CN112382394A - Event processing method and device, electronic equipment and storage medium - Google Patents
Event processing method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN112382394A CN112382394A CN202011223233.XA CN202011223233A CN112382394A CN 112382394 A CN112382394 A CN 112382394A CN 202011223233 A CN202011223233 A CN 202011223233A CN 112382394 A CN112382394 A CN 112382394A
- Authority
- CN
- China
- Prior art keywords
- blood pressure
- evaluation model
- target
- sample data
- hypotension
- 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
- 238000003672 processing method Methods 0.000 title claims abstract description 18
- 208000001953 Hypotension Diseases 0.000 claims abstract description 232
- 230000036543 hypotension Effects 0.000 claims abstract description 226
- 230000036772 blood pressure Effects 0.000 claims abstract description 190
- 238000013210 evaluation model Methods 0.000 claims abstract description 177
- 238000011156 evaluation Methods 0.000 claims abstract description 64
- 238000012545 processing Methods 0.000 claims abstract description 41
- 238000000034 method Methods 0.000 claims abstract description 23
- 238000012549 training Methods 0.000 claims description 107
- 238000005070 sampling Methods 0.000 claims description 50
- 238000012360 testing method Methods 0.000 claims description 36
- 238000012795 verification Methods 0.000 claims description 31
- 208000021822 hypotensive Diseases 0.000 claims description 6
- 230000001077 hypotensive effect Effects 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 4
- 238000012544 monitoring process Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 description 16
- 230000004872 arterial blood pressure Effects 0.000 description 15
- 230000003287 optical effect Effects 0.000 description 6
- 238000012502 risk assessment Methods 0.000 description 6
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 5
- 239000008280 blood Substances 0.000 description 5
- 210000004369 blood Anatomy 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 230000035487 diastolic blood pressure Effects 0.000 description 5
- 230000000694 effects Effects 0.000 description 5
- 229910052760 oxygen Inorganic materials 0.000 description 5
- 239000001301 oxygen Substances 0.000 description 5
- 230000035488 systolic blood pressure Effects 0.000 description 5
- 230000008901 benefit Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 239000013307 optical fiber Substances 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 206010002091 Anaesthesia Diseases 0.000 description 1
- 230000037005 anaesthesia Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000002045 lasting effect Effects 0.000 description 1
- 238000000968 medical method and process Methods 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 238000012954 risk control Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- Data Mining & Analysis (AREA)
- Biomedical Technology (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Epidemiology (AREA)
- Pathology (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (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 & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Measuring Pulse, Heart Rate, Blood Pressure Or Blood Flow (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention discloses an event processing method, an event processing device, electronic equipment and a storage medium. The method comprises the following steps: acquiring a target event based on a first preset time interval, wherein the target event comprises target blood pressure related data within a first preset time; inputting the target blood pressure related data into a pre-trained target hypotension prediction evaluation model to obtain a blood pressure evaluation result corresponding to the target blood pressure related data; and determining an event processing result of the target event according to the blood pressure evaluation result so as to predict whether the user will have the hypotension event more quickly, conveniently and accurately, thereby improving the hypotension event evaluation accuracy.
Description
Technical Field
The embodiment of the invention relates to the technical field of medical treatment, in particular to an event processing method, an event processing device, electronic equipment and a storage medium.
Background
The medical risk management process comprises three links of risk identification, risk assessment and risk control, wherein the risk assessment is an important link of medical risk management. The hypotension risk assessment is to predict the hypotension risk assessment result of the medical process, assist doctors to realize medical decision and provide basis for risk treatment.
Most of the existing hypotension risk assessment carries out medical risk assessment on the intraoperative blood pressure of a patient through the knowledge and experience of medical personnel so as to predict whether hypotension risk events exist.
When the hypotension event is evaluated manually, the problems of poor evaluation instantaneity, high labor cost and large error of an evaluation result exist, so that the hypotension event cannot be predicted accurately.
Disclosure of Invention
The invention provides an event processing method, an event processing device, electronic equipment and a storage medium, which are used for realizing more rapid, convenient and accurate prediction on whether a user is in a hypotension event or not, so that the estimation accuracy of the hypotension event is improved.
In a first aspect, an embodiment of the present invention provides an event processing method, including:
acquiring a target event based on a first preset time interval, wherein the target event comprises target blood pressure related data within a first preset time;
inputting the target blood pressure related data into a pre-trained target hypotension prediction evaluation model to obtain a blood pressure evaluation result corresponding to the target blood pressure related data;
and determining an event processing result of the target event according to the blood pressure evaluation result.
In a second aspect, an embodiment of the present invention further provides an event processing apparatus, where the apparatus includes:
the event acquisition module is used for acquiring a target event based on a first preset time interval, wherein the target event comprises target blood pressure related data within a first preset time;
the result determining module is used for inputting the target blood pressure related data into a pre-trained target hypotension prediction evaluation model to obtain a blood pressure evaluation result corresponding to the target blood pressure related data;
and the event processing module is used for determining an event processing result of the target event according to the blood pressure evaluation result.
In a third aspect, an embodiment of the present invention further provides an electronic device, where the electronic device includes:
one or more processors;
a storage device for storing one or more programs which, when executed by the processor, cause the processor to implement the event processing method as provided by any of the embodiments of the invention.
In a fourth aspect, the embodiments of the present invention further provide a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the event processing method provided in any embodiment of the present invention.
According to the technical scheme, the target event is obtained, wherein the target event comprises target blood pressure related data within a first preset time length, the target blood pressure related data are input into a pre-trained target hypotension prediction evaluation model, a blood pressure evaluation result corresponding to the target blood pressure related data is obtained, an event processing result of the target event is determined according to the blood pressure evaluation result, the problem that the event cannot be accurately predicted due to certain errors of the obtained result caused by manual evaluation of the event is solved, and the effects of quickness, convenience and accuracy in evaluation are achieved.
Drawings
In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, a brief description is given below of the drawings used in describing the embodiments. It should be clear that the described figures are only views of some of the embodiments of the invention to be described, not all, and that for a person skilled in the art, other figures can be derived from these figures without inventive effort.
Fig. 1 is a schematic flow chart of an event processing method according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of an event processing method according to a second embodiment of the present invention;
fig. 3 is a schematic flow chart of an event processing method according to a third embodiment of the present invention;
fig. 4 is a schematic diagram of an event processing apparatus module according to a fourth embodiment of the present invention;
fig. 5 is a schematic structural diagram of an electronic device according to a fifth embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
Example one
Fig. 1 is a flowchart of an event processing method according to an embodiment of the present invention, where the embodiment is applicable to a case where blood pressure related data within a certain time period is processed by a target hypotension prediction and evaluation model, so as to obtain an event evaluation result corresponding to the blood pressure related data, the method may be executed by an event processing device, and the event processing device may be implemented by software and/or hardware, and the event processing device may be integrated in an electronic device, such as a computer or a server.
The method comprises the following steps:
s101, acquiring a target event based on a first preset time interval, wherein the target event comprises target blood pressure related data within a first preset time.
The first preset time interval is the time interval for collecting the blood pressure related data, and optionally, 30S. The event of collecting blood pressure related data at intervals of a first preset duration can be taken as a target event. The target blood pressure related data may include, but is not limited to, the following data: mean arterial pressure, blood oxygen, heart rate, invasive diastolic pressure, invasive systolic pressure. In this embodiment, the target blood pressure related data used may be mean arterial pressure data.
Specifically, according to a preset first preset time interval, for example, the interval is 30S, blood pressure related data is collected every 30S, for example, the collected time is 5S, the collected data includes average arterial pressure, blood oxygen, heart rate, invasive diastolic pressure and invasive systolic pressure, and the collected data is processed to obtain target blood pressure related data, that is, average arterial pressure data.
S102, inputting the target blood pressure related data into a pre-trained target hypotension prediction evaluation model to obtain a blood pressure evaluation result corresponding to the target blood pressure related data.
The target hypotension prediction and evaluation model is obtained by training and verifying a large amount of blood pressure related sample data, and is used for processing the target blood pressure related data to obtain a blood pressure evaluation result corresponding to the blood pressure related data. The blood pressure assessment may be indicative of a probability value for the occurrence of a hypotensive event or may be used to indicate a risk value for the occurrence of a hypotensive event.
S103, determining an event processing result of the target event according to the blood pressure evaluation result.
Specifically, since the blood pressure evaluation result is used to represent a probability value of occurrence of a hypotension event or a risk value of occurrence of a hypotension event, whether the target event has a hypotension event or not, that is, whether the event processing result is occurrence or not, may be predicted based on the blood pressure evaluation result.
In the present embodiment, when the blood pressure evaluation result processed with the blood pressure-related data is 0.1 based on the target hypotension prediction evaluation model, it indicates that the probability value of predicting the occurrence of the hypotension event of the user is low, and thus it is preliminarily determined that the user will not have the hypotension in the near future; when the blood pressure of the patient is evaluated to be 0.8, it is preliminarily determined that the user is about to have a hypotensive event in the near future.
Based on the above results, in order to improve convenience and accuracy of prediction, a preset threshold value of the blood pressure estimation result may be set in advance, and whether or not the current user has the occurrence of the hypotension event may be predicted by comparing a relationship between the blood pressure estimation result output by the target hypotension prediction estimation model and the preset threshold value.
In this embodiment, the determining the event processing result of the target event may further be: determining that a hypotensive event has occurred when the blood pressure assessment is above a preset assessment threshold.
Illustratively, the preset evaluation threshold is 0.9, and when the target hypotension associated data is processed based on the target hypotension prediction evaluation model, an evaluation value for characterizing the occurrence of hypotension events can be obtained. If the obtained hypotension evaluation value is 0.95, namely the hypotension evaluation result output by the model is higher than 0.9, preliminarily determining that the patient has a hypotension event recently; if the hypotension estimate obtained is 0.75, i.e., the blood pressure estimate is below 0.9, then it is initially determined that the patient has not recently experienced a hypotensive event. The advantage of presetting the evaluation threshold is that whether the hypotension event happens can be accurately and rapidly predicted based on the reference standard, so that the relevant medical personnel can quickly and accurately deal with the hypotension event according to the blood pressure evaluation result, and the treatment effect of the user is improved. In this embodiment, the blood pressure evaluation result is fed back to the relevant medical staff, and may be an alarm notification or a special prompt tone notification.
According to the technical scheme, the target event of the target blood pressure related data within the preset time length is obtained, the target blood pressure related data is input into the target hypotension prediction evaluation model trained in advance, the blood pressure evaluation result corresponding to the target blood pressure related data is obtained, the event processing result of the target event is determined according to the blood pressure evaluation result, the problems that when the hypotension event is evaluated manually, the evaluation instantaneity is poor, the labor cost is high, and the error of the evaluation result is large are solved, the hypotension event result cannot be predicted accurately, the target hypotension related data is processed based on the target hypotension prediction evaluation model obtained through training in advance, and the technical effects of improving the instantaneity, the accuracy and the efficiency of the hypotension event prediction are achieved.
Example two
Fig. 2 is a flowchart illustrating an event processing method according to a second embodiment of the present invention, in which, on the basis of the foregoing embodiments, before processing hypotension-related data based on a target hypotension prediction and evaluation model, a target hypotension prediction and evaluation model needs to be trained, and this embodiment mainly describes the trained target hypotension prediction and evaluation model. The technical terms that are the same as or corresponding to the above embodiments are not repeated herein.
As shown in fig. 2, the method comprises the following specific steps:
s201, obtaining a training sample data set, wherein the training sample data set comprises a plurality of training sample data, and the training sample data comprises positive sample data and negative sample data; the positive sample data is hypotension.
The sample data set comprises training sample data, and the training sample data is mainly used for training the model. In order to improve the accuracy of the trained model, the training sample data needs to be as many and as rich as possible. Therefore, positive and negative examples may be included in the training sample data. In this embodiment, the dividing criteria of the positive and negative samples may be: selecting sample data of hypotension events, and collecting the sample data of hypotension events according to preset conditions. Namely, the positive sample data and the negative sample data are both sample data corresponding to the occurrence of the hypotension event, and the difference is that the acquisition time of the positive sample data and the acquisition time of the negative sample data are different.
The positive sample data may be blood pressure related data acquired a certain time period before the occurrence time, for example, blood pressure related data within five minutes before the occurrence time, according to the occurrence time of the hypotension event when the hypotension event occurs currently. For example, if the occurrence time of the hypotension event is 10 am, blood pressure related data between 9 o 'clock 55 and 9 o' clock 59 may be collected, and a positive sample in the sample data may be generated based on the blood pressure related data; in order to improve the richness of the sample data, the sample data may be not limited to the blood pressure related data acquired within 5min before the occurrence time, but may be generated based on the blood pressure related data acquired respectively 10min before the occurrence time and 15min before the occurrence time.
