CN116884615A - Hypertension risk prediction method, system, electronic equipment and storage medium - Google Patents
Hypertension risk prediction method, system, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN116884615A CN116884615A CN202310952324.4A CN202310952324A CN116884615A CN 116884615 A CN116884615 A CN 116884615A CN 202310952324 A CN202310952324 A CN 202310952324A CN 116884615 A CN116884615 A CN 116884615A
- Authority
- CN
- China
- Prior art keywords
- data
- blood pressure
- hypertension
- pressure measurement
- risk
- 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
- 206010020772 Hypertension Diseases 0.000 title claims abstract description 72
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000009530 blood pressure measurement Methods 0.000 claims abstract description 51
- 238000005065 mining Methods 0.000 claims abstract description 21
- 238000007781 pre-processing Methods 0.000 claims abstract description 12
- 238000004458 analytical method Methods 0.000 claims description 13
- 230000036772 blood pressure Effects 0.000 claims description 13
- 238000004891 communication Methods 0.000 claims description 13
- 238000010845 search algorithm Methods 0.000 claims description 11
- 230000006870 function Effects 0.000 claims description 9
- 238000012216 screening Methods 0.000 claims description 7
- 230000005484 gravity Effects 0.000 claims description 6
- 230000008569 process Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 230000001133 acceleration Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 3
- 239000002245 particle Substances 0.000 description 3
- 238000013058 risk prediction model Methods 0.000 description 3
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical group [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 2
- 239000008280 blood Substances 0.000 description 2
- 210000004369 blood Anatomy 0.000 description 2
- 230000035487 diastolic blood pressure Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 229910052760 oxygen Inorganic materials 0.000 description 2
- 239000001301 oxygen Substances 0.000 description 2
- 238000001228 spectrum Methods 0.000 description 2
- 230000035488 systolic blood pressure Effects 0.000 description 2
- 208000001953 Hypotension Diseases 0.000 description 1
- 208000025174 PANDAS Diseases 0.000 description 1
- 208000021155 Paediatric autoimmune neuropsychiatric disorders associated with streptococcal infection Diseases 0.000 description 1
- 240000000220 Panda oleosa Species 0.000 description 1
- 235000016496 Panda oleosa Nutrition 0.000 description 1
- 230000004872 arterial blood pressure Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000036543 hypotension Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 238000012883 sequential measurement Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT 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
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/50—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for simulation or modelling of medical disorders
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT 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
-
- 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
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Data Mining & Analysis (AREA)
- Biomedical Technology (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Measuring Pulse, Heart Rate, Blood Pressure Or Blood Flow (AREA)
Abstract
A hypertension risk prediction method, a system, an electronic device and a storage medium; the prediction method comprises the following steps: s1, acquiring blood pressure measurement historical data of a patient at a certain n continuous moments, and preprocessing to form a data set of characteristic information of the blood pressure measurement historical data of the patient and corresponding hypertension risk data; s2, extracting association rules between the blood pressure measurement history data characteristic information and corresponding hypertension risk data by using an association rule mining algorithm, and generating an association rule base; s3, predicting and analyzing the hypertension risk based on the association rule base.
Description
Technical Field
The application relates to the technical field of medical treatment, in particular to a hypertension risk prediction method, a hypertension risk prediction system, electronic equipment and a storage medium.
Background
Hypertension is an important disease which is harmful to life and health of people, and how to timely perform risk early warning on rising or falling of blood pressure becomes a hot spot problem of research. In recent years, many predictive models have been proposed. For example, experts have proposed a new recursive model with context layers based on long-short term memory neural networks (LSTM) that can model both sequential measurement data and context data to predict trends in the user's blood pressure, but without taking into account the time-series change data versus blood pressure value changes.
In addition, the prior art has the following publication numbers: CN112420195a discloses a method and device for predicting risk of hypertension, the method comprising the following steps: obtaining data to be detected, wherein the data to be detected comprises blood oxygen signal images, power spectrum characteristic images and clinical characteristics of an OSA patient; inputting data to be detected into a pre-trained hypertension risk prediction model; the output result of the hypertension risk prediction model is the hypertension illness probability of the OSA patient. According to the application, more hypertension associated information is provided for the hypertension risk prediction model through the blood oxygen signal image and the power spectrum characteristic image, so that the hypertension prediction accuracy rate is improved.
The above solution also does not consider the relationship between the time-series change data and the blood pressure value change, and cannot provide a solution for avoiding risks more effectively.
Disclosure of Invention
The application mainly aims to provide a hypertension risk prediction method, a system, electronic equipment and a storage medium, which are used for solving the problem that the prior art excessively depends on experience of doctors and specialists when predicting hypertension risk and cannot provide a solution for effectively avoiding risk.
To achieve the above object, in a first aspect, the present application provides a method for predicting risk of hypertension, comprising the steps of:
s1, acquiring blood pressure measurement historical data of a patient at a certain n continuous moments, and preprocessing to form a data set of characteristic information of the blood pressure measurement historical data of the patient and corresponding hypertension risk data;
s2, extracting association rules between the blood pressure measurement history data characteristic information and corresponding hypertension risk data by using an association rule mining algorithm, and generating an association rule base;
s3, predicting and analyzing the hypertension risk based on the association rule base.
Further improved, in step S2, the association rule mining algorithm includes: based on the data set, according to the statistical frequency of the blood pressure value of the same patient at a certain n continuous moments, deleting the items with the frequency smaller than a preset minimum support threshold value, and generating a frequent item set; and carrying out association rule analysis based on the characteristic information of the blood pressure measurement data of the same patient in the frequent item set at a certain n continuous moments to obtain association rules between the characteristic information of the blood pressure measurement data and the corresponding hypertension risks.
The method is further improved, patients with optimal support degree in a data set are screened through an gravitation search algorithm, the patients with the optimal support degree in the data set are extracted, the patients with the optimal support degree are arranged in descending order according to the support degree, a frequent pattern tree is constructed according to the arrangement order, and association rules among the patients are analyzed based on the frequent pattern tree.
Further improved, the screening of patients with optimal support in the data set by the gravity search algorithm comprises:
screening N patients from the frequent item set to re-conduct the individual of the gravity search algorithm;
setting a fitness function based on the support degree and the confidence degree of each patient, and calculating the fitness of each individual;
and updating the individual position based on the current optimal fitness, and re-calculating the fitness for iterative transportation until reaching a termination condition, and outputting the individual position where the optimal fitness is located as the optimal support degree.
Further improved is that the fitness function is f (x) =t 1 support(x)+t 2 In step S3, the prediction and analysis of the hypertension risk are performed by using an association rule base, wherein the support (x) is the support degree of the patient x, the H (x) is the information entropy of the patient x, t1 and t2 are weight coefficients, t1+t2=1, the blood pressure measurement data of the same patient at a certain n continuous moments are matched with the parameter data in the association rule base one by one, the nearest neighbor distance value is calculated, and the minimum value of the nearest neighbor distance value is taken as a matching output result, so that the prediction of the hypertension risk is realized.
Further improved is that the step S1 and the step S2 also comprise the step of encoding the characteristic information of the blood pressure measurement historical data in the data set after merging the blood pressure measurement data of the same patient with the hypertension risk data according to the time sequence logic.
In order to achieve the above object, in a second aspect, the present application provides a system for predicting risk of hypertension based on a time series model, comprising
And a data acquisition module: the method comprises the steps of acquiring blood pressure measurement historical data of a patient at a certain n continuous moments, and preprocessing to form a data set of characteristic information of the blood pressure measurement historical data of the patient and corresponding hypertension risk data;
and a data preprocessing module: for encoding the characteristic information in the data set;
rule mining module: the method comprises the steps of extracting association rules between blood pressure measurement historical data characteristic information and corresponding hypertension risk data by using an association rule mining algorithm, and generating an association rule base;
risk prediction module: the method is used for predicting and analyzing the hypertension risk based on the association rule base.
Further improved, the rule mining module includes:
a threshold setting unit: presetting a minimum support threshold and a minimum confidence threshold;
frequent item statistics unit: based on the preprocessed data set, according to the statistical frequency of the blood pressure value of the same patient at a certain n continuous moments, deleting the items with the frequency smaller than the minimum support threshold value, and generating a frequent item set;
rule analysis unit: and the association rule mining algorithm is used for respectively carrying out association rule analysis on the characteristic information of the blood pressure measurement data of the same patient in the set at a certain n continuous moments based on the statistical result of the frequent item statistical unit to obtain association rules between the characteristic information of the blood pressure measurement data and the corresponding hypertension risk.
In order to achieve the above object, according to a third aspect, the present application provides an electronic device, including at least one processor, at least one memory, a communication interface, and a bus, where the processor, the memory, and the communication interface complete communication with each other through the bus, and the memory stores program instructions for the processor to execute the above method.
In order to achieve the above object, in a fourth aspect, the present application provides a storage medium storing computer instructions that cause the computer to implement the above method.
Compared with the prior art, the beneficial effects are as follows:
according to the method, the linear sequential logic is utilized to conduct hypertension risk prediction on blood pressure measurement data of the same patient at a certain n continuous moments, and the development context of the hypertension risk of the patient can be better obtained, so that an effective risk avoiding solution is provided for the patient.
Essentially, a time series model is a mathematical model that can "interpret" the autocorrelation in a time series. According to the application, based on a time sequence model, the corresponding relation between the blood pressure measurement data of the same patient at a certain n continuous moments and the hypertension risk data is established by using the association rule algorithm, the association rule between the blood pressure measurement data and the hypertension risk data can be clarified, the originally fuzzy relation between the hypertension risk and the blood pressure measurement data of the same patient at a certain n continuous moments is expressed in a regularization manner, the hypertension risk prediction is realized based on the association rule expressed in the regularization manner, excessive dependence on doctors and expert experiences is avoided, and the cognition difficulty is reduced.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application, are incorporated in and constitute a part of this specification. The drawings and their description are illustrative of the application and are not to be construed as unduly limiting the application. In the drawings:
FIG. 1 is a flow chart of a prediction method;
FIG. 2 is a flow chart of a prediction system;
fig. 3 is a functional block diagram of an electronic device.
Wherein: 1. a data acquisition module; 2. a data preprocessing module; 3. a rule mining module; 4. a risk prediction module; 301. a threshold setting unit; 302. a frequent item statistics unit; 303. a rule analysis unit; 5. a display screen; 6. a processor; 7. a communication interface; 8. a memory.
Detailed Description
In order that those skilled in the art will better understand the present application, a technical solution in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present application without making any inventive effort, shall fall within the scope of the present application.
It should be noted that the terms "first," "second," and the like in the description and the claims of the present application and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate in order to describe the embodiments of the application herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
In the present application, the terms "upper", "lower", "left", "right", "front", "rear", "top", "bottom", "inner", "outer", "middle", "vertical", "horizontal", "lateral", "longitudinal" and the like indicate an azimuth or a positional relationship based on that shown in the drawings. These terms are only used to better describe the present application and its embodiments and are not intended to limit the scope of the indicated devices, elements or components to the particular orientations or to configure and operate in the particular orientations.
Also, some of the terms described above may be used to indicate other meanings in addition to orientation or positional relationships, for example, the term "upper" may also be used to indicate some sort of attachment or connection in some cases. The specific meaning of these terms in the present application will be understood by those of ordinary skill in the art according to the specific circumstances.
In addition, the term "plurality" shall mean two as well as more than two.
It should be noted that, without conflict, the embodiments of the present application and features of the embodiments may be combined with each other. The application will be described in detail below with reference to the drawings in connection with embodiments.
As shown in fig. 1, a method for predicting risk of hypertension includes the following steps:
s1, acquiring blood pressure measurement historical data of a patient at a certain n continuous moments, and preprocessing to form a data set of characteristic information of the blood pressure measurement historical data of the patient and corresponding hypertension risk data.
Wherein: the blood pressure measurement history data comprise systolic pressure, diastolic pressure, mean arterial pressure, heart rate and the highest and lowest values thereof in the whole day, daytime and night, and the hypertension risk data comprise that the blood pressure value reaches or exceeds the systolic pressure 140mmHg and/or the diastolic pressure 90mmHg for at least 3 times in different days, so that hypertension can be considered; when the blood pressure is lower than 90/60mmHg, the blood pressure is called hypotension and the like; furthermore, data preprocessing typically includes data cleansing: removing duplicate values, processing missing values, processing outliers, etc.; data integration: integrating data of a plurality of data sources, including connection, merging and the like of the data; data conversion: conversion of data types, conversion of data formats, and the like; data normalization: normalization of naming and units, including case, symbol, time format, and the like.
Preferably, the method further comprises the step of: the blood pressure measurement history data characteristic information in the data set is encoded after the blood pressure measurement data of the same patient are combined with the hypertension risk data according to the time sequence logic, wherein the combination according to the time sequence logic can adopt pandas time sequence data combination, and the pd.merge_ordered function allows the combination of time sequence and other ordered data, in particular, the method has an optional fill_method keyword to fill/insert missing data: ordered in the order of s columns, it also applies to time type data. In contrast, in the case of encoding characteristic information of blood pressure measurement history data, since the computer learning algorithm performs linear algebraic calculation on a matrix, the characteristic to be calculated must be numerical, encoding processing is required for non-numerical characteristics, and encoding of discrete data is usually performed in two ways, namely, tag encoding and single-heat encoding.
S2, extracting association rules between the blood pressure measurement history data characteristic information and corresponding hypertension risk data by using an association rule mining algorithm, and generating an association rule base;
the strategy adopted by the association rule mining algorithm is to decompose the association rule mining task into two main subtasks: frequent item set generation and rule generation.
The step specifically includes, based on the data set, deleting items whose frequency is smaller than a minimum support threshold value, which is preset by the threshold value setting unit 301, according to the blood pressure value statistics frequency of the same patient at a certain n continuous times, generating a frequent item set; based on the statistical result in the frequent item set, carrying out association rule analysis on the characteristic information of the blood pressure measurement data of the same patient in the set at a certain n continuous moments by using an association rule algorithm to obtain association rules between the characteristic information of the blood pressure measurement data and the corresponding hypertension risk, wherein the association rule analysis specifically refers to finding and finding out all rules of which the support degree is greater than or equal to a set minimum support degree threshold value and the confidence degree is greater than or equal to a preset minimum confidence degree given the transaction set.
In addition, in order to enable the model to more accurately determine the correspondence between blood pressure measurement data and hypertension risk data, and simultaneously reduce the data analysis amount of the model, preferably, patients with optimal support in a preprocessed thick blood pressure measurement data set are screened out through an gravitation search algorithm, and the preprocessed blood pressure measurement data set is extracted and arranged in descending order of support, a frequent pattern tree is constructed according to the sorting order, and association rules among the patients are analyzed based on the frequent pattern tree.
The frequent pattern Tree algorithm, i.e., FP-Tree algorithm, is generally called FrequentPattern Tree algorithm, which is also used to mine frequent item sets as with Apriori algorithm, but is different in that FP-Tree algorithm is an optimization process of Apriori algorithm, which solves the problem that Apriori algorithm generates a large number of candidate sets in the process, and FP-Tree algorithm finds frequent patterns without generating candidate sets.
The Gravity Search Algorithm (GSA) is a stochastic heuristic search algorithm proposed by espat raskii et al in 2009, and the inspiration of the algorithm is derived from newton's law of universal gravitation and law of motion: 1. any two particles have a force on each other in the direction of the connecting line, the magnitude of the force being proportional to the product of their masses and inversely proportional to the square of their distances; 2. the force causes the object to acquire acceleration. In GSA, particles are abstracted into one solution of a solution space, a mutual attractive force exists between solutions, the attractive force is determined by the mass of the solution and the distance between the two solutions, the mass of the particles is abstracted into an evaluation function value of the solution, in the solution space, each solution obtains acceleration by the attractive force of other solutions on the solution, the acceleration provided by the larger mass (the better evaluation function value) is larger, and therefore the solution moves towards the better solution, and compared with other optimization algorithms, the solution has the advantages of stronger adaptability, robustness, parallel processing and the like.
Preferably, screening the patient with the optimal support in the data set specifically by the gravity search algorithm includes:
screening N patients from the frequent item set to re-conduct the individual of the gravity search algorithm;
setting a fitness function based on the support degree and the confidence degree of each patient, and calculating the fitness of each individual;
and updating the individual position based on the current optimal fitness, and re-calculating the fitness for iterative transportation until reaching a termination condition, and outputting the individual position where the optimal fitness is located as the optimal support degree.
Further preferably, the fitness function is a support degree of the patient x, H (x) is an information entropy of the patient x, t1 and t2 are weight coefficients, and t1+t2=1.
S3, predicting and analyzing hypertension risk based on the association rule base, and specifically: and predicting and analyzing the hypertension risk by using the association rule base, namely matching the blood pressure measurement data of the same patient with the parameter data in the association rule base one by one at a certain n continuous moments, calculating the nearest neighbor distance value, and taking the minimum value of the nearest neighbor distance value as a matching output result to realize the prediction of the hypertension risk.
As shown in fig. 2, the present embodiment further provides a system for predicting risk of hypertension based on a time sequence model, which includes
Data acquisition module 1: the method comprises the steps of acquiring blood pressure measurement historical data of a patient at a certain n continuous moments, and preprocessing to form a data set of characteristic information of the blood pressure measurement historical data of the patient and corresponding hypertension risk data;
data preprocessing module 2: for encoding the characteristic information in the data set;
rule mining module 3: the method comprises the steps of extracting association rules between blood pressure measurement historical data characteristic information and corresponding hypertension risk data by using an association rule mining algorithm, and generating an association rule base;
risk prediction module 4: the method is used for predicting and analyzing the hypertension risk based on the association rule base.
In particular, the rule mining module 3 comprises:
the threshold setting unit 301: presetting a minimum support threshold and a minimum confidence threshold;
frequent item statistics unit 302: based on the preprocessed data set, according to the statistical frequency of the blood pressure value of the same patient at a certain n continuous moments, deleting the items with the frequency smaller than the minimum support threshold value, and generating a frequent item set;
rule analysis unit 303: and the association rule mining algorithm is used for respectively carrying out association rule analysis on the characteristic information of the blood pressure measurement data of the same patient in the set at a certain n continuous moments based on the statistical result of the frequent item statistical unit 302 to obtain association rules between the characteristic information of the blood pressure measurement data and the corresponding hypertension risks.
As shown in fig. 3, the present embodiment further provides an electronic device, which includes at least one processor 6, at least one memory 8, a communication interface 7, and a bus, where the processor 6, the memory 8, and the communication interface 7 complete communication with each other through the bus, the memory 8 stores program instructions for the processor 6 to execute the foregoing method, where the processor 6 may use a CPU, and the communication interface 7 may be connected to a receiver, a transmitter, or other communication modules, and a specific communication module may include, but is not limited to, a WiFi module, a bluetooth module, and the electronic device may further include a display screen 5, and the like.
The present embodiment further provides a storage medium storing computer instructions that cause the computer to implement the above method.
The above description is only of the preferred embodiments of the present application and is not intended to limit the present application, but various modifications and variations can be made to the present application by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.
Claims (10)
1. A method for predicting risk of hypertension, characterized by: the method comprises the following steps:
s1, acquiring blood pressure measurement historical data of a patient at a certain n continuous moments, and preprocessing to form a data set of characteristic information of the blood pressure measurement historical data of the patient and corresponding hypertension risk data;
s2, extracting association rules between the blood pressure measurement history data characteristic information and corresponding hypertension risk data by using an association rule mining algorithm, and generating an association rule base;
s3, predicting and analyzing the hypertension risk based on the association rule base.
2. The method for predicting risk of hypertension according to claim 1, wherein: in step S2, the association rule mining algorithm includes: based on the data set, according to the statistical frequency of the blood pressure value of the same patient at a certain n continuous moments, deleting the items with the frequency smaller than a preset minimum support threshold value, and generating a frequent item set; and carrying out association rule analysis based on the characteristic information of the blood pressure measurement data of the same patient in the frequent item set at a certain n continuous moments to obtain association rules between the characteristic information of the blood pressure measurement data and the corresponding hypertension risks.
3. A method of predicting risk of hypertension as claimed in claim 2, wherein: and screening patients with optimal support degree in the data set through an gravitation search algorithm, extracting patients with the optimal support degree in the data set, arranging the patients with the optimal support degree in descending order according to the support degree, constructing a frequent pattern tree according to the arrangement order, and analyzing association rules among the patients based on the frequent pattern tree.
4. A method of predicting risk of hypertension as claimed in claim 3, wherein: screening patients with optimal support in a data set by an gravitation search algorithm comprises:
screening N patients from the frequent item set to re-conduct the individual of the gravity search algorithm;
setting a fitness function based on the support degree and the confidence degree of each patient, and calculating the fitness of each individual;
and updating the individual position based on the current optimal fitness, and re-calculating the fitness for iterative transportation until reaching a termination condition, and outputting the individual position where the optimal fitness is located as the optimal support degree.
5. The method for predicting risk of hypertension of claim 4, wherein: the fitness function is f (x) =t 1 support(x)+t 2 H (x), wherein support (x) isIn the step S3, the prediction and analysis of the hypertension risk are carried out by using an association rule base to match the blood pressure measurement data of the same patient at a certain n continuous moments with the parameter data in the association rule base one by one, the nearest neighbor distance value is calculated, and the minimum value of the nearest neighbor distance value is taken as a matching output result to realize the prediction of the hypertension risk.
6. The method for predicting risk of hypertension according to claim 1, wherein: the step S1 and the step S2 also comprise the step of encoding the characteristic information of the blood pressure measurement historical data in the data set after merging the blood pressure measurement data of the same patient with the hypertension risk data according to the time sequence logic.
7. A hypertension risk prediction system based on a time sequence model, which is characterized in that: comprising
And a data acquisition module: the method comprises the steps of acquiring blood pressure measurement historical data of a patient at a certain n continuous moments, and preprocessing to form a data set of characteristic information of the blood pressure measurement historical data of the patient and corresponding hypertension risk data;
and a data preprocessing module: for encoding the characteristic information in the data set;
rule mining module: the method comprises the steps of extracting association rules between blood pressure measurement historical data characteristic information and corresponding hypertension risk data by using an association rule mining algorithm, and generating an association rule base;
risk prediction module: the method is used for predicting and analyzing the hypertension risk based on the association rule base.
8. The timing model-based hypertension risk prediction system as claimed in claim 7, wherein: the rule mining module includes:
a threshold setting unit: presetting a minimum support threshold and a minimum confidence threshold;
frequent item statistics unit: based on the preprocessed data set, according to the statistical frequency of the blood pressure value of the same patient at a certain n continuous moments, deleting the items with the frequency smaller than the minimum support threshold value, and generating a frequent item set;
rule analysis unit: and the association rule mining algorithm is used for respectively carrying out association rule analysis on the characteristic information of the blood pressure measurement data of the same patient in the set at a certain n continuous moments based on the statistical result of the frequent item statistical unit to obtain association rules between the characteristic information of the blood pressure measurement data and the corresponding hypertension risk.
9. An electronic device, characterized in that: comprising at least one processor, at least one memory, a communication interface and a bus, said processor, said memory, said communication interface completing communication with each other via said bus, said memory storing program instructions for said processor to perform the method according to any of claims 1-7.
10. A storage medium, characterized by: the storage medium stores computer instructions that cause the computer to implement the method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310952324.4A CN116884615A (en) | 2023-07-31 | 2023-07-31 | Hypertension risk prediction method, system, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310952324.4A CN116884615A (en) | 2023-07-31 | 2023-07-31 | Hypertension risk prediction method, system, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116884615A true CN116884615A (en) | 2023-10-13 |
Family
ID=88256770
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310952324.4A Pending CN116884615A (en) | 2023-07-31 | 2023-07-31 | Hypertension risk prediction method, system, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116884615A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117352178A (en) * | 2023-11-10 | 2024-01-05 | 西安艾派信息技术有限公司 | Big data-based drug risk assessment system and method |
-
2023
- 2023-07-31 CN CN202310952324.4A patent/CN116884615A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117352178A (en) * | 2023-11-10 | 2024-01-05 | 西安艾派信息技术有限公司 | Big data-based drug risk assessment system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11217349B2 (en) | System and method for processing human related data including physiological signals to make context aware decisions with distributed machine learning at edge and cloud | |
| Sailasya et al. | Analyzing the performance of stroke prediction using ML classification algorithms | |
| CN112132955B (en) | Method for constructing digital twin body of human skeleton | |
| KR101903522B1 (en) | The method of search for similar case of multi-dimensional health data and the apparatus of thereof | |
| CN108597605B (en) | personal health life big data acquisition and analysis system | |
| CN116386869B (en) | Disease critical degree assessment method based on multiple variables | |
| CN116884615A (en) | Hypertension risk prediction method, system, electronic equipment and storage medium | |
| CN111063437B (en) | Personalized chronic disease analysis system | |
| Ali et al. | Multitask deep learning for cost-effective prediction of patient's length of stay and readmission state using multimodal physical activity sensory data | |
| CN117542474A (en) | Remote nursing monitoring system and method based on big data | |
| CN114241270A (en) | Intelligent monitoring method, system and device for home care | |
| CN114886404A (en) | Heart rhythm data classification method and device, electronic equipment and storage medium | |
| CN114758786A (en) | Dynamic early warning system for post-traumatic hemorrhagic shock based on noninvasive parameters | |
| CN111643056B (en) | Data processing method and system | |
| CN116098595B (en) | System and method for monitoring and preventing sudden cardiac death and sudden cerebral death | |
| Irshad et al. | Convolutional neural network enable optoelectronic system for predicting cardiac response by analyzing auction-based optimization algorithms | |
| CN115547502A (en) | Hemodialysis patient risk prediction device based on time sequence data | |
| WO2022216618A1 (en) | Medical event prediction using a personalized dual-channel combiner network | |
| CN113499037A (en) | Method and device for determining sleep quality of user, electronic equipment and storage medium | |
| Khidirova et al. | Intelligent system of diagnosing and predicting cardiovascular diseases | |
| CN117850601B (en) | System and method for automatically detecting vital signs of handheld PDA | |
| CN111797866A (en) | Feature extraction method and device, storage medium and electronic equipment | |
| Patil et al. | Dynamic data mining approach to WMRHM | |
| Pijl | Tracking of human motion over time | |
| US20230008923A1 (en) | Information processing device |
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 |