CN110782989A - Data analysis method, device, equipment and computer readable storage medium - Google Patents

Data analysis method, device, equipment and computer readable storage medium Download PDF

Info

Publication number
CN110782989A
CN110782989A CN201910884245.8A CN201910884245A CN110782989A CN 110782989 A CN110782989 A CN 110782989A CN 201910884245 A CN201910884245 A CN 201910884245A CN 110782989 A CN110782989 A CN 110782989A
Authority
CN
China
Prior art keywords
time sequence
historical
index
data analysis
time
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
Application number
CN201910884245.8A
Other languages
Chinese (zh)
Other versions
CN110782989B (en
Inventor
赵惟
徐卓扬
左磊
孙行智
田静涛
胡岗
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Ping An Technology Shenzhen Co Ltd
Original Assignee
Ping An Technology Shenzhen Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Ping An Technology Shenzhen Co Ltd filed Critical Ping An Technology Shenzhen Co Ltd
Priority to CN201910884245.8A priority Critical patent/CN110782989B/en
Publication of CN110782989A publication Critical patent/CN110782989A/en
Priority to PCT/CN2020/112468 priority patent/WO2021052156A1/en
Application granted granted Critical
Publication of CN110782989B publication Critical patent/CN110782989B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G16INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16HHEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/30ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition
    • G06F18/20Analysing
    • G06F18/24Classification techniques
    • GPHYSICS
    • G16INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16HHEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/70ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients

Landscapes

  • Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Public Health (AREA)
  • Medical Informatics (AREA)
  • Health & Medical Sciences (AREA)
  • Theoretical Computer Science (AREA)
  • Primary Health Care (AREA)
  • General Health & Medical Sciences (AREA)
  • Epidemiology (AREA)
  • Pathology (AREA)
  • Databases & Information Systems (AREA)
  • Biomedical Technology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • Evolutionary Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The invention relates to the field of data analysis, and provides a data analysis method, a device, equipment and a computer readable storage medium, wherein time sequence sample indexes of historical patients with chronic diseases, which show numerical value change along with the time, are analyzed, time sequence prediction indexes relevant to the disease development are identified, time sequence prediction index change trends corresponding to different historical patient groups are analyzed and determined, reference basis is provided for slow patient grouping, then the time sequence test index change trend of the current patient along with the time is compared and matched with the time sequence prediction index change trends corresponding to the historical patient groups, and the grouping result of the current patient is further determined; because the embodiment of the invention carries out patient grouping according to the multiple test indexes of the patient, the adverse effect of the contingency and the randomness of single test data on the grouping reliability is reduced, and the reliability of the patient grouping is improved.

Description

Data analysis method, device, equipment and computer readable storage medium
Technical Field
The present invention relates to the field of data analysis technologies, and in particular, to a data analysis method, apparatus, device, and computer-readable storage medium.
Background
The core of precision medicine is to provide individualized treatment according to individual differences of patients, which is also the most difficult place for treatment. For chronic diseases, it is a great challenge to divide patients (e.g. one hundred million diabetics) into several sub-groups, and to set different treatment methods for each sub-group to achieve optimal treatment effect.
For patients with chronic diseases, multiple visits and continuous observation are often needed, but the existing patient grouping method generally only considers the current single examination index and basic information, ignores the correlation between the indexes before and when the patients, so that the existing grouping method has the contingency and randomness for the chronic diseases, and the reliability of the obtained grouping recommendation is not high.
Disclosure of Invention
The invention mainly aims to provide a data analysis method, a data analysis device, data analysis equipment and a computer-readable storage medium, and aims to solve the technical problem that the existing patient grouping result is not high in reliability.
In order to achieve the above object, an embodiment of the present invention provides a data analysis method, where the data analysis method includes:
accessing a preset database, acquiring time sequence sample indexes of historical patients from the preset database, and screening the time sequence sample indexes in a significance test mode to obtain time sequence prediction indexes which are statistically associated with the health information of the historical patients;
analyzing the change relation of the numerical value of the time sequence prediction index along with time to obtain a numerical value change slope average value corresponding to the change relation;
analyzing a nonlinear relation between the numerical value change slope mean value and the historical clustering result based on a characteristic attribution method and the historical clustering result of the historical patients, determining a classification control slope representing the nonlinear relation, and simulating in a preset coordinate system according to the classification control slope to obtain a control trajectory line;
acquiring a time sequence inspection index of the current patient according to the index type of the time sequence prediction index, and fitting in the preset coordinate system according to the time sequence inspection index to obtain a corresponding inspection trajectory line;
and comparing the positions of the test trajectory line and the control trajectory line, and determining the grouping result of the current patient according to the position relation between the test trajectory line and the control trajectory line and the historical grouping result of the historical patients.
In addition, to achieve the above object, an embodiment of the present invention further provides a data analysis apparatus, including:
the index acquisition module is used for accessing a preset database, acquiring time sequence sample indexes of historical patients from the preset database, and screening the time sequence sample indexes in a significance test mode to obtain time sequence prediction indexes which are statistically associated with the health information of the historical patients;
the first analysis module is used for analyzing the change relation of the numerical value of the time sequence prediction index along with time to obtain a numerical value change slope average value corresponding to the change relation;
the second analysis module is used for analyzing a nonlinear relation between the numerical value change slope mean value and the historical clustering result based on a characteristic attribution method and the historical clustering result of the historical patients, determining a classification control slope representing the nonlinear relation, and simulating in a preset coordinate system according to the classification control slope to obtain a control trajectory;
the track fitting module is used for acquiring the time sequence inspection index of the current patient according to the index type of the time sequence prediction index and fitting the time sequence inspection index in the preset coordinate system to obtain a corresponding inspection track line;
and the position comparison module is used for performing position comparison on the inspection track line and the control track line and determining the grouping result of the current patient according to the position relation between the inspection track line and the control track line and the historical grouping result of the historical patients.
Furthermore, in order to achieve the above object, an embodiment of the present invention further provides a data analysis device, which includes a processor, a memory, and a computer program stored on the memory and executable by the processor, wherein when the computer program is executed by the processor, the steps of the data analysis method as described above are implemented.
In addition, to achieve the above object, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, wherein the computer program, when executed by a processor, implements the steps of the data analysis method as described above.
The embodiment of the invention analyzes the time sequence sample indexes of historical patients with chronic diseases, which show numerical value change along with the time, identifies the time sequence prediction indexes relevant to the disease development, analyzes and determines the time sequence prediction index change trends corresponding to different historical patient groups, provides reference basis for the grouping of the patients with chronic diseases, then compares and matches the time sequence test index change trend of the current patient with the time sequence prediction index change trend corresponding to the historical patient groups, and further determines the grouping result of the current patient; because the embodiment of the invention carries out patient grouping according to the multiple test indexes of the patient, the adverse effect of the contingency and the randomness of single test data on the grouping reliability is reduced, and the reliability of the patient grouping is improved.
Drawings
Fig. 1 is a schematic diagram of a hardware configuration of a data analysis apparatus according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of a first embodiment of a data analysis method according to the present invention;
FIG. 3 is a schematic diagram of the SHAP value for K-value change slope mean K according to the first embodiment of the data analysis method of the present invention;
fig. 4 is a functional block diagram of a data analysis apparatus according to a first embodiment of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The data analysis method according to the embodiment of the present invention is mainly applied to data analysis equipment, and the data analysis equipment may be equipment with a data processing function, such as a server, a Personal Computer (PC), a notebook computer, and the like.
Referring to fig. 1, fig. 1 is a schematic diagram of a hardware structure of a data analysis device according to an embodiment of the present invention. In this embodiment of the present invention, the data analysis device may include a processor 1001 (e.g., a central processing Unit, CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used for realizing connection communication among the components; the user interface 1003 may include a Display screen (Display), an input unit such as a Keyboard (Keyboard); the network interface 1004 may optionally include a standard wired interface, a WIreless interface (e.g., a WI-FI interface, WI-FI interface); the memory 1005 may be a Random Access Memory (RAM), a non-volatile memory (non-volatile memory), such as a disk memory, and optionally, the memory 1005 may be a storage device independent of the processor 1001. Those skilled in the art will appreciate that the hardware configuration depicted in FIG. 1 is not intended to be limiting of the present invention, and may include more or less components than those shown, or some components in combination, or a different arrangement of components.
With continued reference to FIG. 1, the memory 1005 of FIG. 1, which is one type of computer-readable storage medium, may include an operating system, a network communication module, and a computer program. In fig. 1, the network communication module may be configured to connect to a preset database, and perform data communication with the database; and the processor 1001 may call the computer program stored in the memory 1005 and perform the data analysis method provided by the embodiment of the present invention.
Based on the hardware architecture, embodiments of the data analysis method of the present invention are provided.
The embodiment of the invention provides a data analysis method.
Referring to fig. 2, fig. 2 is a schematic flow chart of a data analysis method according to a first embodiment of the present invention.
In this embodiment, the data analysis method includes the following steps:
step S10, accessing a preset database, obtaining time sequence sample indexes of historical patients from the preset database, and screening the time sequence sample indexes in a significance test mode to obtain time sequence prediction indexes which are statistically associated with the health information of the historical patients;
for chronic diseases, it is a great challenge to divide patients (e.g. one hundred million diabetics) into several sub-groups, and to set different treatment methods for each sub-group to achieve optimal treatment effect. For patients with chronic diseases, multiple visits and continuous observation are often needed, but the existing patient grouping method generally only considers the current single examination index and basic information, ignores the correlation between the indexes before and when the patients, so that the existing grouping method has the contingency and randomness for the chronic diseases, and the reliability of the obtained grouping recommendation is not high. In contrast, the embodiment provides a data analysis method based on a risk index trajectory trend, which analyzes time sequence sample indexes of historical patients with chronic diseases, which show numerical changes along with time, identifies time sequence prediction indexes relevant to disease development, analyzes and determines time sequence prediction index change trends corresponding to different historical patient groups, provides reference basis for slow patients to be grouped, compares and matches the time sequence test index change trend of the current patient along with time with the time sequence prediction index change trends corresponding to the historical patient groups, and further determines the grouping result of the current patient; because the patient clustering is performed according to the multiple examination indexes of the patient, the adverse influence of the contingency and the randomness of single examination data on the clustering reliability is reduced, the reliability of the patient clustering is improved, and an effective reference basis is further provided for the health assessment of the patient.