The negative sample data may be blood pressure related data acquired a certain time period before the occurrence time according to the occurrence time of the hypotension event when the hypotension event occurs currently, for example, blood pressure related data acquired a certain time period before 20min before the occurrence time. For example, if the occurrence time of the hypotension event is 10 am, blood pressure related data between 9 o 'clock 35 and 9 o' clock 39 may be collected, and a negative sample in the sample data may be generated based on the blood pressure related data; in order to improve the effectiveness of the sample data, the time interval duration of negative sample collection may be set, for example, 30min, and the blood pressure related data is collected every 30min for a certain time duration
S202, aiming at each to-be-trained hypotension prediction evaluation model, taking training blood pressure related data of training sample data as input of the current to-be-trained hypotension prediction evaluation model, and obtaining an output evaluation value corresponding to the training sample data.
In order to improve the accuracy of the prediction result of the target hypotension prediction and evaluation model, a plurality of to-be-trained hypotension prediction and evaluation models can be trained in advance, and the target hypotension prediction and evaluation model is obtained from the to-be-trained hypotension prediction and evaluation models based on the accuracy of the trained to-be-verified hypotension prediction and evaluation models.
It should be noted that the same training method is applied to each hypotension prediction and evaluation model to be trained, and this embodiment will be described by taking as an example the training of one of the hypotension prediction and evaluation models to be trained.
The hypotension prediction evaluation model to be trained may be an XGBoost model or other models, and the prediction evaluation result is not limited herein as long as the blood pressure related data can be processed.
It should be further noted that the acquired training sample data includes the following elements: when the hypotension prediction evaluation model to be trained is trained based on the elements, the importance degree of each element can be determined in order to determine the importance of each element and further improve the accuracy of the blood pressure prediction evaluation result, and the sample data of the training model is determined based on the importance degree of each element.
Specifically, a training sample is determined based on a plurality of elements of the blood pressure related parameters, and a to-be-trained hypotension prediction evaluation model is trained based on the training sample to obtain the to-be-verified hypotension prediction evaluation model. The importance degree of each element is introduced by taking the hypotension prediction evaluation model to be trained as an XGboost model as an example, and then the hypotension prediction evaluation model to be verified with higher accuracy is obtained through training. Optionally, the elements of the blood pressure related parameters include B1, B2, B3, and B4, a training sample 1 is determined according to the elements B1, B2, B3, and B4 in the blood pressure related parameters, a plurality of training samples for training the XGBoost model are obtained in this way, the XGBoost model is trained based on the training sample 1, and the model obtained by training at this time can be labeled as a model a1(ii) a Determining a training sample 2 according to elements B2, B3 and B4 in the blood pressure related parameters, training an XGboost model based on the training sample 2, and marking the model obtained by training at the moment as a model A2(ii) a Determining a training sample 3 according to elements B3 and B4 in the blood pressure related parameters, training an XGboost model based on the training sample 3, and marking the model obtained by training at the moment as a model A3. To obtain a model A1、A2And A3Test samples corresponding to the model may be collected, e.g., to determine model A1When the accuracy of the method is higher, the corresponding test sample is determined based on the elements B1, B2, B3 and B4, and the importance degree of each element is determined, optionally, if the accuracy of a1 is 85%, the accuracy of a2 is 90%, and the accuracy of A3 is 95%, the elements B3 and B4 which can determine the blood pressure related parameters are more important, so that the method is applied to the determination of the accuracy of the blood pressure related parametersWhen training the XGBoost model, training samples may be generated based on elements B3 and B4. Determining a training sample of the hypotension prediction evaluation model to be verified based on the important elements of the blood pressure related parameters, inputting the training sample into the hypotension prediction evaluation model to be verified, and obtaining an output evaluation value corresponding to the training sample. Correspondingly, in the process of checking and testing, the checking sample data and the testing sample are obtained on the basis of the elements adopted in the process of training the model.
It should be noted that, when training other models, the importance degree of each element may also be determined in the above manner, and then the corresponding model is trained based on the determined elements, which has the advantage of improving the accuracy of the model obtained by training.
S203, calculating a loss value of a loss function in the to-be-trained hypotension prediction evaluation model based on the output evaluation value and the set output value of the training sample data, and adjusting network parameters in the to-be-trained hypotension prediction evaluation model based on the loss value.
It should be noted that before training the model to be trained for the hypotension prediction evaluation, the training parameters in the model may be set to default values. When training the to-be-trained hypotension prediction evaluation model, the training parameters in the model may be corrected based on the output result of the to-be-trained hypotension prediction evaluation model, that is, the to-be-verified hypotension prediction evaluation model may be obtained by correcting the loss function in the to-be-trained hypotension prediction evaluation model.
Specifically, training sample data of the training model is determined according to the importance degree of each element, the training sample data is input into the hypotension prediction evaluation model to be trained, an evaluation value output correspondingly by the training sample data is obtained, a loss value of a loss function in the hypotension prediction evaluation model to be trained is calculated according to the output evaluation value and a set output value of the training sample data, and network parameters in the hypotension prediction evaluation model to be trained are adjusted according to the loss value.
And S204, taking the convergence of the loss function as a training target, and training the blood pressure prediction evaluation model to be trained to obtain the hypotension prediction evaluation model to be verified.
Specifically, the training error of the loss function may be used as a condition for detecting whether the loss function reaches convergence currently, for example, whether the training error is smaller than a preset error or whether an error variation trend tends to be stable, or whether the current iteration number is equal to the preset number. If the convergence condition is reached, for example, the training error of the loss function is smaller than the preset error or the error change tends to be stable, which indicates that the training of the hypotension prediction evaluation model to be trained is completed, the iterative training may be stopped at this time. If the current condition is not met, training samples in the training sample data can be further obtained to train the hypotension prediction evaluation model to be trained until the training error of the loss function is within the preset range. When the training error of the loss function reaches convergence, the hypotension prediction evaluation model to be trained can be used as the hypotension prediction evaluation model to be verified.
S205, according to the verification sample data, verifying the to-be-verified hypotension prediction evaluation model, and obtaining the to-be-used hypotension prediction evaluation model based on the verification result.
The verification sample data is the same as the test sample and comprises a positive sample and a negative sample. The verification sample data is used for verifying the trained multiple hypotension prediction evaluation models to be verified so as to determine whether the accuracy of each hypotension prediction evaluation model to be verified meets the preset requirement, and then the target hypotension prediction evaluation model is determined from all the hypotension prediction evaluation models to be verified.
Specifically, according to the number of elements in training sample data corresponding to each to-be-verified hypotension prediction evaluation model, verification sample data corresponding to each to-be-verified hypotension prediction evaluation model is determined. After the verification sample data of the corresponding hypotension prediction evaluation model to be verified is determined, the verification sample data can be input into each hypotension prediction evaluation model to be verified, and an output result can be obtained. And repeatedly executing the step to obtain a plurality of output results, and determining the accuracy of each hypotension prediction and evaluation model to be verified according to each output result and the corresponding set output result. For example, the number of the verification sample data is 1000, 800 of the model output results match the output result values in the verification sample data, and the accuracy of the to-be-verified hypotension prediction evaluation model is 800/1000 ═ 0.8. And repeating the steps for each hypotension prediction and evaluation model to be verified, and determining the accuracy of each hypotension prediction and evaluation model to be verified. According to the accuracy of each hypotension prediction and evaluation model to be verified, the accuracy of which does not reach the requirement, can be eliminated. Or, obtaining test sample data and training the hypotension prediction evaluation model to be verified which does not meet the requirement until the accuracy rate of the hypotension prediction evaluation model meets the preset requirement.
Optionally, the verifying the to-be-verified hypotension prediction and evaluation model according to verification sample data, and obtaining the to-be-used hypotension prediction and evaluation model based on a verification result includes:
inputting each verification sample data into the hypotension prediction evaluation model to be verified to obtain a reference output result corresponding to each verification sample data;
according to the reference output result and a set output result in the verification sample data, determining the accuracy of the hypotension prediction evaluation model to be verified;
and when the accuracy is lower than a preset accuracy threshold, taking the hypotension prediction evaluation model to be verified as a hypotension prediction evaluation model to be trained, and training until the accuracy of an output result of the hypotension prediction evaluation model to be trained is higher than the preset accuracy threshold.
Specifically, according to the number of elements in training sample data corresponding to each to-be-verified hypotension prediction evaluation model, verification sample data corresponding to each to-be-verified hypotension prediction evaluation model is determined. After the verification sample data of the corresponding hypotension prediction and evaluation model to be verified is determined, the verification sample data can be input into the hypotension prediction and evaluation model to be verified, and an output result can be obtained. And repeatedly executing the step to obtain a plurality of output results, determining the accuracy of the to-be-verified hypotension prediction evaluation model according to each output result and the corresponding set output result, presetting an accuracy threshold value meeting the to-be-verified hypotension prediction evaluation model, and when the accuracy of the to-be-verified hypotension prediction evaluation model is lower than the preset accuracy threshold value, taking the to-be-verified hypotension prediction evaluation model as the to-be-trained hypotension prediction evaluation model and training until the accuracy of the output result of the to-be-trained hypotension prediction evaluation model is higher than the preset accuracy threshold value.
S206, inputting the test sample data in the test sample data set to the hypotension prediction evaluation model to be used at present aiming at each hypotension prediction evaluation model to be used, and obtaining an actual output result corresponding to each test sample data; the test sample data comprises test blood pressure related parameters and a set output result.
The test sample data is used for testing the verified multiple hypotension prediction and evaluation models to be used to determine whether the accuracy of each hypotension prediction and evaluation model to be used meets a preset condition, and then a target hypotension prediction and evaluation model is determined from all the hypotension prediction and evaluation models to be used.
Specifically, according to the number of elements in training sample data corresponding to each hypotension prediction evaluation model to be verified, test sample data corresponding to each hypotension prediction evaluation model to be used is determined. After determining the corresponding test sample data to be used in the hypotension prediction evaluation model, the test sample data may be input into the hypotension prediction evaluation model, and an actual output result may be obtained. And repeating the step to obtain an actual output result corresponding to each test sample data. S207, determining the accuracy of the current hypotension prediction and evaluation model to be used according to the actual output result and the corresponding set output result; determining the target hypotension prediction evaluation model according to the accuracy of each hypotension prediction evaluation model to be used.
Specifically, the actual output results are obtained by inputting the test sample data into each hypotension prediction and evaluation model to be used, and the actual output results and the corresponding set output results are output. This step is repeatedly performed to obtain a plurality of actual output results, and according to each actual output result and a corresponding set output result, the accuracy of each hypotension prediction estimation model to be used may be determined, for example, 1000 test sample data are provided, 900 of the model output results match the output results of the sample data to be tested, and the accuracy of the hypotension prediction estimation model to be used is 900/1000 ═ 0.9. The steps are repeatedly executed for each hypotension prediction evaluation model to be used, the accuracy of each hypotension prediction evaluation model to be used is determined, and the target hypotension prediction evaluation model is determined according to the accuracy of each hypotension prediction evaluation model to be used.
And S208, inputting the target blood pressure related data into a pre-trained target hypotension prediction evaluation model to obtain a blood pressure evaluation result corresponding to the target blood pressure related data.
And S209, determining an event processing result of the target event according to the blood pressure evaluation result.
The technical solution of this embodiment is to train a hypotension prediction and evaluation model to be trained by training sample data, adjust network parameters in the hypotension prediction and evaluation model to be trained by a loss value of a loss function in the hypotension prediction and evaluation model to be trained, iterate until the loss function converges to obtain a hypotension prediction and evaluation model to be verified, verify the hypotension prediction and evaluation model to be verified by verifying sample data to obtain a verification result, obtain a hypotension prediction and evaluation model to be used according to the verification result, test the hypotension prediction and evaluation model to be used by testing sample data to obtain an accuracy of the hypotension prediction and evaluation model to be used, determine a target hypotension prediction and evaluation model according to the accuracy of the hypotension prediction and evaluation model to be used, determine an event processing result of a target event based on the target hypotension prediction and evaluation model, the method solves the problems that when the hypotension event is evaluated manually, the evaluation instantaneity is poor, the labor cost is high, and the evaluation result error is large, so that the hypotension event result cannot be predicted accurately, the target hypotension related data is processed based on a target hypotension prediction evaluation model obtained through pre-training, and the technical effects of instantaneity, accuracy and high efficiency of hypotension event prediction are improved.
EXAMPLE III
Fig. 3 is a schematic flow chart of an event processing method according to a third embodiment of the present invention, which mainly describes how to determine sample data when training a target hypotension prediction evaluation model. The technical terms that are the same as or corresponding to the above embodiments are not repeated herein.
As shown in fig. 3, the method comprises the steps of:
s301, collecting a group of original blood pressure related parameters corresponding to each user based on the vital sign monitoring equipment.
Wherein the vital signs monitoring device may be an operating room anesthesia system device, and the original blood pressure related parameters may include, but are not limited to, the following data: mean arterial pressure, invasive diastolic pressure, invasive systolic pressure, heart rate, and blood oxygen.
S302, determining that the original blood pressure related parameters are the initial time of the target parameters when the target parameter values in a second preset time period are lower than a preset parameter threshold value based on the current original blood pressure related parameters aiming at each group of original blood pressure related parameters.
The second preset time duration is the time duration that the average arterial pressure in the collected original blood pressure related parameters is lower than the preset parameters, and optionally 1 min. The target parameter may be mean arterial pressure, i.e. the target parameter value is a mean arterial pressure value, and the preset parameter threshold may be a mean arterial pressure value preset when hypotension occurs.
Specifically, according to a preset second preset time period, for example, the time period is 1min, the preset average arterial pressure parameter threshold is 65mmHg, the start time of acquiring the target parameter is determined at 9 am, and when the average arterial pressure is lower than 65mmHg after lasting for 1min, that is, the start time of acquiring the target parameter is determined at 9 am when the average arterial pressure is lower than 65 mmHg.
S303, obtaining blood pressure related parameters to be used according to the starting time, at least one preset sample sampling interval and sampling frequency, generating the sample data according to the blood pressure related parameters to be used, and training the hypotension prediction evaluation model to be trained according to the sample data.
Wherein the sample sampling interval is the interval duration between the acquisition of two samples, and the sample sampling interval setting is different based on different sample types. The sampling frequency may be the number of times the blood pressure related data is acquired within a certain time period, or may be understood as how often the blood pressure related data is acquired, for example, 30S/time. And obtaining blood pressure related data from the original blood pressure related parameters according to a preset acquisition rule by using the blood pressure related parameters. The blood pressure related parameters to be used may include, but are not limited to, the following: mean arterial pressure, blood oxygen, heart rate, invasive diastolic pressure, invasive systolic pressure. The sample data is data including blood pressure related data to be used.
Illustratively, the mean arterial pressure was below 65mmHg at 9 am for 1min, i.e. nine am was the starting time, and the blood pressure related data to be used was collected every 30S. The positive sample data is respectively collected for 5min, 10min and 15min before the last 9 am, taking the sample of 5min before the positive sample data is collected, the blood pressure related data to be used is collected from 54 minutes at 8 o ' clock to 59 minutes at 8 o ' clock, every 30 seconds, namely the blood pressure related data corresponding to the time of 54 minutes at 8 o ' clock, 54 minutes 30 seconds at 8 o ' clock, … and 58 minutes 30 seconds at 8 o ' clock are collected from the blood pressure related data to be used, and the data collected at this time is used as one sample data in the positive sample data. The negative sample data is to acquire the blood pressure related data to be used 20 minutes before 9 o ' clock in 5 minutes, namely acquiring the blood pressure related data to be used from 8 o ' clock 35 to 8 o ' clock 40, wherein the sampling time length of the negative sample data is not limited. The time interval for acquiring the negative sample data may be 30min, for example, the blood pressure related data to be used is acquired every 30 seconds from 8 o 'clock 35 min to 8 o' clock 40 min as the negative sample 1, and the negative sample 2 is acquired every 30 seconds from 8 o 'clock to 8 o' clock 05 min as the sample time interval is 30 min.
In this embodiment, the sampling interval includes a first sampling interval and a second sampling interval, a duration of the first sampling interval is less than a duration of the second sampling interval, the obtaining a blood pressure related parameter to be used according to the starting time, at least one preset sampling interval and a sampling frequency, and generating the sample data according to the blood pressure related parameter to be used includes: acquiring a first blood pressure related parameter to be used from an original blood pressure related parameter according to the starting moment, the first sample sampling interval and the sampling frequency, and generating a positive sample based on the first blood pressure related parameter to be used; the set output in the positive sample is a first set output value.
Wherein the first sample sampling interval is a positive sample sampling interval duration. The second sample sampling interval is a negative sample sampling interval duration. The first blood pressure related parameter to be used may include, but is not limited to, the following parameters: mean arterial pressure, blood oxygen, heart rate, invasive diastolic pressure, invasive systolic pressure. The duration of the first sample sampling interval is less than that of the second sample sampling interval, so that the setting benefit is that when the hypotension event occurs, the blood pressure related data within a certain duration before the occurrence time can best reflect whether the hypotension event occurs, and therefore when training based on the blood pressure related data, the accuracy of model training can be improved.
Generating sample data according to the blood pressure associated parameters to be used, and further comprising: acquiring a second blood pressure related parameter to be used from the original blood pressure related parameter according to the starting time, the second sample sampling interval and the sampling frequency, and generating a negative sample based on the second blood pressure related parameter to be used; the set output in the negative sample is a second constant output value.
S304, training at least one hypotension prediction evaluation model to be trained based on the training sample data to obtain at least one hypotension prediction evaluation model to be used.
S305, inputting the test sample data in the test sample data set to the hypotension prediction evaluation model to be used at present aiming at each hypotension prediction evaluation model to be used, and obtaining an actual output result corresponding to each test sample data; the test sample data comprises test blood pressure related parameters and a set output result.
S306, determining the accuracy of the current hypotension prediction and evaluation model to be used according to the actual output result and the corresponding set output result.
And S307, determining the target hypotension prediction evaluation model according to the accuracy of each hypotension prediction evaluation model to be used.
And S308, inputting the target blood pressure related data into a pre-trained target hypotension prediction evaluation model to obtain a blood pressure evaluation result corresponding to the target blood pressure related data.
S309, determining an event processing result of the target event according to the blood pressure evaluation result.
According to the technical scheme of the embodiment, by acquiring the original blood pressure related parameters, based on each acquired original blood pressure related parameter, according to the acquisition time interval and sampling frequency of different sample data, each sample data is determined, the model is trained, checked and predicted, a target hypotension prediction evaluation model is determined, and an event processing result of a target event is determined based on the target hypotension prediction evaluation model.
Example four
Fig. 4 is a schematic block diagram of an event processing apparatus according to a fourth embodiment of the present invention, where the event processing apparatus includes:
an event obtaining module 410, configured to obtain a target event based on a first preset time interval, where the target event includes target blood pressure related data within a first preset time; a result determining module 420, configured to input the target blood pressure related data into a pre-trained target hypotension prediction and evaluation model, so as to obtain a blood pressure evaluation result corresponding to the target blood pressure related data; and the event processing module 430 is configured to determine an event processing result of the target event according to the blood pressure evaluation result.
Optionally, the event processing module 430 is configured to determine that a hypotension event occurs when the blood pressure evaluation result is higher than a preset evaluation threshold.
Optionally, the apparatus further comprises: the model determining module 440 is configured to train at least one to-be-trained hypotension prediction evaluation model based on the training sample data to obtain at least one to-be-used hypotension prediction evaluation model; inputting the test sample data in the test sample data set to the hypotension prediction evaluation model to be used at present aiming at each hypotension prediction evaluation model to be used, and obtaining an actual output result corresponding to each test sample data; the test sample data comprises test blood pressure related parameters and a set output result; according to the actual output result and the corresponding set output result, determining the accuracy of the hypotension prediction and evaluation model to be used currently; determining the target hypotension prediction evaluation model according to the accuracy of each hypotension prediction evaluation model to be used; the target hypotension prediction evaluation model is used for determining a blood pressure evaluation result corresponding to the input data.
Optionally, the model determining module 440 is configured to obtain a training sample data set, where the training sample data set includes a plurality of training sample data, and the training sample data includes positive sample data and negative sample data; the positive sample data is hypotension; aiming at each to-be-trained hypotension prediction evaluation model, taking training blood pressure associated data of training sample data as input of the current to-be-trained hypotension prediction evaluation model to obtain an output evaluation value corresponding to the training sample data; calculating a loss value of a loss function in the hypotension prediction evaluation model to be trained based on the output evaluation value and a set output value of the training sample data, and adjusting network parameters in the hypotension prediction evaluation model to be trained based on the loss value; taking the convergence of the loss function as a training target, and training the to-be-trained blood pressure prediction evaluation model to obtain a to-be-verified blood pressure prediction evaluation model; and verifying the hypotension prediction evaluation model to be verified according to verification sample data, and obtaining the hypotension prediction evaluation model to be used based on a verification result.
Optionally, the model determining module 440 is configured to input each verification sample data into the to-be-verified hypotension prediction evaluation model, so as to obtain a reference output result corresponding to each verification sample data; according to the reference output result and a set output result in the verification sample data, determining the accuracy of the hypotension prediction evaluation model to be verified; and when the accuracy is lower than a preset accuracy threshold, taking the hypotension prediction evaluation model to be verified as a hypotension prediction evaluation model to be trained, and training until the accuracy of an output result of the hypotension prediction evaluation model to be trained is higher than the preset accuracy threshold.
Optionally, the model determining module includes a sample acquiring sub-module, and the sample acquiring sub-module 4401 is configured to determine sample data, where the determining sample data includes:
collecting a group of original blood pressure related parameters corresponding to each user based on the vital sign monitoring equipment;
for each group of original blood pressure associated parameters, determining that the original blood pressure associated parameters are the initial time of the target parameters when the target parameter values in a second preset time period are lower than a preset parameter threshold value based on the current original blood pressure associated parameters;
and obtaining blood pressure associated parameters to be used according to the starting time, at least one sample sampling interval and sampling frequency which are preset, generating the sample data according to the blood pressure associated parameters to be used, and training the hypotension prediction evaluation model to be trained according to the sample data.
Optionally, the sample acquiring sub-module 4401 is configured to enable the sample sampling interval to include a first sample sampling interval and a second sample sampling interval, where a duration of the first sample sampling interval is smaller than a duration of the second sample sampling interval, obtain the blood pressure related parameter to be used according to the starting time, preset at least one sample sampling interval and a sampling frequency, and generate the sample data according to the blood pressure related parameter to be used, where the sample acquiring sub-module 4401 is configured to:
acquiring a first blood pressure related parameter to be used from an original blood pressure related parameter according to the starting moment, the first sample sampling interval and the sampling frequency, and generating a positive sample based on the first blood pressure related parameter to be used; the set output in the positive sample is a first set output value;
acquiring a second blood pressure related parameter to be used from the original blood pressure related parameter according to the starting time, the second sample sampling interval and the sampling frequency, and generating a negative sample based on the second blood pressure related parameter to be used; the set output in the negative sample is a second constant output value.
According to the technical scheme, a trained target hypotension prediction evaluation model is obtained by selecting a sample data training model, a target event of target blood pressure related data within a preset time length is obtained, the target blood pressure related data is input into the pre-trained target hypotension prediction evaluation model, a blood pressure evaluation result corresponding to the target blood pressure related data is obtained, an event processing result of the target event is determined according to the blood pressure evaluation result, the problem that the event cannot be accurately predicted due to certain errors of the obtained result caused by manual evaluation of the event is solved, and the effect of quickly, conveniently and accurately determining whether the hypotension event occurs is achieved.
The device can execute the event processing method provided by any embodiment of the invention, and has corresponding functional modules and beneficial effects of the execution method.
EXAMPLE five
Fig. 5 is a schematic structural diagram of an electronic device according to a fifth embodiment of the present invention. FIG. 5 illustrates a block diagram of an exemplary device 50 suitable for use in implementing embodiments of the present invention. The device 50 shown in fig. 5 is only an example and should not bring any limitation to the function and scope of use of the embodiments of the present invention.
As shown in FIG. 5, device 50 is embodied in a general purpose computing device. The components of the device 50 may include, but are not limited to: one or more processors or processing units 501, a system memory 502, and a bus 503 that couples the various system components (including the system memory 502 and the processing unit 501).
The system memory 502 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM)504 and/or cache memory 505. The device 50 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 506 may be used to read from and write to non-removable, nonvolatile magnetic media (not shown in FIG. 5, commonly referred to as a "hard drive"). Although not shown in FIG. 5, a magnetic disk drive for reading from and writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 503 by one or more data media interfaces. Memory 502 may include at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of embodiments of the invention.
A program/utility 508 having a set (at least one) of program modules 507 may be stored, for instance, in memory 502, such program modules 507 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which examples or some combination thereof may comprise an implementation of a network environment. Program modules 507 generally perform the functions and/or methodologies of embodiments of the invention as described herein.
The processing unit 501 executes various functional applications and data processing, for example, an event processing method provided by an embodiment of the present invention, by executing a program stored in the system memory 502.
EXAMPLE six
An embodiment of the present invention also provides a storage medium containing computer-executable instructions, which when executed by a computer processor, perform a method of event processing.
The method comprises the following steps:
acquiring a target event based on a first preset time interval, wherein the target event comprises target blood pressure related data within a first preset time;
inputting the target blood pressure related data into a pre-trained target hypotension prediction evaluation model to obtain a blood pressure evaluation result corresponding to the target blood pressure related data;
and determining an event processing result of the target event according to the blood pressure evaluation result.
Computer storage media for embodiments of the invention may employ any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for embodiments of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (10)
1. An event processing method, comprising:
acquiring a target event based on a first preset time interval, wherein the target event comprises target blood pressure related data within a first preset time;
inputting the target blood pressure related data into a pre-trained target hypotension prediction evaluation model to obtain a blood pressure evaluation result corresponding to the target blood pressure related data;
and determining an event processing result of the target event according to the blood pressure evaluation result.
2. The method of claim 1, further comprising:
training at least one hypotension prediction evaluation model to be trained on the basis of training sample data to obtain at least one hypotension prediction evaluation model to be used;
inputting the test sample data in the test sample data set to the hypotension prediction evaluation model to be used at present aiming at each hypotension prediction evaluation model to be used, and obtaining an actual output result corresponding to each test sample data; the test sample data comprises test blood pressure related parameters and a set output result;
according to the actual output result and the corresponding set output result, determining the accuracy of the hypotension prediction and evaluation model to be used currently;
determining the target hypotension prediction evaluation model according to the accuracy of each hypotension prediction evaluation model to be used;
the target hypotension prediction evaluation model is used for determining a blood pressure evaluation result corresponding to the input data.
3. The method according to claim 2, wherein training at least one hypotension prediction evaluation model to be trained based on training sample data to obtain at least one hypotension prediction evaluation model to be used comprises:
acquiring a training sample data set, wherein the training sample data set comprises a plurality of training sample data, and the training sample data comprises positive sample data and negative sample data; the positive sample data is hypotension;
aiming at each to-be-trained hypotension prediction evaluation model, taking training blood pressure associated data of training sample data as input of the current to-be-trained hypotension prediction evaluation model to obtain an output evaluation value corresponding to the training sample data;
calculating a loss value of a loss function in the hypotension prediction evaluation model to be trained based on the output evaluation value and a set output value of the training sample data, and adjusting network parameters in the hypotension prediction evaluation model to be trained based on the loss value;
taking the convergence of the loss function as a training target, and training the to-be-trained blood pressure prediction evaluation model to obtain a to-be-verified blood pressure prediction evaluation model;
and verifying the hypotension prediction evaluation model to be verified according to verification sample data, and obtaining the hypotension prediction evaluation model to be used based on a verification result.
4. The method according to claim 3, wherein the verifying the hypotension prediction evaluation model to be verified according to verification sample data, and based on a verification result, obtaining the hypotension prediction evaluation model to be used comprises:
inputting each verification sample data into the hypotension prediction evaluation model to be verified to obtain a reference output result corresponding to each verification sample data;
according to the reference output result and a set output result in the verification sample data, determining the accuracy of the hypotension prediction evaluation model to be verified;
and when the accuracy is lower than a preset accuracy threshold, taking the hypotension prediction evaluation model to be verified as a hypotension prediction evaluation model to be trained, and training until the accuracy of an output result of the hypotension prediction evaluation model to be trained is higher than the preset accuracy threshold.
5. The method of claim 2, further comprising: determining sample data;
the determining sample data comprises:
collecting a group of original blood pressure related parameters corresponding to each user based on the vital sign monitoring equipment;
for each group of original blood pressure associated parameters, determining that the original blood pressure associated parameters are the initial time of the target parameters when the target parameter values in a second preset time period are lower than a preset parameter threshold value based on the current original blood pressure associated parameters;
and obtaining blood pressure associated parameters to be used according to the starting time, at least one sample sampling interval and sampling frequency which are preset, generating the sample data according to the blood pressure associated parameters to be used, and training the hypotension prediction evaluation model to be trained according to the sample data.
6. The method according to claim 5, wherein the sample sampling interval includes a first sample sampling interval and a second sample sampling interval, the duration of the first sample sampling interval is smaller than the duration of the second sample sampling interval, the obtaining a blood pressure related parameter to be used according to the starting time, at least one preset sample sampling interval and sampling frequency, and generating the sample data according to the blood pressure related parameter to be used comprises:
acquiring a first blood pressure related parameter to be used from an original blood pressure related parameter according to the starting moment, the first sample sampling interval and the sampling frequency, and generating a positive sample based on the first blood pressure related parameter to be used; the set output in the positive sample is a first set output value;
acquiring a second blood pressure related parameter to be used from the original blood pressure related parameter according to the starting time, the second sample sampling interval and the sampling frequency, and generating a negative sample based on the second blood pressure related parameter to be used; the set output in the negative sample is a second constant output value.
7. The method of claim 1, wherein determining an event processing result of the target event based on the blood pressure assessment result comprises:
determining that a hypotensive event has occurred when the blood pressure assessment is above a preset assessment threshold.
8. An event processing apparatus, comprising:
the event acquisition module is used for acquiring a target event based on a first preset time interval, wherein the target event comprises target blood pressure related data within a first preset time;
the result determining module is used for inputting the target blood pressure related data into a pre-trained target hypotension prediction evaluation model to obtain a blood pressure evaluation result corresponding to the target blood pressure related data;
and the event processing module is used for determining an event processing result of the target event according to the blood pressure evaluation result.
9. An electronic device, characterized in that the electronic device comprises:
one or more processors;
storage means for storing one or more programs which, when executed by the processor, cause the processor to carry out an event handling method as claimed in any one of claims 1 to 7.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out an event processing method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011223233.XA CN112382394A (en) | 2020-11-05 | 2020-11-05 | Event processing method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011223233.XA CN112382394A (en) | 2020-11-05 | 2020-11-05 | Event processing method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112382394A true CN112382394A (en) | 2021-02-19 |
Family
ID=74578365
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011223233.XA Pending CN112382394A (en) | 2020-11-05 | 2020-11-05 | Event processing method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112382394A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113066580A (en) * | 2021-03-17 | 2021-07-02 | 上海电气集团股份有限公司 | Medical score determining method and device, electronic equipment and storage medium |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108378835A (en) * | 2018-02-11 | 2018-08-10 | 中国联合网络通信集团有限公司 | Blood pressure prediction technique and device |
| CN110059112A (en) * | 2018-09-12 | 2019-07-26 | 中国平安人寿保险股份有限公司 | Usage mining method and device based on machine learning, electronic equipment, medium |
| CN110141201A (en) * | 2019-05-14 | 2019-08-20 | 中国科学院深圳先进技术研究院 | Blood pressure estimation method and device |
| CN110197720A (en) * | 2019-03-12 | 2019-09-03 | 平安科技（深圳）有限公司 | Prediction technique and device, storage medium, the computer equipment of diabetes |
| CN110251105A (en) * | 2019-06-12 | 2019-09-20 | 广州视源电子科技股份有限公司 | A kind of non-invasive blood pressure measuring method, device, equipment and system |
| CN110349038A (en) * | 2019-06-13 | 2019-10-18 | 中国平安人寿保险股份有限公司 | Risk evaluation model training method and methods of risk assessment |
| CN110648764A (en) * | 2019-08-20 | 2020-01-03 | 南京医渡云医学技术有限公司 | Method and device for obtaining clinical data prediction model, readable medium and electronic equipment |
| CN111462911A (en) * | 2020-04-02 | 2020-07-28 | 深圳阿拉丁医疗科技有限公司 | Algorithm for predicting blood pressure abnormity of cerebral apoplexy based on big data and artificial intelligence |
| CN111639766A (en) * | 2020-05-26 | 2020-09-08 | 上海极链网络科技有限公司 | Sample data generation method and device |
-
2020
- 2020-11-05 CN CN202011223233.XA patent/CN112382394A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108378835A (en) * | 2018-02-11 | 2018-08-10 | 中国联合网络通信集团有限公司 | Blood pressure prediction technique and device |
| CN110059112A (en) * | 2018-09-12 | 2019-07-26 | 中国平安人寿保险股份有限公司 | Usage mining method and device based on machine learning, electronic equipment, medium |
| CN110197720A (en) * | 2019-03-12 | 2019-09-03 | 平安科技（深圳）有限公司 | Prediction technique and device, storage medium, the computer equipment of diabetes |
| CN110141201A (en) * | 2019-05-14 | 2019-08-20 | 中国科学院深圳先进技术研究院 | Blood pressure estimation method and device |
| CN110251105A (en) * | 2019-06-12 | 2019-09-20 | 广州视源电子科技股份有限公司 | A kind of non-invasive blood pressure measuring method, device, equipment and system |
| CN110349038A (en) * | 2019-06-13 | 2019-10-18 | 中国平安人寿保险股份有限公司 | Risk evaluation model training method and methods of risk assessment |
| CN110648764A (en) * | 2019-08-20 | 2020-01-03 | 南京医渡云医学技术有限公司 | Method and device for obtaining clinical data prediction model, readable medium and electronic equipment |
| CN111462911A (en) * | 2020-04-02 | 2020-07-28 | 深圳阿拉丁医疗科技有限公司 | Algorithm for predicting blood pressure abnormity of cerebral apoplexy based on big data and artificial intelligence |
| CN111639766A (en) * | 2020-05-26 | 2020-09-08 | 上海极链网络科技有限公司 | Sample data generation method and device |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113066580A (en) * | 2021-03-17 | 2021-07-02 | 上海电气集团股份有限公司 | Medical score determining method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2019001278A1 (en) | Actuarial forecasting method and device for medical benefits fund, and computer device | |
| US10431338B2 (en) | System and method for weighting manageable patient attributes during criteria evaluations for treatment | |
| CN112885481A (en) | Case grouping method, case grouping device, electronic equipment and storage medium | |
| CN111883222B (en) | Text data error detection method and device, terminal equipment and storage medium | |
| CN111639766A (en) | Sample data generation method and device | |
| CN110647447A (en) | Abnormal instance detection method, apparatus, device and medium for distributed system | |
| CN112382394A (en) | Event processing method and device, electronic equipment and storage medium | |
| CN112182067A (en) | Individual height prediction method and device, electronic equipment and storage medium | |
| WO2022033224A1 (en) | Human reliability evaluation method and system, and computer device and storage medium | |
| CN109947651B (en) | Artificial intelligence engine optimization method and device | |
| CN110716843A (en) | System fault analysis processing method and device, storage medium and electronic equipment | |
| US11004564B2 (en) | Method and apparatus for processing medical data | |
| KR102420605B1 (en) | CNN MODEL PREDICTING METHOD AND CNN MODEL APPARATUS FOR PREDICTING DISEASE FROM X-ray IMAGE | |
| CN112184295A (en) | Health maintenance service determination method and device, electronic equipment and storage medium | |
| CN115240870A (en) | Early warning method and device for unknown infectious diseases, electronic equipment and computer medium | |
| CN111708681A (en) | Log processing method, device, equipment and storage medium | |
| CN115759040A (en) | Electronic medical record analysis method, device, equipment and storage medium | |
| CN115762704A (en) | Prescription auditing method, device, equipment and storage medium | |
| US20200302914A1 (en) | Method, device, computer apparatus, and storage medium of processing claim data | |
| CN113990512A (en) | Abnormal data detection method and device, electronic equipment and storage medium | |
| CN114266501A (en) | Automatic prediction and root cause analysis method and system for hospital operation index | |
| WO2021103623A1 (en) | Sepsis early warning apparatus and device, and storage medium | |
| CN110908818B (en) | Verification method, device, equipment and storage medium | |
| CN112582054A (en) | Medical insurance data supervision method and device, electronic equipment and medium | |
| CN114741377B (en) | Method and device for identifying and processing natural gas abnormal data |
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 |