CN117997352A - Optimized storage method for monitoring data of anesthesia machine - Google Patents
Optimized storage method for monitoring data of anesthesia machine Download PDFInfo
- Publication number
- CN117997352A CN117997352A CN202410405310.5A CN202410405310A CN117997352A CN 117997352 A CN117997352 A CN 117997352A CN 202410405310 A CN202410405310 A CN 202410405310A CN 117997352 A CN117997352 A CN 117997352A
- Authority
- CN
- China
- Prior art keywords
- anesthesia
- data
- cluster
- type
- association
- 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.)
- Granted
Links
- 206010002091 Anaesthesia Diseases 0.000 title claims abstract description 327
- 230000037005 anaesthesia Effects 0.000 title claims abstract description 327
- 238000000034 method Methods 0.000 title claims abstract description 78
- 238000012544 monitoring process Methods 0.000 title claims abstract description 28
- 238000007906 compression Methods 0.000 claims abstract description 71
- 230000006835 compression Effects 0.000 claims abstract description 71
- 239000006185 dispersion Substances 0.000 claims abstract description 6
- 238000001228 spectrum Methods 0.000 claims description 13
- 230000003444 anaesthetic effect Effects 0.000 claims description 11
- 238000001514 detection method Methods 0.000 claims description 8
- 230000000737 periodic effect Effects 0.000 claims description 6
- 238000005070 sampling Methods 0.000 claims description 6
- 230000009466 transformation Effects 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 13
- 238000013144 data compression Methods 0.000 abstract description 6
- 238000005457 optimization Methods 0.000 abstract description 3
- 230000000875 corresponding effect Effects 0.000 description 46
- 239000007789 gas Substances 0.000 description 8
- 238000010606 normalization Methods 0.000 description 8
- 238000004364 calculation method Methods 0.000 description 5
- 239000003814 drug Substances 0.000 description 4
- 238000012377 drug delivery Methods 0.000 description 4
- 230000003595 spectral effect Effects 0.000 description 3
- 241001123248 Arma Species 0.000 description 2
- 238000007476 Maximum Likelihood Methods 0.000 description 2
- 230000036772 blood pressure Effects 0.000 description 2
- 229940079593 drug Drugs 0.000 description 2
- 230000036387 respiratory rate Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 239000003994 anesthetic gas Substances 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
- 230000005540 biological transmission Effects 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000000857 drug effect Effects 0.000 description 1
- 239000001301 oxygen Substances 0.000 description 1
- 229910052760 oxygen Inorganic materials 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000001373 regressive effect Effects 0.000 description 1
- 230000000241 respiratory effect Effects 0.000 description 1
- 230000036391 respiratory frequency Effects 0.000 description 1
- 230000029058 respiratory gaseous exchange Effects 0.000 description 1
- 210000002345 respiratory system Anatomy 0.000 description 1
- 238000001356 surgical procedure Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H03—ELECTRONIC CIRCUITRY
- H03M—CODING; DECODING; CODE CONVERSION IN GENERAL
- H03M7/00—Conversion of a code where information is represented by a given sequence or number of digits to a code where the same, similar or subset of information is represented by a different sequence or number of digits
- H03M7/30—Compression; Expansion; Suppression of unnecessary data, e.g. redundancy reduction
- H03M7/3059—Digital compression and data reduction techniques where the original information is represented by a subset or similar information, e.g. lossy compression
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2131—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on a transform domain processing, e.g. wavelet transform
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/27—Regression, e.g. linear or logistic regression
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/60—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices
-
- H—ELECTRICITY
- H03—ELECTRONIC CIRCUITRY
- H03M—CODING; DECODING; CODE CONVERSION IN GENERAL
- H03M7/00—Conversion of a code where information is represented by a given sequence or number of digits to a code where the same, similar or subset of information is represented by a different sequence or number of digits
- H03M7/30—Compression; Expansion; Suppression of unnecessary data, e.g. redundancy reduction
- H03M7/3084—Compression; Expansion; Suppression of unnecessary data, e.g. redundancy reduction using adaptive string matching, e.g. the Lempel-Ziv method
- H03M7/3086—Compression; Expansion; Suppression of unnecessary data, e.g. redundancy reduction using adaptive string matching, e.g. the Lempel-Ziv method employing a sliding window, e.g. LZ77
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Public Health (AREA)
- General Business, Economics & Management (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- General Health & Medical Sciences (AREA)
- Business, Economics & Management (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Medical Informatics (AREA)
Abstract
The invention relates to the technical field of data compression, in particular to an optimized storage method for monitoring data of an anesthesia machine. According to the invention, the anesthesia data in each anesthesia type in time sequence are clustered to obtain clusters, and the fluctuation influence degree of each cluster is obtained according to the fluctuation, the distribution dispersion and the period significance of the anesthesia data in each cluster and the same frequency of data fluctuation; according to the position distribution among the clusters, analyzing the correlation degree between each anesthesia type and other anesthesia types to obtain the correlation difference index of each anesthesia type; and obtaining a preferred compression window for compression storage through the total quantity of the anesthesia data, the variation influence degree of the cluster and the associated difference index of the anesthesia type. According to the invention, the data change condition is analyzed more accurately, so that the selected compression window is better, the compression efficiency is high, the storage occupied space is reduced finally, and the storage optimization effect is better.
Description
Technical Field
The invention relates to the technical field of data compression, in particular to an optimized storage method for monitoring data of an anesthesia machine.
Background
The primary function of the anesthesia machine is to mix oxygen, anesthetic gas and other auxiliary gases, which are then delivered to the patient through the respiratory system. The combination of these gases may be adjusted to achieve the appropriate level of anesthesia as desired by the patient. During operation of the anesthesia machine, a large amount of monitoring data is generated, which can be monitored and recorded in real time for vital signs of the patient, anesthetic use and surgical procedures. The data volume of these data is very huge, and a large amount of storage space is occupied. And because of special conditions such as sharing of medical records, remote monitoring and the like, data stored by the anesthesia machine need to be transmitted, data compression is very important for the data stored by the anesthesia machine.
In the existing compression storage process of data, in order to improve the compression effect of the data with a repeated mode and optimize storage, the size of a compression window in an LZ77 algorithm is generally improved to obtain better compression efficiency, but anesthesia data monitored in the anesthesia process are affected by various events in the anesthesia process, different data change effects exist among different types of anesthesia data, in the existing analysis process of data change characteristics, the repeated mode of complex and various data is not combined for analysis, so that the analysis of the change characteristics of the data is inaccurate, the selection of the compression window is unreliable, the compression efficiency is poor, the final storage occupied space is still large, and the storage effect is poor.
Disclosure of Invention
In order to solve the technical problems of unreliable selection of compression windows, poor compression efficiency, large final storage occupation space and poor storage effect in the prior art, the invention aims to provide an anesthesia machine monitoring data optimized storage method, and the adopted technical scheme is as follows:
The invention provides an optimized storage method of monitoring data of an anesthesia machine, which comprises the following steps:
Acquiring anesthesia data of each anesthesia type at each sampling time in the anesthesia process; clustering the anesthesia data in each anesthesia type according to the data size and the time sequence position of all the anesthesia data in each anesthesia type to obtain a cluster corresponding to each anesthesia type;
In each cluster corresponding to each anesthesia type, according to the fluctuation, the distribution dispersion and the period significance of anesthesia data, obtaining the data change index of each cluster; obtaining the fluctuation influence degree of each cluster according to the occurrence frequency and the size of the corresponding data fluctuation index of each cluster; obtaining an associated difference index of each anesthesia type according to the associated condition of the position distribution of the cluster between each anesthesia type and other anesthesia types;
obtaining a preferred compression window according to the total quantity of all anesthesia data, the variation influence degree of each cluster and the associated difference index of each anesthesia type; all anesthetic data is stored in compression according to the preferred compression window.
Further, clustering the anesthesia data in each anesthesia type according to the data size and the time sequence position of all the anesthesia data in each anesthesia type to obtain a cluster corresponding to each anesthesia type, including:
for any anesthesia type, the data size of all anesthesia data in the anesthesia type is taken as an ordinate, time sequence information is taken as an abscissa, and a time sequence coordinate system is constructed;
And clustering the anesthesia data according to the positions of the anesthesia data in the time sequence coordinate system to obtain a cluster of the anesthesia type.
Further, the method for acquiring the data change index comprises the following steps:
For any one cluster in any anesthesia type, obtaining the fluctuation degree of each anesthesia data in the cluster through a GARCH model, and taking the average value of the fluctuation degrees of all anesthesia data in the cluster as the fluctuation of the cluster;
Obtaining the frequency spectrum of the cluster through Fourier transformation, and obtaining the periodic saliency of the cluster through integrating the amplitude spectrum density of all frequencies in the frequency spectrum through the maximum frequency and the minimum frequency;
taking the ratio of the range of anesthesia data to the average value in the cluster as the distribution discreteness of the cluster;
According to the fluctuation of the cluster, the period significance and the distribution discreteness, the data fluctuation index of the cluster is obtained; the volatility, the period significance and the distribution discreteness are in positive correlation with the data change index.
Further, the method for acquiring the variation influence degree comprises the following steps:
For any one cluster in any anesthesia type, counting the occurrence probability of the data change index of the cluster in the data change indexes of all clusters in all anesthesia types, and obtaining the occurrence frequency of the data change index corresponding to the cluster;
and taking the product of the data change index of the cluster and the corresponding occurrence frequency as the change influence degree of the cluster.
Further, the method for acquiring the association difference index comprises the following steps:
In a time sequence coordinate system, the anesthesia data with the maximum abscissa corresponding to each cluster is used as a data change point of each cluster;
For any anesthesia type, acquiring an association type of the anesthesia type and an association cluster pair of the anesthesia type and each association type according to the distance difference of the data change points in a time sequence coordinate system between the data change points of each cluster in the anesthesia type and the data change points of all clusters in other anesthesia types;
acquiring the association difference degree of the anesthesia type and each association type according to the position difference between the data change points of the association cluster pair cluster between the anesthesia type and each association type;
and taking the average value of the association difference degrees of the anesthesia type and all the association types as an association difference index of the anesthesia type.
Further, the obtaining the association type of the anesthesia type and the association cluster pairs of the anesthesia type and each association type according to the distance difference of the data change points in the time sequence coordinate system between the data change points of each cluster in the anesthesia type and the data change points of all clusters in other anesthesia types, and the association cluster pairs of the anesthesia type and each association type comprise:
Taking any one other anesthesia type corresponding to the anesthesia type as a reference type; calculating the distance between the data change points of each cluster in the anesthesia type and the data change points of each cluster in the reference type in sequence in a time sequence coordinate system to obtain an associated distance index;
When the associated distance index is smaller than or equal to the preset distance threshold, taking the reference type corresponding to the associated distance index as the associated type of the anesthesia type; and taking two cluster clusters meeting the condition that the association distance index is smaller than or equal to a preset distance threshold value as an association cluster pair of the anesthesia type and the association type.
Further, the specific expression of the association difference degree is:
In the method, in the process of the invention, Expressed as type of anesthesia/>And corresponding association type/>Related degree of difference,/>Expressed as the total number of associated cluster pairs,/>Expressed as/>Anesthesia type/>, in each associated cluster pairData change points corresponding to cluster,/>Expressed as/>Association type/>, in individual association cluster pairsData change points corresponding to cluster,/>Indicated as a preset distance threshold value,Expressed as/>The anesthesia type/>, in each associated cluster pairData change points and associated types of corresponding clusterThe distance between the data change points of the corresponding clusters in the time sequence coordinate system.
Further, the method for acquiring the preferred compression window comprises the following steps:
Taking the maximum value of the correlation difference indexes corresponding to all anesthesia types as the correlation corresponding to all anesthesia data; taking the accumulated value of the fluctuation influence degree of all clusters of all anesthesia types as the corresponding variability of all anesthesia data; normalizing the ratio of the relevance corresponding to all the anesthesia data to the variability to obtain a data characteristic index;
obtaining an initial window size according to the total number of all anesthesia data; the product of the data characteristic index and the initial window size is taken as the size of the preferred compression window.
Further, the compressing and storing all anesthesia data according to the preferred compression window includes:
And encoding the anesthesia data of each anesthesia type by adopting an LZ77 algorithm through a preferable compression window, and obtaining compressed data for storage.
Further, the method for obtaining the initial window size includes:
Taking the ratio of the total quantity of all anesthesia data to a preset detection threshold value as the initial window size; the preset detection threshold is a positive number.
The invention has the following beneficial effects:
According to the invention, the anesthesia data in each anesthesia type in time sequence are clustered to obtain clusters, each cluster represents a special event in the anesthesia process, and the influence degree on a compression window is obtained according to the data change characteristic of each special event, namely, the fluctuation influence degree of each cluster is obtained according to the fluctuation, the distribution dispersion and the period significance of the anesthesia data and the same frequency of data fluctuation. And analyzing the correlation degree between each anesthesia type and other anesthesia types according to the position distribution among the clusters to obtain a correlation difference index. According to the invention, by carrying out self analysis and relevance analysis on different clustering clusters in different data types, the data change condition is analyzed more accurately, so that the selected compression window is better, the compression efficiency is high, the storage occupation space is reduced finally, and the storage optimization effect is better.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of an optimized storage method for monitoring data of an anesthesia machine according to an embodiment of the invention.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following description refers to the specific implementation, structure, characteristics and effects of an optimized storage method for monitoring data of an anesthesia machine according to the invention by combining the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The following specifically describes a specific scheme of the anesthesia machine monitoring data optimizing and storing method provided by the invention with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of a method for optimally storing monitoring data of an anesthesia machine according to an embodiment of the invention is shown, the method includes the following steps:
S1: acquiring anesthesia data of each anesthesia type at each sampling time in the anesthesia process; clustering the anesthesia data in each anesthesia type according to the data size and the time sequence position of all the anesthesia data in each anesthesia type to obtain a cluster corresponding to each anesthesia type.
The data to be monitored by the anesthesia machine covers a plurality of aspects, and main data acquisition sources comprise physiological monitoring instruments, gas measuring instruments, drug delivery systems, monitoring system interfaces and the like. The physiological monitoring instrument can monitor heart rate, blood pressure, respiratory rate and the like; the gas measuring instrument can measure the breathing gas component; the drug delivery system may record the drug dosage and rate. Therefore, in the embodiment of the invention, the anesthesia machine acquires anesthesia data by connecting the physiological monitoring instrument, the gas measuring instrument and the drug delivery system, the variety of data to be acquired is various in the process of performing one complete anesthesia, and the anesthesia data of each anesthesia type at each sampling time in the anesthesia process are acquired for completely storing the monitored data change in the anesthesia process.
In the embodiment of the invention, the preset sampling interval is set to be 0.5 seconds, namely, each item of data is acquired every 0.5 seconds in the anesthesia process, each item of data is the monitored anesthesia data of various anesthesia types, the sampling time is the time corresponding to the data acquisition time every 0.5 seconds in the anesthesia starting process, and the anesthesia types comprise but are not limited to heart rate, blood pressure, respiratory frequency, respiratory gas component medicine dosage and medicine transmission speed. It should be noted that, the collected anesthesia data has been normalized to eliminate the influence of different dimension on analysis and calculation, and the collection process and normalization process of the data are all technical means well known to those skilled in the art, which are not described herein.
Because the monitoring data in the anesthesia process is the data which shows a certain regular change, the repeated data can be identified and compressed through the compression window, in the embodiment of the invention, the LZ77 algorithm is adopted to compress through the compression window, the LZ77 algorithm can be used for efficiently compressing the data with repeated contents or modes, and the LZ77 algorithm is a technical means well known to the person skilled in the art and is not described herein.
However, during the anesthesia process, the monitored anesthesia data will not always remain in a steady state until the end, and the anesthesia data will be changed differently due to special events during the anesthesia process, such as the administration of drugs during the operation phase, etc., which will change the anesthesia data, resulting in various changes in the data of the physiological parameters, gas level, drug effect, etc. of the anesthetized person. The variable anesthetic data can lead the compression effect of the data to be poor in the compression and storage process and occupy larger storage space, so the invention analyzes the anesthetic data of the special events, optimizes the compression window and leads the compression effect of the anesthetic data to be better.
The data changes due to special events may be time-series and the different types of anesthesia may be affected differently, for example, drug delivery may be reduced when the anesthetized person is in a recovery phase after the end of the procedure, but other data such as heart rate and respiratory rate may remain relatively stable. Therefore, the anesthesia data in each anesthesia type can be clustered according to the data size and the time sequence position of all the anesthesia data in each anesthesia type, and a cluster corresponding to each anesthesia type is obtained. The characteristics of each cluster represent the impact of a particular event to which each type of anesthesia is subjected.
Preferably, for any one anesthesia type, the data size of all anesthesia data in the anesthesia type is taken as an ordinate, time sequence information is taken as an abscissa, a time sequence coordinate system is constructed, wherein the time sequence information is the time for collecting each anesthesia data, the time sequence change condition of each anesthesia type on time sequence is reflected through the time sequence coordinate system, and different events can be divided through clustering according to the position coordinates in the time sequence coordinate system.
In one embodiment of the invention, a DBSCAN clustering algorithm is adopted for clustering, and the anesthesia data in the anesthesia type is clustered according to the position of the anesthesia data in a time sequence coordinate system, so as to obtain a cluster of the anesthesia type. Each cluster represents a special event, and the anesthesia data change in the clusters can reflect the data change condition of the corresponding special event.
In the DBSCAN clustering process in the embodiment of the present invention, the neighborhood radius is set to be 4, the minimum density point number is set to be 5, and a specific numerical value implementer can adjust according to specific implementation conditions, and it should be noted that the DBSCAN clustering algorithm is a technical means well known to those skilled in the art, and will not be described herein.
So far, considering that anesthesia data is influenced by different events, the cluster in each anesthesia type is obtained, and the compression window for compression can be adjusted through the characteristics of the cluster, so that a better compression effect is achieved.
S2: in each cluster corresponding to each anesthesia type, according to the fluctuation, the distribution dispersion and the period significance of anesthesia data, obtaining the data change index of each cluster; obtaining the fluctuation influence degree of each cluster according to the occurrence frequency and the size of the corresponding data fluctuation index of each cluster; and obtaining an associated difference index of each anesthesia type according to the associated condition of the position distribution of the cluster between each anesthesia type and other anesthesia types.
For each special event, the data change characteristics caused by the special event can influence the data compression result, so that the data change of each cluster is analyzed, and the data change index of each cluster is obtained through comprehensive analysis of three aspects of fluctuation, distribution discreteness and cycle significance of anesthesia data.
Preferably, for any one of the anesthesia types, the fluctuation degree of each anesthesia data in the cluster is obtained through a GARCH model, wherein the GARCH model is a generalized autoregressive conditional heteroscedastic (GENERALISED AUTO REGRESSIVE CONDITIONAL HETEROSKEDASTICITY, GARCH) model, so that the fluctuation dynamic change of each anesthesia data can be analyzed, and the abnormal fluctuation mode corresponding to each cluster is better reflected, and in the embodiment of the invention, the specific expression of the fluctuation degree of each anesthesia data in the cluster is as follows:
In the method, in the process of the invention, Expressed as/>Fluctuation degree of individual anesthesia data,/>Wave constant term expressed as GARCH model,/>Expressed as autoregressive order of the GARCH model,/>Expressed as/>Auto regression coefficient corresponding to order,/>Expressed as front in the cluster/>Residual square of individual anesthesia data,/>Generalized autoregressive order expressed as GARCH model,/>Expressed as/>Generalized autoregressive coefficients corresponding to the order,/>Expressed as front in the cluster/>Fluctuation of individual anesthesia data.
In the calculation of the GARCH model in the embodiment of the invention, an autoregressive moving average (Auto-REGRESSIVE MOVING AVERAGE, ARMA) model is used to obtain the mean value part in the GARCH model,And/>The value of (2), parameter/>，/>And/>And obtaining by adopting a maximum likelihood estimation method. It is noted that/>The calculation mode of the method is a general form equation of a GARCH model, the GARCH model, an ARMA model and a maximum likelihood estimation method are all technical means well known to the skilled person, and the calculation formula of the fluctuation degree is the application of the existing GARCH model, and the specific meaning of the formula is not explained.
Further obtaining the fluctuation of the cluster, taking the average value of the fluctuation degrees of all anesthesia data in the cluster as the fluctuation of the cluster, wherein in the embodiment of the invention, the expression of the fluctuation of the cluster is as follows:
In the method, in the process of the invention, Expressed as/>Volatility of individual clusters,/>Expressed as/>Total number of anesthesia data in each cluster,/>Expressed as/>Fluctuation of individual anesthesia data.
After analyzing the fluctuation degree of the data in the cluster, analyzing the cycle significance of the data in the cluster, and when the cycle in the cluster is obvious, characterizing more repeated information through a larger compression window, therefore, preferably, obtaining a frequency spectrum of the cluster through Fourier transformation, wherein the fluctuation cycle condition of the data can be reflected through the frequency spectrum, and integrating the amplitude spectrum density of all frequencies through the maximum frequency and the minimum frequency in the frequency spectrum to obtain the cycle significance of the cluster, wherein in the embodiment of the invention, the specific expression of the cycle significance is as follows:
Wherein, Expressed as/>Periodic saliency of individual clusters,/>Represented as the frequency minima in the frequency spectrum,Expressed as the frequency maxima in the frequency spectrum,/>Expressed as frequency/>, in the corresponding spectrum of clustersThe amplitude spectral density at which,The epitope is the result of taking a definite integral of the amplitude spectral density. It should be noted that fourier transform, amplitude spectral density and fixed integral are well known techniques known to those skilled in the art, and will not be described herein.
The greater the periodicity salience, the more obvious the periodicity of the data in the cluster is reflected, and when the periodicity is more obvious, the more repeatable the change of the data is indicated, more repeated information can be reflected through a larger compression window. Finally, analyzing the distribution discreteness of the anesthesia data, and preferably taking the ratio of the range of the anesthesia data to the average value in the cluster as the distribution discreteness of the cluster. When the distribution discreteness is larger, the distribution range of the anesthesia data in the clustering cluster is larger, and the distribution is more discrete.
According to the three aspects, according to the fluctuation, the periodic saliency and the distribution discreteness of the cluster, the data change index of the cluster is obtained, the data change characteristics of the cluster are reflected through the data change index, and the fluctuation, the periodic saliency and the distribution discreteness are in positive correlation with the data change index. In the embodiment of the invention, the specific expression of the data change index is:
In the method, in the process of the invention, Expressed as/>Data change index of each cluster,/>Expressed as/>Periodic saliency of individual clusters,/>Expressed as/>Volatility of individual clusters,/>Expressed as/>Maximum value of anesthesia data in each cluster,/>Expressed as/>Minimum value of anesthesia data in each cluster,/>Expressed as/>Average of anesthesia data in each cluster.
Wherein,Expressed as/>Extremely bad anesthetic data in each cluster,/>Expressed as/>Distribution discreteness of anesthetic data in the clusters. When the fluctuation of the cluster is larger, the period significance and the distribution discreteness are larger, which means that the fluctuation degree of the data in the cluster is more obvious, the fluctuation range is large, the period is obvious, and more repeated information can be obtained through a larger compression window. In the embodiment of the invention, the fluctuation is reflected in a multiplication mode, the cycle significance and the distribution discreteness are in positive correlation with the data fluctuation index, and in other embodiments of the invention, the fluctuation can be reflected by other basic mathematical operations, and the cycle significance and the distribution discreteness are in positive correlation with the data fluctuation index, such as addition and the like, without limitation.
Because different anesthesia types correspond to a plurality of clusters, the change characteristics of the data have a certain diversity, different weights are given to different data change characteristics through frequencies, and the data change characteristics with a large occurrence number have a stronger duty ratio when a final compression window is considered, so that the change influence degree of each cluster is obtained according to the occurrence frequency and the size of the data change index corresponding to each cluster.
Preferably, for any one cluster in any anesthesia type, the probability that the size of the data change index of the cluster appears in the data change indexes of all clusters in all anesthesia types is counted, the frequency of occurrence of the data change index corresponding to the cluster is obtained, and the frequency of occurrence reflects the duty ratio degree of each data change characteristic. And taking the product of the data change index of the cluster and the corresponding occurrence frequency as the change influence degree of the cluster.
So far, the analysis of the change of the data set of each cluster is completed, and the influence degree of the change characteristics of the data in each cluster on the compression window is reflected by the change influence degree. Because the anesthesia data of different anesthesia types causes the data change in time sequence due to special events, when one special event simultaneously causes the anesthesia data of a plurality of anesthesia types to change together, the data change of the overall anesthesia data is proved to have a repeated mode, and at the moment, the compression effect can be improved by adjusting the compression window.
The correlation among the clusters is analyzed, and when the more the clusters are correlated in the anesthesia data, the higher the synchronism of the data change characteristics caused by special events is, and when the data are compressed and stored, the compression efficiency can be improved through a higher repetition mode. Because the special events of the association of the anesthesia data of different anesthesia types occur synchronously in time sequence, the association difference index of each anesthesia type is obtained between each anesthesia type and other anesthesia types according to the association condition of the position distribution of the cluster.
Preferably, in order to more conveniently determine the position relationship between the clusters, in the time sequence coordinate system, the anesthesia data with the largest abscissa corresponding to each cluster is used as the data change point of each cluster, wherein the size of the abscissa represents the time sequence information of each anesthesia data, and the data change point is the point where the data change occurs between the clusters and is used for reflecting the position information of each cluster.
For any anesthesia type, the association type of the anesthesia type is obtained according to the distance difference of the data change points in a time sequence coordinate system between the data change points of each cluster in the anesthesia type and the data change points of all clusters in other anesthesia types, and the association cluster pairs of the anesthesia type and each association type reflect the position difference condition of the clusters on time sequence through the distance between the data change points, the association type associated with the anesthesia type can be screened out according to the difference, and the association cluster pairs between the anesthesia type and the association type are obtained at the same time.
For the convenience of analysis, any one of other anesthesia types corresponding to the anesthesia type is used as a reference type, and all other anesthesia types except the anesthesia type can be used as the reference type for analysis and calculation. Preferably, the distance between the data change point of each cluster in the anesthesia type and the data change point of each cluster in the reference type in sequence is calculated in a time sequence coordinate system, so as to obtain a correlation distance index, namely, the distance between each data change point in the anesthesia type and all the data change points in the reference type is calculated, so that a plurality of correlation distance indexes are obtained. The distance is the Euclidean distance between two data change points in the time sequence coordinate system, and the Euclidean distance is a technical means known to those skilled in the art, and is not described herein.
When the associated distance index is smaller than or equal to the preset distance threshold, the special event related to the anesthesia type exists in the reference type, so that the reference type corresponding to the associated distance index is used as the associated type of the anesthesia type. And simultaneously, two cluster clusters meeting the condition that the association distance index is smaller than or equal to a preset distance threshold value are taken as association cluster pairs of the anesthesia type and the association type, wherein a plurality of association cluster pairs exist between the anesthesia type and the association type, but at least one association cluster pair exists. In the embodiment of the present invention, the preset distance threshold is set to 5, and the specific numerical value implementation can be adjusted according to the specific implementation situation.
Between the anesthesia type and each association type, according to the position difference between the data change points of the cluster in the association cluster pair, obtaining the association difference degree of the anesthesia type and each association type, wherein the association cluster pair reflects two clusters subjected to the same special event and having data change, the similarity degree of the clusters subjected to the same data change in time is further reflected through the cluster position difference in the association cluster pair, and the association difference degree is obtained, in the embodiment of the invention, the anesthesia type is obtainedAnd corresponding association type/>The specific expression of the association difference degree of (2) is as follows:
In the method, in the process of the invention, Expressed as type of anesthesia/>And corresponding association type/>Related degree of difference,/>Expressed as the total number of associated cluster pairs,/>Expressed as/>Anesthesia type/>, in each associated cluster pairData change points corresponding to cluster,/>Expressed as/>Association type/>, in individual association cluster pairsData change points corresponding to cluster,/>Indicated as a preset distance threshold value,Expressed as/>The anesthesia type/>, in each associated cluster pairData change points and associated types of corresponding clusterThe distance between the data change points of the corresponding clusters in the time sequence coordinate system.
The method comprises the steps of calculating the association difference degree, wherein the association range is controlled when the distance threshold is preset, and the smaller the association difference degree is, the more consistent the data change generated by the same special event is, the smaller the association difference degree is, and the higher the association degree of the two anesthesia types is. When the association degree is larger, the association degree between the two anesthesia types is lower, and the association degree is larger, so that the selection of a compression window is influenced finally.
Each anesthesia type may have different association relations with a plurality of anesthesia types, so that an average value of association differences between the anesthesia type and all the association types is used as an association difference index of the anesthesia type, and in the embodiment of the invention, the specific expression of the association difference index is as follows:
In the method, in the process of the invention, Expressed as type of anesthesia/>Related difference index,/>Expressed as type of anesthesia/>Total number of all association types,/>Expressed as type of anesthesia/>And corresponds to the/>Association variability of individual association types.
So far, based on the cluster representing the special event, the feature of the data change in each cluster is considered, the position distribution feature of the clusters among different types of anesthesia data is considered, and the analysis of the anesthesia data is completed.
S3: obtaining a preferred compression window according to the total quantity of all anesthesia data, the variation influence degree of each cluster and the associated difference index of each anesthesia type; all anesthetic data is stored in compression according to the preferred compression window.
In the embodiment of the invention, the LZ77 algorithm is selected for compression, and the selection of the initial window is usually based on the data volume, in the anesthesia process of the invention, the size of the initial window can be determined according to the total data amount of the collected anesthesia data because the collected monitoring data is the data of the whole anesthesia process, and the preferred window is further obtained according to the association condition between the data change characteristics of the cluster in different anesthesia types and the anesthesia types.
Preferably, the maximum value of the correlation difference index corresponding to all the anesthesia types is used as the correlation corresponding to all the anesthesia data, and as all the anesthesia data of the anesthesia types are acquired on the same time sequence, the maximum value of one correlation difference index is selected to reflect the worst correlation condition of the anesthesia data of different types, so that the selected window meets the compression requirement of all the anesthesia types as much as possible.
Further taking the accumulated value of the fluctuation influence of all the clusters of all the anesthesia types as the corresponding variability of all the anesthesia data, adding and summing the influence of each cluster on the compression window, and reflecting the total influence of all the clusters through the variability. And carrying out normalization processing on the correlation and variability ratio corresponding to all the anesthesia data to obtain a data characteristic index, wherein the data characteristic index reflects the adjustment degree required by the compression window.
According to the total amount of all the anesthesia data, the initial window size is obtained, in one embodiment of the invention, the ratio of the total amount of all the anesthesia data to the preset detection threshold is used as the initial window size, in the embodiment of the invention, the preset detection threshold is positive, the preset detection threshold is set to be 100, namely, the compression window is detected for 100 times at least to complete data compression, and a specific numerical value implementer can adjust according to specific implementation conditions. In other embodiments of the present invention, the compression control parameter may be set according to the system resource, and the initial window size is obtained by using the total amount of the anesthesia data and the compression control parameter, which is not described herein.
Finally, taking the product of the data characteristic index and the initial window size as the size of the preferred compression window to obtain the preferred compression window, wherein in the embodiment of the invention, the specific expression for obtaining the size of the preferred compression window is as follows:
In the method, in the process of the invention, Expressed as the size of the preferred compression window,/>Expressed as the total number of all anaesthetic data,/>Expressed as a preset detection threshold,/>Expressed as the correlation of all anaesthetic data correspondence,/>Expressed as/>The type of anesthesia is/>Data change index of each cluster,/>Expressed as/>The type of anesthesia is/>Frequency of occurrence of clusters,/>Expressed as total number of types of anesthesia,/>Expressed as/>Total number of clusters in anesthesia type. /(I)It should be noted that, normalization is a technical means well known to those skilled in the art, and the normalization function may be selected as a linear normalization, and in other embodiments of the present invention, a standard normalization method or a maximum-minimum normalization method may also be selected, and the specific normalization method is not limited herein.
Wherein,Expressed as/>The type of anesthesia is/>The degree of fluctuation influence of the individual clusters,Expressed as variability corresponding to all anesthesia data,/>Expressed as data characteristic index corresponding to all anesthesia data,/>Represented as an initial window size. When the variability is larger, the fluctuation degree of the data change characteristics is obvious, the period is obvious, the compression window can be increased to obtain more repeated information, and when the relevance is larger, the data change relevance among different anesthesia types is poorer, and the data change has the characteristic of being unique, so that the compression window needs to be reduced, and the data compression amount is reduced.
Finally, all the anesthesia data are compressed and stored according to the optimized compression window, in the embodiment of the invention, the optimized compression window is used for sequentially encoding the anesthesia data of each anesthesia type by adopting an LZ77 algorithm to obtain the compressed data, the compression encoding process has higher inclusion on the monitored complex type data, the robustness of compression is improved, the stored data can improve the compression efficiency after the compressed data are stored, the occupied space is saved, and the optimal storage and the better storage optimization effect are realized.
In summary, the invention obtains cluster clusters by clustering the anesthesia data in each anesthesia type in time sequence, characterizes special events in the anesthesia process by each cluster, and obtains the influence degree of the compression window according to the data change characteristics of each special event, namely obtains the fluctuation influence degree of each cluster according to the fluctuation, the distribution dispersion and the period significance of the anesthesia data and the same frequency of data fluctuation. And analyzing the correlation degree between each anesthesia type and other anesthesia types according to the position distribution among the clusters to obtain a correlation difference index. The compression window is comprehensively optimized through changing influence degree and associated difference indexes, so that compression efficiency is improved.
It should be noted that: the sequence of the embodiments of the present invention is only for description, and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments.
Claims (10)
1. An optimized storage method for monitoring data of an anesthesia machine, which is characterized by comprising the following steps:
Acquiring anesthesia data of each anesthesia type at each sampling time in the anesthesia process; clustering the anesthesia data in each anesthesia type according to the data size and the time sequence position of all the anesthesia data in each anesthesia type to obtain a cluster corresponding to each anesthesia type;
In each cluster corresponding to each anesthesia type, according to the fluctuation, the distribution dispersion and the period significance of anesthesia data, obtaining the data change index of each cluster; obtaining the fluctuation influence degree of each cluster according to the occurrence frequency and the size of the corresponding data fluctuation index of each cluster; obtaining an associated difference index of each anesthesia type according to the associated condition of the position distribution of the cluster between each anesthesia type and other anesthesia types;
obtaining a preferred compression window according to the total quantity of all anesthesia data, the variation influence degree of each cluster and the associated difference index of each anesthesia type; all anesthetic data is stored in compression according to the preferred compression window.
2. The method for optimally storing monitoring data of an anesthesia machine according to claim 1, wherein the clustering of the anesthesia data in each anesthesia type according to the data size and the time sequence position of all the anesthesia data in each anesthesia type to obtain a cluster corresponding to each anesthesia type comprises the following steps:
for any anesthesia type, the data size of all anesthesia data in the anesthesia type is taken as an ordinate, time sequence information is taken as an abscissa, and a time sequence coordinate system is constructed;
And clustering the anesthesia data according to the positions of the anesthesia data in the time sequence coordinate system to obtain a cluster of the anesthesia type.
3. The method for optimally storing monitoring data of an anesthesia machine according to claim 1, wherein the method for acquiring the data change index comprises the steps of:
For any one cluster in any anesthesia type, obtaining the fluctuation degree of each anesthesia data in the cluster through a GARCH model, and taking the average value of the fluctuation degrees of all anesthesia data in the cluster as the fluctuation of the cluster;
Obtaining the frequency spectrum of the cluster through Fourier transformation, and obtaining the periodic saliency of the cluster through integrating the amplitude spectrum density of all frequencies in the frequency spectrum through the maximum frequency and the minimum frequency;
taking the ratio of the range of anesthesia data to the average value in the cluster as the distribution discreteness of the cluster;
According to the fluctuation of the cluster, the period significance and the distribution discreteness, the data fluctuation index of the cluster is obtained; the volatility, the period significance and the distribution discreteness are in positive correlation with the data change index.
4. The method for optimally storing monitoring data of an anesthesia machine according to claim 1, wherein the method for acquiring the fluctuation influence comprises the steps of:
For any one cluster in any anesthesia type, counting the occurrence probability of the data change index of the cluster in the data change indexes of all clusters in all anesthesia types, and obtaining the occurrence frequency of the data change index corresponding to the cluster;
and taking the product of the data change index of the cluster and the corresponding occurrence frequency as the change influence degree of the cluster.
5. The method for optimally storing monitoring data of an anesthesia machine according to claim 2, wherein the method for acquiring the associated difference index comprises the following steps:
In a time sequence coordinate system, the anesthesia data with the maximum abscissa corresponding to each cluster is used as a data change point of each cluster;
For any anesthesia type, acquiring an association type of the anesthesia type and an association cluster pair of the anesthesia type and each association type according to the distance difference of the data change points in a time sequence coordinate system between the data change points of each cluster in the anesthesia type and the data change points of all clusters in other anesthesia types;
acquiring the association difference degree of the anesthesia type and each association type according to the position difference between the data change points of the association cluster pair cluster between the anesthesia type and each association type;
and taking the average value of the association difference degrees of the anesthesia type and all the association types as an association difference index of the anesthesia type.
6. The method for optimally storing monitoring data of an anesthesia machine according to claim 5, wherein the obtaining the association type of the anesthesia type and the association cluster pairs of the anesthesia type and each association type according to the distance difference of the data change points in the time sequence coordinate system between the data change points of each cluster in the anesthesia type and the data change points of all clusters in other anesthesia types comprises:
Taking any one other anesthesia type corresponding to the anesthesia type as a reference type; calculating the distance between the data change points of each cluster in the anesthesia type and the data change points of each cluster in the reference type in sequence in a time sequence coordinate system to obtain an associated distance index;
When the associated distance index is smaller than or equal to the preset distance threshold, taking the reference type corresponding to the associated distance index as the associated type of the anesthesia type; and taking two cluster clusters meeting the condition that the association distance index is smaller than or equal to a preset distance threshold value as an association cluster pair of the anesthesia type and the association type.
7. The optimized storage method of monitoring data of anesthesia machine according to claim 5, wherein the specific expression of the association difference degree is:
In the method, in the process of the invention, Expressed as type of anesthesia/>And corresponding association type/>Related degree of difference,/>Expressed as the total number of associated cluster pairs,/>Expressed as/>Anesthesia type/>, in each associated cluster pairData change points corresponding to cluster,/>Expressed as/>Association type/>, in individual association cluster pairsData change points corresponding to cluster,/>Indicated as a preset distance threshold value,Expressed as/>The anesthesia type/>, in each associated cluster pairData change points and associated types of corresponding clusterThe distance between the data change points of the corresponding clusters in the time sequence coordinate system.
8. The method for optimally storing monitoring data of an anesthesia machine according to claim 1, wherein the method for acquiring the preferred compression window comprises the steps of:
Taking the maximum value of the correlation difference indexes corresponding to all anesthesia types as the correlation corresponding to all anesthesia data; taking the accumulated value of the fluctuation influence degree of all clusters of all anesthesia types as the corresponding variability of all anesthesia data; normalizing the ratio of the relevance corresponding to all the anesthesia data to the variability to obtain a data characteristic index;
obtaining an initial window size according to the total number of all anesthesia data; the product of the data characteristic index and the initial window size is taken as the size of the preferred compression window.
9. The optimized storage method of monitoring data of anesthesia machine according to claim 1, wherein the compressing and storing all anesthesia data according to the preferred compression window comprises:
And encoding the anesthesia data of each anesthesia type by adopting an LZ77 algorithm through a preferable compression window, and obtaining compressed data for storage.
10. The method for optimally storing monitoring data of an anesthesia machine according to claim 8, wherein the method for obtaining the initial window size comprises:
Taking the ratio of the total quantity of all anesthesia data to a preset detection threshold value as the initial window size; the preset detection threshold is a positive number.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410405310.5A CN117997352B (en) | 2024-04-07 | 2024-04-07 | Optimized storage method for monitoring data of anesthesia machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410405310.5A CN117997352B (en) | 2024-04-07 | 2024-04-07 | Optimized storage method for monitoring data of anesthesia machine |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117997352A true CN117997352A (en) | 2024-05-07 |
| CN117997352B CN117997352B (en) | 2024-05-31 |
Family
ID=90901258
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410405310.5A Active CN117997352B (en) | 2024-04-07 | 2024-04-07 | Optimized storage method for monitoring data of anesthesia machine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117997352B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170251980A1 (en) * | 2016-03-02 | 2017-09-07 | Roche Diabetes Care, Inc. | Patient diabetes monitoring system with clustering of unsupervised daily cgm profiles (or insulin profiles) and method thereof |
| CN117235548A (en) * | 2023-11-15 | 2023-12-15 | 山东济宁运河煤矿有限责任公司 | Coal quality data processing method and intelligent system based on laser firing |
| CN117290364A (en) * | 2023-11-24 | 2023-12-26 | 深圳市成为高科技有限公司 | Intelligent market investigation data storage method |
| CN117459418A (en) * | 2023-12-25 | 2024-01-26 | 天津神州海创科技有限公司 | Real-time data acquisition and storage method and system |
| CN117556279A (en) * | 2024-01-12 | 2024-02-13 | 江苏雷博微电子设备有限公司 | Method and system for monitoring running state of spin coater based on electrical parameter analysis |
| CN117609813A (en) * | 2024-01-23 | 2024-02-27 | 山东第一医科大学附属省立医院(山东省立医院) | Intelligent management method for intensive patient monitoring data |
| CN117668583A (en) * | 2024-02-01 | 2024-03-08 | 泰安北航科技园信息科技有限公司 | Investment optimization method based on artificial intelligent investment research |
| CN117828511A (en) * | 2024-03-04 | 2024-04-05 | 中国中医科学院广安门医院 | Anesthesia depth electroencephalogram signal data processing method |
-
2024
- 2024-04-07 CN CN202410405310.5A patent/CN117997352B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170251980A1 (en) * | 2016-03-02 | 2017-09-07 | Roche Diabetes Care, Inc. | Patient diabetes monitoring system with clustering of unsupervised daily cgm profiles (or insulin profiles) and method thereof |
| CN117235548A (en) * | 2023-11-15 | 2023-12-15 | 山东济宁运河煤矿有限责任公司 | Coal quality data processing method and intelligent system based on laser firing |
| CN117290364A (en) * | 2023-11-24 | 2023-12-26 | 深圳市成为高科技有限公司 | Intelligent market investigation data storage method |
| CN117459418A (en) * | 2023-12-25 | 2024-01-26 | 天津神州海创科技有限公司 | Real-time data acquisition and storage method and system |
| CN117556279A (en) * | 2024-01-12 | 2024-02-13 | 江苏雷博微电子设备有限公司 | Method and system for monitoring running state of spin coater based on electrical parameter analysis |
| CN117609813A (en) * | 2024-01-23 | 2024-02-27 | 山东第一医科大学附属省立医院(山东省立医院) | Intelligent management method for intensive patient monitoring data |
| CN117668583A (en) * | 2024-02-01 | 2024-03-08 | 泰安北航科技园信息科技有限公司 | Investment optimization method based on artificial intelligent investment research |
| CN117828511A (en) * | 2024-03-04 | 2024-04-05 | 中国中医科学院广安门医院 | Anesthesia depth electroencephalogram signal data processing method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117997352B (en) | 2024-05-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20240023886A1 (en) | Noninvasive method and system for sleep apnea detection | |
| US7299088B1 (en) | Apparatus and methods for brain rhythm analysis | |
| AU2005318949B2 (en) | Method for detecting and disciminatng breathing patterns from respiratory signals | |
| Papini et al. | Photoplethysmography beat detection and pulse morphology quality assessment for signal reliability estimation | |
| Meng et al. | Detection of respiratory sounds based on wavelet coefficients and machine learning | |
| US20120016218A1 (en) | Discrimination of cheyne-stokes breathing patterns by use of oximetry signals | |
| EP3410924A1 (en) | Machine learnt model to detect rem sleep periods using a spectral analysis of heart rate and motion | |
| WO2014036173A1 (en) | Methods and systems for calculating and using statistical models to predict medical events | |
| Casaseca-de-la-Higuera et al. | Weaning from mechanical ventilation: a retrospective analysis leading to a multimodal perspective | |
| CN115868941A (en) | Information management method for intelligent ring | |
| CN117997352B (en) | Optimized storage method for monitoring data of anesthesia machine | |
| WO2021034960A1 (en) | Systems and methods for imputing real-time physiological signals | |
| CN117579080B (en) | Medical care remote monitoring system based on 5G communication | |
| Ali et al. | A novel technique to diagnose sleep apnea in suspected patients using their ECG data | |
| CN115251856B (en) | Pulse strength judging method and device, electronic equipment and storage medium | |
| Sepúlveda-Cano et al. | Relevance analysis of stochastic biosignals for identification of pathologies | |
| Rizal et al. | Lung sound classification using wavelet transform and entropy to detect lung abnormality | |
| CN116631563A (en) | Big data storage and intelligent matching method for pharmaceutical industry | |
| Rolink et al. | Improving sleep/wake classification with recurrence quantification analysis features | |
| Salatian et al. | A data wavelets approach to deriving trends in historical ICU monitor data | |
| CN118000683B (en) | Anesthesia depth monitoring method and system based on artificial intelligence | |
| CN118512156B (en) | Prediction method of intraoperative anesthesia depth and related equipment | |
| Al Rasyid et al. | Anomaly detection in wireless body area network using Mahalanobis distance and sequential minimal optimization regression | |
| Chuiko et al. | Abdominal electromyograms mining: breathing patterns of asleep adults | |
| US20230309855A1 (en) | Respiration rate monitoring system and method |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |