CN112435757A - Prediction device and system for acute hepatitis - Google Patents

Prediction device and system for acute hepatitis Download PDF

Info

Publication number
CN112435757A
CN112435757A CN202011162284.6A CN202011162284A CN112435757A CN 112435757 A CN112435757 A CN 112435757A CN 202011162284 A CN202011162284 A CN 202011162284A CN 112435757 A CN112435757 A CN 112435757A
Authority
CN
China
Prior art keywords
probability
data
model
diseased
predicted
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202011162284.6A
Other languages
Chinese (zh)
Other versions
CN112435757B (en
Inventor
刘阳
谭世琦
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Lilaishan Technology Co ltd
Original Assignee
Shenzhen Lilaishan Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shenzhen Lilaishan Technology Co ltd filed Critical Shenzhen Lilaishan Technology Co ltd
Priority to CN202011162284.6A priority Critical patent/CN112435757B/en
Publication of CN112435757A publication Critical patent/CN112435757A/en
Application granted granted Critical
Publication of CN112435757B publication Critical patent/CN112435757B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • G16H50/80—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for detecting, monitoring or modelling epidemics or pandemics, e.g. flu
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Public Health (AREA)
  • Medical Informatics (AREA)
  • Data Mining & Analysis (AREA)
  • Biomedical Technology (AREA)
  • Databases & Information Systems (AREA)
  • Pathology (AREA)
  • Epidemiology (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Measuring And Recording Apparatus For Diagnosis (AREA)

Abstract

The present invention provides an acute hepatitis prediction device, including: the data acquisition module (11) is used for acquiring relevant data of the patient with acute hepatitis; the data processing module (12) is connected with the data acquisition module (11) and is used for processing the relevant data of the acute hepatitis patient to generate characteristic data; the prediction module (13) is connected with the data processing module (12) and is used for predicting the characteristic data to obtain a plurality of preliminary non-sick probabilities and sick probabilities; and the integration module (14) is connected with the prediction module (13) and is used for counting the plurality of preliminary non-diseased probabilities and diseased probabilities to obtain the final non-diseased probability and diseased probability of the acute hepatitis patient. The invention also provides a prediction system of acute hepatitis. The invention can conveniently and quickly predict the acute hepatitis diseases, strive for valuable treatment time for patients, and reduce the probability and death rate of sudden acute hepatitis diseases, thereby achieving the function of disease early warning.

Description

Prediction device and system for acute hepatitis
Technical Field
The invention relates to the field of medical data processing, in particular to a prediction device and a prediction system for acute hepatitis.
Background
Acute liver failure in acute hepatitis is a liver disease with multiple causes, and clinical manifestations of patients with acute liver failure are massive hepatocyte necrosis in a short time and severe liver function damage, and can cause a series of liver diseases. At present, no specific treatment method for acute liver failure exists, and the death rate is high due to the short morbidity of the disease. Therefore, it is important to be able to predict the disease. At present, biological reagents are mainly used for detection, but the detection means needs to purchase a kit and special medical personnel for guidance, the detection of a patient cannot be conveniently and quickly finished, and the optimal treatment or rescue opportunity of the patient is probably missed.
Therefore, there is a need for an acute hepatitis prediction device and system to address the above problems.
Disclosure of Invention
In view of the above, an object of the embodiments of the present invention is to provide an acute hepatitis prediction apparatus and system, which aim to solve the problem in the prior art that an acute hepatitis disease cannot be detected conveniently and quickly.
In order to achieve the above object, a first aspect of the present invention provides an acute hepatitis prediction device including:
the data acquisition module 11 is used for acquiring relevant data of the acute hepatitis patient;
the data processing module 12 is connected with the data acquisition module 11 and is used for processing the relevant data of the acute hepatitis patient and generating characteristic data;
the prediction module 13 is connected with the data processing module 12 and is used for predicting the generated feature data to obtain a plurality of preliminary non-disease probabilities and disease probabilities;
and the integration module 14 is connected with the prediction module 13 and is used for counting the plurality of preliminary non-diseased probabilities and diseased probabilities to obtain the final non-diseased probability and diseased probability of the acute hepatitis patient.
Preferably, the related data includes: continuous data and discrete data;
the continuous data includes: pulse rate, heart rate, respiratory rate, blood oxygen saturation, age, height, gender, body mass index, blood pressure, and cholesterol indicator;
the discrete data includes: emotional state, whether alcohol was consumed, whether there was diabetes, whether there was a family history of inherited diabetes, whether there was hepatitis, whether there was a history of hepatitis inherited disease, whether there was heart disease, and whether there was a history of heart disease inherited disease.
Preferably, the apparatus further comprises:
a model training module 15, connected to the prediction module 13, for:
inputting the continuous data of the sample set into a training algorithm of an SVM model to obtain an optimal weight parameter,
inputting the discrete data of the sample set into a training algorithm of a decision tree model to construct an optimal classification decision tree,
inputting continuous data and discrete data of the sample set into a training algorithm of an MLP model to obtain optimal weight parameters;
wherein the sample set comprises the relevant data for a plurality of diseased and non-diseased individuals.
Preferably, the data processing module 12 is configured to:
the regularization processes the continuous data, specifically,
using a formula
Figure BDA0002744737410000021
Calculating the middle value of a certain index x;
wherein, x is an original value of a certain index, x _ min is an empirical minimum value of the certain index, x _ max is an empirical maximum value of the certain index, and x' is a middle value of the certain index x;
carrying out binary processing on x' to obtain characteristic data: when x 'is greater than 1, x' is set to 1, and when x 'is less than 0, x' is set to 0.
Preferably, the data processing module 12 is further configured to:
and carrying out binary coding processing on the discrete data to obtain characteristic data.
Preferably, the prediction module 13 is configured to:
forecasting the continuous data by adopting an SVM model to obtain the preliminary non-diseased probability and diseased probability of the continuous data;
predicting the discrete data by adopting a decision tree model to obtain the preliminary non-diseased probability and diseased probability of the discrete data; and
and predicting the continuous data and the discrete data by adopting an MLP model to obtain combined initial non-disease probability and disease probability.
Preferably, the integration module 14 is configured to:
inputting the preliminary non-diseased probability and diseased probability of the continuous data, the preliminary non-diseased probability and diseased probability of the discrete data and the combined preliminary non-diseased probability and diseased probability into an ensemble learning model, and predicting the final non-diseased probability p0And probability of illness p1Probability of not being affected p0And probability of illness p1The concrete formula is as follows,
Figure BDA0002744737410000031
wherein p is10Probability of non-morbidity, p, predicted for SVM models20Probability of non-morbidity, p, predicted for a decision tree model30Probability of non-morbidity, p, predicted for MLP model11Probability of illness, p, predicted for SVM model21Probability of illness, p, predicted for decision tree model31Probability of illness predicted for MLP model, P0The final probability of no illness;
Figure BDA0002744737410000032
wherein p is11Probability of illness, p, predicted for SVM model21Probability of illness, p, predicted for decision tree model31Probability of illness, p, predicted for MLP model10Probability of non-morbidity, p, predicted for SVM models20Probability of non-morbidity, p, predicted for a decision tree model30Probability of non-morbidity, P, predicted for MLP model1The final prevalence probability.
Preferably, the data obtaining module 11 is configured to:
the data is acquired by a browser and/or a wechat applet and/or an application.
In order to achieve the purpose, the second technical scheme adopted by the invention is as follows: provided is a system for predicting acute hepatitis, comprising:
the terminal and a device which is in communication connection with the terminal and realizes the module;
the terminal includes: at least one of a mobile terminal, a tablet computer, a notebook computer, a desktop computer and an intelligent television.
According to the prediction device and the prediction system for the acute hepatitis, provided by the invention, relevant data of an acute hepatitis patient is obtained; processing the relevant data of the acute hepatitis patient to generate characteristic data; predicting the characteristic data to obtain a plurality of preliminary non-disease probability and disease probability; and then, the plurality of preliminary non-illness probabilities and illness probabilities are counted to obtain the final non-illness probability and illness probability of the acute hepatitis patient, so that the acute hepatitis disease can be conveniently and quickly predicted, precious treatment time is strived for the patient, and the probability and death rate of sudden acute hepatitis disease are reduced, thereby achieving the function of disease early warning.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the structures shown in the drawings without creative efforts.
FIG. 1 is a block diagram of an acute hepatitis prediction apparatus according to a first embodiment of the present invention;
FIG. 2 is a schematic block diagram of an acute hepatitis prediction apparatus according to a second embodiment of the present invention;
FIG. 3 is a schematic diagram showing the structure of a system for predicting acute hepatitis according to a third embodiment of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In addition, technical solutions between various embodiments may be combined with each other, but must be realized by a person skilled in the art, and when the technical solutions are contradictory or cannot be realized, such a combination should not be considered to exist, and is not within the protection scope of the present invention.
The invention is further described in detail below with reference to the figures and the specific embodiments.
Referring to fig. 1, fig. 1 is a block diagram of a prediction apparatus for acute hepatitis. In an embodiment of the present invention, the acute hepatitis prediction apparatus includes:
the data acquisition module 11 is used for acquiring relevant data of the acute hepatitis patient;
the data processing module 12 is connected with the data acquisition module 11 and is used for processing the relevant data of the acute hepatitis patient and generating characteristic data;
the prediction module 13 is connected with the data processing module 12 and is used for predicting the generated feature data to obtain a plurality of preliminary non-disease probabilities and disease probabilities;
an integration module 14, connected to the prediction module 13, configured to count the multiple preliminary non-disease probabilities and disease probabilities to obtain final non-disease probabilities and disease probabilities;
specifically, the data obtaining module 11 is configured to obtain data related to a disease through a web browser, a wechat applet, an application program, and the like. Relevant data for diseases include: body index data of a patient, such as pulse rate, heart rate, respiratory rate, blood oxygen saturation, age, height, sex, body mass index, blood pressure (high pressure and low pressure), cholesterol index, emotional state, whether or not drinking alcohol, whether or not having diabetes, whether or not family genetic diabetes history exists, whether or not having hepatitis genetic disease history, whether or not having heart disease genetic disease history, and the like;
specifically, the data processing module 12 processes the continuous data by using regularization, specifically,
(1) using a formula
Figure BDA0002744737410000051
Calculating the middle value of a certain index x;
wherein, x is an original value of a certain index, x _ min is an empirical minimum value of the certain index, x _ max is an empirical maximum value of the certain index, and x' is a middle value of the certain index x;
(2) carrying out binary processing on x' to obtain characteristic data: setting x 'to 1 when x' is greater than 1, and setting x 'to 0 when x' is less than 0;
for example, if the heart rate index is calculated, the heart rate original value is 120, the experience minimum value is 60, and the experience maximum value is 100, the initial value of the heart rate index calculated by the formula in (1) is 1.5, and after binary processing, the heart rate index value is 1, that is, the obtained characteristic data is 1;
specifically, the data processing module 12 is further configured to process the discrete data by using binary coding to obtain feature data, for example, three kinds of emotional states, namely good emotional state, general emotional state, and depressed emotional state, which correspond to decimal codes 0, 1, and 2, respectively. If the emotional state of the patient is general, the value is taken as 1, then the 1 is converted into binary system, and 01 is obtained, namely the generated characteristic data;
specifically, the prediction module 13 is configured to predict the continuous data by using an svm (support Vector machine) model to obtain a preliminary non-morbidity probability p of the continuous data10And probability of illness p11(ii) a Predicting discrete data by adopting a decision tree model to obtain the preliminary non-diseased probability p of the discrete data20And probability of illness p21(ii) a Prediction of continuous data and discrete data using MLP (Multi-layer Perceptron) modelData to obtain combined preliminary non-diseased probability p30And probability of illness p31；
In particular, the integration module 14 is configured to assign a preliminary probability of non-prevalence p of the continuous data10And probability of illness p11Preliminary non-prevalence probability p of discrete data20And probability of illness p21And combined preliminary non-disease probability p30And probability of illness p31Inputting the integrated learning model to predict the final non-ill probability P of the acute hepatitis patient0And probability of illness P1；
The concrete formula is as follows,
Figure BDA0002744737410000061
wherein p is10Probability of non-morbidity, p, predicted for SVM (support Vector machine) model20Probability of non-morbidity, p, predicted for a decision tree model30Probability of non-morbidity predicted for MLP (Multi-layer Perceptin) model, p11Probability of illness, p, predicted for SVM (support Vector machine) model21Probability of illness, p, predicted for decision tree model31Probability of illness predicted for MLP (Multi-layer Perceptin) model, P0The final probability of no illness;
in the above-mentioned non-disease probability calculation formula,
Figure BDA0002744737410000062
predicting the arithmetic mean value of the non-disease probability for the SVM model, the decision tree model and the MLP model,
Figure BDA0002744737410000063
forecasting harmonic mean values of the non-disease probability for the three models of the SVM, the decision tree and the MLP, and performing arithmetic mean value statistics on the two mean values once again to enable the accuracy of the final statistical result to be higher;
Figure BDA0002744737410000064
wherein p is11Probability of illness, p, predicted for SVM (support Vector machine) model21Probability of illness, p, predicted for decision tree model31Probability of illness predicted for MLP (Multi-layer Perceptin) model, p10Probability of non-morbidity, p, predicted for SVM (support Vector machine) model20Probability of non-morbidity, p, predicted for a decision tree model30Probability of non-morbidity predicted for MLP (Multi-layer Perceptin) model, P1The final disease probability;
in the above-mentioned calculation formula of the prevalence probability,
Figure BDA0002744737410000071
predicting the arithmetic mean of the disease probability for the SVM, decision tree and MLP models,
Figure BDA0002744737410000072
and predicting harmonic mean values of the disease probability for the SVM, decision tree and MLP models, and performing arithmetic mean value statistics on the two mean values once again to ensure that the accuracy of the final statistical result is higher.
Referring to fig. 2, fig. 2 is another block diagram of the prediction apparatus for acute hepatitis. In an embodiment of the present invention, the acute hepatitis prediction apparatus includes:
a data acquisition module 21, configured to acquire data related to an acute hepatitis patient;
the data processing module 22 is connected with the data acquisition module 21 and is used for processing the relevant data of the acute hepatitis patient to generate characteristic data;
the prediction module 23 is connected to the data processing module 22 and configured to predict the generated feature data to obtain a plurality of preliminary non-disease probabilities and disease probabilities;
the integration module 24 is connected to the prediction module 23, and is configured to count the multiple preliminary non-diseased probabilities and diseased probabilities to obtain final non-diseased probabilities and diseased probabilities;
the model training module 25 is connected with the prediction module 23 and used for training an SVM model, a decision tree model and an MLP model so as to optimize the prediction algorithms of the three models;
specifically, the data obtaining module 21, the data processing module 22, the prediction module 23, and the integration module 24 correspond to the data obtaining module 11, the data processing module 12, the prediction module 13, and the integration module 14 in fig. 1, respectively, and are not described herein again;
the specific implementation of the model training module 25 is:
collecting related data of a plurality of sick and unaffected individuals, including continuous data such as heart rate and discrete data such as whether to drink alcohol, and forming a sample set; inputting continuous data of the sample set into a training algorithm of an SVM model to obtain optimal weight parameters, inputting discrete data of the sample set into a training algorithm of a decision tree model to construct an optimal classification decision tree, and inputting continuous data and discrete data of the sample set into a training algorithm of an MLP model to obtain optimal weight parameters; by training the model, the high accuracy of predicting the non-morbidity probability and the morbidity probability by adopting the SVN model, the decision tree model and the MLP is ensured.
Referring to fig. 3, fig. 3 is a schematic structural diagram of a prediction system for acute hepatitis. In an embodiment of the present invention, the system for predicting acute hepatitis includes:
the system comprises terminals 1 to N and acute hepatitis prediction devices which are respectively in communication connection with the terminals 1 to N;
the terminals 1 to N include: network terminals such as a mobile terminal, a tablet computer, a notebook computer, a desktop computer and an intelligent television;
specifically, the terminals 1 to N are connected and interacted with the acute hepatitis prediction device through wired or wireless communication modes. For example, the user uses a mobile phone to send data related to acute hepatitis diseases to an acute hepatitis prediction device; the acute hepatitis prediction device predicts after receiving the relevant data and returns the prediction result to the mobile phone. The user can check the prediction result of the acute hepatitis through the mobile phone.
According to the prediction device and the prediction system for the acute hepatitis, provided by the invention, relevant data of an acute hepatitis patient is obtained; processing the relevant data of the acute hepatitis patient to generate characteristic data; predicting the characteristic data to obtain a plurality of preliminary non-disease probability and disease probability; and then, the plurality of preliminary non-illness probabilities and illness probabilities are counted to obtain the final non-illness probability and illness probability of the acute hepatitis patient, so that the acute hepatitis disease can be conveniently and quickly predicted, precious treatment time is strived for the patient, and the probability and death rate of sudden acute hepatitis disease are reduced, thereby achieving the function of disease early warning.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and system may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, a division of modules is merely a division of logical functions, and an actual implementation may have another division, for example, a plurality of modules or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or modules, and may be in an electrical, mechanical or other form.
Modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical modules, may be located in one place, or may be distributed on a plurality of network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
In addition, functional modules in the embodiments of the present application may be integrated into one processing module, or each of the modules may exist alone physically, or two or more modules are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode.
The integrated module, if implemented in the form of a software functional module and sold or used as a separate product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a readable storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method of the embodiments of the present application. And the aforementioned readable storage medium includes: various media capable of storing program codes, such as a U disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk.
It should be noted that, for the sake of simplicity, the above-mentioned method embodiments are described as a series of acts or combinations, but those skilled in the art should understand that the present application is not limited by the described order of acts, as some steps may be performed in other orders or simultaneously according to the present application. Further, those skilled in the art should also appreciate that the embodiments described in the specification are preferred embodiments and that the acts and modules referred to are not necessarily required in this application.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the scope of the present invention, and all modifications and equivalents made by the contents of the specification and drawings or directly/indirectly applied to other related technical fields within the spirit of the present invention are included in the scope of the present invention.

Claims (9)

1. An apparatus for predicting acute hepatitis, the apparatus comprising:
the data acquisition module (11) is used for acquiring relevant data of the patient with acute hepatitis;
the data processing module (12) is connected with the data acquisition module (11) and is used for processing the relevant data of the acute hepatitis patient to generate characteristic data;
the prediction module (13) is connected with the data processing module (12) and is used for predicting the characteristic data to obtain a plurality of preliminary non-sick probabilities and sick probabilities;
and the integration module (14) is connected with the prediction module (13) and is used for counting the plurality of preliminary non-diseased probabilities and diseased probabilities to obtain the final non-diseased probability and diseased probability of the acute hepatitis patient.
2. The apparatus of claim 1, wherein the related data comprises: continuous data and discrete data;
the continuous data includes: pulse rate, heart rate, respiratory rate, blood oxygen saturation, age, height, gender, body mass index, blood pressure, and cholesterol indicator;
the discrete data includes: emotional state, whether alcohol was consumed, whether there was diabetes, whether there was a family history of inherited diabetes, whether there was hepatitis, whether there was a history of hepatitis inherited disease, whether there was heart disease, and whether there was a history of heart disease inherited disease.
3. The apparatus of claim 2, further comprising:
a model training module 15, connected to the prediction module 13, for:
inputting continuous data of the sample set into a training algorithm of an SVM model to obtain an optimal weight parameter;
inputting discrete data of the sample set into a training algorithm of a decision tree model to construct an optimal classification decision tree;
inputting continuous data and discrete data of the sample set into a training algorithm of an MLP model to obtain optimal weight parameters;
wherein the sample set comprises the relevant data for a plurality of diseased and non-diseased individuals.
4. The apparatus of claim 2, wherein the data processing module (12) is configured to:
the regularization processes the continuous data, specifically,
using a formula
Figure FDA0002744737400000021
Calculating a middle value x' of a certain index x;
wherein, x is an original value of a certain index, x _ min is an empirical minimum value of the certain index, x _ max is an empirical maximum value of the certain index, and x' is a middle value of the certain index x;
carrying out binary processing on x' to obtain characteristic data: when x 'is greater than 1, x' is set to 1, and when x 'is less than 0, x' is set to 0.
5. The apparatus of claim 2, wherein the data processing module (12) is further configured to:
and carrying out binary coding processing on the discrete data to obtain characteristic data.
6. The apparatus according to claim 2, wherein the prediction module (13) is configured to:
forecasting the continuous data by adopting an SVM model to obtain the preliminary non-diseased probability and diseased probability of the continuous data;
predicting the discrete data by adopting a decision tree model to obtain the preliminary non-diseased probability and diseased probability of the discrete data; and
and predicting the continuous data and the discrete data by adopting an MLP model to obtain combined initial non-disease probability and disease probability.
7. The apparatus according to claim 6, characterized in that said integration module (14) is configured to:
integrating the preliminary non-prevalence probability and prevalence probability of the continuous data, the preliminary non-prevalence probability and prevalence probability of the discrete data, and the combined preliminary non-prevalence probability and prevalence probability inputLearning model to predict final probability of no disease p0And probability of illness p1Probability of not being affected p0And probability of illness p1The concrete formula is as follows,
Figure FDA0002744737400000022
wherein p is10Probability of non-morbidity, p, predicted for SVM models20Probability of non-morbidity, p, predicted for a decision tree model30Probability of non-morbidity, p, predicted for MLP model11Probability of illness, p, predicted for SVM model21Probability of illness, p, predicted for decision tree model31Probability of illness predicted for MLP model, P0The final probability of no illness;
Figure FDA0002744737400000023
wherein p is11Probability of illness, p, predicted for SVM model21Probability of illness, p, predicted for decision tree model31Probability of illness, p, predicted for MLP model10Probability of non-morbidity, p, predicted for SVM models20Probability of non-morbidity, p, predicted for a decision tree model30Probability of non-morbidity, P, predicted for MLP model1The final prevalence probability.
8. The apparatus according to claim 1, wherein the data acquisition module (11) is configured to:
the data is acquired by a browser and/or a wechat applet and/or an application.
9. A system for predicting acute hepatitis, comprising:
a terminal, and the apparatus of any one of claims 1 to 8 communicatively connected to the terminal;
the terminal includes: at least one of a mobile terminal, a tablet computer, a notebook computer, a desktop computer and an intelligent television.
CN202011162284.6A 2020-10-27 2020-10-27 Prediction device and system for acute hepatitis Active CN112435757B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011162284.6A CN112435757B (en) 2020-10-27 2020-10-27 Prediction device and system for acute hepatitis

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011162284.6A CN112435757B (en) 2020-10-27 2020-10-27 Prediction device and system for acute hepatitis

Publications (2)

Publication Number Publication Date
CN112435757A true CN112435757A (en) 2021-03-02
CN112435757B CN112435757B (en) 2024-07-16

Family

ID=74696160

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011162284.6A Active CN112435757B (en) 2020-10-27 2020-10-27 Prediction device and system for acute hepatitis

Country Status (1)

Country Link
CN (1) CN112435757B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113057589A (en) * 2021-03-17 2021-07-02 上海电气集团股份有限公司 Method and system for predicting organ failure infection diseases and training prediction model

Citations (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080131439A1 (en) * 2005-12-01 2008-06-05 Prometheus Laboratories Inc. Methods of diagnosing inflammatory bowel disease
WO2009024796A1 (en) * 2007-08-23 2009-02-26 University Of Plymouth Method for prediction and diagnosis of medical conditions and apparatus for performing the same
KR20110097528A (en) * 2010-02-25 2011-08-31 고려대학교 산학협력단 Generation predicting system for vaccine preventable disease
US20120059779A1 (en) * 2010-06-15 2012-03-08 Henry Ford Health System Personalized Health Risk Assessment For Critical Care
US20170175169A1 (en) * 2015-12-18 2017-06-22 Min Lee Clinical decision support system utilizing deep neural networks for diagnosis of chronic diseases
KR20180046432A (en) * 2016-10-27 2018-05-09 가톨릭대학교 산학협력단 Method and Apparatus for Classification and Prediction of Pathology Stage using Decision Tree for Treatment of Prostate Cancer
CN108648827A (en) * 2018-05-11 2018-10-12 北京邮电大学 Cardiovascular and cerebrovascular disease Risk Forecast Method and device
CN109473169A (en) * 2018-10-18 2019-03-15 安吉康尔（深圳）科技有限公司 A kind of methods for the diagnosis of diseases, device and terminal device
CN110111901A (en) * 2019-05-16 2019-08-09 湖南大学 Transportable patient classification system based on RNN neural network
CN110236571A (en) * 2019-04-30 2019-09-17 深圳六合六医疗器械有限公司 Fatigue state detection method, device, equipment and storage medium
US20200126662A1 (en) * 2017-02-20 2020-04-23 Ping An Technology (Shenzhen) Co., Ltd. Method, device, and apparatus for detecting disease probability, and computer-readable storage medium
CN111222395A (en) * 2019-10-21 2020-06-02 杭州飞步科技有限公司 Target detection method and device and electronic equipment
CN111312392A (en) * 2020-03-13 2020-06-19 中南大学 Prostate cancer auxiliary analysis method and device based on integration method and electronic equipment
CN111489827A (en) * 2020-04-10 2020-08-04 吉林大学 Thyroid disease prediction modeling method based on associative decision tree
CN111742370A (en) * 2017-05-12 2020-10-02 密歇根大学董事会 Individual and cohort pharmacological phenotype prediction platform
CN111785369A (en) * 2020-06-30 2020-10-16 安徽科大讯飞医疗信息技术有限公司 Diagnostic prediction method, related device and readable storage medium

Patent Citations (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080131439A1 (en) * 2005-12-01 2008-06-05 Prometheus Laboratories Inc. Methods of diagnosing inflammatory bowel disease
WO2009024796A1 (en) * 2007-08-23 2009-02-26 University Of Plymouth Method for prediction and diagnosis of medical conditions and apparatus for performing the same
KR20110097528A (en) * 2010-02-25 2011-08-31 고려대학교 산학협력단 Generation predicting system for vaccine preventable disease
US20120059779A1 (en) * 2010-06-15 2012-03-08 Henry Ford Health System Personalized Health Risk Assessment For Critical Care
US20170175169A1 (en) * 2015-12-18 2017-06-22 Min Lee Clinical decision support system utilizing deep neural networks for diagnosis of chronic diseases
KR20180046432A (en) * 2016-10-27 2018-05-09 가톨릭대학교 산학협력단 Method and Apparatus for Classification and Prediction of Pathology Stage using Decision Tree for Treatment of Prostate Cancer
US20200126662A1 (en) * 2017-02-20 2020-04-23 Ping An Technology (Shenzhen) Co., Ltd. Method, device, and apparatus for detecting disease probability, and computer-readable storage medium
CN111742370A (en) * 2017-05-12 2020-10-02 密歇根大学董事会 Individual and cohort pharmacological phenotype prediction platform
CN108648827A (en) * 2018-05-11 2018-10-12 北京邮电大学 Cardiovascular and cerebrovascular disease Risk Forecast Method and device
CN109473169A (en) * 2018-10-18 2019-03-15 安吉康尔（深圳）科技有限公司 A kind of methods for the diagnosis of diseases, device and terminal device
CN110236571A (en) * 2019-04-30 2019-09-17 深圳六合六医疗器械有限公司 Fatigue state detection method, device, equipment and storage medium
CN110111901A (en) * 2019-05-16 2019-08-09 湖南大学 Transportable patient classification system based on RNN neural network
CN111222395A (en) * 2019-10-21 2020-06-02 杭州飞步科技有限公司 Target detection method and device and electronic equipment
CN111312392A (en) * 2020-03-13 2020-06-19 中南大学 Prostate cancer auxiliary analysis method and device based on integration method and electronic equipment
CN111489827A (en) * 2020-04-10 2020-08-04 吉林大学 Thyroid disease prediction modeling method based on associative decision tree
CN111785369A (en) * 2020-06-30 2020-10-16 安徽科大讯飞医疗信息技术有限公司 Diagnostic prediction method, related device and readable storage medium

Non-Patent Citations (7)

* Cited by examiner, † Cited by third party
Title
CAO, Y等: "Two Classifiers Based on Serum Peptide Pattern for Prediction of HBV-Induced Liver Cirrhosis Using MALDI-TOF MS", 《 BIOMED RESEARCH INTERNATIONAL》, pages 1 - 7 *
刁秀芳;李望晨;: "基于SVM模型和ARIMA模型在拟合病毒性肝炎发病率中的应用", 现代预防医学, no. 09, pages 15 - 18 *
刘迷迷;蔡永铭;: "基于多层感知神经网络的糖尿病并发症预测研究", 软件, no. 10, pages 4 - 8 *
史斌;王建立;: "人工神经网络在肝癌诊疗与预后预测中的应用进展", 癌症进展, no. 12, pages 16 - 19 *
张晔;张晗;尹玢璨;赵玉虹;: "基于电子病历利用支持向量机构建疾病预测模型――以重度急性胰腺炎早期预警为例", 现代图书情报技术, no. 02, pages 88 - 94 *
艾新;毛文涛;田梅;: "基于机器学习技术的在线疾病诊疗方案倾向性识别研究", 中华医学图书情报杂志, no. 07, pages 38 - 43 *
董肖凯;方宏舰;周波;: "区间映射规则下的时间序列相似形态搜索算法――基于改进的正则化损失函数", 价值工程, no. 03, pages 213 - 216 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113057589A (en) * 2021-03-17 2021-07-02 上海电气集团股份有限公司 Method and system for predicting organ failure infection diseases and training prediction model

Also Published As

Publication number Publication date
CN112435757B (en) 2024-07-16

Similar Documents

Publication Publication Date Title
Kim et al. A deep learning model for real-time mortality prediction in critically ill children
Scarpato et al. E-health-IoT universe: A review
EP3255573A1 (en) Clinical decision supporting ensemble system and clinical decison supporting method using the same
Taylan et al. Early prediction in classification of cardiovascular diseases with machine learning, neuro-fuzzy and statistical methods
US11195616B1 (en) Systems and methods using ensemble machine learning techniques for future event detection
KR20200136950A (en) Systems and methods for personalized drug treatment management
US10622099B2 (en) Systems and methods for supporting hospital discharge decision making
JP2020518050A (en) Learning and applying contextual similarity between entities
US20190237192A1 (en) Personal health operating system
Ding et al. The effectiveness of multitask learning for phenotyping with electronic health records data
KR20180058159A (en) Method and apparatus for predicting probability of the outbreak of a disease
Vesselkov et al. Technology and value network evolution in telehealth
CN111612278A (en) Life state prediction method and device, electronic equipment and storage medium
CN111933302B (en) Medicine recommendation method and device, computer equipment and storage medium
Gupta et al. A novel approach based on computing with words for monitoring the heart failure patients
Lin et al. A health informatics transformation model based on intelligent cloud computing–exemplified by type 2 diabetes mellitus with related cardiovascular diseases
Vale-Silva et al. MultiSurv: Long-term cancer survival prediction using multimodal deep learning
CN112435757B (en) Prediction device and system for acute hepatitis
CN113066531B (en) Risk prediction method, risk prediction device, computer equipment and storage medium
CN110570945A (en) AI chronic disease management method, computer storage medium and electronic device
CN114255837A (en) Data query method and device, computer readable storage medium and electronic equipment
Ebada et al. Applying apache spark on streaming big data for health status prediction
KR20160123151A (en) System for providing medical information
Dhand et al. Deep enriched salp swarm optimization based bidirectional-long short term memory model for healthcare monitoring system in big data
US11769592B1 (en) Classifier apparatus with decision support tool

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
GR01 Patent grant
GR01 Patent grant