CN114283947B - Health management method and system suitable for surgical patients - Google Patents
Health management method and system suitable for surgical patients Download PDFInfo
- Publication number
- CN114283947B CN114283947B CN202111617376.3A CN202111617376A CN114283947B CN 114283947 B CN114283947 B CN 114283947B CN 202111617376 A CN202111617376 A CN 202111617376A CN 114283947 B CN114283947 B CN 114283947B
- Authority
- CN
- China
- Prior art keywords
- strategy
- historical
- blood transfusion
- model
- data set
- 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
Abstract
The invention discloses a health management method and system suitable for a surgical patient. The invention comprises the following steps: acquiring a hospital historical user data set, dividing the historical user data set into a training number set and a test data set for model training, and training to obtain a blood transfusion amount prediction model; inputting a blood transfusion quantity prediction model according to the related information of the current patient blood transfusion, mutually fusing the collected health strategy set and the hospital historical user data set to obtain a basic strategy map, inputting the individual blood transfusion quantity of the patient to the sequencing strategy model for sequencing learning, and generating a Top-N recommendation strategy list. The invention additionally incorporates the target value of the postoperative related index on the basis of incorporating the preoperative related index of the patient by the obtained recommended value of the blood transfusion volume, determines the target value of the postoperative related index with the aim of optimal prognosis of the patient, and substitutes the parameter value of the set postoperative related index into the blood transfusion volume prediction model according to the set parameter value of the postoperative related index to predict and recommend the intraoperative blood transfusion volume of the patient for reference of a clinician.
Description
Technical Field
The invention belongs to the technical field of postoperative management, particularly relates to the technical field of medical informatization processing, and particularly relates to a health management method and system suitable for an operation patient.
Background
The method can accurately predict the blood transfusion amount of a patient before operation, and is not only related to related indexes before operation, but also related to target values of related indexes after operation, such as target values of hemoglobin after operation. Previous studies have been based on pre-operative or intra-operative relevant indices, such as restricted blood transfusion and non-restricted blood transfusion strategies, which decide whether to transfuse blood based on pre-operative hemoglobin or intra-operative hemoglobin, with less consideration given to target values of the post-operative relevant indices.
Therefore, the recommended blood transfusion amount value obtained in the application document is additionally taken into the target value of the postoperative relevant index on the basis of the preoperative relevant index of the patient, the target value of the postoperative relevant index is determined with the aim of optimal prognosis of the patient, the related condition of the patient mastered before the operation and the expected development of the prognosis are comprehensively considered, and the recommended blood transfusion amount value has a better clinical reference value for a clinician.
Disclosure of Invention
The invention aims to provide a health management method and system suitable for a surgical patient, which are used for supplementing and bringing in a post-operation related index target value on the basis of bringing in a pre-operation related index of the patient by an obtained blood transfusion volume recommended value and determining the post-operation related index target value by taking the best prognosis of the patient as a target, so that the problem of low clinical reference value caused by the fact that the existing hospital only pays attention to the related indexes before and during the operation and does not pay attention to the post-operation index is solved.
In order to solve the technical problems, the invention is realized by the following technical scheme:
the invention relates to a health management method suitable for a surgical patient, which comprises the following steps:
step S1: acquiring a hospital historical user data set, and dividing the historical user data set into a training set and a test data set;
step S2: collecting a large number of patient medical records, corresponding treatment methods and postoperative corresponding methods to manufacture a health strategy set;
and step S3: extracting characteristic parameters in a training set, and extracting a characteristic parameter set suitable for representing the blood transfusion volume of a single user from a plurality of characteristics according to the distribution characteristics, the relevant characteristics and the importance of the characteristics to train a blood transfusion volume prediction model;
and step S4: verifying the trained blood transfusion amount prediction model by adopting a test data set;
step S5: inputting the relevant information of the current patient blood transfusion into a blood transfusion quantity prediction model to determine the blood transfusion quantity of the individual patient;
step S6: fusing the collected health strategy set and the hospital historical user data set to obtain a basic strategy map;
step S7: embedding the entities in the basic strategy map into an n-dimensional space through a Node2Vec network representation algorithm of deep learning;
step S8: calculating the similarity between strategy maps, and constructing a training model as the input of a sequencing strategy model;
step S9: inputting the blood transfusion volume of the individual patient to a sequencing strategy model for sequencing learning to generate a Top-N recommendation strategy list;
step S10: and pushing the generated user postoperative health management strategy list to a user mobile intelligent terminal.
As a preferable technical solution, in the step S1, the user data set takes historical blood usage information of a predetermined department as input, a curve formed by discrete values arranged in time is formed, whether the curve fluctuates is judged, if the curve fluctuates, a multi-step difference is used for performing stabilization adjustment until a curve stabilization difference parameter is zero, an autoregressive moving average time sequence model is established according to smooth time series information, and an order is determined.
As a preferred technical solution, in the step S2, preprocessing is required after the hospital historical user data set is acquired; the pretreatment comprises the following specific steps:
step S11: cleaning a historical user data set acquired on hospital equipment;
step S12: carrying out semantic analysis on the cleaned data;
step S13: labeling labels for the medical record, the treatment scheme and the postoperative coping method data of the user according to the semantic analysis result;
step S14: and constructing a basic knowledge graph according to the relation between the labels and the data.
As a preferred technical solution, the historical blood usage information includes historical preoperative blood loss information, historical intraoperative blood transfusion information, and historical postoperative blood index information.
As a preferred technical solution, in step S7, the basic knowledge graph is described in the form of (entity, attribute value) triples, the entity is embedded in the n-dimensional space through the Node2Vec network representation algorithm, and corresponding vectors are generated to obtain an entity vector set and an attribute vector set, and the entity vector set and the attribute vector set are translated by using a TransE algorithm, so as to obtain a triplet vector set capable of quickly calculating the voice similarity of the entity.
As a preferred technical solution, in step S8, node2Vec is used to perform knowledge-graph network feature learning, and the entity is mapped to an n-dimensional space, and in a low-dimensional vector space, the closer the entity in geometry is, the greater the correlation is, and the cosine identity of the vector is used to calculate the entitye i Ande j correlation between themSim(e i ,e j )；
Wherein the content of the first and second substances,Sim(e i ,e j ) The calculation formula of (2) is as follows:
as a preferred technical solution, in step S9, the constructed training is used as a training input of a ranking model, a Top-N recommendation list is generated through a decision function, and a weight proportion set of N-dimensional features to ranking results is obtained to construct a feedback model.
The invention relates to a health management system suitable for surgical patients, which comprises a historical data acquisition module, a feature extraction module, a model training module, a strategy map construction module, a sequencing strategy model generation module, an information feedback unit and a health strategy recommendation unit, wherein the historical data acquisition module is used for acquiring historical data;
the historical data acquisition module, the feature extraction module, the model training module, the information feedback unit and the health strategy recommendation unit are sequentially connected;
the strategy map building module, the sequencing strategy model generating module, the information feedback unit and the health strategy recommending unit are sequentially connected;
the historical data acquisition module is used for acquiring a hospital historical user data set and dividing the historical user data set into a training set and a test data set;
the characteristic extraction module is used for acquiring original characteristics from the training data set and training the original characteristics through a gradient lifting decision tree GBDT algorithm to acquire corresponding combined characteristics;
the model training module is used for learning and verifying by using a training data set and a test data set and adopting a model training algorithm to obtain a mapping relation between the at least one characteristic parameter set and the blood transfusion volume of the single user as a blood transfusion volume prediction model;
the strategy map building module is used for mutually fusing the collected health strategy set and the hospital historical user data set to build a strategy map;
the sequencing strategy model generation module generates a corresponding Top-N recommendation list according to the blood transfusion volume of the individual patient;
the information feedback unit is used for inputting the data information of the current patient to the model training module and feeding back the result information processed by the model training module to the intelligent terminal of the doctor;
and the health strategy recommending unit is used for acquiring feedback information of a doctor to generate a postoperative health management strategy of the user and pushing the postoperative health management strategy to the patient.
As a preferred technical solution, the model training module at least includes a first model training subunit and a second model training subunit:
the first model training subunit is used for learning and verifying by using a training data set and a model training algorithm to obtain a mapping relation between a second characteristic parameter set and the blood loss of the single user as a blood loss prediction model;
and the second model training subunit is used for learning and verifying by using a training data set and adopting a model training algorithm to obtain a mapping relation between a characteristic parameter set and the blood transfusion volume of the single user as a blood transfusion volume prediction model, wherein the characteristic parameter set comprises the blood transfusion volume of the single user predicted according to the blood transfusion volume prediction model.
The invention has the following beneficial effects:
the invention additionally incorporates the target value of the postoperative related index on the basis of incorporating the preoperative related index of the patient by the obtained recommended value of the blood transfusion amount, determines the target value of the postoperative related index by taking the optimal prognosis of the patient as a target, substitutes the parameter value of the set postoperative related index into a blood transfusion amount prediction model according to the set parameter value of the postoperative related index, and predicts and recommends the intraoperative blood transfusion amount of the patient for reference of a clinician.
Of course, it is not necessary for any product in which the invention is practiced to achieve all of the above-described advantages at the same time.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flow chart illustrating the steps of a health management method for a surgical patient according to the present invention;
FIG. 2 is a schematic flowchart of step S2 of the health management method for surgical patients according to the present invention;
fig. 3 is a block diagram of a health management system suitable for a surgical patient according to the present invention.
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.
Referring to fig. 1, the present invention is a method for health management of a surgical patient, comprising the following steps:
step S1: acquiring a historical user data set of a hospital, and dividing the historical user data set into a training set and a testing data set;
after the historical user data set is obtained, the training data set and the testing data set are divided according to a preset proportion value. The predetermined ratio may be 7: 3, 8: 2, 12: 4, or other ratios, and is not limited herein.
Step S2: collecting a large number of patient medical records, corresponding treatment methods and postoperative corresponding methods to manufacture a health strategy set;
and step S3: extracting characteristic parameters in a training set, and extracting a characteristic parameter set suitable for representing the blood transfusion volume of a single user from a plurality of characteristics according to the distribution characteristics, the relevant characteristics and the importance of the characteristics to train a blood transfusion volume prediction model;
and (4) establishing a blood transfusion amount prediction model based on massive historical user data. In an embodiment of the present application, a historical user data set is obtained over a predetermined period of time for training and validating/testing a blood transfusion prediction model. The preset time length is a preset time range, and the time range can be selected according to the requirement of the learning model. For example, the patient electronic record data of a certain hospital 2011-2017 is selected as the historical user data set. The historical user data set is a data set of patients who have undergone transfusion therapy collected by a hospital information system, for example, basic information (age, height, weight, sex) of patients, blood routine examination results, pre-medical transfusion or pre-operation vital sign information, biochemical examination results, patient diagnosis results, department affiliation information, and the like. The basic information (age, height, weight and sex) of the patient can be defined as a user basic information data subset, and the blood routine before internal medicine blood transfusion, blood gas, blood coagulation, biochemistry and vital signs, the blood routine after blood transfusion and the like can be defined as a user examination result data subset; or blood routine, blood gas, blood coagulation, biochemistry, vital signs before operation, blood loss after operation, hemoglobin value or hematocrit value after operation and the like can be defined as the data subset of the examination result of the user before and after operation; patient diagnosis results can be defined as a user diagnosis information data subset; and historical patient visit data, etc. may be defined as a subset of the user's past medical history data.
And step S4: verifying the trained blood transfusion amount prediction model by adopting a test data set;
step S5: inputting the relevant information of the current patient blood transfusion into a blood transfusion quantity prediction model to determine the blood transfusion quantity of the individual patient;
step S6: fusing the collected health strategy set and the hospital historical user data set to obtain a basic strategy map;
step S7: embedding the entities in the basic strategy map into an n-dimensional space through a Node2Vec network representation algorithm of deep learning;
step S8: calculating the similarity between strategy maps, and constructing a training model as the input of a sequencing strategy model;
step S9: inputting the blood transfusion volume of the patient individual to a sequencing strategy model for sequencing learning to generate a Top-N recommendation strategy list;
step S10: and pushing the generated user postoperative health management strategy list to a user mobile intelligent terminal.
In step S1, a user data set takes historical blood usage information of a preset department as input, a curve formed by discrete values arranged according to time is formed, whether the curve fluctuates or not is judged, if the curve fluctuates, multi-order difference is used for carrying out stabilization adjustment until a curve stabilization difference parameter is zero, an autoregressive moving average time sequence model is established according to smooth time sequence information, and the order is determined.
Referring to fig. 2, in step S2, a hospital historical user data set needs to be preprocessed after being acquired; the pretreatment comprises the following specific steps:
step S11: cleaning a historical user data set acquired on hospital equipment;
step S12: carrying out semantic analysis on the cleaned data;
step S13: labeling labels for the medical record, the treatment scheme and the postoperative coping method data of the user according to the semantic analysis result;
step S14: and constructing a basic knowledge graph according to the relation between the labels and the data.
The historical blood usage information comprises historical preoperative blood loss information, historical intraoperative blood transfusion information and historical postoperative blood index information.
In step S7, the basic knowledge graph is described in the form of (entity, attribute value) triples, the entity is embedded in an n-dimensional space through a Node2Vec network representation algorithm, and a corresponding vector is generated to obtain an entity vector set and an attribute vector set, and the entity vector set and the attribute vector set are translated by using a TransE algorithm, thereby obtaining a triplet vector set capable of rapidly calculating the voice similarity of the entity.
In step S8, node2Vec is used for learning knowledge graph network characteristics, entities are mapped to n-dimensional space, in low-dimensional vector space, the closer the entity correlation in geometry is, the larger the entity correlation is, and the cosine identity degree of the vector is used for calculating the entitiese i Ande j correlation between themSim(e i ,e j )；
Wherein the content of the first and second substances,Sim(e i ,e j ) The calculation formula of (2) is as follows:
in step S9, the constructed training is used as a training input of the ranking model, a Top-N recommendation list is generated through a decision function, and a weight proportion set of the N-dimensional features to the ranking result is obtained to construct a feedback model.
Referring to fig. 3, the present invention is a health management system for surgical patients, which includes a historical data acquisition module, a feature extraction module, a model training module, a strategy map construction module, a ranking strategy model generation module, an information feedback unit, and a health strategy recommendation unit;
the historical data acquisition module, the feature extraction module, the model training module, the information feedback unit and the health strategy recommendation unit are sequentially connected;
the strategy map building module, the sequencing strategy model generating module, the information feedback unit and the health strategy recommending unit are sequentially connected;
the system comprises a historical data acquisition module, a training data collection module and a test data collection module, wherein the historical data acquisition module is used for acquiring a hospital historical user data set and dividing the historical user data set into a training set and a test data set; the user basic information data may include parameters such as age, height, weight, sex, etc. of the patient; the first data of the user's pre-and post-operative examination results may include, for example: blood convention before surgery, blood gas, blood coagulation, biochemistry, vital signs, blood loss after surgery, and the like; the user diagnostic information data subset may include, for example, diagnostic data during a patient visit; the user's past medical history data subset may include, for example, data of a patient's historical visits; the user historical procedure data subset may include, for example, data of a patient's historical procedures, and the like.
The characteristic extraction module is used for acquiring original characteristics from the training data set and training the original characteristics through a gradient lifting decision tree GBDT algorithm to obtain corresponding combined characteristics;
the model training module is used for learning and verifying by using a training data set and a test data set and adopting a model training algorithm to obtain a mapping relation between at least one characteristic parameter set and the blood transfusion volume of a single user as a blood transfusion volume prediction model;
the strategy map building module is used for mutually fusing the collected health strategy set and the hospital historical user data set to build a strategy map;
the sequencing strategy model generation module generates a corresponding Top-N recommendation list according to the blood transfusion volume of the individual patient;
the information feedback unit is used for inputting the data information of the current patient to the model training module and feeding back the result information processed by the model training module to the intelligent terminal of the doctor;
and the health strategy recommending unit is used for acquiring feedback information of a doctor to generate a postoperative health management strategy of the user and pushing the postoperative health management strategy to the patient.
The model training module at least comprises a first model training subunit and a second model training subunit:
the first model training subunit is used for learning and verifying by using a training data set and adopting a model training algorithm to obtain a mapping relation between a second characteristic parameter set and the blood loss of the single user as a blood loss prediction model; for example, a user basic information data subset, a user examination result data subset, a user diagnosis information data subset, a user past medical history data subset, and the like. The user basic information data subset can comprise parameters such as age, height, weight, sex and the like of the patient; the user inspection result data subset may include, for example: blood convention before transfusion, blood gas, coagulation, biochemistry, vital signs, blood convention after transfusion, and the like; the user diagnostic information data subset may include, for example, diagnostic data during a patient visit; the user past medical history data subset may include, for example, data of a patient's historical visits.
And the second model training subunit is used for learning and verifying by using a training data set and adopting a model training algorithm to obtain a mapping relation between a characteristic parameter set and the blood transfusion volume of the single user as a blood transfusion volume prediction model, wherein the characteristic parameter set comprises the blood transfusion volume of the single user predicted according to the blood transfusion volume prediction model.
It should be noted that, in the above system embodiment, each included unit is only divided according to functional logic, but is not limited to the above division as long as the corresponding function can be implemented; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention.
In addition, those skilled in the art can understand that all or part of the steps in the method for implementing the embodiments described above can be implemented by a program to instruct related hardware, and the corresponding program can be stored in a computer readable storage medium.
The preferred embodiments of the invention disclosed above are intended to be illustrative only. The preferred embodiments are not intended to be exhaustive or to limit the invention to the precise embodiments disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best utilize the invention. The invention is limited only by the claims and their full scope and equivalents.
Claims (4)
1. A method of health management for a surgical patient, comprising the steps of:
step S1: acquiring a hospital historical user data set, and dividing the historical user data set into a training set and a test data set;
step S2: collecting a large number of patient medical records, corresponding treatment methods and postoperative corresponding methods to manufacture a health strategy set;
and step S3: extracting characteristic parameters in a training set, and extracting a characteristic parameter set suitable for representing the blood transfusion volume of a single user from a plurality of characteristics according to the distribution characteristics, the relevant characteristics and the importance of the characteristics to train a blood transfusion volume prediction model;
and step S4: verifying the trained blood transfusion amount prediction model by adopting a test data set;
step S5: inputting the relevant information of the current patient blood transfusion into a blood transfusion quantity prediction model to determine the blood transfusion quantity of the individual patient;
step S6: fusing the collected health strategy set and the hospital historical user data set to obtain a basic strategy map;
step S7: embedding the entities in the basic strategy map into an n-dimensional space through a Node2Vec network representation algorithm of deep learning;
step S8: calculating the similarity between strategy maps, and constructing a training model as the input of a sequencing strategy model;
step S9: inputting the blood transfusion volume of the individual patient to a sequencing strategy model for sequencing learning to generate a Top-N recommendation strategy list;
step S10: pushing the generated user postoperative health management strategy list to a user mobile intelligent terminal;
in the step S1, a user data set takes historical blood usage historical information of a preset department as input, a curve formed by discrete values arranged according to time is formed, whether the curve fluctuates or not is judged, if the curve fluctuates, multi-order difference is used for carrying out stabilization adjustment until a curve stabilization difference parameter is zero, an autoregressive moving average time sequence model is established according to smooth time sequence information, and the order is determined;
the historical information of the historical blood usage comprises historical preoperative blood loss information, historical intraoperative blood transfusion information and historical postoperative blood index information;
in the step S2, the hospital historical user data set needs to be preprocessed after being acquired; the pretreatment comprises the following specific steps:
step S11: cleaning a historical user data set acquired on hospital equipment;
step S12: carrying out semantic analysis on the cleaned data;
step S13: labeling labels for the medical record, the treatment scheme and the postoperative coping method data of the user according to the semantic analysis result;
step S14: constructing a basic knowledge graph according to the relation between the labels and the data;
in step S7, the basic knowledge graph is described in the form of (entity, attribute value) triples, the entity is embedded into an n-dimensional space through a Node2Vec network representation algorithm, and generates corresponding vectors to obtain an entity vector set and an attribute vector set, and the entity vector set and the attribute vector set are translated by using a TransE algorithm, so as to obtain a triplet vector set capable of rapidly calculating the voice similarity of the entity;
in the step S8, node2Vec is used for learning the network characteristics of the knowledge graph, the entity is mapped to the n-dimensional space, in the low-dimensional vector space, the closer the entity correlation in geometry is, the greater the entity correlation is, and the cosine identity of the vector is used for calculating the entitye i Ande j correlation between themSim(e i ,e j )；
Wherein, the first and the second end of the pipe are connected with each other,Sim(e i ,e j ) Meter (2)The calculation formula is as follows:
2. the method as claimed in claim 1, wherein in step S9, the constructed training is used as training input of the ranking model, the Top-N recommendation list is generated through a decision function, and a set of weight ratios of N-dimensional features to ranking results is obtained to construct the feedback model.
3. A health management system suitable for surgical patients, managed by the method of claim 1, comprising a historical data acquisition module, a feature extraction module, a model training module, a strategy map construction module, a ranking strategy model generation module, an information feedback unit and a health strategy recommendation unit;
the historical data acquisition module, the feature extraction module, the model training module, the information feedback unit and the health strategy recommendation unit are sequentially connected;
the strategy map building module, the sequencing strategy model generating module, the information feedback unit and the health strategy recommending unit are sequentially connected;
the historical data acquisition module is used for acquiring a hospital historical user data set and dividing the historical user data set into a training set and a test data set;
the characteristic extraction module is used for acquiring original characteristics from the training data set and training the original characteristics through a gradient lifting decision tree GBDT algorithm to acquire corresponding combined characteristics;
the model training module is used for learning and verifying by using a training data set and a test data set and adopting a model training algorithm to obtain a mapping relation between at least one characteristic parameter set and the blood transfusion volume of a single user as a blood transfusion volume prediction model;
the strategy map building module is used for mutually fusing the collected health strategy set and the hospital historical user data set to build a strategy map;
the sequencing strategy model generation module generates a corresponding Top-N recommendation list according to the blood transfusion volume of the individual patient;
the information feedback unit is used for inputting the data information of the current patient to the model training module and feeding back the result information processed by the model training module to the intelligent terminal of the doctor;
the health strategy recommendation unit is used for acquiring feedback information of a doctor to generate a postoperative health management strategy of a user and pushing the postoperative health management strategy to a patient;
the user data set takes historical blood usage historical information of a preset department as input, a curve formed by discrete values arranged according to time is formed, whether the curve fluctuates or not is judged, if the curve fluctuates, multi-order difference is used for carrying out stabilization adjustment until a curve stabilization difference parameter is zero, an autoregressive moving average time sequence model is established according to smooth time sequence information, and the order is determined;
the historical information of the historical blood usage comprises historical preoperative blood loss information, historical intraoperative blood transfusion information and historical postoperative blood index information.
4. The system of claim 3, wherein the model training module comprises at least a first model training subunit and a second model training subunit:
the first model training subunit is used for learning and verifying by using a training data set and adopting a model training algorithm to obtain a mapping relation between a second characteristic parameter set and the blood loss of the single user as a blood loss prediction model;
and the second model training subunit is used for learning and verifying by using a training data set and adopting a model training algorithm to obtain a mapping relation between a characteristic parameter set and the blood transfusion volume of the single user as a blood transfusion volume prediction model, wherein the characteristic parameter set comprises the blood transfusion volume of the single user predicted according to the blood transfusion volume prediction model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111617376.3A CN114283947B (en) | 2021-12-27 | 2021-12-27 | Health management method and system suitable for surgical patients |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111617376.3A CN114283947B (en) | 2021-12-27 | 2021-12-27 | Health management method and system suitable for surgical patients |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114283947A CN114283947A (en) | 2022-04-05 |
| CN114283947B true CN114283947B (en) | 2022-11-18 |
Family
ID=80876726
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111617376.3A Active CN114283947B (en) | 2021-12-27 | 2021-12-27 | Health management method and system suitable for surgical patients |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114283947B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114883007A (en) * | 2022-07-12 | 2022-08-09 | 南昌大学第一附属医院 | Big data based data model construction method, system, medium and computer |
| CN116030990B (en) * | 2022-12-26 | 2023-10-27 | 北京和兴创联健康科技有限公司 | Perioperative blood transfusion scheme generation method and system based on cascading model |
| CN117373690B (en) * | 2023-12-08 | 2024-02-23 | 天津医科大学第二医院 | Intelligent postoperative rehabilitation management method for hepatobiliary surgery patient |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108511057A (en) * | 2018-02-28 | 2018-09-07 | 北京和兴创联健康科技有限公司 | Transfusion volume model foundation and prediction technique, device, equipment and its storage medium |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110704636B (en) * | 2019-09-27 | 2021-01-05 | 吉林大学 | Improved Node2 vec-based knowledge graph vector representation method |
| US11935653B2 (en) * | 2019-12-05 | 2024-03-19 | University Hospitals Cleveland Medical Center | Blood transfusion management using artificial intelligence analytics |
| CN113611401A (en) * | 2021-08-26 | 2021-11-05 | 中国医学科学院阜外医院 | Perioperative blood management system and method |
-
2021
- 2021-12-27 CN CN202111617376.3A patent/CN114283947B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108511057A (en) * | 2018-02-28 | 2018-09-07 | 北京和兴创联健康科技有限公司 | Transfusion volume model foundation and prediction technique, device, equipment and its storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114283947A (en) | 2022-04-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114283947B (en) | Health management method and system suitable for surgical patients | |
| Ahmed et al. | A multi-module case-based biofeedback system for stress treatment | |
| KR20170061222A (en) | The method for prediction health data value through generation of health data pattern and the apparatus thereof | |
| KR20190132290A (en) | Method, server and program of learning a patient diagnosis | |
| CN110364259B (en) | Method, system, medium and electronic device for predicting altitude disease | |
| Cobb et al. | Seeing the forest beyond the trees: Predicting survival in burn patients with machine learning | |
| US11710572B2 (en) | Experience engine-method and apparatus of learning from similar patients | |
| CN111933237A (en) | Chronic disease processing method and device and related equipment | |
| CN112967819A (en) | Preoperative evaluation method and system for neurosurgery | |
| CN113707253A (en) | Medical scheme recommendation method, device, equipment and medium | |
| CN115116612A (en) | Intelligent risk assessment system and method for child patient state of illness | |
| JPWO2019220833A1 (en) | Diagnostic support system, diagnostic support device and diagnostic support method | |
| EP3929939A1 (en) | System and method for peri-anaesthetic risk evaluation | |
| CN112435745B (en) | Method and device for recommending treatment strategy, electronic equipment and storage medium | |
| WO2021151273A1 (en) | Disease prediction method and apparatus, electronic device, and storage medium | |
| CN114446470A (en) | Artificial intelligence model-based acute kidney injury recovery time prediction method | |
| CN114649071A (en) | Real world data-based peptic ulcer treatment scheme prediction system | |
| CN115101192B (en) | Symptom recommendation method, device, equipment and storage medium based on prescription | |
| CN116936107B (en) | Cardiac data risk analysis method, system and medium based on convolutional neural network | |
| WO2022141928A1 (en) | Covid-19 detection device, intervention device, and detection-intervention system | |
| Sreenivasan et al. | PCPS: Personalized Care through Patient Similarity | |
| CN110827945B (en) | Control method for generating key factors based on medical data | |
| KR20230174596A (en) | Healthcare system through Big-data and history management and how to operation method it's | |
| CN117038094A (en) | Method and system for mining and analyzing specific disease knowledge based on clinical data | |
| CN114360675A (en) | Prediction method, prediction device, electronic equipment and computer-readable 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |