CN108986915B - Artificial intelligence early prediction method and device for acute kidney injury - Google Patents
Artificial intelligence early prediction method and device for acute kidney injury Download PDFInfo
- Publication number
- CN108986915B CN108986915B CN201810822603.8A CN201810822603A CN108986915B CN 108986915 B CN108986915 B CN 108986915B CN 201810822603 A CN201810822603 A CN 201810822603A CN 108986915 B CN108986915 B CN 108986915B
- Authority
- CN
- China
- Prior art keywords
- aki
- time period
- parameters
- kidney injury
- acute kidney
- 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.)
- Active
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
- G16H50/50—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for simulation or modelling of medical disorders
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Business, Economics & Management (AREA)
- Biophysics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Economics (AREA)
- Data Mining & Analysis (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Biomedical Technology (AREA)
- General Physics & Mathematics (AREA)
- Primary Health Care (AREA)
- Databases & Information Systems (AREA)
- Tourism & Hospitality (AREA)
- Operations Research (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Epidemiology (AREA)
- Pathology (AREA)
- Quality & Reliability (AREA)
- Physiology (AREA)
- Genetics & Genomics (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
Abstract
The invention provides an artificial intelligence early prediction method and device of acute kidney injury, comprising the following steps: acquiring various original parameters, and performing data cleaning and feature extraction on the various original parameters to obtain feature parameters; obtaining the development state of the acute kidney injury AKI in each time period by the characteristic parameters through a genetic algorithm and a random forest algorithm; acquiring an AKI state point; determining the reward value of the AKI in each time period through a Monte Carlo tree and a reinforcement learning algorithm according to the development state of the AKI in each time period, and endowing the reward value of the AKI in each time period to the state point of the AKI; and predicting the incidence probability of the AKI after each time period by the random forest algorithm according to the reward value of the AKI in each time period and various original parameters, thereby predicting the occurrence of the AKI earlier and accurately and establishing an artificial intelligence intervention early prediction mode.
Description
Technical Field
The invention relates to the technical field of medicine, in particular to an artificial intelligence early prediction method and device of acute kidney injury.
Background
Currently, the diagnosis of AKI (Acute Kidney Injury), the amount of creatinine and urine used by DIGO, cannot specifically reflect renal function due to its limitations, the time lag relative to renal Injury, and the nature of the renal Injury.
With the development of medicine, the onset of AKI cannot be predicted early by using biomarkers, fst (fuzzy grade test) functional models, introduction of decision trees, deep learning, machine learning, and the like.
Disclosure of Invention
In view of the above, the present invention provides an artificial intelligence early prediction method and apparatus for acute kidney injury, which can predict the occurrence of AKI earlier and accurately and establish an artificial intelligence intervention early prediction mode.
In a first aspect, the embodiments of the present invention provide an artificial intelligence method for early prediction of acute kidney injury, the method including:
acquiring various original parameters, and performing data cleaning and feature extraction on the various original parameters to obtain feature parameters;
obtaining the development state of the acute kidney injury AKI in each time period by the characteristic parameters through a genetic algorithm and a random forest algorithm;
acquiring a state point of the AKI;
determining the reward value of the AKI in each time period through a Monte Carlo tree and a reinforcement learning algorithm according to the development state of the AKI in each time period, and endowing the reward value of the AKI in each time period to the state point of the AKI;
and predicting the incidence probability of the AKI after each time period by the random forest algorithm according to the reward value of the AKI in each time period and the various original parameters.
In combination with the first aspect, the present embodiments provide a first possible implementation manner of the first aspect, where the types of original parameters include a physiological parameter, a population property parameter, and a drug, the physiological parameter includes one or more of blood pressure, heart rate, body temperature, urine volume, creatinine, platelets, erythrocytes, leukocytes, blood glucose, bilirubin, K +, Na +, Cl ", and a pH value, the population property parameter further includes one or more of age, race, and sex, and the drug includes one or more of furosemide, phenylephrine, amphotericin, and vancomycin.
In combination with the first aspect, the present examples provide a second possible implementation manner of the first aspect, where the respective time periods include 24 hours, 48 hours, and 72 hours.
With reference to the second possible implementation manner of the first aspect, the embodiment of the present invention provides a third possible implementation manner of the first aspect, wherein the predicting, by the random forest algorithm, the probability of occurrence of AKI after each time period by using the reward value of AKI in each time period and the various types of original parameters includes:
AUC greater than and equal to 90% in the 24 hour prediction of AKI;
AUC greater than and equal to 85% in the 48 hour prediction of AKI;
AUC is greater than and equal to 80% in the 72 hour AKI prediction.
With reference to the first aspect, an embodiment of the present invention provides a fourth possible implementation manner of the first aspect, where the feature parameter includes a feature item and a feature value corresponding to the feature item.
In a second aspect, the embodiments of the present invention further provide an artificial intelligence early prediction apparatus for acute kidney injury, the apparatus including:
the extraction unit is used for acquiring various original parameters, and performing data cleaning and feature extraction on the various original parameters to obtain feature parameters;
the first development state acquisition unit is used for acquiring the development states of the acute kidney injury AKI in each time period by the characteristic parameters through a genetic algorithm and a random forest algorithm;
a state point acquiring unit, configured to acquire a state point of the AKI;
the determining unit is used for determining the reward value of the AKI in each time period through a Monte Carlo tree and a reinforcement learning algorithm according to the development state of the AKI in each time period, and endowing the reward value of the AKI in each time period to the state point of the AKI;
and the second development state acquisition unit is used for obtaining the incidence probability of the AKI after each time period by using the random forest algorithm according to the reward value of the AKI in each time period and each type of original parameters.
In combination with the second aspect, the embodiments of the present invention provide a first possible implementation manner of the second aspect, wherein the types of original parameters include physiological parameters, population property parameters and drugs, the physiological parameters include one or more of blood pressure, heart rate, body temperature, urine volume, creatinine, platelets, erythrocytes, leukocytes, blood glucose, bilirubin, K +, Na +, Cl ", and pH value, the population property parameters further include one or more of age, race and sex, and the drugs include one or more of furosemide, phenylephrine, amphotericin, and vancomycin
In combination with the second aspect, the present examples provide a second possible implementation manner of the second aspect, wherein the respective time periods include 24 hours, 48 hours, and 72 hours.
With reference to the second possible implementation manner of the second aspect, an embodiment of the present invention provides a third possible implementation manner of the second aspect, where the second development state acquiring unit includes:
AUC greater than and equal to 90% in the 24 hour prediction of AKI;
AUC greater than and equal to 85% in the 48 hour prediction of AKI;
AUC is greater than and equal to 80% in the 72 hour AKI prediction.
With reference to the second aspect, the present invention provides a fourth possible implementation manner of the second aspect, where the feature parameter includes a feature item and a feature value corresponding to the feature item.
The embodiment of the invention provides an artificial intelligence early prediction method and device of acute kidney injury, comprising the following steps: acquiring various original parameters, and performing data cleaning and feature extraction on the various original parameters to obtain feature parameters; obtaining the development state of the acute kidney injury AKI in each time period by the characteristic parameters through a genetic algorithm and a random forest algorithm; acquiring an AKI state point; determining the reward value of the AKI in each time period through a Monte Carlo tree and a reinforcement learning algorithm according to the development state of the AKI in each time period, and endowing the reward value of the AKI in each time period to the state point of the AKI; and predicting the incidence probability of the AKI after each time period by the random forest algorithm according to the reward value of the AKI in each time period and various original parameters, thereby predicting the occurrence of the AKI earlier and accurately and establishing an artificial intelligence intervention early prediction mode.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
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, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flow chart of a method for early prediction of acute kidney injury with artificial intelligence according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating step S105 of the method for early predicting acute renal injury with artificial intelligence according to an embodiment of the present invention;
FIG. 3 is a diagram illustrating various original parameters according to a first embodiment of the present invention;
fig. 4 is a schematic diagram of an artificial intelligence early prediction apparatus for acute kidney injury according to a second embodiment of the present invention.
Icon:
10-an extraction unit; 20-a first development status acquisition unit; 30-a state point acquisition unit; 40-a determination unit; 50-a second development status acquisition unit.
Detailed Description
To make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some, but not all embodiments of the present invention. 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.
For the understanding of the present embodiment, the following detailed description will be given of the embodiment of the present invention.
The first embodiment is as follows:
fig. 1 is a flowchart of an artificial intelligence early stage prediction method for acute kidney injury according to an embodiment of the present invention.
Referring to fig. 1, the method includes the steps of:
step S101, acquiring various original parameters, and performing data cleaning and feature extraction on the various original parameters to obtain feature parameters;
here, after acquiring various types of original parameters, it is necessary to process the various types of original parameters, that is, perform data cleaning and feature extraction, so as to obtain useful information, that is, feature parameters. For example, doctors obtain characteristic parameters from CT, B-ultrasonic or magnetic resonance, or from blood test and laboratory test sheets, or chinese medicine obtains characteristic parameters by looking at pulse conditions and tongue coating.
Further, the characteristic parameters comprise characteristic items and characteristic values corresponding to the characteristic items.
Here, the feature items include, but are not limited to, vital signs, examination indexes, nursing records, and medication orders, and are obtained by obtaining the feature items and feature values corresponding to the feature items and serving as inputs of the random forest algorithm.
Specifically, in the application, KDIGO (2012) is selected to define the starting point of AKI, and Stage-1 is taken as the prediction starting point, instead of the commonly adopted Stage-2, the starting point is taken as the prediction starting point, Stage-1 is actually the occurrence of AKI, and Stage-2 is already the middle and later period, so that the occurrence of AKI can be predicted earlier through Stage-1.
The present application uses a comprehensive definition of KDIGO (2012) with respect to the classification of AKI classes, rather than only a partial definition as in the prior art. The algorithm of the application has higher practicability due to the early prediction and more comprehensive standard. Before this, the algorithm of the present application also calculated a baseline creatinine value for each patient.
Step S102, obtaining the development state of the acute kidney injury AKI in each time period by the characteristic parameters through a genetic algorithm and a random forest algorithm;
here, by adopting the random forest algorithm, under the condition that the small sample has multiple characteristics, overfitting can be resisted more, and a stable result is output.
Step S103, acquiring the state point of AKI;
step S104, determining the reward value of the AKI in each time period through a Monte Carlo Tree and a reinforcement learning algorithm according to the development state of the AKI in each time period, and endowing the reward value of the AKI in each time period to the state point of the AKI;
here, the respective periods include 24 hours, 48 hours, and 72 hours. Establishing AKI development state, transferring each patient among state points in a training sample, introducing reinforcement learning, performing reward and punishment by taking the incorporated characteristic input of each time point as an action, and calculating a reward value; and then predicting the reward value by adopting a random forest algorithm.
Specifically, the progress state of the AKI in each time period is determined to be good or bad, judgment can be carried out by rewarded values, and if the AKI progresses towards the good direction, the rewarded value is given as + 1; if AKI progresses in a bad direction, a reward value of-1 is assigned; if not, it is 0. The value assigned to reward is then returned to each state point of the AKI.
And S105, predicting the development state of the AKI after each time period by the aid of the random forest algorithm according to the reward values of the AKI in each time period and various original parameters.
Here, the reward value of the AKI in each time period and various original parameters are used as the input of a random forest algorithm, and learning and prediction are carried out through the random forest algorithm to predict the incidence probability of the AKI after each time period.
Further, referring to fig. 3, the various original parameters include physiological parameters, population attribute parameters and drugs, the physiological parameters include one or more of blood pressure, heart rate, body temperature, urine volume, creatinine, platelets, erythrocytes, leukocytes, blood glucose, bilirubin, K +, Na +, Cl-, and pH values, the population attribute parameters further include one or more of age, race, and gender, and the drugs include one or more of furosemide, phenylephrine, amphotericin, and vancomycin.
Here, the physiological parameter includes other parameters in addition to the above parameters, and is not limited to the above parameters; the physiological parameters include other parameters besides the above parameters, and are not limited to the above parameters; the drug includes other drugs in addition to the above drugs, and is not limited to the above drugs.
Further, each time period includes 24 hours, 48 hours, and 72 hours.
Further, referring to fig. 2, step S105 includes the steps of:
step S201, in the AKI prediction of 24 hours, the AUC is more than or equal to 90%;
step S202, AUC is greater than or equal to 85% in AKI prediction of 48 hours;
in step S203, AUC is 80% or higher in the AKI prediction for 72 hours.
Here, auc (area under the Curve of ROC) is the area under the ROC Curve, and is a criterion for determining the quality of the two-class prediction model.
The embodiment of the invention provides an artificial intelligent early prediction method of acute kidney injury, which comprises the following steps: acquiring various original parameters, and performing data cleaning and feature extraction on the various original parameters to obtain feature parameters; obtaining the development state of the acute kidney injury AKI in each time period by the characteristic parameters through a genetic algorithm and a random forest algorithm; acquiring an AKI state point; determining the reward value of the AKI in each time period according to the development state of the AKI in each time period, and endowing the reward value of the AKI in each time period to the state point of the AKI; and predicting the incidence probability of the AKI after each time period by the random forest algorithm according to the reward value of the AKI in each time period and various original parameters, thereby predicting the occurrence of the AKI earlier and accurately and establishing an artificial intelligence intervention early prediction mode.
Example two:
fig. 4 is a schematic diagram of an artificial intelligence early prediction apparatus for acute kidney injury according to a second embodiment of the present invention.
Referring to fig. 4, the apparatus includes:
the extraction unit 10 is used for acquiring various original parameters, and performing data cleaning and feature extraction on the various original parameters to obtain feature parameters;
the first development state acquisition unit 20 is configured to obtain the development states of the acute kidney injury AKI in each time period by using the characteristic parameters through a genetic algorithm and a random forest algorithm;
a state point acquiring unit 30, configured to acquire a state point of AKI;
a determining unit 40, configured to determine the reward value of each time period AKI according to the development state of each time period AKI, and assign the reward value of each time period AKI to the state point of the AKI;
and the second development state acquisition unit 50 is used for predicting the incidence probability of the AKI after each time period by using the random forest algorithm on the reward value of the AKI in each time period and various original parameters.
Further, the various original parameters comprise physiological parameters, population attribute parameters and medicines, the physiological parameters comprise one or more of blood pressure, heart rate, body temperature, urine volume, creatinine, platelets, erythrocytes, leukocytes, blood glucose, bilirubin, K +, Na +, Cl-and pH values, the population attribute parameters further comprise one or more of age, race and gender, and the medicines comprise one or more of furosemide, phenylephrine, amphotericin and vancomycin.
Further, each time period includes 24 hours, 48 hours, and 72 hours.
Further, the second development state acquiring unit 50 includes:
AUC greater than and equal to 90% in 24-hour AKI prediction;
AUC greater than and equal to 85% in the 48 hour AKI prediction;
AUC was greater than and equal to 80% in the AKI prediction at 72 hours.
Further, the characteristic parameter includes a characteristic item and a characteristic value corresponding to the characteristic item.
The embodiment of the invention provides an artificial intelligent early prediction device of acute kidney injury, which comprises: acquiring various original parameters, and performing data cleaning and feature extraction on the various original parameters to obtain feature parameters; obtaining the development state of the acute kidney injury AKI in each time period by the characteristic parameters through a genetic algorithm and a random forest algorithm; acquiring an AKI state point; determining the reward value of the AKI in each time period through a Monte Carlo tree and a reinforcement learning algorithm according to the development state of the AKI in each time period, and endowing the reward value of the AKI in each time period to the state point of the AKI; and predicting the incidence probability of the AKI after each time period by the random forest algorithm according to the reward value of the AKI in each time period and various original parameters, thereby predicting the occurrence of the AKI earlier and accurately and establishing an artificial intelligence intervention early prediction mode.
The embodiment of the present invention further provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the steps of the artificial intelligence early prediction method for acute kidney injury provided by the above embodiments are implemented.
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, performs the steps of the artificial intelligence early stage prediction method for acute kidney injury of the embodiments.
The computer program product provided in the embodiment of the present invention includes a computer-readable storage medium storing a program code, where instructions included in the program code may be used to execute the method described in the foregoing method embodiment, and specific implementation may refer to the method embodiment, which is not described herein again.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the system and the apparatus described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In addition, in the description of the embodiments of the present invention, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, e.g., as meaning either a fixed connection, a removable connection, or an integral connection; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium 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 according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only for convenience of description and simplicity of description, but do not indicate or imply that the device or element being referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus, should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
Finally, it should be noted that: the above-mentioned embodiments are only specific embodiments of the present invention, which are used for illustrating the technical solutions of the present invention and not for limiting the same, and the protection scope of the present invention is not limited thereto, although the present invention is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: any person skilled in the art can modify or easily conceive the technical solutions described in the foregoing embodiments or equivalent substitutes for some technical features within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the embodiments of the present invention, and they should be construed as being included therein. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. An artificial intelligence early prediction method of acute kidney injury, which is characterized by comprising the following steps:
acquiring various original parameters, and performing data cleaning and feature extraction on the various original parameters to obtain feature parameters;
obtaining the development state of the acute kidney injury AKI in each time period by the characteristic parameters through a genetic algorithm and a random forest algorithm;
acquiring a state point of the AKI;
determining the reward value of the AKI in each time period through a Monte Carlo tree algorithm according to the development state of the AKI in each time period, and endowing the reward value of the AKI in each time period to the state point of the AKI;
and predicting the incidence probability of the AKI after each time period by the random forest algorithm according to the reward value of the AKI in each time period and the various original parameters.
2. The method of claim 1, wherein the various types of original parameters include physiological parameters, population property parameters and drugs, the physiological parameters include one or more of blood pressure, heart rate, body temperature, urine volume, creatinine, platelets, erythrocytes, leukocytes, blood glucose, bilirubin, K +, Na +, Cl-, and pH values, the population property parameters further include one or more of age, race, and gender, and the drugs include one or more of furosemide, phenylephrine, amphotericin, and vancomycin.
3. The intelligent early prediction method for acute kidney injury according to claim 1, wherein the respective time periods include 24 hours, 48 hours and 72 hours.
4. The artificial intelligence early prediction method for acute kidney injury according to claim 3, wherein the step of predicting the probability of onset of AKI after each time period by the random forest algorithm using the reward value of AKI in each time period and the various types of original parameters comprises:
AUC greater than and equal to 90% in the 24 hour prediction of AKI;
AUC greater than and equal to 85% in the 48 hour prediction of AKI;
AUC is greater than and equal to 80% in the 72 hour AKI prediction.
5. The method of claim 1, wherein the characteristic parameters comprise characteristic terms and characteristic values corresponding to the characteristic terms.
6. An artificial intelligence early stage prediction device of acute kidney injury, characterized in that the device comprises:
the extraction unit is used for acquiring various original parameters, and performing data cleaning and feature extraction on the various original parameters to obtain feature parameters;
the first development state acquisition unit is used for acquiring the development states of the acute kidney injury AKI in each time period by the characteristic parameters through a genetic algorithm and a random forest algorithm;
a state point acquiring unit, configured to acquire a state point of the AKI;
a determining unit, configured to determine the reward value of the AKI in each time period through a monte carlo tree algorithm according to the development state of the AKI in each time period, and assign the reward value of the AKI in each time period to a state point of the AKI;
and the second development state acquisition unit is used for predicting the incidence probability of the AKI after each time period by the random forest algorithm according to the reward value of the AKI in each time period and each type of original parameters.
7. The apparatus of claim 6, wherein the types of original parameters comprise physiological parameters, population property parameters and drugs, the physiological parameters comprise one or more of blood pressure, heart rate, body temperature, urine volume, creatinine, platelets, erythrocytes, leukocytes, blood glucose, bilirubin, K +, Na +, Cl-and pH values, the population property parameters further comprise one or more of age, race and sex, and the drugs comprise one or more of furosemide, phenylephrine, amphotericin and vancomycin.
8. The apparatus for early prediction of artificial intelligent acute kidney injury according to claim 6, wherein the respective time periods include 24 hours, 48 hours and 72 hours.
9. The apparatus for early prediction of artificial intelligence acute kidney injury according to claim 8, wherein the second development state obtaining unit includes:
AUC greater than and equal to 90% in the 24 hour prediction of AKI;
AUC greater than and equal to 85% in the 48 hour prediction of AKI;
AUC is greater than and equal to 80% in the 72 hour AKI prediction.
10. The apparatus for early prediction of artificial intelligence acute kidney injury of claim 6, wherein the characteristic parameters include characteristic terms and characteristic values corresponding to the characteristic terms.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810822603.8A CN108986915B (en) | 2018-07-24 | 2018-07-24 | Artificial intelligence early prediction method and device for acute kidney injury |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810822603.8A CN108986915B (en) | 2018-07-24 | 2018-07-24 | Artificial intelligence early prediction method and device for acute kidney injury |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108986915A CN108986915A (en) | 2018-12-11 |
| CN108986915B true CN108986915B (en) | 2021-07-06 |
Family
ID=64550270
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810822603.8A Active CN108986915B (en) | 2018-07-24 | 2018-07-24 | Artificial intelligence early prediction method and device for acute kidney injury |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108986915B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111640512B (en) * | 2020-06-02 | 2023-08-15 | 戴松世 | Kidney substitution therapy starting strategy evaluation method and device and electronic equipment |
| CN113012814A (en) * | 2021-03-10 | 2021-06-22 | 浙江大学医学院附属邵逸夫医院 | Acute kidney injury volume responsiveness prediction method and system |
| CN115295147A (en) * | 2022-08-04 | 2022-11-04 | 戴松世 | Renal failure AI doctor system and renal failure medical system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104871004A (en) * | 2012-12-20 | 2015-08-26 | 诺华股份有限公司 | Acute kidney injury |
| CN105556305A (en) * | 2013-06-05 | 2016-05-04 | 阿斯图特医药公司 | Methods and compositions for diagnosis and prognosis of renal injury and renal failure |
| CN107908819A (en) * | 2017-10-19 | 2018-04-13 | 深圳和而泰智能控制股份有限公司 | The method and apparatus for predicting User Status change |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2798713A1 (en) * | 2010-05-10 | 2011-11-17 | Intrinsic Lifesciences Llc | Markers for acute kidney injury |
| WO2013184868A1 (en) * | 2012-06-06 | 2013-12-12 | The Cleveland Clinic Foundation | Prediction of acute kidney injury from a post-surgical metabolic blood panel |
-
2018
- 2018-07-24 CN CN201810822603.8A patent/CN108986915B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104871004A (en) * | 2012-12-20 | 2015-08-26 | 诺华股份有限公司 | Acute kidney injury |
| CN105556305A (en) * | 2013-06-05 | 2016-05-04 | 阿斯图特医药公司 | Methods and compositions for diagnosis and prognosis of renal injury and renal failure |
| CN107908819A (en) * | 2017-10-19 | 2018-04-13 | 深圳和而泰智能控制股份有限公司 | The method and apparatus for predicting User Status change |
Non-Patent Citations (3)
| Title |
|---|
| "Fuzzy Modeling to Predict Short and Long-Term Mortality Among Patients with Acute Kidney Injury";Vanessa S. Cunha等;《2016 IEEE International Conference on Fuzzy Systems》;20161231;全文 * |
| "Using Context Ontology and Linear SVM for Chronic Kidney Disease Prediction";Hatim Guermah等;《2018 Association for Computing Machinery》;20180505;全文 * |
| "前列腺电特性成像研究现状及展望";刘阳,戴松世等;《生物医学工程学杂志》;20121031;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108986915A (en) | 2018-12-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zohora et al. | Forecasting the risk of type ii diabetes using reinforcement learning | |
| CN108986915B (en) | Artificial intelligence early prediction method and device for acute kidney injury | |
| US20220084633A1 (en) | Systems and methods for automatically identifying a candidate patient for enrollment in a clinical trial | |
| US20220084662A1 (en) | Systems and methods for automatically notifying a caregiver that a patient requires medical intervention | |
| EP3281132B1 (en) | System for laboratory values automated analysis and risk notification in intensive care unit | |
| Moreno-Sánchez | Data-driven early diagnosis of chronic kidney disease: development and evaluation of an explainable AI model | |
| Singh et al. | Data mining classifier for predicting diabetics | |
| CN111128327B (en) | Hypoglycemia early warning method and device | |
| CN117612703A (en) | Diabetes retinopathy classification method based on medical test indexes | |
| CN117045889A (en) | End stage renal disease hemodialysis blood pressure mode identification and intervention system and related device | |
| CN113345584A (en) | Disease prognosis risk prediction model training method and device and electronic equipment | |
| CN117133471A (en) | Blood transfusion prediction method, system, equipment and medium for acute aortic dissection diseases | |
| WO2021260171A2 (en) | System and method for peri-anaesthetic risk evaluation | |
| EP3327598A1 (en) | A system and a method for automatically analyzing continuous glucose monitoring data indicative of glucose level in a bodily fluid | |
| WO2021247557A1 (en) | Artificial intelligence and/or machine learning based systems, devices, and methods for designing patient prescriptions | |
| CN114049952A (en) | Intelligent prediction method and device for postoperative acute kidney injury based on machine learning | |
| CN113902186B (en) | Patient death risk prediction method, system, terminal and readable storage medium based on electronic medical records | |
| Srimedha et al. | A comprehensive machine learning based pipeline for an accurate early prediction of sepsis in ICU | |
| Pal et al. | Future of healthcare—sensor data-driven prognosis | |
| US20240321447A1 (en) | Method and System for Personalized Prediction of Infection and Sepsis | |
| CN112037918B (en) | Chronic disease medical insurance cost prediction method fusing complication risks and related equipment | |
| US11830340B1 (en) | Method and system for secretion analysis embedded in a garment | |
| CN117009839A (en) | Patient clustering method and device based on heterogeneous hypergraph neural network | |
| CN113782187B (en) | Index data processing method, related equipment and medium | |
| Cattinelli et al. | Computational intelligence for the Balanced Scorecard: Studying performance trends of hemodialysis clinics |
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 |