;
RMSSD: root mean square of adjacent RR interval difference values;
NN50: the difference between RR intervals exceeds the number of 50 ms;
PNN50: the NN50 is a percentage of the total number of RR intervals;
3 calculating other mathematical features of the PPG Signal
Kurtosis K: kurtosis during RR intervals:
bias state S: RR interval symmetry:
wherein RR is i A numerical value representing the ith RR interval in the RR interval sequence, n is the number of RR intervals in the sampling time, and mean (RR) represents the average value of the RR interval sequence;
the entropy features of the 4 PPG signal include:
sample entropy sampenn; the approximate entropy ApEn; shannon entropy;
5. feature importance ranking and screening
And (3) the basic data of the age, sex, height and weight of the acquired object and the PPG signal characteristic value obtained through calculation form a characteristic vector T. The numerical value of the age and the height of the acquisition object forms a numerical value characteristic vector, and the sex of the acquisition object is converted into the numerical value by the following steps: the male is 0, and the female is 1, and the feature vector is inputted. Dividing the training set acquisition object data collected in advance into low-risk, medium-risk and high-risk acquisition objects according to SCD risk levels, and endowing labels 0,1 and 2.
The importance of the features is sequenced and the data is screened to reduce the dimension, so that the redundant features are reduced, the complexity of the model is reduced, the training speed is improved, and the problems of over fitting and the like are avoided.
In the embodiment, the linear correlation between features and tags is evaluated by using the pearson correlation coefficient, and feature values with high correlation with tags and information with low correlation are screened.
First, the pearson correlation coefficient between different eigenvalues can be calculated:where x, y respectively represent two different features, and the closer the absolute value of the pearson correlation coefficient between the two feature values is to 1, the stronger the linear correlation between the two feature values. The feature vector after the dimension reduction can be obtained by calculating the pearson correlation coefficient between each pair of feature values and defining the threshold value of the pearson correlation coefficient.
Based on the feature vector after dimension reduction, the pearson correlation coefficients of different feature values and the labels are calculated to sort the importance of the feature values, and the first n important features are selected to form a new feature vector S.
The classification screening module is used for classifying the cardiac sudden death risk of the acquisition object according to the important features output by the feature extraction module, obtaining a cardiac sudden death risk classification screening model, classifying the risk of the acquisition object through the cardiac sudden death risk classification screening model, judging whether the acquisition object belongs to a middle-high risk crowd, and reminding the acquisition object to pay attention to precaution if the acquisition object belongs to the middle-high risk crowd, so that the screening of the high-risk crowd and the SCD risk prompt are realized.
In the embodiment, a Gaussian naive Bayes classifier is adopted to construct a cardiac sudden death risk classification screening model. The gaussian naive bayes classifier is a probability-based classification method. The classifier is based on a Bayesian formula, and obtains prior probabilities P (C) of different labels through a training set, wherein the labels of the training set, which are collected, are C types, and the values of the C are 0,1 and 2, and the labels respectively represent low risk, medium risk and high risk.
Obtaining conditional probability distribution of feature vectors under different training set acquisition object labels through training data，
According to the principle of mutual independence among dimensions of the naive Bayes model hypothesis feature S:
，S 1 … Sn represent the different dimensions of the feature vector.
Since most of the features are continuous values, which can be regarded as gaussian distribution, the feature value class C acquires the feature value S of the object i Probability density function of
Wherein the method comprises the steps ofAcquiring a characteristic value S of an object for class C i Variance of->Acquiring a characteristic value S of an object for class C i Is not limited to the above-described embodiments.
For the feature vector calculated by the PPG signal acquired by the acquisition object with unknown risk, the posterior probability of the acquisition object under different label C classifications can be calculated:
,
the classification of the collection object prediction is the classification with the highest posterior probability: i.e.。
The algorithm can be used for multi-classification task processing, and simultaneously has good performance on small-scale data and stable classification efficiency.
Claims (10)
1. The device comprises a data acquisition part and a processing part, wherein the data acquisition part comprises a data acquisition module, a signal processing module and a data uploading module, the data processing part comprises a feature extraction module and a classification screening module,
the signal acquisition module is used for acquiring PPG signals and comprises an LED emitter and a photoelectric sensor;
the signal processing module is used for processing the PPG signals acquired by the photoelectric sensor;
the data uploading module is used for uploading the PPG signal processed by the signal processing module to the processing part;
the feature extraction module is used for carrying out feature extraction and feature screening processing according to the PPG signal and the basic data of the acquisition object, evaluating the correlation between the features and the labels, calculating correlation coefficients between every two feature values, limiting a threshold value of the correlation coefficients, and reserving one of the two feature values if the correlation coefficient between the two feature values is higher than the set threshold value; further screening to obtain feature vectors after dimension reduction; based on the feature vectors after dimension reduction, carrying out importance ranking on the feature values, and selecting important features with top ranking;
the classification screening module is used for classifying the cardiac sudden death risk of the acquisition object according to the important features output by the feature extraction module to obtain a cardiac sudden death risk classification screening model.
2. The sudden cardiac death high risk group screening apparatus according to claim 1, wherein the processing of the collected PPG signal comprises a filtering process.
3. The screening device for cardiac sudden death high risk group according to claim 1, wherein the feature extraction module performs feature extraction according to the PPG signal to obtain heart rate, heart rate variability and mathematical features.
4. The sudden cardiac death high risk group screening device according to claim 1, wherein heart rate variability comprises SDNN, RMSSD, NN and PNN50.
5. The sudden cardiac death high risk group screening device according to claim 1, wherein the signal processing module comprises a filtering process, and the filtering process link comprises one or more of power frequency filtering, IIR filtering, FIR filtering, wavelet filtering, wiener filtering, zero-phase filtering, integral transformation and differential transformation.
6. The screening device for cardiac sudden death high risk group according to claim 1, wherein the signal processing module has a sampling frequency of 100HZ.
7. The sudden cardiac death high risk group screening apparatus according to claim 1, wherein the basic data of the collection subject includes height, weight, age and sex.
8. The device for screening the sudden cardiac death high risk group according to claim 1, wherein the pearson correlation coefficient between features and labels is evaluated by using pearson correlation coefficients, the pearson correlation coefficient between different feature values is calculated, the absolute value of the pearson correlation coefficient between two feature values is closer to 1, which means that the linear correlation between the two feature values is stronger, the pearson correlation coefficient between each pair of feature values is calculated, the threshold value of the pearson correlation coefficient is defined, and if the pearson correlation coefficient between the two feature values is higher than the set threshold value, one of the two feature values is reserved, and then the feature vector after dimension reduction is screened.
9. The screening device for the sudden cardiac death high risk group according to claim 8, wherein the importance ranking of the feature values is performed by calculating pearson correlation coefficients of different feature values and labels based on feature vectors after dimension reduction, and important features with top ranking are selected.
10. The device for screening the high risk group of sudden cardiac death of claim 8, wherein the classification screening module classifies the sudden cardiac death risk of the acquired subject using a gaussian naive bayes classifier.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310950299.6A CN116671887A (en) | 2023-07-31 | 2023-07-31 | Device for screening sudden cardiac death high risk group based on photoelectric volume pulse wave signals |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310950299.6A CN116671887A (en) | 2023-07-31 | 2023-07-31 | Device for screening sudden cardiac death high risk group based on photoelectric volume pulse wave signals |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116671887A true CN116671887A (en) | 2023-09-01 |
Family
ID=87785792
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310950299.6A Pending CN116671887A (en) | 2023-07-31 | 2023-07-31 | Device for screening sudden cardiac death high risk group based on photoelectric volume pulse wave signals |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116671887A (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090177102A1 (en) * | 2008-01-07 | 2009-07-09 | The General Electric Company | System, method and device for predicting sudden cardiac death risk |
| CN112494026A (en) * | 2020-09-07 | 2021-03-16 | 南京云思创智信息科技有限公司 | Non-contact-based remote sudden cardiac death early warning method |
-
2023
- 2023-07-31 CN CN202310950299.6A patent/CN116671887A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090177102A1 (en) * | 2008-01-07 | 2009-07-09 | The General Electric Company | System, method and device for predicting sudden cardiac death risk |
| CN112494026A (en) * | 2020-09-07 | 2021-03-16 | 南京云思创智信息科技有限公司 | Non-contact-based remote sudden cardiac death early warning method |
Non-Patent Citations (3)
| Title |
|---|
| 吴秋硕 等: "机器学习应用于心脏骤停早期预测模型的系统评价", 《中国循证医学杂志》, vol. 21, no. 8, pages 942 - 952 * |
| 崔晓旭: "基于数据挖掘的疾病预测组合模型研究", 《中国优秀硕士学位论文全文数据库医药卫生科技辑》, no. 12, pages 38 - 39 * |
| 陈峰: "可穿戴设备心率监测预警在院前心肺复苏急救中的应用研究", 《中国优秀硕士学位论文全文数据库医药卫生科技辑》, no. 02, pages 7 - 8 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111184508B (en) | Electrocardiosignal detection device and analysis method based on joint neural network | |
| Houssein et al. | An automatic arrhythmia classification model based on improved marine predators algorithm and convolutions neural networks | |
| CN111990989A (en) | Electrocardiosignal identification method based on generation countermeasure and convolution cyclic network | |
| CN111407243B (en) | Pulse signal pressure identification method based on deep learning | |
| CN113397555A (en) | Arrhythmia classification algorithm of C-LSTM for physiological parameter monitoring | |
| CN110638430B (en) | Method for building cascade neural network ECG signal arrhythmia classification model | |
| CN111134662A (en) | Electrocardio abnormal signal identification method and device based on transfer learning and confidence degree selection | |
| CN113095302B (en) | Depth model for arrhythmia classification, method and device using same | |
| CN109907753B (en) | Multi-dimensional ECG signal intelligent diagnosis system | |
| CN114052744B (en) | Electrocardiosignal classification method based on impulse neural network | |
| CN111544256A (en) | Brain-controlled intelligent full limb rehabilitation method based on graph convolution and transfer learning | |
| CN112906748A (en) | 12-lead ECG arrhythmia detection classification model construction method based on residual error network | |
| Qaisar et al. | Signal-piloted processing metaheuristic optimization and wavelet decomposition based elucidation of arrhythmia for mobile healthcare | |
| Fang et al. | Dual-channel neural network for atrial fibrillation detection from a single lead ECG wave | |
| US20220296169A1 (en) | System and methods for collecting and processing data on one or more physiological parameters of monitored subject | |
| Arvanaghi et al. | Classification cardiac beats using arterial blood pressure signal based on discrete wavelet transform and deep convolutional neural network | |
| CN114431873B (en) | Electrocardiogram heart rate multi-type prediction model construction method based on graph convolution | |
| CN111643074A (en) | Lossy compression electrocardiosignal atrial fibrillation screening system | |
| Liu et al. | LSTM Neural Network for Beat Classification in ECG Identity Recognition. | |
| CN112120711B (en) | Noninvasive diabetes prediction system and method based on photoplethysmography pulse waves | |
| CN114847905A (en) | Arrhythmia data detection and identification method and system | |
| Wang et al. | Ppg signal reconstruction using deep convolutional generative adversarial network | |
| CN116671887A (en) | Device for screening sudden cardiac death high risk group based on photoelectric volume pulse wave signals | |
| CN116369877A (en) | Noninvasive blood pressure estimation method based on photoelectric volume pulse wave | |
| Paila et al. | Detection and Analysis of Cardiac Arrhythmias from Heartbeat Classification |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |