CN110767316A - Establishment method of wound blood transfusion prediction model, and method and system for determining blood transfusion volume - Google Patents
Establishment method of wound blood transfusion prediction model, and method and system for determining blood transfusion volume Download PDFInfo
- Publication number
- CN110767316A CN110767316A CN201910840653.3A CN201910840653A CN110767316A CN 110767316 A CN110767316 A CN 110767316A CN 201910840653 A CN201910840653 A CN 201910840653A CN 110767316 A CN110767316 A CN 110767316A
- Authority
- CN
- China
- Prior art keywords
- blood
- blood transfusion
- transfusion
- information
- prediction model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
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
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- External Artificial Organs (AREA)
Abstract
The invention provides a method for establishing a wound blood transfusion prediction model, which comprises the following steps: acquiring historical data related to transfusion of a trauma patient as a historical user data set; obtaining original features from the historical user data set; training the original features by using a gradient lifting decision tree algorithm to obtain corresponding combined features or reconstructed new features; and extracting a characteristic parameter set suitable for representing the blood transfusion volume of the single user from the plurality of characteristics according to the distribution characteristics, the related characteristics and the importance of the combined characteristics or the new characteristics to train the blood transfusion prediction model. By the invention, the mode that doctors carry out experiential blood transfusion only through descriptive test results can be solved, the success rate of patient treatment is improved, the death rate is reduced, and blood resources are saved.
Description
Technical Field
The invention relates to the technical field of medical treatment, in particular to a method for establishing a wound blood transfusion prediction model and a method and a system for determining blood transfusion volume.
Background
Traumatic injuries account for about 10% of the worldwide deaths, with 80% of operating room deaths and 50% of deaths within 24h after trauma being associated with bleeding. Uncontrolled bleeding is a leading cause of potentially preventable death in trauma patients. The 24h mortality rate and the 30d mortality rate of the patients who were transfused before admission were obviously lower than those of the patients who were not transfused in the control group. Early administration of blood products in the early period of trauma, shortening of the pre-hospital transfer time, early admission of medical intervention, and rational blood transfusion are important measures for reducing the mortality rate. Early evaluation of pre-hospital emergency, when and what amount of blood transfusion is the key point affecting the success rate of treatment, is also a difficult point. At present, there are relevant regulations for blood transfusion in the medical field, such as the Chinese "clinical transfusion technical Specification-" guidelines for surgery and trauma transfusion ": hb >100g/L can be transfused without blood; hb <70g/L transfusions should be considered; hb is 70-100g/L, which is determined by anemia degree, cardiopulmonary compensation function, metabolic rate increase and age; guidelines recommended by the american blood bank association: if the hemodynamics of the patient is stable and the red blood cell threshold value is lower than 70g/L of Hb, transfusion is required and can be performed; if the patient needs to be operated, the red blood cell threshold value is lower than Hb 70-80g/L, blood transfusion is needed; recommended guidelines for management of traumatic severe hemorrhage and coagulopathy in Europe (2019 edition) include target Hb of 70-90 g/L. At present, many countries or regions determine whether transfusion is needed according to scoring system reference, and the main scoring systems are a trauma-related severe bleeding scoring (TASH) scoring system and a blood consumption assessment scoring (ABC) system. The former incorporates 7 variables into a scoring system of 0-28 points, the latter uses 4 non-laboratory, unweighted parameters to identify patients requiring massive transfusions, and has 75% sensitivity and 86% specificity, and the method is fast, simple and accurate.
Although the guidelines at home and abroad have prediction thresholds for blood transfusion, the guidelines only judge whether a large-dose transfusion scheme needs to be started, do not provide guidance for refinement of red blood cell transfusion during wound treatment, and do not make clear how much blood transfused by patients can reach relatively safe thresholds.
Disclosure of Invention
In view of the above, the present invention has been developed to provide a solution that overcomes, or at least partially solves, the above-mentioned problems.
In one aspect of the present invention, a method for establishing a prediction model of trauma blood transfusion is provided, the method comprising: acquiring historical data related to transfusion of a trauma patient as a historical user data set;
obtaining original features from the historical user data set;
training the original features by using a gradient lifting decision tree algorithm to obtain corresponding combined features or reconstructed new features;
and extracting a characteristic parameter set suitable for representing the blood transfusion volume of the single user from the plurality of characteristics according to the distribution characteristics, the related characteristics and the importance of the combined characteristics or the new characteristics to train the blood transfusion prediction model.
Acquiring historical trauma patient transfusion related data as a historical user data set, comprising: the method comprises the steps of collecting parameter information of a large number of trauma patients at the beginning and after the end of blood transfusion as a user basic information data subset through a non-invasive monitor, collecting a user inspection result data subset related to blood sample monitoring indexes, obtaining a doctor diagnosis result as a user diagnosis information data subset, collecting data of historical patient treatment of the patients as a user past medical history data subset, and obtaining transfusion blood components as a blood data subset.
The invention also provides a method for determining blood transfusion volume based on the wound blood transfusion prediction model established in the method, which comprises the following steps:
receiving and recording basic information of a patient, current diagnosis information, trauma related information and inspection and examination information;
detecting blood parameter indexes before blood transfusion;
and calculating by using the blood transfusion prediction model according to the collected information and the blood parameter indexes to determine a blood transfusion decision including whether blood transfusion is carried out or not and the blood transfusion amount and a curative effect evaluation result after prediction of blood transfusion.
Optionally, the method further includes:
acquiring historical blood transfusion information, past medical history and expected values of physical sign parameter information of a patient as input information; adjusting parameters of the blood transfusion prediction model by using the acquired information;
and calculating by using the adjusted blood transfusion prediction model according to the collected information and the blood parameter indexes to determine a transfusion decision including whether transfusion is carried out or not and the blood transfusion amount and a curative effect evaluation result after prediction of transfusion.
The present invention also provides a system for determining the amount of blood transfused based on the wound blood transfusion prediction model established in the method described above, the system comprising:
the data collection module is used for acquiring the basic information of the blood recipient;
the non-invasive monitoring module is used for detecting blood parameter indexes of a blood recipient before blood transfusion;
and the data processing module is used for calculating by using the blood transfusion prediction model according to the collected information and the blood parameter indexes, and determining a blood transfusion decision including whether blood transfusion is carried out or not and the blood transfusion quantity and predicting a curative effect evaluation result after blood transfusion.
The technical scheme provided in the embodiment of the application at least has the following technical effects or advantages: the mode that doctors only carry out experiential blood preparation through the most basic symptoms, signs and/or descriptive test results is solved, the blood transfusion volume of each patient can be accurately predicted, the success rate of patient treatment can be improved, and the death rate can be reduced.
The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
fig. 1 shows a flow chart of a proposed method for wound transfusion prediction modeling according to the present invention;
FIG. 2 shows a flow diagram of a method of making a wound transfusion prediction;
fig. 3 shows an architecture diagram of a wound transfusion prediction system.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
The invention aims to provide an intelligent auxiliary software system for wound blood transfusion diagnosis and treatment by researching the relevance of requirement evaluation of wound patients before blood transfusion and curative effect evaluation after blood transfusion, and provides accurate and rapid blood transfusion decision suggestion for the treatment of bleeding of wound patients.
In one aspect of the present invention, there is provided a method for establishing a prediction model of trauma blood transfusion, as shown in fig. 1, the method comprising:
s1, acquiring historical data related to blood transfusion of a trauma patient as a historical user data set;
s2, acquiring original characteristics from the historical user data set;
s3, training the original features by utilizing a gradient lifting decision tree algorithm to obtain corresponding combined features or reconstructed new features;
and S4, extracting a characteristic parameter set suitable for representing the blood transfusion volume of the single user from the plurality of characteristics according to the distribution characteristics, the relevant characteristics and the importance of the combined characteristics or the new characteristics to train a blood transfusion prediction model.
Wherein obtaining historical trauma patient transfusion related data as a historical user data set comprises: the method comprises the steps of collecting parameter information of a large number of trauma patients at the beginning and after the end of blood transfusion as a user basic information data subset through a non-invasive monitor, collecting a user examination result data subset related to blood monitoring, obtaining a doctor diagnosis result as a user diagnosis information data subset, collecting data of historical patient visits of the patients as a user past medical history data subset, and obtaining transfusion blood components as a blood data subset. The above information is written as input information into the information base, and includes both classification variables and continuous variables.
Specifically, data before and after blood transfusion are collected, correlation between information before and after blood transfusion is mined, characteristic variables with high correlation are extracted, and interpretability of results of the characteristic variables has important significance for assisting clinical decision. First, the expected results of the first examination (blood routine, blood gas, blood coagulation, biochemistry, vital signs) and image examination (mainly bedside ultrasound, CT, chest fluoroscopy) after the emergency triage (blood routine, blood gas, blood coagulation, biochemistry, vital signs) and historical inpatient blood transfusion information, the past medical history and the last hemoglobin before the emergency, mean arterial pressure, heart rate, respiration, are entered into the system as input values based on the patient basic information (height, weight, sex), diagnostic information, wound type (open or closed), wound site (head and neck, upper limbs, lower limbs, thoracoabdominal, spine, pelvis, trunk).
Secondly, checking that the hemoglobin, the mean arterial pressure, the heart rate and the respiration are close to the desired set hemoglobin value after blood transfusion, wherein the error is within an acceptable range;
and finally, extracting characteristic variables with higher correlation according to input and output correlation analysis.
The method comprises the steps of obtaining original features from historical user data sets, training the original features through a Gradient Boosting decision Tree algorithm (GBDT) to obtain corresponding combined features, or reconstructing more effective features by the aid of the Gradient Boosting decision Tree algorithm. For example, before the blood transfusion in the emergency department, the blood routine, the blood gas, the blood coagulation, the biochemistry and the vital signs are checked, the blood routine of the patient after the blood transfusion in the emergency department is checked, and the like, the diagnosis data of the patient in the emergency department in the treatment process trains a gradient boosting decision tree model, and then a new feature is constructed by using the tree learned by the gradient boosting decision tree model, wherein the length of the new feature vector is equal to the sum of leaf node trees contained in all the trees in the gradient boosting decision tree model. Model training is performed on the original features and the new features together.
The gradient lifting decision tree belongs to a supervised learning method, is used for classification analysis (processing discrete data) and regression tree analysis (processing continuous data), and is an integrated learning model. The gradient lifting decision tree algorithm is composed of a loss function and a regular function, the loss function calculates the error between the prediction model and the real result, and the loss function is restrained based on the minimum error in the actual calculation; the regular function is used for detecting the complexity of the model and avoiding overfitting. Wherein the loss function and the objective function can be specified according to actual conditions.
The gradient lifting decision tree can quickly finish data training, can solve the problem of high-dimensional data analysis, has higher prediction precision, is widely applied to large-scale data competition, but is rarely applied to transfusion big data. The method applies the gradient lifting decision tree algorithm to the prediction of the trauma blood transfusion model for the first time, the algorithm is superior to other machine learning methods, namely, the prediction result and the training data difference are used for training, the accuracy is improved in the continuous iteration process, and the incremental learning characteristic of the model is ensured; in addition, the model can reconstruct more effective characteristics from the training process of the big blood transfusion data, and the characteristics can represent the blood transfusion volume of a single user to carry out model prediction, so that the model has stronger generalization capability, reduces overfitting and has important significance for assisting clinical decision.
And extracting a characteristic parameter set suitable for representing the blood transfusion volume of a single user from the plurality of characteristics according to the distribution characteristics, the relevant characteristics and the importance of the characteristics to train the blood transfusion prediction model, so that the generalization capability of the model is stronger, and overfitting is reduced.
The method for improving the decision tree by using the gradient realizes accurate blood use, the model can reconstruct more effective characteristics from the training process of big blood transfusion data, and the characteristics can represent the blood transfusion volume of a single user to carry out model prediction, so that the generalization capability of the model is stronger, and overfitting is reduced. And (3) predicting auxiliary blood by using a model, and accurately controlling the postoperative hemoglobin result: on the one hand, the classification is performed according to the infusion amount, and the root mean square error of the infusion amount AI prediction model of each stage is compared with the prediction result of the clinician. The AI prediction model error rate is lower than the clinician indicating that the AI prediction is more accurate than the clinician.
The present invention also provides a method for determining a blood transfusion volume based on the wound blood transfusion prediction model established in the above method, as shown in fig. 2, the method comprising:
s11, recording basic information of a wound patient, current diagnosis information, wound related information and inspection and examination information;
s21, detecting blood parameter indexes before blood transfusion;
and S31, calculating by using the blood transfusion prediction model according to the collected information and the blood parameter indexes, and determining whether blood transfusion is carried out or not, the blood transfusion decision of the blood transfusion amount and the prediction of the curative effect evaluation result after blood transfusion.
And S41, displaying the blood transfusion decision and the curative effect evaluation result after blood transfusion.
The invention establishes a blood transfusion prediction model by a big data method, combines related blood transfusion information collected from the current patient according to the model, and can make individualized, accurate and quantitative decision-making opinions. The patient is guided by the specific red blood cell infusion amount under different vital sign states.
The method further comprises the following steps:
acquiring historical blood transfusion information, past medical history and expected values of physical sign parameter information of a patient as input information; adjusting parameters of the blood transfusion prediction model by using the acquired information;
and calculating by using the adjusted blood transfusion prediction model according to the collected information and the blood parameter indexes to determine whether blood transfusion is performed and predict the curative effect evaluation result after blood transfusion.
The invention not only effectively limits the unnecessary blood transfusion quantity, but also can meet the minimum oxygen supply requirement of the organism of a patient, and is a difficult problem which is urgently needed to be solved in the current clinical blood transfusion practice.
The present invention also provides a system for determining a blood transfusion volume based on the wound blood transfusion prediction model established in the aforementioned method, as shown in fig. 3, the system comprising:
a data collection module 100, configured to obtain basic information of a recipient;
the non-invasive monitoring module 200 is used for detecting blood parameter indexes of a blood recipient before blood transfusion;
a data processing module 300, configured to perform an operation by using the blood transfusion prediction model according to the collected information and the blood parameter index, and determine a blood transfusion decision suggestion including whether blood transfusion is performed or not and a blood transfusion amount, and a curative effect evaluation result after blood transfusion prediction;
and the data display module 400 is used for displaying the blood transfusion decision suggestion and the curative effect evaluation result after blood transfusion.
According to the technical scheme, the wound blood transfusion prediction model provided by the embodiment can be used for evaluating the requirements of wound patients before blood transfusion and evaluating the curative effect after blood transfusion, is suitable for being carried out in emergency rescue, and provides technical support for assisting doctors to make blood transfusion decisions quickly and accurately in the emergency rescue environment.
As a preferred implementation way of the construction of the system, the data acquisition module is used for acquiring historical blood transfusion information, past medical history and expected value of physical sign parameter information of a patient as input information; the model parameter adjusting module is used for adjusting parameters of the blood transfusion prediction model by using the acquired information; and the data processing module performs operation by using the adjusted blood transfusion prediction model according to the collected information and the blood parameter indexes to determine whether blood transfusion and blood transfusion quantity are performed and predict the curative effect evaluation result after blood transfusion. This embodiment enables a more accurate model-based prediction result by the adaptation of the parameters of the current patient adaptation.
The technical scheme provided in the embodiment of the application at least has the following technical effects or advantages: the method solves the problem that a doctor only carries out an experiential blood preparation mode through descriptive test results, can accurately predict the blood transfusion volume of each patient, and can improve the success rate of patient treatment and reduce the death rate.
In the description provided herein, numerous specific details are set forth. It is understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be interpreted as reflecting an intention that: that the invention as claimed requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim.
Claims (6)
1. A method for establishing a trauma blood transfusion prediction model is characterized by comprising the following steps:
acquiring historical data related to transfusion of a trauma patient as a historical user data set;
obtaining original features from the historical user data set;
training the original features by using a gradient lifting decision tree algorithm to obtain corresponding combined features or reconstructed new features;
and extracting a characteristic parameter set suitable for representing the blood transfusion volume of the single user from the plurality of characteristics according to the distribution characteristics, the related characteristics and the importance of the combined characteristics or the new characteristics to train the blood transfusion prediction model.
2. The method of claim 1, further characterized by obtaining historical trauma patient transfusion related data as a historical user data set comprising: the method comprises the steps of collecting parameter information of a large number of trauma patients at the beginning and after the end of blood transfusion as a user basic information data subset through a non-invasive monitor, collecting a user examination result data subset related to blood monitoring, obtaining a doctor diagnosis result as a user diagnosis information data subset, collecting data of historical patient visits of the patients as a user past medical history data subset, and obtaining transfusion blood components as a blood data subset.
3. A method for determining the amount of blood transfused based on the wound transfusion prediction model established in the method of claim 1 or 2, the method comprising:
receiving and recording basic information of a patient, current diagnosis information, trauma related information and inspection and examination information;
detecting blood parameter indexes before blood transfusion;
and calculating by using the blood transfusion prediction model according to the collected information and the blood parameter indexes to determine a blood transfusion decision including whether blood transfusion is carried out or not and the blood transfusion amount and a curative effect evaluation result after prediction of blood transfusion.
4. The method of determining blood volume of claim 3, further comprising:
acquiring historical blood transfusion information, past medical history and expected values of physical sign parameter information of a patient as input information;
adjusting parameters of the blood transfusion prediction model by using the acquired information;
and calculating by using the adjusted blood transfusion prediction model according to the collected information and the blood parameter indexes to determine a transfusion decision including whether transfusion is carried out or not and the blood transfusion amount and a curative effect evaluation result after prediction of transfusion.
5. A system for determining the amount of blood transfused based on the wound transfusion prediction model established in the method of claim 1 or 2, the system comprising:
the data collection module is used for acquiring the basic information of the blood recipient;
the non-invasive monitoring module is used for detecting blood parameter indexes of a blood recipient before blood transfusion;
and the data processing module is used for calculating by using the blood transfusion prediction model according to the collected information and the blood parameter indexes, and determining a blood transfusion decision including whether blood transfusion is carried out or not and the blood transfusion quantity and predicting a curative effect evaluation result after blood transfusion.
6. The system for determining blood transfusion volume according to claim 5, further comprising:
the data acquisition module is used for acquiring historical blood transfusion information, past medical history and expected values of physical sign parameter information of the patient as input information;
the model parameter adjusting module is used for adjusting parameters of the blood transfusion prediction model by using the acquired information;
and the data processing module performs operation by using the adjusted blood transfusion prediction model according to the collected information and the blood parameter indexes to determine whether blood transfusion and blood transfusion quantity are performed and predict the curative effect evaluation result after blood transfusion.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910840653.3A CN110767316A (en) | 2019-09-06 | 2019-09-06 | Establishment method of wound blood transfusion prediction model, and method and system for determining blood transfusion volume |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910840653.3A CN110767316A (en) | 2019-09-06 | 2019-09-06 | Establishment method of wound blood transfusion prediction model, and method and system for determining blood transfusion volume |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110767316A true CN110767316A (en) | 2020-02-07 |
Family
ID=69330586
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910840653.3A Pending CN110767316A (en) | 2019-09-06 | 2019-09-06 | Establishment method of wound blood transfusion prediction model, and method and system for determining blood transfusion volume |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110767316A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112200213A (en) * | 2020-08-20 | 2021-01-08 | 北京和兴创联健康科技有限公司 | Method and device for realizing accurate newborn blood transfusion |
| CN113611391A (en) * | 2021-08-25 | 2021-11-05 | 中南大学湘雅三医院 | Liver transplantation process blood transfusion prediction method, system, equipment and medium |
| CN114496209A (en) * | 2022-02-18 | 2022-05-13 | 青岛市中心血站 | Blood donation intelligent decision method and system |
| CN116030990A (en) * | 2022-12-26 | 2023-04-28 | 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 |
-
2019
- 2019-09-06 CN CN201910840653.3A patent/CN110767316A/en active Pending
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112200213A (en) * | 2020-08-20 | 2021-01-08 | 北京和兴创联健康科技有限公司 | Method and device for realizing accurate newborn blood transfusion |
| CN112200213B (en) * | 2020-08-20 | 2024-05-14 | 北京和兴创联健康科技有限公司 | Method and device for realizing accurate blood transfusion of neonate |
| CN113611391A (en) * | 2021-08-25 | 2021-11-05 | 中南大学湘雅三医院 | Liver transplantation process blood transfusion prediction method, system, equipment and medium |
| CN114496209A (en) * | 2022-02-18 | 2022-05-13 | 青岛市中心血站 | Blood donation intelligent decision method and system |
| CN114496209B (en) * | 2022-02-18 | 2022-09-27 | 青岛市中心血站 | Intelligent decision-making method and system for blood donation |
| CN116030990A (en) * | 2022-12-26 | 2023-04-28 | 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 |
| 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 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110767316A (en) | Establishment method of wound blood transfusion prediction model, and method and system for determining blood transfusion volume | |
| RU2728855C9 (en) | Quantitative indicator of cardiovascular deterioration warning | |
| RU2630122C2 (en) | Method for continuous forecasting of disease severity, death and hospitalization duration | |
| CN112365978A (en) | Method and device for establishing early risk assessment model of tachycardia event | |
| WO2023202500A1 (en) | Deep reinforcement learning based assistive adjustment system for dry weight of hemodialysis patient | |
| RU2657384C2 (en) | Method and system for noninvasive screening physiological parameters and pathology | |
| CN114023441A (en) | Severe AKI early risk assessment model and device based on interpretable machine learning model and development method thereof | |
| CN113284126B (en) | Method for predicting hydrocephalus shunt operation curative effect by artificial neural network image analysis | |
| CN109147884B (en) | Sufficiency evaluation method and system | |
| Weil et al. | Experience with a digital computer for study and improved management of the critically ill | |
| CN112967803A (en) | Early mortality prediction method and system for emergency patients based on integrated model | |
| CN116884570B (en) | Intraoperative real-time simulation curative effect evaluation system based on image processing | |
| CN112183572B (en) | Method and device for generating prediction model for predicting severity of pneumonia | |
| CN113270192A (en) | Hemodialysis risk prediction system based on combination of dynamic and static data and depth self-encoder | |
| CN114121278A (en) | Prediction model of AKI risk after heart valve replacement based on age and clinical index | |
| CN117649943A (en) | Shaping data intelligent analysis system and method based on machine learning | |
| CN111916213A (en) | Medical service method and device based on cloud computing | |
| Chen et al. | PREDICTIVE MODELING OF POSTOPERATIVE OUTCOMES | |
| CN117079810A (en) | Cardiovascular disease unscheduled re-hospitalization risk prediction method | |
| Liu et al. | A machine learning method for predicting the probability of MODS using only non-invasive parameters | |
| CN114145722B (en) | Pulse pathological feature mining method for pancreatitis patients | |
| Liu et al. | Application of big data deep learning in auxiliary diagnosis of lower extremity arteriosclerosis obliterans | |
| CN113808724B (en) | Data analysis method and device, storage medium and electronic terminal | |
| Zhang et al. | Prediction of Deterioration in Critically Ill Patients with Heart Failure Based on Vital Signs Monitoring | |
| TW202406507A (en) | Method and system for timely prediction of non-invasive surrogate arterial pressure waveforms by electrocardiogram and oxygen saturation waveform |
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 |