CN117954085A - Physiological condition prediction method, device and readable storage medium - Google Patents
Physiological condition prediction method, device and readable storage medium Download PDFInfo
- Publication number
- CN117954085A CN117954085A CN202311772552.XA CN202311772552A CN117954085A CN 117954085 A CN117954085 A CN 117954085A CN 202311772552 A CN202311772552 A CN 202311772552A CN 117954085 A CN117954085 A CN 117954085A
- Authority
- CN
- China
- Prior art keywords
- physiological
- physiological condition
- condition prediction
- module
- digital signal
- 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
- 230000004962 physiological condition Effects 0.000 title claims abstract description 66
- 238000000034 method Methods 0.000 title claims abstract description 30
- 210000004369 blood Anatomy 0.000 claims abstract description 32
- 239000008280 blood Substances 0.000 claims abstract description 32
- 238000007781 pre-processing Methods 0.000 claims abstract description 18
- 208000024891 symptom Diseases 0.000 claims abstract description 8
- 238000013527 convolutional neural network Methods 0.000 claims description 19
- 238000012545 processing Methods 0.000 claims description 11
- 238000012549 training Methods 0.000 claims description 10
- 238000006243 chemical reaction Methods 0.000 claims description 8
- 238000004159 blood analysis Methods 0.000 claims description 6
- 238000013135 deep learning Methods 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 5
- 239000012503 blood component Substances 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 5
- 239000000306 component Substances 0.000 claims description 4
- 238000002372 labelling Methods 0.000 claims description 4
- 238000009529 body temperature measurement Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000003745 diagnosis Methods 0.000 abstract description 3
- 230000008569 process Effects 0.000 description 5
- 238000011176 pooling Methods 0.000 description 4
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 3
- 210000004185 liver Anatomy 0.000 description 3
- 201000010099 disease Diseases 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 208000019423 liver disease Diseases 0.000 description 2
- 208000007848 Alcoholism Diseases 0.000 description 1
- 206010019663 Hepatic failure Diseases 0.000 description 1
- 206010061218 Inflammation Diseases 0.000 description 1
- 230000003213 activating effect Effects 0.000 description 1
- 201000007930 alcohol dependence Diseases 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000017531 blood circulation Effects 0.000 description 1
- 238000013075 data extraction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 235000006694 eating habits Nutrition 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 210000003743 erythrocyte Anatomy 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000004054 inflammatory process Effects 0.000 description 1
- 208000007903 liver failure Diseases 0.000 description 1
- 231100000835 liver failure Toxicity 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 229910052760 oxygen Inorganic materials 0.000 description 1
- 239000001301 oxygen Substances 0.000 description 1
- 230000002572 peristaltic effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000002054 transplantation Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Landscapes
- Investigating Or Analysing Biological Materials (AREA)
Abstract
The invention relates to a physiological condition prediction method, a physiological condition prediction device and a readable storage medium. The method comprises the following steps: acquiring a first physiological index of a target person, wherein the first physiological index is obtained by analyzing a blood sample of the target person; converting the first physiological index into a corresponding digital signal, and performing data preprocessing on the digital signal to obtain a first input signal; constructing a physiological condition prediction model based on second physiological indexes of different symptoms at different stages; and inputting the first input signal into a physiological condition prediction model to obtain a physiological condition prediction result. The invention can give accurate diagnosis results in time.
Description
Technical Field
The present invention relates to the field of data prediction technologies, and in particular, to a method and apparatus for predicting a physiological condition, and a readable storage medium.
Background
Today, with the continuous improvement of the living standard of people, liver failure diseases have become common diseases nowadays due to long-term alcoholism, poor eating habits, abuse of drugs and the like. China is a country with high incidence of liver diseases, and various liver disease target persons reach more than 1 hundred million, but only 10% of target persons have the opportunity of liver transplantation, and obviously, the development of artificial liver is more important.
The current stage artificial liver can only acquire the data of various components in blood of a target person in the blood circulation process by manpower, and obtain a rough treatment scheme by comparing the data with normal physiological indexes of a human body, and then manually operate a treatment instrument.
The prior art has the defects that the acquisition and treatment time is too long, and the physiological condition of a target person cannot be timely predicted accurately, and the physiological condition can be judged by manpower through experience.
Disclosure of Invention
In view of the foregoing, there is a need for a physiological condition prediction method, apparatus and readable storage medium for solving the problem of untimely diagnosis in the prior art.
In order to solve the above problems, the present invention provides a physiological condition prediction method, including:
Acquiring a first physiological index of a target person, wherein the first physiological index is obtained by analyzing a blood sample of the target person;
Converting the first physiological index into a corresponding digital signal, and performing data preprocessing on the digital signal to obtain a first input signal;
Constructing a physiological condition prediction model based on second physiological indexes of different symptoms at different stages;
And inputting the first input signal into the physiological condition prediction model to obtain a physiological condition prediction result.
Further, analyzing the blood sample of the target person includes: temperature measurement and component analysis are performed on the blood sample.
Further, converting the first physiological indicator into a corresponding digital signal includes:
classifying the first physiological index according to the dimensions of blood components and temperature to obtain a plurality of dimension indexes, and converting the dimension indexes into digital signals.
Further, performing data preprocessing on the digital signal to obtain a first input signal, including: and carrying out normalization processing on the digital signals.
Further, the physiological condition prediction model includes a parallel convolutional neural network.
Further, constructing a physiological condition prediction model based on physiological indexes of different symptoms at different stages, including:
Acquiring second physiological indexes of different symptoms at different stages;
labeling the second physiological index to obtain a training data set;
inputting the training data set into the parallel convolutional neural network for deep learning;
And taking the parallel convolutional neural network subjected to deep learning as the physiological condition prediction model.
The invention also provides a physiological condition prediction device, comprising: the device comprises a blood collection module, a blood analysis module, a digital signal conversion module, a data preprocessing module and a physiological condition prediction module;
the blood collection module is used for collecting a blood sample;
The blood analysis module is used for analyzing the blood sample to obtain the first physiological index;
The digital signal conversion module is used for converting the first physiological index into a digital signal;
the data preprocessing module is used for carrying out data preprocessing on the digital signals to obtain first input signals;
the physiological condition prediction module is used for outputting a physiological condition prediction result according to the first input signal.
Further, the device also includes a control module for controlling the temperature and flow rate of the blood sample.
Further, the device also comprises a control decision module for giving a treatment decision according to the physiological condition prediction result.
The invention also provides a readable storage medium, which comprises a stored computer program, and when the computer program is executed, the device where the readable storage medium is located is controlled to execute the physiological condition prediction method according to the embodiment of any one of the method items of the invention.
Drawings
FIG. 1 is a flowchart of a method for predicting physiological conditions according to an embodiment of the present invention
FIG. 2 is a flowchart of a method for constructing a physiological prediction model according to an embodiment of the present invention;
Fig. 3 is a schematic structural diagram of a physiological condition prediction apparatus according to an embodiment of the present invention.
Detailed Description
The following detailed description of preferred embodiments of the application is made in connection with the accompanying drawings, which form a part hereof, and together with the description of the embodiments of the application, are used to explain the principles of the application and are not intended to limit the scope of the application.
Example 1:
As shown in fig. 1, embodiment 1 of the present invention discloses a physiological condition prediction method, which includes: step S101: acquiring a first physiological index of a target person, wherein the first physiological index is obtained by analyzing a blood sample of the target person;
As one example, analyzing a blood sample of a target person includes: a temperature measurement and a component analysis are performed on the blood sample.
Step S102: the first physiological indicator is converted into a corresponding digital signal.
Step S103: and carrying out data preprocessing on the digital signal to obtain a first input signal.
As one embodiment, converting the first physiological indicator into a corresponding digital signal includes:
Classifying the first physiological index according to the dimensions of blood components and temperature to obtain a plurality of dimension indexes, and converting the dimension indexes into digital signals.
As one embodiment, performing data preprocessing on a digital signal to obtain a first input signal includes: and carrying out normalization processing on the digital signals to obtain first input signals.
Specifically, in this embodiment, the first physiological index specifically includes physiological indexes of multiple dimensions such as blood temperature, blood oxygen concentration, red blood cell concentration, and platelet concentration, and the temperature data, blood components, and content thereof of the blood sample are obtained through analysis in step S102, and these data belong to data of different dimensions, and different reference indexes are also corresponding when the physiological condition is predicted subsequently, so that it is necessary to classify the analysis result of the blood sample according to different dimensions, and then perform digital signal conversion one by one, so that the accuracy of the prediction is further improved while the physiological condition is predicted conveniently.
In data prediction techniques, data preprocessing is an important step. In the original data, the distribution range of the feature values is greatly different due to the source and the measurement unit of each dimension feature. When the Euclidean distance between different samples is calculated, the characteristic with large value range plays a leading role. Therefore, for the machine learning method based on similarity comparison, the sample must be preprocessed first, the feature of each dimension is normalized to the same value interval, and the correlation between different features is eliminated, so that an ideal result can be obtained.
Step S104: constructing a physiological condition prediction model based on second physiological indexes of different symptoms at different stages;
step S105: the first input signal is input to a physiological condition prediction model.
Step S106: and obtaining a physiological condition prediction result.
As one embodiment, the physiological condition prediction model includes a parallel convolutional neural network.
As one example, as shown in fig. 2, constructing a physiological condition prediction model based on physiological indexes of different conditions at different stages includes:
step S201: and obtaining second physiological indexes of different symptoms at different stages.
Specifically, the second physiological index is the same as the first physiological index, and includes blood temperature, blood components and concentration thereof. The second physiological index can be acquired by inquiring historical data of diagnosis of various diseases and is collected and stored in an image form.
Step S202: and labeling the second physiological index to obtain a sample data set.
Specifically, in order to avoid the influence of color factors on data extraction, firstly, gray processing is performed on a plurality of collected images, then, labeling is performed on a plurality of images subjected to gray processing, so as to obtain a sample data set, and for facilitating subsequent training of a network model, the sample data set can be divided into a training data set, a verification data set and a test data set.
Step S203: and inputting the sample data set into a parallel convolutional neural network for deep learning.
Step S204: and taking the parallel convolutional neural network subjected to deep learning as a physiological condition prediction model.
Specifically, the parallel convolutional neural network includes a plurality of independent convolutional neural network branches, each of which is divided into a convolutional layer, a pooling layer, and a fully-connected layer. Parallel convolutional neural networks are one way to accelerate the training and inference process of convolutional neural networks by means of parallel computation. The general working procedure of the parallel convolutional neural network includes:
1. Data input: first, the input data is partitioned into subsets. These subsets may be different parts of the image or information of different channels. In this embodiment, the first physiological indexes are classified according to different dimensions in advance, and digital signal conversion and preprocessing are performed to obtain the first input signal, so that the first input signal is directly input to the parallel convolutional neural network.
2. Parallel convolution: each subset is fed into a separate convolutional neural network branch, which may run on a different processing unit, such as an image processor or a multi-core central processor. Each branch is responsible for processing its corresponding subset of data, performing operations such as convolving, activating functions, etc. This means that multiple convolution operations can be performed in parallel at the same time, speeding up the overall processing speed.
3. Information integration: at the output level of each branch, the resulting feature maps may be merged or integrated. This step may include a pooling operation (e.g., max-pooling or average pooling), a stitching operation, or other network architecture specific integration.
4. Subsequent layer operations: the integrated signature may be fed into the next layer of the network, which may be another set of parallel convolution branches, or may be another type of layer, such as a fully connected layer or an output layer.
5. Back propagation: during training, the loss is calculated and the weights are updated by a back propagation algorithm. The accuracy of model output is further improved, and due to parallel operation, counter-propagating gradients can be independently calculated at each branch, so that the whole process is accelerated.
6. Model output: the final output is the output of the entire parallel network, representing the result of processing the input data. In this embodiment, the final output of the parallel convolutional neural network is the physiological condition of the target person, such as the presence of inflammation in the body of the target person.
The parallel convolutional neural network has the main advantages of fully utilizing hardware resources and accelerating the training and deducing processes of the model. This is particularly beneficial for processing large-scale data sets or complex network structures. However, it should be noted that in designing a parallel convolutional neural network, it is necessary to balance the load between the various branches to ensure optimal performance of the overall system.
Compared with the prior art, the physiological condition prediction method provided by the embodiment is characterized in that the blood of the target person is analyzed to obtain the physiological index of the target person, the physiological index is input into the physiological condition prediction model after being subjected to a series of processing, and the physiological condition prediction model is introduced with the parallel convolution neural network, so that the prediction efficiency is greatly improved, and a great deal of training is performed on the model while the physiological condition prediction model is built, so that the input data and the output result of the model have stronger relevance, and the more accurate prediction result can be obtained quickly, and the consumption of manpower and material resources in the detection process is reduced.
Example 2:
As shown in fig. 3, embodiment 2 of the present invention provides a physiological condition prediction apparatus including: a blood collection module 301, a blood analysis module 303, a digital signal conversion module 304, a data preprocessing module 305, a physiological condition prediction module 306;
The blood collection module 301 is used for collecting a blood sample;
The blood analysis module 303 is configured to analyze a blood sample to obtain a first physiological index;
The digital signal conversion module 304 is configured to convert the first physiological indicator into a digital signal;
the data preprocessing module 305 is configured to perform data preprocessing on the digital signal to obtain a first input signal;
the physiological condition prediction module 306 is configured to output a physiological condition prediction result according to the first input signal.
As one example, the physiological condition prediction device further includes a control module 302, where the control module 302 is configured to control the temperature and flow rate of the blood sample.
Specifically, in this embodiment, the control module 302 includes a peristaltic pump to control the flow rate, a temperature controller to control the temperature, etc., and the entire physiological condition prediction device is controlled to output by a specific mechanical device.
As one embodiment, the physiological condition prediction apparatus further comprises a control decision module 307, the control decision module 307 being configured to give a treatment decision based on the physiological condition prediction result.
Example 3:
embodiment 3 of the present invention provides a readable storage medium, where the readable storage medium includes a stored computer program, which when executed controls a device in which the readable storage medium is located to perform a physiological condition prediction method according to an embodiment of any one of the method aspects of the present invention.
Those skilled in the art will appreciate that all or part of the flow of the methods of the embodiments described above may be accomplished by way of a computer program to instruct associated hardware, where the program may be stored on a computer readable storage medium. Wherein the computer readable storage medium is a magnetic disk, an optical disk, a read-only memory or a random access memory, etc.
The present invention is not limited to the above-mentioned embodiments, and any changes or substitutions that can be easily understood by those skilled in the art within the technical scope of the present invention are intended to be included in the scope of the present invention.
Claims (10)
1. A method of predicting a physiological condition, comprising:
Acquiring a first physiological index of a target person, wherein the first physiological index is obtained by analyzing a blood sample of the target person;
Converting the first physiological index into a corresponding digital signal, and performing data preprocessing on the digital signal to obtain a first input signal;
Constructing a physiological condition prediction model based on second physiological indexes of different symptoms at different stages;
And inputting the first input signal into the physiological condition prediction model to obtain a physiological condition prediction result.
2. The method of claim 1, wherein analyzing the blood sample of the subject person comprises:
temperature measurement and component analysis are performed on the blood sample.
3. The physiological condition prediction method of claim 2, converting the first physiological indicator into a corresponding digital signal, comprising:
classifying the first physiological index according to the dimensions of blood components and temperature to obtain a plurality of dimension indexes, and converting the dimension indexes into digital signals.
4. The method of claim 1, wherein data preprocessing the digital signal to obtain a first input signal comprises:
and carrying out normalization processing on the digital signals to obtain the first input signals.
5. The physiological condition prediction method of claim 1, wherein the physiological condition prediction model comprises a parallel convolutional neural network.
6. The method of claim 5, wherein constructing a physiological condition prediction model based on physiological indicators of different conditions at different stages comprises:
Acquiring second physiological indexes of different symptoms at different stages;
labeling the second physiological index to obtain a training data set;
inputting the training data set into the parallel convolutional neural network for deep learning;
And taking the parallel convolutional neural network subjected to deep learning as the physiological condition prediction model.
7. A physiological condition prediction device, comprising: the device comprises a blood collection module, a blood analysis module, a digital signal conversion module, a data preprocessing module and a physiological condition prediction module;
the blood collection module is used for collecting a blood sample;
The blood analysis module is used for analyzing the blood sample to obtain the first physiological index;
The digital signal conversion module is used for converting the first physiological index into a digital signal;
the data preprocessing module is used for carrying out data preprocessing on the digital signals to obtain first input signals;
the physiological condition prediction module is used for outputting a physiological condition prediction result according to the first input signal.
8. The physiological condition prediction device of claim 7, further comprising a control module for controlling the temperature and flow rate of the blood sample.
9. The physiological condition prediction device of claim 7, further comprising a control decision module for giving a treatment decision based on the physiological condition prediction result.
10. A readable storage medium, characterized in that the readable storage medium comprises a stored computer program which, when executed, controls a device in which the readable storage medium is located to perform the physiological condition prediction method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311772552.XA CN117954085A (en) | 2023-12-21 | 2023-12-21 | Physiological condition prediction method, device and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311772552.XA CN117954085A (en) | 2023-12-21 | 2023-12-21 | Physiological condition prediction method, device and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117954085A true CN117954085A (en) | 2024-04-30 |
Family
ID=90800918
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311772552.XA Pending CN117954085A (en) | 2023-12-21 | 2023-12-21 | Physiological condition prediction method, device and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117954085A (en) |
-
2023
- 2023-12-21 CN CN202311772552.XA patent/CN117954085A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111680706A (en) | Double-channel output contour detection method based on coding and decoding structure | |
| CN113053535B (en) | Medical information prediction system and medical information prediction method | |
| CN113855038B (en) | Electrocardiosignal critical value prediction method and device based on multi-model integration | |
| CN113610859B (en) | Automatic thyroid nodule segmentation method based on ultrasonic image | |
| CN111312399A (en) | Method for establishing model for early prediction of gestational diabetes | |
| CN113392894A (en) | Cluster analysis method and system for multi-group mathematical data | |
| CN114663383A (en) | Blood cell segmentation and identification method and device, electronic equipment and storage medium | |
| CN113808747A (en) | Ischemic stroke recurrence prediction method | |
| CN107169264B (en) | complex disease diagnosis system | |
| CN113222944B (en) | Cell nucleus segmentation method and cancer auxiliary analysis system and device based on pathological image | |
| CN114445356A (en) | Multi-resolution-based full-field pathological section image tumor rapid positioning method | |
| CN117274185B (en) | Detection method, detection model product, electronic device, and computer storage medium | |
| CN116842996A (en) | Space transcriptome method and device based on depth compressed sensing | |
| CN113838018B (en) | Cnn-former-based liver fibrosis lesion detection model training method and system | |
| CN117954085A (en) | Physiological condition prediction method, device and readable storage medium | |
| CN116130105A (en) | Health risk prediction method based on neural network | |
| CN110765908A (en) | Cascade type cancer cell detection system based on deep learning | |
| CN115131628A (en) | Mammary gland image classification method and equipment based on typing auxiliary information | |
| CN114897057A (en) | Intelligent yin deficiency syndrome diagnosis system, method and equipment based on multi-mode data fusion | |
| CN114581425A (en) | Myocardial segment defect image processing method based on deep neural network | |
| CN114565617A (en) | Pruning U-Net + + based breast tumor image segmentation method and system | |
| CN117476110B (en) | Multi-scale biomarker discovery system based on artificial intelligence | |
| Hossain et al. | A Hybrid Neural Network Model for Brain Tumor Detection in Brain MRI Images | |
| Deng et al. | Tongue image datasets and performance evaluation | |
| CN115705633A (en) | Model training method, device and storage medium |
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 |