The data analysis method in this embodiment is implemented by a data analysis device, which may be a server, a personal computer, a notebook computer, or the like, and the server is taken as an example in this embodiment for description. The server is in communication connection with a preset database; the database stores sample indexes provided by a plurality of historical patients, and the corresponding sample indexes are different for the historical patients with different disease types, for example, the sample indexes of the diabetic patients comprise glycosylated hemoglobin, blood glucose concentration, blood pressure and the like, and the sample indexes of the chronic kidney disease patients comprise glomerular filtration rate and the like. It should be noted that each type of test sample includes data values at a plurality of test times, and the data values are not in a time sequence, i.e. the sample index is a time sequence sample index.
The server in this embodiment may obtain the time sequence sample index from a preset database. For the time sequence sample indexes, because the time sequence sample indexes are of a plurality of types, in practice, not all the time sequence sample indexes have correlation with a certain type of diseases, the server can screen out the time sequence prediction indexes which have correlation with the health (adverse events and death outcome) of the user from the time sequence sample indexes in a significance inspection or manual marking screening mode and perform subsequent analysis as possible risk factors; the health of the user can be obtained according to the health information of the historical user corresponding to the time series sample index, so that the time series prediction index can be considered to be statistically associated with the health information of the historical patient (has a significant statistical significance). For example, when a significance test mode is adopted, various time sequence sample indexes can be respectively used as characteristic variables, the final health condition (or disease diagnosis result, adverse event, death and the like) of a historical patient is used as an ending variable, then the relation between the characteristic variables and the ending variable is mined in a chi-square test mode, the characteristic variables having significant statistical significance on the influence of the ending variable are identified in a mode that a P-value calculated by the chi-square test is less than 0.05, and the time sequence sample index corresponding to the characteristic variables is a time sequence prediction index; further, the relative risk degree RR OR the ratio OR can be used to analyze whether the characteristic variables have positive OR negative influence on the outcome variable (so as to determine the time-series sample index as a risk OR protection factor).
Step S20, analyzing the time sequence prediction index value change relation along with time to obtain the value change slope average value corresponding to the change relation;
in this embodiment, when the server obtains the time series prediction indexes having correlation with the health of the user, the server may analyze a change relationship of the numerical values of the time series prediction indexes with time, and characterize the change relationship in a manner of a change slope of the numerical values. When analysis is carried out, time is used as an independent variable (x axis), the numerical value of the time sequence prediction index is used as a dependent variable (y axis), then numerical value points corresponding to each time sequence prediction index are drawn in a preset coordinate system, and then all the numerical value points are connected into a line according to the time sequence to obtain a prediction index line; and then, carrying out slope analysis on the prediction index line to determine the numerical value change slope average value of the prediction index, wherein the numerical value change slope average value represents the time-varying relation of the numerical value of the time sequence prediction index. It should be noted that when the types of the timing prediction indexes include multiple types, the server analyzes the various types of timing prediction indexes respectively to obtain a plurality of value change slope averages.
Furthermore, considering that the index having correlation with the irreversible disease change generally changes monotonically when the disease change occurs, only the index with relatively small fluctuation and stability can be analyzed in this embodiment. Specifically, before the step S20, the method further includes;
performing stability screening on the time sequence prediction index to obtain a target preset index meeting a preset change rule;
in the embodiment, when the server obtains the time sequence prediction index which is related to health, in order to make the analysis process more accurate and reliable, the time sequence prediction index can be subjected to stability screening firstly, the time sequence prediction index with larger fluctuation is eliminated, a target prediction index which is gentle in fluctuation and has a monotonous change rule is obtained, and then the target prediction index is analyzed; the monotone change law includes monotone decrease and monotone increase. For the index with gentle fluctuation and single-point regular change, the identification can be performed through the following formula:
for a monotonically decreasing index:
Figure BDA0002205714560000061
for a monotonically rising index:
Figure BDA0002205714560000062
in the above formula, x (i +1) is the data value of the time series prediction index at the time i +1, and x (i) is the data value of the time series prediction index at the time i; a is a constant greater than zero and close to zero, b is a constant less than zero and close to zero; threshold1 and threshold2 are absolute value thresholds of the rate of change, and are constants greater than zero. The fluctuation is smooth, namely the absolute value of the numerical change rate of the time sequence prediction index is limited within a threshold value.
The step S20 includes:
analyzing the change relation of the numerical value of the target prediction index along with time to obtain a numerical value change slope average value corresponding to the change relation;
when the server obtains the target prediction index again, the server can analyze the change relation of the numerical value of the target prediction index along with time to obtain the corresponding numerical value change slope average value, and the specific analysis process is as above, and is not repeated here.
Step S30, analyzing a nonlinear relation between the numerical value change slope mean value and the historical clustering result based on a characteristic attribution method and the historical clustering result of the historical patients, determining a classification control slope representing the nonlinear relation, and simulating in a preset coordinate system according to the classification control slope to obtain a control trajectory;
in this embodiment, when the server obtains the numerical change slope mean value corresponding to the time-series prediction index (target prediction index), the server analyzes the nonlinear relationship between the numerical change slope mean value and the historical patient clustering standard (patient health condition) based on the SHAP feature attribution method and the historical clustering result of the historical patients (i.e., the historical clustering result of the historical patients corresponding to the time-series prediction index), and finds the classification control slope representing the nonlinear relationship, where the classification control slope may include an optimal control value k, a positive control value k1 having a positive typical influence on the classification outcome, and a negative control value k2 having a negative typical influence on the classification outcome, thereby establishing a prediction model of the numerical change slope mean value of the index for patient clustering. The SHAP is a method for explaining the output of a machine learning model, the marginal contribution of a feature when the feature is added into the model is calculated, then the different marginal contributions of the feature under all feature sequences are considered and averaged, the average value is the SHAP value of the feature, the nonlinear relation between the feature pair and the outcome is represented by the SHAP value, the larger the SHAP value is, the more positive the influence on the outcome is, and the smaller the value is, the more negative the influence on the outcome is.
Specifically, in the present embodiment, a plurality of numerical change slopes K may be used as characteristic variables, which form a whole set N, and a historical clustering result of historical patients is used as an ending variable, one of the characteristic variables may be randomly selected from the whole set N as a current variable α, then all subsets including the current variable α in the whole set N (including N itself) may be determined, all subsets including the current variable α may be designated as Ri (γ + α), and the number of the subsets may be designated as N, when the subsets are determined, the current variable α in the subsets may be further removed, so as to obtain a non- α subset corresponding to Ri (γ + α), which may be designated as Ri (γ), and then each average Value (γ + α) may be calculated for the average Value of the local variable [ i.e. the average Value of the gradient-gravity gradient prediction algorithm, i.e. the average Value of the gradient-average Value when the gradient of the current variable is calculated as a typical average Value of the average Value Ri (γ + α) and the gradient of the average Value of the local variable (γ + gradient), which may be calculated as a typical average Value of the local variable Ri (Ri + gradient), which may be calculated as a typical gradient of the average Value of the gradient-average Value, which may be calculated as a typical gradient-average Value of the gradient-average Value, which is calculated as a typical gradient-average Value, when the gradient-average Value of the gradient-average Value, and the gradient-average Value of the gradient-average Value (Fi + gradient-average Value of the gradient-average gradient-score (Fi), and the average gradient-gradient.
After the classification control slopes (k, k1, k2) are obtained, corresponding control trajectory lines can be obtained in a preset coordinate system through fitting according to the classification control slopes, and the control trajectory lines can divide index value change trajectories corresponding to the time sequence prediction indexes into three typical types; these control tracks can be respectively marked as y ═ k × x + b, y1 ═ k1 × x + b1, and y2 ═ k2 × x + b2, where b1, b2, and b3 are all constants, y represents an index value track having no significant influence on the historical clustering result, y1 represents an index value track having significant positive influence on the historical clustering result, y2 represents an index value track having significant negative influence on the historical clustering result, and these three control tracks are data track central lines corresponding to the index value change trends corresponding to the historical clustering result. It is worth noting that in practice, the number of categorizing control slopes and control traces may be defined on a case-by-case basis.
Step S40, obtaining the time sequence inspection index of the current patient according to the index type of the time sequence prediction index, and fitting in the preset coordinate system according to the time sequence inspection index to obtain a corresponding inspection trajectory line;
in this embodiment, when the control trajectory line is obtained, the patients may be grouped according to the control trajectory line in combination with the current time sequence testing index of the patients. First, the server may obtain a timing test indicator of the current patient according to an indicator type of the timing prediction indicator, that is, obtain a test indicator corresponding to the control trajectory line (for example, the indicator of the diabetic patient includes glycated hemoglobin, blood glucose concentration, blood pressure, etc., and the indicator of the chronic kidney disease includes glomerular filtration rate, etc.).
Specifically, the step of obtaining the time series test index of the current patient according to the index type of the time series prediction index includes:
and acquiring periodic physical examination data of the current patient in a preset period from the preset database, screening the periodic physical examination data according to the index type of the time sequence prediction index, and acquiring a time sequence inspection index corresponding to the index type of the time sequence prediction index.
In this embodiment, in order to provide data for the current patient conveniently, the time-series inspection index can be obtained by automatically identifying and screening the time-series inspection index according to the physical examination data of the current patient. Specifically, after the current patient is subjected to physical examination (or some physical examination), the current patient can upload the physical examination data of the current patient to a database (such as a medical system database of a hospital) by himself or by authorizing others. The server is connected with the database, obtains periodic physical examination data of the current patient in a certain preset period from the database, screens the periodic physical examination data according to the index type of the time sequence prediction index, obtains the time sequence detection index corresponding to the index type of the time sequence prediction index, and performs subsequent analysis processing according to the time sequence detection index, so that the index (data) obtaining efficiency is improved, and the current patient can conveniently provide related detection index data.
Further, since the physical examination data of the patient belongs to the private data, for the physical examination data of the current patient, the security of the storage of the physical examination data of the current patient can be improved by setting the permission and the encryption mode. Specifically, before the step of obtaining the periodic physical examination data of the current patient in a preset period from the preset database, the method further includes:
sending a data acquisition request to a patient terminal;
in this embodiment, the physical examination data stored in the database of each patient is respectively tabulated and stored by different account identifiers, the physical examination data is stored in the database in an encrypted manner, and a key used for decryption is stored by the current patient, so that the security of data storage is improved. Before acquiring the periodic physical examination data of the current patient, the server first sends a data acquisition request to a patient terminal (such as a mobile phone, a tablet computer, and the like) of the current patient to obtain a right to call the physical examination data of the current patient.
Receiving data permission information returned by the patient terminal, and analyzing the data permission information to obtain a corresponding patient account identifier and a corresponding patient data key;
in this embodiment, if the current patient agrees that the server calls the medical examination data of the patient, the patient terminal may be operated to return the data permission information to the server, where the data permission information includes the patient account identifier and the patient data key. When the server receives the data permission information, the server can analyze the data permission information to obtain a corresponding patient account identifier and a corresponding patient data key.
The step of obtaining the period physical examination data of the current patient in a preset period from the preset database comprises:
accessing the preset database through the patient account identifier to acquire encrypted experience data of the current patient;
in this embodiment, when the server obtains the patient account identifier and the patient data key, the server may access the preset database through the patient account identifier, query the corresponding data table (account data), and obtain the encrypted experience data of the current patient
And decrypting the encrypted experience data through the patient data secret key, and acquiring periodic physical examination data of the current patient in a preset period according to a decryption result.
In this embodiment, when obtaining the encrypted experience data of the current patient, the server may decrypt the encrypted experience data through the patient data key, and obtain the period physical examination data of the current patient in the preset period according to the decryption result.
When the server obtains the periodic physical examination data, the periodic physical examination data can be screened according to the index type of the time sequence prediction index, and a time sequence inspection index corresponding to the index type of the time sequence prediction index is obtained; and then fitting the numerical value in the time sequence test index as a dependent variable (y axis) and time as an independent variable (x axis) in a preset coordinate system to obtain a corresponding test trajectory line.
Step S50, comparing the positions of the test trajectory line and the control trajectory line, and determining the clustering result of the current patient according to the position relationship between the test trajectory line and the control trajectory line and the historical clustering result of the historical patients.
In this embodiment, when the inspection trajectory line is obtained, the inspection trajectory line and the control trajectory line may be subjected to position comparison, and then the trajectory type of the inspection trajectory line is determined according to the position relationship between the inspection trajectory line and the control trajectory line; and for different position relations, corresponding to different historical clustering results of historical patients, when the position relation between the inspection track line and the control track line is determined, the clustering result of the current patient can be determined according to the position relation, so that the similar patient group of the current patient is determined. Specifically, taking a control trajectory as an example, the historical clustering results of historical patients include two results; in a preset coordinate system, a certain target quadrant of the preset coordinate system can be divided into at least two sub-areas through the control track line, wherein each sub-area corresponds to a historical clustering result; then, a target sub-area where the inspection trajectory is located can be determined, and a historical clustering result corresponding to the target sub-area is a clustering result of the current patient; it should be noted that, in order to compare the position relationship between the control trace line and the test trace line, certain translation processing may be performed on the two lines during comparison, so that the two lines intersect at the same point in the y axis or the x axis.
Further, after the step S50, the method further includes:
sending the grouping result of the current patient to a corresponding diagnosis and treatment terminal;
in this embodiment, when obtaining the clustering result of the current patient, the server may send the clustering result of the current patient to the corresponding diagnosis and treatment terminal, so that medical staff can provide reference for diagnosis and treatment of the current patient.
When the grouping adjustment information returned by the diagnosis and treatment terminal is received, the grouping result of the current patient is adjusted according to the grouping correction information, and the adjusted grouping result of the current patient and the time sequence inspection index are stored in the preset database in an associated mode.
In this embodiment, since the clustering result of the current patient provided by the server is only used as a reference, the medical staff may adjust the clustering result of the current patient; when the adjustment is needed, the medical staff can return the corresponding grouping adjustment information to the server through the diagnosis and treatment terminal. And when receiving the grouping adjustment information returned by the diagnosis and treatment terminal, the server adjusts the grouping result of the current patient according to the grouping correction information, and then associates and stores the adjusted grouping result of the current patient and the time sequence inspection index into a database for subsequent reference. By the mode, more sample data can be accumulated continuously according to the actual medical treatment process, and the subsequent optimization and adjustment of the analysis process are facilitated.
Still further, the data analysis method of the embodiment further includes:
and when the number of times of receiving the grouping adjustment information is larger than a preset threshold value, re-acquiring a corresponding control track line according to the newly-put time sequence inspection index in the preset database and a grouping result corresponding to the newly-put time sequence inspection index.
In this embodiment, the server further counts the number of times of receiving the grouping adjustment information, and when the number of times of receiving the grouping adjustment information is greater than a preset threshold, it may be considered that the control trajectory line that is determined by previous analysis and currently used does not conform to the actual situation; at the moment, the server can call the newly-put time sequence inspection index and the grouping result corresponding to the newly-put time sequence inspection index, and then analysis processing is carried out again according to the newly-put time sequence inspection index and the grouping result thereof so as to obtain the corresponding control track line again and use the control track line for subsequent patient grouping; the re-acquisition process of the control trace line is as described above, and is not described herein again. By the mode, the control track line can be continuously optimized and adjusted according to the actual medical treatment condition, and the accuracy and the reliability of patient grouping are further improved.
The embodiment analyzes time sequence sample indexes of historical patients with chronic diseases, which show numerical value change along with the time, identifies time sequence prediction indexes relevant to disease development, analyzes and determines time sequence prediction index change trends corresponding to different historical patient groups, provides reference basis for grouping the patients with chronic diseases, then compares and matches the time sequence test index change trend of the current patient with the time sequence prediction index change trends corresponding to the historical patient groups, and further determines the grouping result of the current patient; according to the embodiment of the invention, the grouping of the patients is carried out according to the multiple test indexes of the patients, so that the adverse influence of the contingency and randomness of single test data on the grouping reliability is reduced, the reliability of the grouping of the patients is improved, and an effective reference basis is further provided for the health assessment of the patients.
Based on the embodiment shown in fig. 2, a second embodiment of the data analysis method of the present invention is provided.
In this embodiment, after step S50, the method further includes:
and acquiring historical health data of similar patients from the preset database according to the grouping result of the current patient, and sending the historical health data to a corresponding terminal.
In this embodiment, when obtaining the clustering result of the current patient, the server may obtain historical health data of similar patients from the database according to the clustering result of the current patient, and then send the historical health data to corresponding terminals (such as diagnosis and treatment terminals of diagnosis and treatment staff, patient terminals of the current patient, and the like), so as to provide a health reference basis for the corresponding terminal staff and provide convenience for subsequent diagnosis and treatment.
In addition, the embodiment of the invention also provides a data analysis device.
Referring to fig. 4, fig. 4 is a functional block diagram of a data analysis apparatus according to a first embodiment of the present invention.
In this embodiment, the data analysis apparatus includes:
the index obtaining module 10 is configured to access a preset database, obtain time series sample indexes of historical patients from the preset database, and screen the time series sample indexes in a significance test manner to obtain time series prediction indexes statistically associated with health information of the historical patients;
the first analysis module 20 is configured to analyze a change relationship of the numerical value of the time sequence prediction index with time to obtain a numerical value change slope mean value corresponding to the change relationship;
the second analysis module 30 is configured to analyze a nonlinear relationship between the numerical change slope mean and the historical clustering results based on a feature attribution method and the historical clustering results of the historical patients, determine a classification control slope representing the nonlinear relationship, and simulate in a preset coordinate system according to the classification control slope to obtain a control trajectory;
the track fitting module 40 is configured to obtain a time sequence inspection index of the current patient according to the index type of the time sequence prediction index, and fit the time sequence inspection index in the preset coordinate system to obtain a corresponding inspection track line;
and the position comparison module 50 is configured to perform position comparison on the inspection trajectory and the control trajectory, and determine a clustering result of the current patient according to a position relationship between the inspection trajectory and the control trajectory and a historical clustering result of the historical patients.
Each virtual function module of the data analysis apparatus is stored in the memory 1005 of the data analysis device shown in fig. 1, and is used for realizing all functions of a computer program; the modules, when executed by the processor 1001, may perform the function of patient clustering.
Further, the data analysis apparatus further includes:
the index screening module is used for performing stability screening on the time sequence prediction index to obtain a target prediction index meeting a preset change rule;
the first analysis module 20 is further configured to analyze a change relationship of the value of the target prediction index with time, and obtain a value change slope mean value corresponding to the change relationship.
Further, the preset variation law comprises a monotone descending and/or a monotone ascending,
the index screening module is specifically configured to perform stability screening on the time sequence prediction index through a first formula to obtain a target prediction index meeting a monotonic decrease rule, where the first formula is
Figure BDA0002205714560000131
And/or performing stability screening on the time sequence prediction index through a second formula to obtain a target prediction index meeting the monotone rising rule, wherein the second formula is
Figure BDA0002205714560000132
Wherein x (i +1) is the data value of the time sequence prediction index at the time i +1, and x (i) is the data value of the time sequence prediction index at the time i;
a is a constant greater than zero and b is a constant less than zero;
threshold1 and threshold2 are both constants greater than zero.
Further, the second analysis module 30 includes:
the system comprises a slope determination unit, a calculation unit and a classification unit, wherein the slope determination unit is used for taking the numerical change slope mean value as a characteristic variable and taking the historical clustering result as an ending variable, the characteristic variable forms a complete set N, one characteristic variable is selected from the N as a current variable α, all subsets Ri (gamma + α) of the N including a current variable α are determined, non- α subsets Ri (gamma) corresponding to Ri (gamma + α) and not including the current variable α are determined, contribution degrees F [ Ri (gamma + α) ] of the Ri (gamma + α) to the ending variable and contribution degrees F [ Ri (gamma) ] of the Ri (gamma) to the ending variable are respectively calculated through a preset algorithm, contribution degree difference values of the Ri (gamma + α) ] and the corresponding F [ Ri (gamma) ] are respectively calculated, the mean value of the respective DeltaFi is calculated as a SHAP value of the current variable α, the SHAP value of the characteristic variables in the N is respectively calculated, the SHAP value of the characteristic variables is determined, and the slope average value of the target variable is classified into a typical control target variable.
Further, the trajectory fitting module 40 includes a data acquisition unit,
the data acquisition unit is used for acquiring periodic physical examination data of the current patient in a preset period from the preset database, screening the periodic physical examination data according to the index type of the time sequence prediction index, and acquiring a time sequence inspection index corresponding to the index type of the time sequence prediction index.
Further, the data analysis apparatus further includes:
and the data sending module is used for acquiring historical health data of similar patients from the preset database according to the grouping result of the current patient and sending the historical health data to a corresponding terminal.
The function implementation of each module in the data analysis apparatus corresponds to each step in the data analysis method embodiment, and the function and implementation process thereof are not described in detail herein.
In addition, the embodiment of the invention also provides a computer readable storage medium.
The computer-readable storage medium of the present invention has stored thereon a computer program, which when executed by a processor, performs the steps of the data analysis method as described above.
The method implemented when the computer program is executed may refer to various embodiments of the data analysis method of the present invention, and details thereof are not repeated herein.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) as described above and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.

Claims (10)

1. A data analysis method, characterized in that the data analysis method comprises:
accessing a preset database, acquiring time sequence sample indexes of historical patients from the preset database, and screening the time sequence sample indexes in a significance test mode to obtain time sequence prediction indexes which are statistically associated with the health information of the historical patients;
analyzing the change relation of the numerical value of the time sequence prediction index along with time to obtain a numerical value change slope average value corresponding to the change relation;
analyzing a nonlinear relation between the numerical value change slope mean value and the historical clustering result based on a characteristic attribution method and the historical clustering result of the historical patients, determining a classification control slope representing the nonlinear relation, and simulating in a preset coordinate system according to the classification control slope to obtain a control trajectory line;
acquiring a time sequence inspection index of the current patient according to the index type of the time sequence prediction index, and fitting in the preset coordinate system according to the time sequence inspection index to obtain a corresponding inspection trajectory line;
and comparing the positions of the test trajectory line and the control trajectory line, and determining the grouping result of the current patient according to the position relation between the test trajectory line and the control trajectory line and the historical grouping result of the historical patients.
2. The data analysis method according to claim 1, wherein before the step of analyzing the time-varying relationship between the time series prediction index value and the time, and obtaining the mean value of the value variation slopes corresponding to the time-varying relationship, the method further comprises:
performing stability screening on the time sequence prediction index to obtain a target prediction index meeting a preset change rule;
the step of analyzing the time-varying relationship of the value of the time sequence prediction index and obtaining the value variation slope mean value corresponding to the variation relationship comprises:
and analyzing the change relation of the numerical value of the target prediction index along with time to obtain a numerical value change slope average value corresponding to the change relation.
3. The data analysis method of claim 2, wherein the preset variation law includes a monotone decrease and/or a monotone increase,
the step of performing stability screening on the time sequence prediction index to obtain a target prediction index meeting a preset change rule comprises the following steps:
performing stability screening on the time sequence prediction index through a first formula to obtain a target prediction index meeting a monotone decreasing rule, wherein the first formula is
max(x(i+1)-x(i))<a,and
Figure FDA0002205714550000021
And/or performing stability screening on the time sequence prediction index through a second formula to obtain a target prediction index meeting the monotone rising rule, wherein the second formula is
max(x(i+1)-x(i))>b,and
Figure FDA0002205714550000022
Wherein x (i +1) is the data value of the time sequence prediction index at the time i +1, and x (i) is the data value of the time sequence prediction index at the time i;
a is a constant greater than zero and b is a constant less than zero;
threshold1 and threshold2 are both constants greater than zero.
4. The data analysis method of claim 1, wherein the analyzing a non-linear relationship between the mean of the numerical change slopes and the historical clustering results based on a feature attribution method and the historical clustering results of the historical patients, and wherein the determining a classification control slope characterizing the non-linear relationship comprises:
taking the numerical value change slope mean value as a characteristic variable, and taking the historical clustering result as an ending variable, wherein the characteristic variable forms a complete set N;
selecting a characteristic variable from the N as a current variable α, determining all subsets Ri (gamma + α) of the N including the current variable α, and determining non- α subsets Ri (gamma) corresponding to Ri (gamma + α) and not including the current variable α;
respectively calculating the contribution degree F [ Ri (gamma + α) ] of each Ri (gamma + α) to the ending variable and the contribution degree F [ Ri (gamma) ] of each Ri (gamma) to the ending variable through a preset algorithm;
respectively calculating contribution degree difference values delta Fi of each F [ Ri (gamma + α) ] and the corresponding F [ Ri (gamma) ], and calculating the average value of each delta Fi to serve as the SHAP value of the current variable α;
and calculating SHAP values of the characteristic variables in the N respectively according to the classification control slope, determining target variables having typical influence on the ending variable according to the SHAP values of the characteristic variables, and determining the average value of the numerical change slopes corresponding to the target variables as the classification control slope.
5. The data analysis method of claim 1, wherein the step of comparing the position of the test trajectory with the position of the control trajectory and determining the clustering result of the current patient according to the position relationship between the test trajectory and the control trajectory and the historical clustering results of the historical patients comprises:
dividing a target quadrant of the preset coordinate system into at least two sub-regions through the control trajectory line, wherein each sub-region is in one-to-one correspondence with the historical clustering results of the historical patients;
and determining a target sub-region where the inspection trajectory is located, and determining a clustering result of the current patient according to a historical clustering result corresponding to the target sub-region.
6. The data analysis method of claim 1, wherein the step of obtaining a time series test metric for the current patient based on the metric type of the time series predictor comprises:
and acquiring periodic physical examination data of the current patient in a preset period from the preset database, screening the periodic physical examination data according to the index type of the time sequence prediction index, and acquiring a time sequence inspection index corresponding to the index type of the time sequence prediction index.
7. The data analysis method of any one of claims 1 to 6, wherein after the step of comparing the position of the test trajectory with the control trajectory and determining the clustering result of the current patient according to the position relationship between the test trajectory and the control trajectory and the historical clustering results of the historical patients, the method further comprises:
and acquiring historical health data of similar patients from the preset database according to the grouping result of the current patient, and sending the historical health data to a corresponding terminal.
8. A data analysis apparatus, characterized in that the data analysis apparatus comprises:
the index acquisition module is used for accessing a preset database, acquiring time sequence sample indexes of historical patients from the preset database, and screening the time sequence sample indexes in a significance test mode to obtain time sequence prediction indexes which are statistically associated with the health information of the historical patients;
the first analysis module is used for analyzing the change relation of the numerical value of the time sequence prediction index along with time to obtain a numerical value change slope average value corresponding to the change relation;
the second analysis module is used for analyzing a nonlinear relation between the numerical value change slope mean value and the historical clustering result based on a characteristic attribution method and the historical clustering result of the historical patients, determining a classification control slope representing the nonlinear relation, and simulating in a preset coordinate system according to the classification control slope to obtain a control trajectory;
the track fitting module is used for acquiring the time sequence inspection index of the current patient according to the index type of the time sequence prediction index and fitting the time sequence inspection index in the preset coordinate system to obtain a corresponding inspection track line;
and the position comparison module is used for performing position comparison on the inspection track line and the control track line and determining the grouping result of the current patient according to the position relation between the inspection track line and the control track line and the historical grouping result of the historical patients.
9. A data analysis device, characterized in that the data analysis device comprises a processor, a memory, and a computer program stored on the memory and executable by the processor, wherein the computer program, when executed by the processor, implements the steps of the data analysis method according to any one of claims 1 to 7.
10. A computer-readable storage medium, having a computer program stored thereon, wherein the computer program, when being executed by a processor, carries out the steps of the data analysis method according to any one of claims 1 to 7.
CN201910884245.8A 2019-09-18 2019-09-18 Data analysis method, device, equipment and computer readable storage medium Active CN110782989B (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN201910884245.8A CN110782989B (en) 2019-09-18 2019-09-18 Data analysis method, device, equipment and computer readable storage medium
PCT/CN2020/112468 WO2021052156A1 (en) 2019-09-18 2020-08-31 Data analysis method, apparatus and device, and computer readable storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910884245.8A CN110782989B (en) 2019-09-18 2019-09-18 Data analysis method, device, equipment and computer readable storage medium

Publications (2)

Publication Number Publication Date
CN110782989A true CN110782989A (en) 2020-02-11
CN110782989B CN110782989B (en) 2022-06-17

Family

ID=69384226

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910884245.8A Active CN110782989B (en) 2019-09-18 2019-09-18 Data analysis method, device, equipment and computer readable storage medium

Country Status (2)

Country Link
CN (1) CN110782989B (en)
WO (1) WO2021052156A1 (en)

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111401788A (en) * 2020-04-10 2020-07-10 支付宝(杭州)信息技术有限公司 Attribution method and device of service timing sequence index
CN111461055A (en) * 2020-04-14 2020-07-28 上海异工同智信息科技有限公司 Method and device for identifying state of signal to be monitored and electronic equipment
CN111755125A (en) * 2020-07-07 2020-10-09 医渡云(北京)技术有限公司 Method, device, medium and electronic device for analyzing patient measurement index
CN111816310A (en) * 2020-07-16 2020-10-23 山东大学 Bone marrow blood disease risk factor contribution rate calculation and risk prediction system
CN112151136A (en) * 2020-09-30 2020-12-29 上海依智医疗技术有限公司 Medical data processing method and device and storage medium
WO2021052156A1 (en) * 2019-09-18 2021-03-25 平安科技(深圳)有限公司 Data analysis method, apparatus and device, and computer readable storage medium
CN114496264A (en) * 2022-04-14 2022-05-13 深圳市瑞安医疗服务有限公司 Health index analysis method, device, equipment and medium based on multi-dimensional data
CN117373664A (en) * 2023-10-09 2024-01-09 曜立科技(北京)有限公司 Coronary artery postoperative dangerous data analysis early warning system based on digital therapy
CN117854732A (en) * 2024-03-08 2024-04-09 微脉技术有限公司 Chronic disease management method and system based on big data analysis

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113159453B (en) * 2021-05-17 2024-04-30 北京字跳网络技术有限公司 Resource data prediction method, device, equipment and storage medium
CN116089491B (en) * 2022-12-15 2024-01-30 清华大学 Retrieval matching method and device based on time sequence database
CN116682566B (en) * 2023-08-03 2023-10-31 青岛市中医医院(青岛市海慈医院、青岛市康复医学研究所) Hemodialysis data processing method and system
CN117150891B (en) * 2023-08-15 2024-04-26 幂光新材料科技(上海)有限公司 Intelligent prediction method and system for LED lamp bead power based on data driving
CN117708764B (en) * 2024-02-06 2024-05-03 青岛天高智慧科技有限公司 Intelligent analysis method for student consumption data based on campus card

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110161094A1 (en) * 2002-08-23 2011-06-30 Dxcg, Inc. System and method for health care costs and outcomes modeling using dosage and routing pharmacy information
CN106778042A (en) * 2017-01-26 2017-05-31 中电科软件信息服务有限公司 Cardio-cerebral vascular disease patient similarity analysis method and system
US20170342503A1 (en) * 2016-05-24 2017-11-30 The Board Of Regents Of The University Of Texas System Xrn2 as a determinant of sensitivity to dna damage
CN109493979A (en) * 2018-10-23 2019-03-19 平安科技(深圳)有限公司 A kind of disease forecasting method and apparatus based on intelligent decision
CN109817338A (en) * 2019-02-13 2019-05-28 北京大学第三医院(北京大学第三临床医学院) A kind of chronic disease aggravates risk assessment and warning system
CN110085318A (en) * 2019-03-12 2019-08-02 平安科技(深圳)有限公司 Predict the method, apparatus and computer equipment of future blood glucose value
WO2019160504A1 (en) * 2018-02-13 2019-08-22 Agency For Science, Technology And Research System and method for assessing clinical event risk based on heart rate complexity

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20130082551A (en) * 2011-12-08 2013-07-22 한국전자통신연구원 Clinical data analysis apparatus and clinical data analysis method thereof
JP6625730B2 (en) * 2015-05-06 2019-12-25 プレサイエント メディスン ホールディングズ リミテッド ライアビリティ カンパニーPrescient Medicine Holdings, Llc. Development of a new automated screening method for the detection of FVIII inhibitors
US20180150609A1 (en) * 2016-11-29 2018-05-31 Electronics And Telecommunications Research Institute Server and method for predicting future health trends through similar case cluster based prediction models
CN110163195A (en) * 2018-02-14 2019-08-23 中国医药大学附设医院 Liver cancer divides group's prediction model, its forecasting system and liver cancer to divide group's judgment method
CN109509549B (en) * 2018-05-28 2024-05-14 深圳平安医疗健康科技服务有限公司 Diagnosis and treatment service provider evaluation method, diagnosis and treatment service provider evaluation device, computer equipment and storage medium
CN109634801B (en) * 2018-10-31 2022-04-12 深圳壹账通智能科技有限公司 Data trend analysis method, system, computer device and readable storage medium
CN110782989B (en) * 2019-09-18 2022-06-17 平安科技(深圳)有限公司 Data analysis method, device, equipment and computer readable storage medium

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110161094A1 (en) * 2002-08-23 2011-06-30 Dxcg, Inc. System and method for health care costs and outcomes modeling using dosage and routing pharmacy information
US20170342503A1 (en) * 2016-05-24 2017-11-30 The Board Of Regents Of The University Of Texas System Xrn2 as a determinant of sensitivity to dna damage
CN106778042A (en) * 2017-01-26 2017-05-31 中电科软件信息服务有限公司 Cardio-cerebral vascular disease patient similarity analysis method and system
WO2019160504A1 (en) * 2018-02-13 2019-08-22 Agency For Science, Technology And Research System and method for assessing clinical event risk based on heart rate complexity
CN109493979A (en) * 2018-10-23 2019-03-19 平安科技(深圳)有限公司 A kind of disease forecasting method and apparatus based on intelligent decision
CN109817338A (en) * 2019-02-13 2019-05-28 北京大学第三医院(北京大学第三临床医学院) A kind of chronic disease aggravates risk assessment and warning system
CN110085318A (en) * 2019-03-12 2019-08-02 平安科技(深圳)有限公司 Predict the method, apparatus and computer equipment of future blood glucose value

Cited By (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2021052156A1 (en) * 2019-09-18 2021-03-25 平安科技(深圳)有限公司 Data analysis method, apparatus and device, and computer readable storage medium
CN111401788A (en) * 2020-04-10 2020-07-10 支付宝(杭州)信息技术有限公司 Attribution method and device of service timing sequence index
CN111401788B (en) * 2020-04-10 2022-03-25 支付宝(杭州)信息技术有限公司 Attribution method and device of service timing sequence index
CN111461055A (en) * 2020-04-14 2020-07-28 上海异工同智信息科技有限公司 Method and device for identifying state of signal to be monitored and electronic equipment
CN111755125A (en) * 2020-07-07 2020-10-09 医渡云(北京)技术有限公司 Method, device, medium and electronic device for analyzing patient measurement index
CN111755125B (en) * 2020-07-07 2024-04-23 医渡云(北京)技术有限公司 Method, device, medium and electronic equipment for analyzing patient measurement index
CN111816310A (en) * 2020-07-16 2020-10-23 山东大学 Bone marrow blood disease risk factor contribution rate calculation and risk prediction system
CN112151136A (en) * 2020-09-30 2020-12-29 上海依智医疗技术有限公司 Medical data processing method and device and storage medium
CN114496264A (en) * 2022-04-14 2022-05-13 深圳市瑞安医疗服务有限公司 Health index analysis method, device, equipment and medium based on multi-dimensional data
CN117373664A (en) * 2023-10-09 2024-01-09 曜立科技(北京)有限公司 Coronary artery postoperative dangerous data analysis early warning system based on digital therapy
CN117373664B (en) * 2023-10-09 2024-05-28 曜立科技(北京)有限公司 Coronary artery postoperative dangerous data analysis early warning system based on digital therapy
CN117854732A (en) * 2024-03-08 2024-04-09 微脉技术有限公司 Chronic disease management method and system based on big data analysis

Also Published As

Publication number Publication date
CN110782989B (en) 2022-06-17
WO2021052156A1 (en) 2021-03-25

Similar Documents

Publication Publication Date Title
CN110782989B (en) Data analysis method, device, equipment and computer readable storage medium
US10140422B2 (en) Progression analytics system
Ratcliff et al. Internal and external sources of variability in perceptual decision-making.
CN104866763B (en) Android malware mixing detection method based on permission
US20100017225A1 (en) Diagnostician customized medical diagnostic apparatus using a digital library
WO2019040634A1 (en) System and method for analyzing electroencephalogram signals
CN112185468B (en) Cloud management system and method for gene data analysis and processing
Pezdek et al. Cross-race (but not same-race) face identification is impaired by presenting faces in a group rather than individually.
CN109065187A (en) A kind of urine trace analysis method and apparatus
CN114283947A (en) Health management method and system suitable for surgical patients
CN111091884B (en) Patient main index matching system and method of hospital information integration platform
CN116705238A (en) Sports prescription health data management platform based on physical and medical combination
CN112507916B (en) Face detection method and system based on facial expression
CN112435745B (en) Method and device for recommending treatment strategy, electronic equipment and storage medium
CN112489806B (en) Intelligent management method and system for disease state information of diabetic foot patient
Rocha et al. Modelling neuromuscular blockade: a stochastic approach based on clinical data
CN112998657A (en) Method and system for preventing skin allergy
CN115240828A (en) Operating room intelligent regulation and control system and method
CN106859597B (en) Remote monitoring method and device
Ollier et al. Penalized Poisson model for network meta‐analysis of individual patient time‐to‐event data
Lutz et al. Patient-focused research in psychotherapy: methodological background, decision rules and feedback tools
CN113488187B (en) Anesthesia accident case collecting and analyzing method and system
US10943693B2 (en) Concise datasets platform
CN109543774B (en) Abnormal hemodialysis ratio detection method, device, equipment and computer storage medium
CN113764106B (en) Epidemic situation prevention and control effect prediction method and related products

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
REG Reference to a national code

Ref country code: HK

Ref legal event code: DE

Ref document number: 40023207

Country of ref document: HK

SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant