CN117633625A - Gynaecology and obstetrics postoperative care data analysis method and system based on big data - Google Patents
Gynaecology and obstetrics postoperative care data analysis method and system based on big data Download PDFInfo
- Publication number
- CN117633625A CN117633625A CN202311640109.7A CN202311640109A CN117633625A CN 117633625 A CN117633625 A CN 117633625A CN 202311640109 A CN202311640109 A CN 202311640109A CN 117633625 A CN117633625 A CN 117633625A
- Authority
- CN
- China
- Prior art keywords
- data
- historical
- postoperative care
- gynecological
- gynecological postoperative
- 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
- 230000002980 postoperative effect Effects 0.000 title claims abstract description 359
- 238000007405 data analysis Methods 0.000 title claims abstract description 82
- 238000000034 method Methods 0.000 title claims abstract description 55
- 230000009467 reduction Effects 0.000 claims abstract description 60
- 230000000474 nursing effect Effects 0.000 claims abstract description 23
- 238000012795 verification Methods 0.000 claims abstract description 20
- 238000004458 analytical method Methods 0.000 claims abstract description 18
- 238000013135 deep learning Methods 0.000 claims abstract description 8
- 238000003860 storage Methods 0.000 claims abstract description 7
- 238000010276 construction Methods 0.000 claims abstract description 5
- 238000011084 recovery Methods 0.000 claims description 60
- 239000011159 matrix material Substances 0.000 claims description 53
- 239000013598 vector Substances 0.000 claims description 25
- 238000012360 testing method Methods 0.000 claims description 18
- 238000006243 chemical reaction Methods 0.000 claims description 17
- 230000006870 function Effects 0.000 claims description 17
- 230000036541 health Effects 0.000 claims description 12
- 238000005457 optimization Methods 0.000 claims description 12
- 238000007781 pre-processing Methods 0.000 claims description 12
- 238000012216 screening Methods 0.000 claims description 12
- 238000012549 training Methods 0.000 claims description 12
- 238000004880 explosion Methods 0.000 claims description 11
- 230000008859 change Effects 0.000 claims description 9
- 238000009825 accumulation Methods 0.000 claims description 7
- 230000001154 acute effect Effects 0.000 claims description 6
- 230000001684 chronic effect Effects 0.000 claims description 6
- 238000001514 detection method Methods 0.000 claims description 6
- 230000002441 reversible effect Effects 0.000 claims description 6
- 230000000739 chaotic effect Effects 0.000 claims description 4
- 238000013507 mapping Methods 0.000 claims description 4
- 238000000586 desensitisation Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 2
- 238000012545 processing Methods 0.000 claims description 2
- 230000007547 defect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000000513 principal component analysis Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 230000007480 spreading Effects 0.000 description 1
- 238000003892 spreading Methods 0.000 description 1
Classifications
-
- 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
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention belongs to the technical field of data analysis, and discloses a gynecological postoperative care data analysis method and system based on big data. The method comprises the following steps: collecting historical gynecological postoperative care big data of a historical patient; performing data dimension reduction; carrying out data clustering; sample equalization is carried out; constructing a gynecological postoperative care data analysis model by using a deep learning algorithm; performing patient verification; performing gynecological postoperative care data analysis on real-time gynecological postoperative care data; and storing analysis results of the gynecological postoperative care data. The system comprises a big data acquisition unit, a data dimension reduction unit, a data clustering unit, a sample equalization unit, a model construction unit, a patient verification unit, a nursing data analysis unit and an analysis result storage unit which are connected in sequence. The invention solves the problems of large labor cost investment, large workload and poor accuracy in the prior art.
Description
Technical Field
The invention belongs to the technical field of data analysis, and particularly relates to a gynecological postoperative care data analysis method and system based on big data.
Background
With the rapid development of the information society and the arrival of the big data age, higher requirements and higher pressures are put forward for data analysis, and with the popularization of big data technology, the method is widely applied to the medical field. Among them, gynaecology and obstetrics is an important department of hospitals, involves a large number of gynaecology and obstetrics operations, and the data generated and having analysis requirements are also huge. And, carry out analysis to postoperative care data, have important meaning to patient's recovery.
In the prior art, analysis is carried out on postoperative care data, most of the analysis depends on professional knowledge and rich experience of nurses, the investment of labor cost is large, the workload is large, and meanwhile, the pressure on medical treatment and nursing resources is large; through nurse personnel to the numerical meaning of postoperative care data read, grasp patient's gynaecology and obstetrics postoperative and resume the condition, but this kind of mode can't excavate the degree of depth data characteristic of postoperative care data, leads to carrying out misjudgement to gynaecology and obstetrics postoperative and resume the condition easily, influences subsequent postoperative care strategy.
Disclosure of Invention
The invention aims to solve the problems of high labor cost, high workload and poor accuracy in the prior art, and provides a gynecological postoperative care data analysis method and system based on big data.
The technical scheme adopted by the invention is as follows:
a gynecological postoperative care data analysis method based on big data comprises the following steps:
collecting historical gynecological postoperative care big data of a historical patient, and preprocessing the historical gynecological postoperative care big data to obtain a preprocessed historical gynecological postoperative care data set;
performing data dimension reduction on the preprocessed historical gynecological postoperative care data set to obtain a data dimension reduction historical gynecological postoperative care data set;
performing data clustering on the historical gynecological postoperative care data set after the data dimension reduction to obtain a plurality of historical gynecological postoperative recovery level clusters;
sample equalization is carried out on a plurality of historical gynaecology and obstetrics postoperative recovery level clusters, and an equalized historical gynaecology and obstetrics postoperative care data set is obtained;
according to the equalized historical gynecological postoperative care data set, a deep learning algorithm is used for constructing a gynecological postoperative care data analysis model;
collecting patient information of a current patient, performing patient verification on the patient information, connecting a patient database of a data center if the patient verification is passed, and collecting real-time gynecological postoperative care data of the current patient;
using a gynecological postoperative care data analysis model to analyze the real-time gynecological postoperative care data to obtain a gynecological postoperative care data analysis result;
And storing the analysis result of the gynecological postoperative care data of the current patient into a corresponding patient database.
Further, the historical gynecological postoperative care data comprises historical health inquiry data, historical clinical detection data, historical acute physiological chronic health scoring data, historical gynecological operation data and historical postoperative care responsibility data of a historical patient;
the real-time gynecological postoperative care data comprises real-time health inquiry data, real-time clinical detection data, real-time acute physiological chronic health scoring data, real-time gynecological operation data and real-time postoperative care responsibility data of a current patient.
Further, the historical gynaecology and obstetrics postoperative care big data of historical patient is gathered to carry out the preliminary treatment to the historical gynaecology and obstetrics postoperative care big data, obtain the historical gynaecology and obstetrics postoperative care dataset of preliminary treatment after, include following step:
connecting a data center, and calling a gynecological postoperative care data template stored in the data center;
acquiring a plurality of historical gynecological postoperative care data of all patient databases in a data center based on a gynecological postoperative care data template to obtain historical gynecological postoperative care big data of historical patients;
Performing format conversion on each piece of historical gynecological postoperative care data in the historical gynecological postoperative care big data to obtain a historical gynecological postoperative care data set after format conversion;
performing data screening on each historical gynecological postoperative care data in the historical gynecological postoperative care big data to obtain a historical gynecological postoperative care data set after data screening;
performing data desensitization on each data post-screening historical gynecological post-operation care data in the data post-screening historical gynecological post-operation care data set to obtain a data desensitized historical gynecological post-operation care data set;
and carrying out normalization processing on each data desensitized historical gynecological postoperative care data in the data desensitized historical gynecological postoperative care data set to obtain a preprocessed historical gynecological postoperative care data set.
Further, performing data dimension reduction, specifically, performing data dimension reduction on the preprocessed historical gynecological postoperative care data set by using a PCA method to obtain the data dimension-reduced historical gynecological postoperative care data set, wherein the method comprises the following steps of:
performing matrix conversion on the preprocessed historical gynecological postoperative care data set to obtain a historical gynecological postoperative care data matrix; the historical gynaecology and obstetrics postoperative care data matrix is composed of a plurality of historical gynaecology and obstetrics postoperative care data row vectors;
Acquiring the mean value and the variance of the historical gynecological postoperative care data matrix, and normalizing the historical gynecological postoperative care data matrix according to the mean value and the variance to obtain a normalized historical gynecological postoperative care data matrix;
acquiring a covariance matrix of a standardized historical gynecological postoperative care data matrix, and acquiring a corresponding conversion matrix according to the covariance matrix;
acquiring a principal component matrix according to the standardized historical gynecological postoperative care data matrix and the corresponding conversion matrix; the principal component matrix is composed of a plurality of alternative principal component column vectors;
according to the variance accumulation contribution rate of all the candidate principal component column vectors, if the variance accumulation contribution rate exceeds 85%, taking a plurality of corresponding candidate principal component column vectors as principal component column vectors to obtain a plurality of corresponding gynecological postoperative care key data indexes;
and carrying out data dimension reduction on the preprocessed historical gynecological postoperative care data set according to the plurality of principal cost column vectors to obtain the data dimension reduction historical gynecological postoperative care data set formed by the principal component column vectors.
Further, data clustering is performed, specifically, the FCM method is used to perform data clustering on the post-dimensional-reduction historical gynecological postoperative care data set to obtain a plurality of historical gynecological postoperative recovery level clusters, and the method comprises the following steps:
Initializing based on the FCM method to obtain initial membership;
based on the initial membership degree, performing data clustering on the post-operation nursing data set of the history gynaecology and obstetrics after the dimension reduction by using an FCM method to obtain a corresponding initial clustering center;
according to the initial membership degree, a Lagrangian multiplier method is used for obtaining a merging function value and a change value;
if the combined function value is larger than the function threshold value or the change value is larger than the change value, updating the initial clustering center and the initial membership degree to obtain an updated clustering center and an updated membership degree, otherwise, obtaining a plurality of final clustering centers, setting a corresponding post-gynecological operation recovery level for each final clustering center, and entering the next step;
according to the plurality of final clustering centers, performing data division on the post-operation nursing data sets of the history gynaecology and obstetrics after the dimension reduction to obtain corresponding clustering clusters;
and using the post-gynecological operation recovery grade corresponding to the final clustering center as a label, and diffusing to the corresponding clustering clusters to obtain a plurality of historical post-gynecological operation recovery grade clusters.
Further, sample equalization is performed on a plurality of historical gynaecology and obstetrics postoperative recovery level clusters to obtain an equalized historical gynaecology and obstetrics postoperative care data set, and the method comprises the following steps:
Taking the post-dimensionality reduction historical post-gynecological care data of the post-gynecological operation recovery level of the data with the post-gynecological operation recovery level of more than or equal to 0 as a positive sample, and taking the post-dimensionality reduction historical post-gynecological care data of the data with the post-gynecological operation recovery level of less than 0 as a negative sample;
according to the definition of the positive sample and the negative sample, dividing all the post-dimensional historical gynecological postoperative care data containing the gynecological postoperative recovery level labels in each historical gynecological postoperative recovery level cluster into a positive sample data set and a negative sample data set of each historical gynecological postoperative recovery level cluster;
performing sample equalization on the sample number of the positive sample data set and the sample number of the negative sample data set to obtain a positive sample data set and a negative sample data set with the same sample number;
integrating the positive sample data sets and the negative sample data sets with the same sample number to obtain a balanced historical gynecological postoperative care data subset of each historical gynecological postoperative recovery level cluster;
and integrating the balanced historical gynecological postoperative care data subsets of all the historical gynecological postoperative recovery level clusters to obtain a final balanced historical gynecological postoperative care data set.
Further, a deep learning algorithm is used, specifically, a DBN-IFWA algorithm is used to construct a gynecological postoperative care data analysis model according to a balanced historical gynecological postoperative care data set, and the method comprises the following steps:
post-equalization historical gynaecological post-operative care dataset was measured according to 7:3, dividing the ratio into a model training sample set and a model testing sample set;
using a plurality of unlabeled data dimension-reducing historical gynecological postoperative care data to pretrain the DBN network, and constructing an initial gynecological postoperative care data analysis model;
taking the initial network parameters of the DBN network as the optimizing targets of the IFWA optimizing algorithm, and optimizing by using the IFWA optimizing algorithm according to the optimizing targets to obtain the optimal initial network parameters of the DBN network;
according to the optimal initial network parameters of the DBN network, optimizing the network structure of an initial gynecological postoperative care data analysis model, inputting a model training sample set, and performing optimization training to obtain an optimized gynecological postoperative care data analysis model;
inputting a model test sample set, and performing model test on an optimized gynecological postoperative care data analysis model to obtain model test accuracy;
If the model test accuracy is greater than the model test accuracy threshold, outputting an optimal gynecological postoperative care data analysis model, otherwise, continuing to perform optimization training.
Further, taking the initial network parameters of the DBN network as the optimizing targets of the IFWA optimizing algorithm, and optimizing by using the IFWA optimizing algorithm according to the optimizing targets to obtain the optimal initial network parameters of the DBN network, comprising the following steps:
taking initial network parameters of the DBN network as optimization targets of an IFWA optimization algorithm;
setting IFWA population parameters, maximum iteration times and fitness function of an IFWA optimizing algorithm, and taking an optimizing target as the position of an IFWA individual in the IFWA population;
according to the IFWA population parameters, carrying out IFWA population initialization by using a Circle chaotic mapping sequence to obtain an initialized IFWA population;
calculating the fitness value of the IFWA individuals in the initialized IFWA population according to the fitness function;
acquiring the explosion radius and the spark number of each initial firework unit in the initial firework set;
performing firework explosion according to the explosion radius and the spark number of each initial IFWA individual in the initialized IFWA population to obtain an updated IFWA population;
performing Gaussian variation on the initialized IFWA population by using a Gaussian variation algorithm to generate a Gaussian variation IFWA population;
Dynamically and reversely learning the initialized IFWA population by using a dynamic and reversely learning algorithm to generate a dynamic and reversely IFWA population;
calculating the fitness values of all IFWA individuals in the updated IFWA population, the IFWA population with Gaussian variation and the IFWA population with dynamic reverse direction, and taking the IFWA individuals with the minimum fitness values as optimal individuals;
and if the iteration times reach the threshold value or the fitness value of the optimal individual meets the requirement, outputting an optimal solution corresponding to the current optimal individual to obtain the optimal initial network parameter of the DBN network.
Further, using a gynecological postoperative care data analysis model, performing gynecological postoperative care data analysis on real-time gynecological postoperative care data to obtain a gynecological postoperative care data analysis result, including the following steps:
preprocessing the real-time gynecological postoperative care data to obtain preprocessed real-time gynecological postoperative care data;
according to a plurality of gynecological postoperative care key data indexes, performing data dimension reduction on the preprocessed real-time gynecological postoperative care data to obtain the data dimension-reduced real-time gynecological postoperative care data;
inputting the real-time gynecological postoperative care data after the data dimension reduction into a gynecological postoperative care data analysis model, and analyzing the gynecological postoperative care data to obtain a label for predicting the recovery level of the gynecological postoperative;
And outputting the predicted post-gynecological postoperative recovery grade label as a gynecological postoperative care data analysis result.
The system comprises a big data acquisition unit, a data dimension reduction unit, a data clustering unit, a sample balancing unit, a model building unit, a patient verification unit, a nursing data analysis unit and an analysis result storage unit which are connected in sequence;
the big data acquisition unit is used for acquiring historical gynecological postoperative care big data of a historical patient, preprocessing the historical gynecological postoperative care big data, and obtaining a preprocessed historical gynecological postoperative care data set;
the data dimension reduction unit is used for carrying out data dimension reduction on the preprocessed historical gynecological postoperative care data set to obtain the data dimension reduction historical gynecological postoperative care data set;
the data clustering unit is used for carrying out data clustering on the historical gynecological postoperative care data sets after the data dimension reduction to obtain a plurality of historical gynecological postoperative recovery level clusters;
the sample equalization unit is used for carrying out sample equalization on a plurality of historical gynaecology and obstetrics postoperative recovery level clusters to obtain an equalized historical gynaecology and obstetrics postoperative care data set;
The model construction unit is used for constructing a gynecological postoperative care data analysis model by using a deep learning algorithm according to the equalized historical gynecological postoperative care data set;
the patient verification unit is used for collecting patient information of a current patient, carrying out patient verification on the patient information, connecting a patient database of a data center if the patient verification is passed, and collecting real-time gynecological postoperative care data of the current patient;
the nursing data analysis unit is used for analyzing the real-time gynecological postoperative nursing data by using a gynecological postoperative nursing data analysis model to obtain a gynecological postoperative nursing data analysis result;
and the analysis result storage unit is used for storing the analysis result of the gynecological postoperative care data of the current patient to the corresponding patient database.
The beneficial effects of the invention are as follows:
according to the gynaecology and obstetrics postoperative care data analysis method and system based on big data, the historical gynaecology and obstetrics postoperative care big data are collected to conduct data analysis, deep association between the gynaecology and obstetrics postoperative care data and the gynaecology and obstetrics postoperative recovery condition is excavated, accuracy of the gynaecology and obstetrics postoperative care data analysis is improved, reference and guidance are provided for a follow-up postoperative care strategy of nurses, and postoperative recovery process and postoperative care experience of patients are accelerated; the constructed gynecological postoperative care data analysis model realizes automatic, accurate and efficient gynecological postoperative care data analysis, avoids the defects of dependence on the professional knowledge and rich experience of nurses, and reduces the labor cost investment and the workload of the nurses.
Other advantageous effects of the present invention will be further described in the detailed description.
Drawings
FIG. 1 is a block flow diagram of an investment decision consulting questioning and answering method in the present invention.
Fig. 2 is a block diagram of the structure of the investment decision consulting question-answering system of the present invention.
Detailed Description
The invention is further illustrated by the following description of specific embodiments in conjunction with the accompanying drawings.
Example 1:
as shown in fig. 1, the embodiment provides a gynecological postoperative care data analysis method based on big data, which includes the following steps:
the method comprises the steps of collecting historical gynecological postoperative care big data of a historical patient, preprocessing the historical gynecological postoperative care big data to obtain a preprocessed historical gynecological postoperative care data set, and comprises the following steps:
connecting a data center, and calling a gynecological postoperative care data template stored in the data center;
acquiring a plurality of historical gynecological postoperative care data of all patient databases in a data center based on a gynecological postoperative care data template to obtain historical gynecological postoperative care big data of historical patients;
the historical gynecological postoperative care data comprises historical health inquiry data, historical clinical detection data, historical acute physiological chronic health scoring data, historical gynecological operation data and historical postoperative care responsibility data of a historical patient;
Performing format conversion on each piece of historical gynecological postoperative care data in the historical gynecological postoperative care big data to obtain a historical gynecological postoperative care data set after format conversion;
performing data screening on each historical gynecological postoperative care data in the historical gynecological postoperative care big data to obtain a historical gynecological postoperative care data set after data screening;
performing data desensitization on each data post-screening historical gynecological post-operation care data in the data post-screening historical gynecological post-operation care data set to obtain a data desensitized historical gynecological post-operation care data set;
normalizing each data desensitized historical gynecological postoperative care data in the data desensitized historical gynecological postoperative care data set to obtain a preprocessed historical gynecological postoperative care data set;
using a principal component analysis (Principal Component Analysis, PCA) method to perform data dimension reduction on the post-preprocessing historical gynecological postoperative care data set to obtain a data dimension-reduced historical gynecological postoperative care data set, comprising the steps of:
performing matrix conversion on the preprocessed historical gynecological postoperative care data set to obtain a historical gynecological postoperative care data matrix X= [ X ] 1 ,x 2 ,...x i ,...,x n ] T Wherein x is i The method comprises the steps that (1) an i-th post-pretreatment historical post-gynecological operation nursing data row vector is obtained, i is a data indication quantity, and n is a total data; the historical gynaecology and obstetrics postoperative care data matrix is formed by a plurality of historical gynaecology and obstetrics postoperative care data line vectors x i Constructing;
the method comprises the steps of obtaining the mean value and the variance of a historical gynecological postoperative care data matrix, normalizing the historical gynecological postoperative care data matrix according to the mean value and the variance to obtain a normalized historical gynecological postoperative care data matrix, wherein the formula is as follows:
wherein X' is a standardized historical gynecological postoperative care data matrix; μ is the mean value of the historical gynecological postoperative care data matrix; σ is the variance of the historical gynecological post-operative care data matrix;
obtaining a covariance matrix of a standardized historical gynecological postoperative care data matrix, and obtaining a corresponding conversion matrix according to the covariance matrix, wherein the formula is as follows:
wherein D is a covariance matrix of a standardized historical gynecological postoperative care data matrix; y is a principal component matrix; p is a conversion matrix; e is a unit feature vector matrix;
according to the standardized historical gynecological postoperative care data matrix and the corresponding conversion matrix, a principal component matrix Y= [ Y ] is obtained 1 ,y 2 ,...y l ,...,y L ]Wherein y is l For the first alternative principal component column vector, L is a data dimension indication quantity, and L is a total number of data dimensions; the principal component matrix is composed of a plurality of alternative principal component column vectors, and the formula is:
Y＝PX'
wherein Y is a matrix of main components; p is a conversion matrix; x' is a standardized historical gynecological postoperative care data matrix;
according to the variance accumulation contribution rate of all the candidate principal component column vectors, if the variance accumulation contribution rate exceeds 85%, using a plurality of corresponding candidate principal component column vectors as principal component column vectors to obtain a plurality of corresponding gynecological postoperative care key data indexes, wherein the formula is as follows:
wherein G is the variance accumulation contribution rate; lambda (lambda) l First alternative principal component y l Is a variance of (2); l is a data dimension indicator; l is the total number of data dimensions; k is the total number of main components;
according to the K principal cost column vectors, performing data dimension reduction on the preprocessed historical gynecological postoperative care data set to obtain a principal component column vector { y } 1 ,y 2 ,...y l ,...,y K Post-operative care data set X "= [ y ] of post-operative history gynaecology and obstetrics with data of } composition 1 ,y 2 ,...y l ,...,y K ]；
Performing data clustering on the post-gynecological postoperative care data set after the data dimension reduction by using a Fuzzy C-Means (FCM) method to obtain a plurality of historical post-gynecological postoperative recovery level clusters, wherein the method comprises the following steps of:
Initializing based on the FCM method to obtain initial membership;
based on the initial membership degree, performing data clustering on the post-operation nursing data set of the history gynaecology and obstetrics after the dimension reduction by using an FCM method to obtain a corresponding initial clustering center;
according to the initial membership, a Lagrangian multiplier method is used for obtaining a merging function value and a change value, and the formula is as follows:
ΔJ t ＝J t -J t-1
wherein J is t 、J t-1 Combining function values for Lagrangian multiplier method at t and t-1; ΔJ t Is a variation value; lambda (lambda) i The characteristic value of the historical gynecological postoperative care data after the dimension reduction of the ith data is obtained;
if the combined function value is larger than the function threshold value or the change value is larger than the change value, updating the initial clustering center and the initial membership degree to obtain an updated clustering center and an updated membership degree, otherwise, obtaining a plurality of final clustering centers, setting a corresponding post-gynecological operation recovery level for each final clustering center, and entering the next step;
the update formula of the membership degree is:
in the method, in the process of the invention,historical gynecological postoperative care data for ith data after dimension reductionUpdated membership to the jth initial cluster center; d, d ij 、d ik The distance from the history gynecological postoperative care data to the j and k updated clustering centers after the dimension reduction of the ith data; alpha is a super parameter; k is a clustering center indication quantity;
The update formula of the clustering center is as follows:
wherein z is j A cluster center updated for the j; x is x i Historical gynecological postoperative care data after dimension reduction for the ith data; i is a data indication quantity; j is a clustering center indication quantity; m is the total number of data; c is the total number of clustering centers; alpha is a super parameter;updating membership degree of historical gynecological postoperative care data after dimension reduction of the ith data to the jth initial clustering center;
according to a plurality of final clustering centers and Euclidean distances from data to the clustering centers, data partitioning is carried out on the historical gynecological postoperative care data sets after dimension reduction to obtain corresponding clustering clusters, wherein the formula is as follows:
d' ij ＝||x' i -z' j || 2
wherein z' j The j-th final cluster center; d' ij The distance from the historical gynecological postoperative care data to the j final clustering center after the dimension reduction of the ith data; x's' i Historical gynecological postoperative care data after dimension reduction for the ith data;
spreading the post-gynecological operation recovery level corresponding to the final clustering center as a label to the corresponding clustering clusters to obtain a plurality of historical post-gynecological operation recovery level clusters;
sample equalization is carried out on a plurality of historical gynaecology and obstetrics postoperative recovery level clusters to obtain an equalized historical gynaecology and obstetrics postoperative care data set, and the method comprises the following steps:
Taking the post-dimensionality reduction historical post-gynecological care data of the post-gynecological operation recovery level of the data with the post-gynecological operation recovery level of more than or equal to 0 as a positive sample, and taking the post-dimensionality reduction historical post-gynecological care data of the data with the post-gynecological operation recovery level of less than 0 as a negative sample;
according to the definition of the positive sample and the negative sample, dividing all the post-dimensional historical gynecological postoperative care data containing the gynecological postoperative recovery level labels in each historical gynecological postoperative recovery level cluster into a positive sample data set and a negative sample data set of each historical gynecological postoperative recovery level cluster;
performing sample equalization on the sample number of the positive sample data set and the sample number of the negative sample data set to obtain a positive sample data set and a negative sample data set with the same sample number;
integrating the positive sample data sets and the negative sample data sets with the same sample number to obtain a balanced historical gynecological postoperative care data subset of each historical gynecological postoperative recovery level cluster;
integrating the equalized historical gynecological postoperative care data subsets of all the historical gynecological postoperative recovery level clusters to obtain a final equalized historical gynecological postoperative care data set;
According to the equalized historical gynecological postoperative care data set, a deep belief network (Deep Belief Network, DBN) -improved firework optimizing (Improved Fireworks Algorithm, IFWA) algorithm is used for constructing a gynecological postoperative care data analysis model, which comprises the following steps:
post-equalization historical gynaecological post-operative care dataset was measured according to 7:3, dividing the ratio into a model training sample set and a model testing sample set;
using a plurality of unlabeled data dimension-reducing historical gynecological postoperative care data to pretrain the DBN network, and constructing an initial gynecological postoperative care data analysis model;
taking the initial network parameters of the DBN network as the optimizing targets of the IFWA optimizing algorithm, and optimizing by using the IFWA optimizing algorithm according to the optimizing targets to obtain the optimal initial network parameters of the DBN network, comprising the following steps:
taking initial network parameters of the DBN network as optimization targets of an IFWA optimization algorithm;
setting IFWA population parameters, maximum iteration times and fitness function of an IFWA optimizing algorithm, and taking an optimizing target as the position of an IFWA individual in the IFWA population;
according to the IFWA population parameters, using a Circle chaotic mapping sequence to initialize the IFWA population to obtain an initialized IFWA population, wherein the formula is as follows:
Wherein q is l' An initial IFWA individual for Circle chaotic mapping; q * l' Initial IFWA individuals generated randomly; l' is an indication quantity;
according to the fitness function, calculating the fitness value of the IFWA individuals in the initialized IFWA population, wherein the formula is as follows:
wherein f (q l' ) For initial IFWA individual q l' Is a fitness value of (a); MSE is a predictive mean square error function; y'. l' 、Y l' Is a predicted value and a true value;
the explosion radius and the spark number of each initial firework unit in the initial firework set are obtained, and the formula is as follows:
wherein S is l' For initial IFWA individual q l' Is a spark number of (2); m' is a constant; f (f) max The maximum fitness value in the initialized IFWA population is obtained; f (q) l' ) For initial IFWA individual q l' Is a fitness value of (a); τ is an infinitesimal constant;
wherein R is l' For initial IFWA individual q l' Is a radius of explosion;adjusting a constant for the explosion radius; f (f) min The minimum fitness value in the initialized IFWA population;
according to the explosion radius and the spark number of each initial IFWA individual in the initialized IFWA population, carrying out firework explosion to obtain an updated IFWA population, wherein the formula is as follows:
q' l' ＝q l' +S l' ×rand(-1,1)
wherein q 'is' l' Is an updated IFWA individual; rand (-1, 1) is a random number from-1 to 1; q l' Is an initial IFWA individual;
using a Gaussian variation algorithm to carry out Gaussian variation on the initialized IFWA population to generate the Gaussian variation IFWA population, wherein the formula is as follows:
q" l' ＝q l' +S l' ×G(1,1)
In the formula, q' l' IFWA individuals with gaussian variation; g (1, 1) is a random number with a Gaussian distribution with a mean and a variance of 1;
and carrying out dynamic reverse learning on the initialized IFWA population by using a dynamic reverse learning algorithm to generate a dynamic reverse IFWA population, wherein the formula is as follows:
q'" l' ＝γ(L max +L min )-q l'
in the formula, q' l' Is a dynamically reversed IFWA individual; x is X best Is a forward candidate optimal solution; gamma is a decreasing inertia coefficient, gamma=0.9-0.5T/T; l (L) max 、L min The vector space is maximum and small respectively;
calculating the fitness values of all IFWA individuals in the updated IFWA population, the IFWA population with Gaussian variation and the IFWA population with dynamic reverse direction, and taking the IFWA individuals with the minimum fitness values as optimal individuals;
if the iteration times reach a threshold value or the fitness value of the optimal individual meets the requirement, outputting an optimal solution corresponding to the current optimal individual to obtain an optimal initial network parameter of the DBN network;
according to the optimal initial network parameters of the DBN network, optimizing the network structure of an initial gynecological postoperative care data analysis model, inputting a model training sample set, and performing optimization training to obtain an optimized gynecological postoperative care data analysis model;
inputting a model test sample set, and performing model test on an optimized gynecological postoperative care data analysis model to obtain model test accuracy;
If the model test accuracy is greater than the model test accuracy threshold, outputting an optimal gynecological postoperative care data analysis model, otherwise, continuing to perform optimization training;
collecting patient information of a current patient, performing patient verification on the patient information, connecting a patient database of a data center if the patient verification is passed, and collecting real-time gynecological postoperative care data of the current patient;
using a gynecological postoperative care data analysis model, performing gynecological postoperative care data analysis on real-time gynecological postoperative care data to obtain a gynecological postoperative care data analysis result, comprising the following steps:
preprocessing the real-time gynecological postoperative care data to obtain preprocessed real-time gynecological postoperative care data;
the real-time gynecological postoperative care data comprise real-time health inquiry data, real-time clinical detection data, real-time acute physiological chronic health scoring data, real-time gynecological operation data and real-time postoperative care responsibility data of a current patient;
according to a plurality of gynecological postoperative care key data indexes, performing data dimension reduction on the preprocessed real-time gynecological postoperative care data to obtain the data dimension-reduced real-time gynecological postoperative care data;
Inputting the real-time gynecological postoperative care data after the data dimension reduction into a gynecological postoperative care data analysis model, and analyzing the gynecological postoperative care data to obtain a label for predicting the recovery level of the gynecological postoperative;
outputting the label for predicting the post-gynecological postoperative recovery level as a gynecological postoperative care data analysis result;
and storing the analysis result of the gynecological postoperative care data of the current patient into a corresponding patient database.
Example 2:
as shown in fig. 2, the embodiment provides a gynecological postoperative care data analysis system based on big data, which is used for realizing a gynecological postoperative care data analysis method, and the system comprises a big data acquisition unit, a data dimension reduction unit, a data clustering unit, a sample equalization unit, a model construction unit, a patient verification unit, a care data analysis unit and an analysis result storage unit which are connected in sequence;
the big data acquisition unit is used for acquiring historical gynecological postoperative care big data of a historical patient, preprocessing the historical gynecological postoperative care big data, and obtaining a preprocessed historical gynecological postoperative care data set;
the data dimension reduction unit is used for carrying out data dimension reduction on the preprocessed historical gynecological postoperative care data set to obtain the data dimension reduction historical gynecological postoperative care data set;
The data clustering unit is used for carrying out data clustering on the historical gynecological postoperative care data sets after the data dimension reduction to obtain a plurality of historical gynecological postoperative recovery level clusters;
the sample equalization unit is used for carrying out sample equalization on a plurality of historical gynaecology and obstetrics postoperative recovery level clusters to obtain an equalized historical gynaecology and obstetrics postoperative care data set;
the model construction unit is used for constructing a gynecological postoperative care data analysis model by using a deep learning algorithm according to the equalized historical gynecological postoperative care data set;
the patient verification unit is used for collecting patient information of a current patient, carrying out patient verification on the patient information, connecting a patient database of a data center if the patient verification is passed, and collecting real-time gynecological postoperative care data of the current patient;
the nursing data analysis unit is used for analyzing the real-time gynecological postoperative nursing data by using a gynecological postoperative nursing data analysis model to obtain a gynecological postoperative nursing data analysis result;
and the analysis result storage unit is used for storing the analysis result of the gynecological postoperative care data of the current patient to the corresponding patient database.
According to the gynaecology and obstetrics postoperative care data analysis method and system based on big data, the historical gynaecology and obstetrics postoperative care big data are collected to conduct data analysis, deep association between the gynaecology and obstetrics postoperative care data and the gynaecology and obstetrics postoperative recovery condition is excavated, accuracy of the gynaecology and obstetrics postoperative care data analysis is improved, reference and guidance are provided for a follow-up postoperative care strategy of nurses, and postoperative recovery process and postoperative care experience of patients are accelerated; the constructed gynecological postoperative care data analysis model realizes automatic, accurate and efficient gynecological postoperative care data analysis, avoids the defects of dependence on the professional knowledge and rich experience of nurses, and reduces the labor cost investment and the workload of the nurses.
The invention is not limited to the alternative embodiments described above, but any person may derive other various forms of products in the light of the present invention. The above detailed description should not be construed as limiting the scope of the invention, which is defined in the claims and the description may be used to interpret the claims.
Claims (10)
1. A gynecological postoperative care data analysis method based on big data is characterized in that: the method comprises the following steps:
collecting historical gynecological postoperative care big data of a historical patient, and preprocessing the historical gynecological postoperative care big data to obtain a preprocessed historical gynecological postoperative care data set;
performing data dimension reduction on the preprocessed historical gynecological postoperative care data set to obtain a data dimension reduction historical gynecological postoperative care data set;
performing data clustering on the historical gynecological postoperative care data set after the data dimension reduction to obtain a plurality of historical gynecological postoperative recovery level clusters;
sample equalization is carried out on a plurality of historical gynaecology and obstetrics postoperative recovery level clusters, and an equalized historical gynaecology and obstetrics postoperative care data set is obtained;
according to the equalized historical gynecological postoperative care data set, a deep learning algorithm is used for constructing a gynecological postoperative care data analysis model;
collecting patient information of a current patient, performing patient verification on the patient information, connecting a patient database of a data center if the patient verification is passed, and collecting real-time gynecological postoperative care data of the current patient;
using a gynecological postoperative care data analysis model to analyze the real-time gynecological postoperative care data to obtain a gynecological postoperative care data analysis result;
And storing the analysis result of the gynecological postoperative care data of the current patient into a corresponding patient database.
2. A method for analyzing gynecological postoperative care data based on big data according to claim 1, wherein: the historical gynecological postoperative care data comprise historical health inquiry data, historical clinical detection data, historical acute physiological chronic health scoring data, historical gynecological operation data and historical postoperative care responsibility data of a historical patient;
the real-time gynecological postoperative care data comprise real-time health inquiry data, real-time clinical detection data, real-time acute physiological chronic health scoring data, real-time gynecological operation data and real-time postoperative care responsibility data of a current patient.
3. A method for analyzing gynecological postoperative care data based on big data according to claim 1, wherein: the method comprises the steps of collecting historical gynecological postoperative care big data of a historical patient, preprocessing the historical gynecological postoperative care big data to obtain a preprocessed historical gynecological postoperative care data set, and comprises the following steps:
connecting a data center, and calling a gynecological postoperative care data template stored in the data center;
Acquiring a plurality of historical gynecological postoperative care data of all patient databases in a data center based on a gynecological postoperative care data template to obtain historical gynecological postoperative care big data of historical patients;
performing format conversion on each piece of historical gynecological postoperative care data in the historical gynecological postoperative care big data to obtain a historical gynecological postoperative care data set after format conversion;
performing data screening on each historical gynecological postoperative care data in the historical gynecological postoperative care big data to obtain a historical gynecological postoperative care data set after data screening;
performing data desensitization on each data post-screening historical gynecological post-operation care data in the data post-screening historical gynecological post-operation care data set to obtain a data desensitized historical gynecological post-operation care data set;
and carrying out normalization processing on each data desensitized historical gynecological postoperative care data in the data desensitized historical gynecological postoperative care data set to obtain a preprocessed historical gynecological postoperative care data set.
4. A method for analyzing gynecological postoperative care data based on big data according to claim 1, wherein: performing data dimension reduction, specifically, performing data dimension reduction on the post-preprocessing historical gynecological postoperative care data set by using a PCA method to obtain the post-data dimension reduction historical gynecological postoperative care data set, wherein the method comprises the following steps of:
Performing matrix conversion on the preprocessed historical gynecological postoperative care data set to obtain a historical gynecological postoperative care data matrix; the historical gynaecology and obstetrics postoperative care data matrix is composed of a plurality of historical gynaecology and obstetrics postoperative care data row vectors;
acquiring the mean value and the variance of the historical gynecological postoperative care data matrix, and normalizing the historical gynecological postoperative care data matrix according to the mean value and the variance to obtain a normalized historical gynecological postoperative care data matrix;
acquiring a covariance matrix of a standardized historical gynecological postoperative care data matrix, and acquiring a corresponding conversion matrix according to the covariance matrix;
acquiring a principal component matrix according to the standardized historical gynecological postoperative care data matrix and the corresponding conversion matrix; the principal component matrix consists of a plurality of alternative principal component column vectors;
according to the variance accumulation contribution rate of all the candidate principal component column vectors, if the variance accumulation contribution rate exceeds 85%, taking a plurality of corresponding candidate principal component column vectors as principal component column vectors to obtain a plurality of corresponding gynecological postoperative care key data indexes;
and carrying out data dimension reduction on the preprocessed historical gynecological postoperative care data set according to the plurality of principal cost column vectors to obtain the data dimension reduction historical gynecological postoperative care data set formed by the principal component column vectors.
5. A method for analyzing gynecological postoperative care data based on big data according to claim 1, wherein: performing data clustering, specifically, performing data clustering on a post-operation nursing data set of a history gynaecology and obstetrics after dimension reduction by using an FCM method to obtain a plurality of post-operation recovery level clusters of the history gynaecology and obstetrics, wherein the method comprises the following steps:
initializing based on the FCM method to obtain initial membership;
based on the initial membership degree, performing data clustering on the post-operation nursing data set of the history gynaecology and obstetrics after the dimension reduction by using an FCM method to obtain a corresponding initial clustering center;
according to the initial membership degree, a Lagrangian multiplier method is used for obtaining a merging function value and a change value;
if the combined function value is larger than the function threshold value or the change value is larger than the change value, updating the initial clustering center and the initial membership degree to obtain an updated clustering center and an updated membership degree, otherwise, obtaining a plurality of final clustering centers, setting a corresponding post-gynecological operation recovery level for each final clustering center, and entering the next step;
according to the plurality of final clustering centers, performing data division on the post-operation nursing data sets of the history gynaecology and obstetrics after the dimension reduction to obtain corresponding clustering clusters;
And using the post-gynecological operation recovery grade corresponding to the final clustering center as a label, and diffusing to the corresponding clustering clusters to obtain a plurality of historical post-gynecological operation recovery grade clusters.
6. A method for analyzing gynecological postoperative care data based on big data according to claim 1, wherein: sample equalization is carried out on a plurality of historical gynaecology and obstetrics postoperative recovery level clusters to obtain an equalized historical gynaecology and obstetrics postoperative care data set, and the method comprises the following steps:
taking the post-dimensionality reduction historical post-gynecological care data of the post-gynecological operation recovery level of the data with the post-gynecological operation recovery level of more than or equal to 0 as a positive sample, and taking the post-dimensionality reduction historical post-gynecological care data of the data with the post-gynecological operation recovery level of less than 0 as a negative sample;
according to the definition of the positive sample and the negative sample, dividing all the post-dimensional historical gynecological postoperative care data containing the gynecological postoperative recovery level labels in each historical gynecological postoperative recovery level cluster into a positive sample data set and a negative sample data set of each historical gynecological postoperative recovery level cluster;
performing sample equalization on the sample number of the positive sample data set and the sample number of the negative sample data set to obtain a positive sample data set and a negative sample data set with the same sample number;
Integrating the positive sample data sets and the negative sample data sets with the same sample number to obtain a balanced historical gynecological postoperative care data subset of each historical gynecological postoperative recovery level cluster;
and integrating the balanced historical gynecological postoperative care data subsets of all the historical gynecological postoperative recovery level clusters to obtain a final balanced historical gynecological postoperative care data set.
7. A method for analyzing gynecological postoperative care data based on big data according to claim 1, wherein: using a deep learning algorithm, specifically, using a DBN-IFWA algorithm according to a balanced historical gynecological postoperative care data set to construct a gynecological postoperative care data analysis model, comprising the following steps:
post-equalization historical gynaecological post-operative care dataset was measured according to 7:3, dividing the ratio into a model training sample set and a model testing sample set;
using a plurality of unlabeled data dimension-reducing historical gynecological postoperative care data to pretrain the DBN network, and constructing an initial gynecological postoperative care data analysis model;
taking the initial network parameters of the DBN network as the optimizing targets of the IFWA optimizing algorithm, and optimizing by using the IFWA optimizing algorithm according to the optimizing targets to obtain the optimal initial network parameters of the DBN network;
According to the optimal initial network parameters of the DBN network, optimizing the network structure of an initial gynecological postoperative care data analysis model, inputting a model training sample set, and performing optimization training to obtain an optimized gynecological postoperative care data analysis model;
inputting a model test sample set, and performing model test on an optimized gynecological postoperative care data analysis model to obtain model test accuracy;
if the model test accuracy is greater than the model test accuracy threshold, outputting an optimal gynecological postoperative care data analysis model, otherwise, continuing to perform optimization training.
8. A method of analyzing gynecological post-operative care data based on big data as claimed in claim 7, wherein: taking the initial network parameters of the DBN network as the optimizing targets of the IFWA optimizing algorithm, and optimizing by using the IFWA optimizing algorithm according to the optimizing targets to obtain the optimal initial network parameters of the DBN network, comprising the following steps:
taking initial network parameters of the DBN network as optimization targets of an IFWA optimization algorithm;
setting IFWA population parameters, maximum iteration times and fitness function of an IFWA optimizing algorithm, and taking an optimizing target as the position of an IFWA individual in the IFWA population;
According to the IFWA population parameters, carrying out IFWA population initialization by using a Circle chaotic mapping sequence to obtain an initialized IFWA population;
calculating the fitness value of the IFWA individuals in the initialized IFWA population according to the fitness function;
acquiring the explosion radius and the spark number of each initial firework unit in the initial firework set;
performing firework explosion according to the explosion radius and the spark number of each initial IFWA individual in the initialized IFWA population to obtain an updated IFWA population;
performing Gaussian variation on the initialized IFWA population by using a Gaussian variation algorithm to generate a Gaussian variation IFWA population;
dynamically and reversely learning the initialized IFWA population by using a dynamic and reversely learning algorithm to generate a dynamic and reversely IFWA population;
calculating the fitness values of all IFWA individuals in the updated IFWA population, the IFWA population with Gaussian variation and the IFWA population with dynamic reverse direction, and taking the IFWA individuals with the minimum fitness values as optimal individuals;
and if the iteration times reach the threshold value or the fitness value of the optimal individual meets the requirement, outputting an optimal solution corresponding to the current optimal individual to obtain the optimal initial network parameter of the DBN network.
9. A method of analyzing gynecological post-operative care data based on big data as defined in claim 4, wherein: using a gynecological postoperative care data analysis model, performing gynecological postoperative care data analysis on real-time gynecological postoperative care data to obtain a gynecological postoperative care data analysis result, comprising the following steps:
Preprocessing the real-time gynecological postoperative care data to obtain preprocessed real-time gynecological postoperative care data;
according to a plurality of gynecological postoperative care key data indexes, performing data dimension reduction on the preprocessed real-time gynecological postoperative care data to obtain the data dimension-reduced real-time gynecological postoperative care data;
inputting the real-time gynecological postoperative care data after the data dimension reduction into a gynecological postoperative care data analysis model, and analyzing the gynecological postoperative care data to obtain a label for predicting the recovery level of the gynecological postoperative;
and outputting the predicted post-gynecological postoperative recovery grade label as a gynecological postoperative care data analysis result.
10. A gynecological postoperative care data analysis system based on big data, for implementing a gynecological postoperative care data analysis method according to any one of claims 1 to 9, characterized in that: the system comprises a big data acquisition unit, a data dimension reduction unit, a data clustering unit, a sample balancing unit, a model building unit, a patient verification unit, a nursing data analysis unit and an analysis result storage unit which are connected in sequence;
the big data acquisition unit is used for acquiring historical gynecological postoperative care big data of a historical patient, preprocessing the historical gynecological postoperative care big data, and obtaining a preprocessed historical gynecological postoperative care data set;
The data dimension reduction unit is used for carrying out data dimension reduction on the preprocessed historical gynecological postoperative care data set to obtain the data dimension reduction historical gynecological postoperative care data set;
the data clustering unit is used for carrying out data clustering on the historical gynecological postoperative care data sets after the data dimension reduction to obtain a plurality of historical gynecological postoperative recovery level clusters;
the sample equalization unit is used for carrying out sample equalization on a plurality of historical gynaecology and obstetrics postoperative recovery level clusters to obtain an equalized historical gynaecology and obstetrics postoperative care data set;
the model construction unit is used for constructing a gynecological postoperative care data analysis model by using a deep learning algorithm according to the equalized historical gynecological postoperative care data set;
the patient verification unit is used for collecting patient information of a current patient, carrying out patient verification on the patient information, connecting a patient database of a data center if the patient verification is passed, and collecting real-time gynecological postoperative care data of the current patient;
the nursing data analysis unit is used for analyzing the real-time gynecological postoperative nursing data by using a gynecological postoperative nursing data analysis model to obtain a gynecological postoperative nursing data analysis result;
And the analysis result storage unit is used for storing the analysis result of the gynecological postoperative care data of the current patient to the corresponding patient database.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311640109.7A CN117633625A (en) | 2023-11-30 | 2023-11-30 | Gynaecology and obstetrics postoperative care data analysis method and system based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311640109.7A CN117633625A (en) | 2023-11-30 | 2023-11-30 | Gynaecology and obstetrics postoperative care data analysis method and system based on big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117633625A true CN117633625A (en) | 2024-03-01 |
Family
ID=90028445
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311640109.7A Pending CN117633625A (en) | 2023-11-30 | 2023-11-30 | Gynaecology and obstetrics postoperative care data analysis method and system based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117633625A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115206538A (en) * | 2022-06-30 | 2022-10-18 | 四川大学 | Perioperative patient sample data set balancing method and sample data set acquisition system |
| CN115359864A (en) * | 2022-06-20 | 2022-11-18 | 山东省日照市人民医院 | Postoperative rehabilitation nursing method and system |
| US20230181121A1 (en) * | 2021-09-17 | 2023-06-15 | Nanowear Inc. | Systems and methods to predict and manage post-surgical recovery |
| CN116403670A (en) * | 2023-04-04 | 2023-07-07 | 中国人民解放军总医院第六医学中心 | Intelligent monitoring management method and system for postoperative care training |
| CN116682557A (en) * | 2023-06-05 | 2023-09-01 | 东南大学 | Chronic complications early risk early warning method based on small sample deep learning |
-
2023
- 2023-11-30 CN CN202311640109.7A patent/CN117633625A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20230181121A1 (en) * | 2021-09-17 | 2023-06-15 | Nanowear Inc. | Systems and methods to predict and manage post-surgical recovery |
| CN115359864A (en) * | 2022-06-20 | 2022-11-18 | 山东省日照市人民医院 | Postoperative rehabilitation nursing method and system |
| CN115206538A (en) * | 2022-06-30 | 2022-10-18 | 四川大学 | Perioperative patient sample data set balancing method and sample data set acquisition system |
| CN116403670A (en) * | 2023-04-04 | 2023-07-07 | 中国人民解放军总医院第六医学中心 | Intelligent monitoring management method and system for postoperative care training |
| CN116682557A (en) * | 2023-06-05 | 2023-09-01 | 东南大学 | Chronic complications early risk early warning method based on small sample deep learning |
Non-Patent Citations (2)
| Title |
|---|
| YE TIAN: "Hidden Dangers of Gynecological Nursing Based on Big Data Analysis", INNOVATIVE COMPUTING - EMERGING TOPICS IN FUTURE INTERNET: PROCEEDINGS OF IC 2023, vol. 2, 1 May 2023 (2023-05-01), pages 251 * |
| 胡绿慧;: "基于多数据分析的术后感染风险挖掘预测仿真", 计算机仿真, vol. 32, no. 03, 15 March 2015 (2015-03-15), pages 403 - 406 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113040711B (en) | Cerebral apoplexy incidence risk prediction system, equipment and storage medium | |
| CN106934235B (en) | Patient's similarity measurement migratory system between a kind of disease areas based on transfer learning | |
| CN109620152B (en) | MutifacolLoss-densenert-based electrocardiosignal classification method | |
| CN111400455A (en) | Relation detection method of question-answering system based on knowledge graph | |
| CN110348608A (en) | A kind of prediction technique for improving LSTM based on fuzzy clustering algorithm | |
| CN111651980A (en) | Wheat cold resistance identification method with hybrid neural network fused with Attention mechanism | |
| CN111081379B (en) | Disease probability decision method and system thereof | |
| CN111862075A (en) | Lung image analysis system and method based on deep learning | |
| CN111415099A (en) | Poverty-poverty identification method based on multi-classification BP-Adaboost | |
| CN114970637A (en) | Lightweight arrhythmia classification method based on deep learning | |
| Adi et al. | Stroke risk prediction model using machine learning | |
| CN113707317B (en) | Disease risk factor importance analysis method based on mixed model | |
| CN116842330B (en) | Health care information processing method and device capable of comparing histories | |
| US6941288B2 (en) | Online learning method in a decision system | |
| CN117633625A (en) | Gynaecology and obstetrics postoperative care data analysis method and system based on big data | |
| CN117520914A (en) | Single cell classification method, system, equipment and computer readable storage medium | |
| CN107909090A (en) | Learn semi-supervised music-book on pianoforte difficulty recognition methods based on estimating | |
| CN114521900B (en) | Arrhythmia classification and identification method based on transfer learning | |
| Siddiqa et al. | Robust Length of Stay Prediction Model for Indoor Patients. | |
| CN113657726B (en) | Personnel risk analysis method based on random forest | |
| CN115204475A (en) | Drug rehabilitation place security incident risk assessment method | |
| CN106845386A (en) | A kind of action identification method based on dynamic time warping Yu Multiple Kernel Learning | |
| CN117854709B (en) | Diabetes six-typing method and system based on depth contrast clustering | |
| Rafiq et al. | A data science approach to Predict the University Students at risk of semester dropout: Bangladeshi University Perspective | |
| CN117942540A (en) | Intelligent physical training monitoring method and system |
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 |