CN114783607A - Surgical blood transfusion risk prediction model and construction method of network calculator thereof - Google Patents
Surgical blood transfusion risk prediction model and construction method of network calculator thereof Download PDFInfo
- Publication number
- CN114783607A CN114783607A CN202210507169.0A CN202210507169A CN114783607A CN 114783607 A CN114783607 A CN 114783607A CN 202210507169 A CN202210507169 A CN 202210507169A CN 114783607 A CN114783607 A CN 114783607A
- Authority
- CN
- China
- Prior art keywords
- risk
- transfusion
- blood transfusion
- surgical
- 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.)
- Granted
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
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Health & Medical Sciences (AREA)
- Public Health (AREA)
- Data Mining & Analysis (AREA)
- Pathology (AREA)
- Databases & Information Systems (AREA)
- Biomedical Technology (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Medical Treatment And Welfare Office Work (AREA)
- Investigating Or Analysing Biological Materials (AREA)
Abstract
The invention discloses a surgical blood transfusion risk prediction model and a construction method of a network calculator thereof.A single-factor logistic regression model is utilized to calculate the correlation between each clinical index and blood transfusion risk, the clinical indexes related to the blood transfusion risk are screened out to carry out multiple logistic regression calculation, and independent prediction factors are screened out to construct a blood transfusion prediction model; generating a network calculator according to a formula of the weight coefficient score of each prediction factor in the prediction model; and collecting a key information data set of the surgical patient, and inputting the key information data set into a network calculator to obtain the predicted blood transfusion probability. The blood transfusion prediction model constructed by the invention can predict the perioperative blood transfusion probability of the operation patient before operation, and a network calculator is generated according to the model, can be applied to medical electronic cases, and provides automatic electronic decision for preoperative planning and blood management.
Description
Technical Field
The invention relates to the technical field of medical informatics, in particular to a surgical blood transfusion risk prediction model and a construction method of a network calculator thereof.
Background
Blood transfusion is an important means for saving life in surgical operation, and preoperative identification of patients with high blood transfusion risk is very important for reasonably arranging limited blood resources. Adverse transfusion reactions caused by blood transfusion, such as fever, allergy, hemolysis, overload of the circulatory system associated with blood transfusion, acute lung injury and blood-borne infection associated with blood transfusion, etc., endanger the health and even life of patients. Identification of high risk transfusion patients for early patient blood management is very important for prevention of adverse transfusion reactions. Preoperative preparation requires blood grouping, blood group antibody screening and cross matching, but most surgical patients do not need blood transfusion. The identification of high-risk patients with surgical blood transfusion before operation is an important means for saving cost by perfecting preoperative relevant examination.
At present, the blood transfusion prediction model is in an exploration stage, and most of the blood transfusion prediction models are used for predicting blood transfusion of single disease species and have inconvenience in clinical use. At present, no universal blood transfusion prediction model is applied to various surgical patients, and no network calculator or APP based on the model is designed.
Disclosure of Invention
The invention aims to provide a surgical blood transfusion risk prediction model and a construction method of a network calculator thereof, wherein the surgical blood transfusion risk prediction model is constructed, the network calculator is designed according to the model, and the model is suitable for perioperative blood transfusion prediction of various surgical patients in the medical field and provides technical support for preoperative planning and blood management.
In order to achieve the purpose, the invention provides the following scheme:
a construction method of a surgical blood transfusion risk prediction model and a network calculator thereof comprises the following steps:
s1, data collection: downloading corresponding clinical indexes of the surgical patients from DATADRYAD database;
s2, constructing a blood transfusion prediction model: calculating the correlation between each clinical index and the blood transfusion risk by using a single-factor logistic regression model, screening out the clinical indexes related to the blood transfusion risk to perform multivariate logistic regression calculation, screening out independent prediction factors to construct a blood transfusion prediction model, and distinguishing high-risk and low-risk blood transfusion patients according to the critical value of a working characteristic curve of a blood transfusion prediction model subject;
s3, the network calculator generates: calculating each prediction factor to obtain a weight coefficient in a blood transfusion prediction model, constructing a Norman diagram of blood transfusion risk, and generating a network calculator according to a formula of the weight coefficient score of each prediction factor in the prediction model;
s4, calculating blood transfusion probability: and collecting a key information data set of the surgical patient, and inputting the key information data set into a network calculator to obtain the predicted blood transfusion probability.
Further, in step S1, the clinical indicators corresponding to the surgical patients specifically include: age, gender, race, ASA score, history of cerebrovascular disease, history of ischemic heart disease, congestive heart failure, insulin dependent diabetes mellitus, renal disease grade, type of anesthesia, surgical priority grade, surgical risk grade, grade 18 variables, and blood transfusion; wherein the 18-degree variable is derived from the width of the red blood cell volume distribution, the anemia level and the mean red blood cell volume.
Further, in step S2, the independent prediction factors specifically include: age, race, ASA score, kidney disease level, anesthesia type, surgical priority level, surgical risk level, and 18-degree variable.
Further, in step S2, the method for distinguishing high-risk and low-risk transfusion patients according to the critical value of the working characteristic curve of the transfusion prediction model subjects includes:
calculating a critical value according to the Johnson index, wherein the Johnson index is sensitivity + specificity-1;
wherein above the critical value is a high risk transfusion patient and below the critical value is a low risk transfusion patient.
Further, in the step S2, the critical value calculated by using the york index is 0.163; those with transfusion probability higher than 0.163 are high risk transfusion patients, and those with transfusion probability lower than 0.163 are low risk transfusion patients.
Further, in step S4, the key information data set includes age, race, ASA score, kidney disease level, anesthesia type, surgery priority level, surgery risk level, and 18-level variable.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects: the invention provides a surgical blood transfusion risk prediction model and a construction method of a network calculator thereof, wherein the surgical blood transfusion risk prediction model is constructed, the network calculator is designed according to the model, and the blood transfusion risk prediction model and the network calculator are integrated into a medical electronic case, so that automatic electronic decision can be provided for preoperative plan and blood management, and doctors can be helped to score blood transfusion risks of surgical patients, thereby distinguishing high-risk patients from low-risk patients; the blood transfusion risk prediction model and the network calculator thereof constructed by the invention are suitable for predicting perioperative blood transfusions of various surgical patients in the medical field, high-risk and low-risk blood transfusion patients are distinguished according to a critical value of a working characteristic curve of a prediction model subject, unnecessary preoperative blood transfusion related detection can be avoided by identifying low-risk patients, the economic cost of the patients is saved, the high-risk patients are identified, preoperative blood management is more actively required clinically, such as anemia optimization, reasonable distribution of blood products, implementation of preoperative deep autologous blood collection, active autologous blood recovery in operation and the like, limited blood resources are reasonably distributed, and the blood management of the patients is carried out as early as possible, so that transfusion complications are prevented and reduced; therefore, the invention has important public health, economic and social significance.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required in the embodiments will be briefly described 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 these drawings without creative efforts.
FIG. 1 is a schematic flow chart of a surgical blood transfusion risk prediction model and a construction method of a network calculator thereof according to an embodiment of the invention;
FIG. 2 is a Nomann plot of a blood transfusion prediction model constructed using multiple logistic regression according to the present invention;
FIG. 3 is a graph of the present invention using the subject's operating characteristics;
FIG. 4 is a working interface of the blood transfusion prediction model generation network calculator 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 obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, belong to the protection scope of the present invention.
The invention aims to provide a surgical blood transfusion risk prediction model and a construction method of a network calculator thereof, wherein the surgical blood transfusion risk prediction model is constructed, the network calculator is designed according to the model, and the model is suitable for perioperative blood transfusion prediction of various surgical patients in the medical field and provides technical support for preoperative planning and blood management.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
As shown in fig. 1, the construction method of the surgical blood transfusion risk prediction model and the network calculator thereof provided by the invention comprises the following steps:
s1, collecting data: downloading corresponding clinical indexes of the surgical patient from an DATADRYAD database, specifically comprising: age, gender, race, ASA score, history of cerebrovascular disease, history of ischemic heart disease, congestive heart failure, insulin dependent diabetes mellitus, renal disease grade, type of anesthesia, surgical priority grade, surgical risk grade, grade 18 variables, and blood transfusion, wherein the grade 18 variables are derived from red blood cell volume distribution width (RDW), anemia grade, and mean red blood cell volume (MCV);
s2, constructing a blood transfusion prediction model: calculating the correlation between each clinical index and the blood transfusion risk by using a single-factor logistic regression model, screening out the clinical indexes related to the blood transfusion risk to perform multivariate logistic regression calculation, screening out independent prediction factors to construct a blood transfusion prediction model, and distinguishing high-risk and low-risk blood transfusion patients according to the critical value of a working characteristic curve of a blood transfusion prediction model subject;
s3, the network calculator generates: calculating each predicting factor to obtain a weight coefficient in a blood transfusion predicting model, constructing a Norman diagram (shown in figure 2) of blood transfusion risks, and generating a network calculator according to a formula of the weight coefficient score of each predicting factor in the predicting model;
s4, calculating blood transfusion probability: collecting a key information data set of a surgical patient, wherein the key information data set comprises age, race, ASA score, kidney disease grade, anesthesia type, surgical priority grade, surgical risk grade and 18 grade variable; and inputting the key information data set into a network calculator to obtain the predicted blood transfusion probability.
In step S2, analyzing whether blood transfusion is performed or not as an outcome variable by using a one-factor logistic regression model to obtain that age, sex, race, ASA score, ischemic heart history, insulin-dependent diabetes, anesthesia type, operation priority level, operation risk level, kidney disease level, and 18-level variables are related to blood transfusion risk;
screening independent prediction factors by using a multiple logistic regression model to construct a blood transfusion prediction model, wherein the independent prediction factors specifically comprise: age, race, ASA score, kidney disease level, anesthesia type, surgical priority level, surgical risk level, and 18-degree variable.
Of course, other algorithms, such as a machine learning algorithm, may also be used to learn the sample data set as needed to establish the prediction model, which is not described herein again.
In practical implementation, the area under the curve of the working characteristic curve of the subject of the blood transfusion prediction model established in step S2 verifies that the blood transfusion risk prediction model has higher accuracy in predicting perioperative blood transfusion of the surgical patient (as shown in fig. 3). Distinguishing high-risk transfusion patients from low-risk transfusion patients according to the critical value of the working characteristic curve of the prediction model testee; wherein the calculation of the critical value is performed according to a john index calculation; yoden index ═ sensitivity + specificity-1; the cut-off value calculated using the yoden index was 0.163; those with transfusion probability higher than 0.163 are high risk transfusion populations, and those with transfusion probability lower than 0.163 are low risk transfusion populations.
In step S3, the formula of the weight coefficient score of each predictor in the prediction model is as follows:
the transfusion probability ═ log [ -4.46158-0.31937 ═ 30-49 years old) -0.03344 ═ 50-69 years old) +0.14430 ═ 70 years old) -0.08761 ═ mary ═ horse-0.24471 ═ indian) +0.18649 ═ other) +0.00145 ═ ii ═ ASA) +0.62873 ═ ASA ═ iii) +1.05376 (ASA ═ iv-vi) +1.41348 (surgical risk grade ═ 2.50588 ═ high) -0.18533 ═ G2-0.04732 (renal disease grade G3) -0.39884 (renal disease grade G4-5 ═ 0.90734 ═ local anesthetic grade (2.43694) + ═ 2.43694 ═ local anesthetic grade (18 steps of variables 6) +1.11155 (18 steps of variables 7) +0.57610 (18 steps of variables 8) +1.99603 (18 steps of variables 9) -0.06304 (18 steps of variables 10) +0.37471 (18 steps of variables 11) -0.07997 (18 steps of variables 12) +0.49281 (18 steps of variables 13) +2.47390 (18 steps of variables 14) +1.15105 (18 steps of variables 15) +2.23242 (18 steps of variables 16) +0.88709 (18 steps of variables 17). Wherein, each parameter in the 18-level variable is expressed as follows:
0: normal RDW, no anemia, normal MCV;
1: high RDW, moderate/severe anemia, high MCV;
2: high RDW, moderate/severe anemia, low MCV;
3: high RDW, mild anemia, high MCV;
4: high RDW, mild anemia, low MCV;
5: normal RDW, moderate/severe anemia, high MCV;
6: normal RDW, moderate/severe anemia, low MCV;
7: normal RDW, mild anemia, high MCV;
8: normal RDW, mild anemia, low MCV;
9: high RDW, no anemia, high MCV;
10: high RDW, no anemia, low MCV;
11: normal RDW, no anemia, high MCV;
12: normal RDW, no anemia, low MCV;
13: high RDW, no anemia, normal MCV;
14: high RDW, moderate/severe anemia, normal MCV;
15: high RDW, mild anemia, normal MCV;
16: normal RDW, moderate/severe anemia, normal MCV;
17: normal RDW, mild anemia, normal MCV;
the working interface of the network calculator generated according to the formula is shown in fig. 4, and the key information data set is input into the network calculator to obtain the predicted blood transfusion probability.
In practical application, the risk of perioperative blood transfusion of the operation patient is considered to be predicted, and the condition of the operation patient is different, such as the type of operation, the patient's condition and the like, and the requirement of blood transfusion is different. Demographic characteristics such as age, surgery risk level and ASA score can be used for classifying surgery patients in different situations, and in addition, race, kidney disease level, anesthesia type and 18-level variables are all key factors for predicting blood transfusion risk, so that preoperative data of the target person can be collected to form the key information data set. And inputting the key information data set into a network calculator to obtain the blood transfusion probability.
The surgical patients are classified into high-risk transfusion patients and low-risk transfusion patients according to the obtained transfusion probabilities. According to the embodiment of the invention, the group with the transfusion probability higher than 0.163 is a high-risk transfusion group, and the related detection before transfusion needs to be perfected for the part of patients, and the blood management of the patients is carried out as early as possible to prevent the occurrence of adverse reactions in transfusion. The blood transfusion probability is lower than 0.163, the patient is a low-risk blood transfusion group, unnecessary blood transfusion related detection before the operation can be avoided for the part of patients, and the economic cost is saved. It is noted that 0.163 is a risk threshold calculated by applying the york index according to the present embodiment, and any changes, modifications, and substitutions made to the present embodiment may result in different thresholds.
The network calculator in the present embodiment is applicable to various electronic devices, which may include, but are not limited to, mobile terminals such as mobile phones, notebook computers, tablet computers, personal digital assistants, portable multimedia players, in-vehicle terminals, and the like. These mobile terminals should not bring any limitations to the functionality or scope of use of the embodiments of the present disclosure.
In conclusion, according to the surgical blood transfusion risk prediction model and the construction method of the network calculator thereof provided by the invention, the construction of the blood transfusion prediction model can predict the perioperative blood transfusion probability of a surgical patient before operation, the network calculator is generated according to the model, and the prediction tool is integrated into a medical electronic case, so that an automatic electronic decision can be provided for preoperative planning and blood management, and a doctor can be helped to score the blood transfusion risk of the surgical patient; in addition, doctors can be helped to distinguish high-risk patients from low-risk patients, unnecessary detection related to blood transfusion before operation can be avoided for the low-risk patients, and the economic cost of the patients is saved; high-risk patients need to actively perform preoperative blood management clinically, intervene as early as possible, and prevent and reduce adverse reactions caused by blood transfusion; the prediction factors for constructing the model only need preoperative evaluation indexes (age, race, ASA score, anesthesia type, operation priority level and operation risk level), kidney disease grade (creatinine in biochemical indexes) and blood general indexes (erythrocyte volume distribution width, anemia grade and average erythrocyte volume) of the patient, and are simple and easy to obtain, and the economic burden of the patient is not increased.
The principle and the embodiment of the present invention are explained by applying specific examples, and the above description of the embodiments is only used to help understanding the method and the core idea of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed. In view of the foregoing, the description is not to be taken in a limiting sense.
Claims (6)
1. A construction method of a surgical blood transfusion risk prediction model and a network calculator thereof is characterized by comprising the following steps:
s1, collecting data: downloading corresponding clinical indexes of the surgical patients from DATADRYAD database;
s2, constructing a blood transfusion prediction model: calculating the correlation between each clinical index and the blood transfusion risk by using a single-factor logistic regression model, screening out the clinical indexes related to the blood transfusion risk to perform multiple logistic regression calculation, screening out independent prediction factors to construct a blood transfusion prediction model, and distinguishing high-risk and low-risk blood transfusion patients according to the critical value of the working characteristic curve of a subject of the blood transfusion prediction model;
s3, the network calculator generates: calculating each prediction factor to obtain a weight coefficient in a blood transfusion prediction model, constructing a Norman diagram of blood transfusion risk, and generating a network calculator according to a formula of the weight coefficient score of each prediction factor in the prediction model;
s4, calculating blood transfusion probability: and collecting a key information data set of the surgical patient, and inputting the key information data set into a network calculator to obtain the predicted blood transfusion probability.
2. The method for constructing the model for predicting risks of surgical blood transfusion and the network calculator thereof according to claim 1, wherein the corresponding clinical indicators of the surgical patients in step S1 specifically include: age, gender, race, ASA score, history of cerebrovascular disease, history of ischemic heart disease, congestive heart failure, insulin dependent diabetes mellitus, renal disease grade, type of anesthesia, surgical priority grade, surgical risk grade, grade 18 variables, and blood transfusion; wherein the 18-degree variable is derived from the width of the red blood cell volume distribution, the anemia level and the mean red blood cell volume.
3. The method for constructing the model for predicting risks of surgical blood transfusion and the network calculator thereof according to claim 2, wherein in the step S2, the independent prediction factors specifically include: age, race, ASA score, kidney disease level, anesthesia type, surgical priority level, surgical risk level, and 18-degree variable.
4. The method for constructing the surgical transfusion risk prediction model and the network calculator thereof according to claim 1, wherein in the step S2, the distinguishing of high-risk transfusion patients and low-risk transfusion patients according to the critical value of the working characteristic curve of the transfusion prediction model subjects specifically comprises:
calculating a critical value according to the Johnson index, wherein the Johnson index is sensitivity + specificity-1;
wherein above the critical value is a high risk transfusion patient and below the critical value is a low risk transfusion patient.
5. The method for constructing a model and a network calculator for predicting risk of surgical transfusion according to claim 4, wherein in step S2, the critical value calculated by using the Jordan index is 0.163; patients with transfusion probability higher than 0.163 are high-risk transfusion patients, and those with transfusion probability lower than 0.163 are low-risk transfusion patients.
6. The method for constructing a surgical transfusion risk prediction model and the network calculator thereof according to claim 2, wherein in step S4, the key information data sets include age, race, ASA score, kidney disease grade, anesthesia type, surgical priority, surgical risk grade, and 18 grade variables.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210507169.0A CN114783607B (en) | 2022-05-10 | 2022-05-10 | Operation blood transfusion risk prediction model and construction method of network calculator thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210507169.0A CN114783607B (en) | 2022-05-10 | 2022-05-10 | Operation blood transfusion risk prediction model and construction method of network calculator thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114783607A true CN114783607A (en) | 2022-07-22 |
| CN114783607B CN114783607B (en) | 2023-06-23 |
Family
ID=82436643
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210507169.0A Active CN114783607B (en) | 2022-05-10 | 2022-05-10 | Operation blood transfusion risk prediction model and construction method of network calculator thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114783607B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1973778A (en) * | 2006-12-08 | 2007-06-06 | 南京大学 | Method of predicting serious complication risk degree after gastric cancer operation |
| WO2008077958A2 (en) * | 2006-12-22 | 2008-07-03 | Hvidovre Hospital | Soluble urokinase plasminogen activator receptor (supar) as marker for diseases |
| CN102187219A (en) * | 2008-08-29 | 2011-09-14 | 阿斯图特医药公司 | Methods and compositions for diagnosis and prognosis of renal injury and renal failure |
| KR20140141520A (en) * | 2013-05-30 | 2014-12-10 | 가톨릭대학교 산학협력단 | Method and system for predicting high risk based on patient safety |
| CN111640509A (en) * | 2020-06-02 | 2020-09-08 | 山东大学齐鲁医院 | Cervical cancer postoperative recurrence risk prediction method and system |
| CN111863257A (en) * | 2020-07-22 | 2020-10-30 | 广州医科大学附属第三医院（广州重症孕产妇救治中心、广州柔济医院） | Serious postpartum hemorrhage risk prediction system and construction method thereof |
| CN113178258A (en) * | 2021-04-28 | 2021-07-27 | 青岛百洋智能科技股份有限公司 | Preoperative risk assessment method and system for surgical operation |
| CN113450910A (en) * | 2020-09-27 | 2021-09-28 | 四川大学华西医院 | Isolated lung nodule malignancy risk prediction system based on logistic regression model |
| CN113921135A (en) * | 2021-09-06 | 2022-01-11 | 首都医科大学附属北京安贞医院 | System suitable for death risk assessment in acute aortic dissection operation |
-
2022
- 2022-05-10 CN CN202210507169.0A patent/CN114783607B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1973778A (en) * | 2006-12-08 | 2007-06-06 | 南京大学 | Method of predicting serious complication risk degree after gastric cancer operation |
| WO2008077958A2 (en) * | 2006-12-22 | 2008-07-03 | Hvidovre Hospital | Soluble urokinase plasminogen activator receptor (supar) as marker for diseases |
| CN102187219A (en) * | 2008-08-29 | 2011-09-14 | 阿斯图特医药公司 | Methods and compositions for diagnosis and prognosis of renal injury and renal failure |
| KR20140141520A (en) * | 2013-05-30 | 2014-12-10 | 가톨릭대학교 산학협력단 | Method and system for predicting high risk based on patient safety |
| CN111640509A (en) * | 2020-06-02 | 2020-09-08 | 山东大学齐鲁医院 | Cervical cancer postoperative recurrence risk prediction method and system |
| CN111863257A (en) * | 2020-07-22 | 2020-10-30 | 广州医科大学附属第三医院（广州重症孕产妇救治中心、广州柔济医院） | Serious postpartum hemorrhage risk prediction system and construction method thereof |
| CN113450910A (en) * | 2020-09-27 | 2021-09-28 | 四川大学华西医院 | Isolated lung nodule malignancy risk prediction system based on logistic regression model |
| CN113178258A (en) * | 2021-04-28 | 2021-07-27 | 青岛百洋智能科技股份有限公司 | Preoperative risk assessment method and system for surgical operation |
| CN113921135A (en) * | 2021-09-06 | 2022-01-11 | 首都医科大学附属北京安贞医院 | System suitable for death risk assessment in acute aortic dissection operation |
Non-Patent Citations (2)
| Title |
|---|
| 廖新华: "引发输血风险的因素分析与输血管理对策研究", 《中国卫生产业》 * |
| 廖新华: "引发输血风险的因素分析与输血管理对策研究", 《中国卫生产业》, 20 October 2019 (2019-10-20) * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114783607B (en) | 2023-06-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102558021B1 (en) | A clinical decision support ensemble system and the clinical decision support method by using the same | |
| Cramer et al. | Predicting the incidence of pressure ulcers in the intensive care unit using machine learning | |
| Jen et al. | Application of classification techniques on development an early-warning system for chronic illnesses | |
| Pathan et al. | Identifying stroke indicators using rough sets | |
| US20200258639A1 (en) | Medical device and computer-implemented method of predicting risk, occurrence or progression of adverse health conditions in test subjects in subpopulations arbitrarily selected from a total population | |
| Peng et al. | Random forest can predict 30‐day mortality of spontaneous intracerebral hemorrhage with remarkable discrimination | |
| CN105009126A (en) | Medical database and system | |
| CN113838577B (en) | Convenient layered old people MODS early death risk assessment model, device and establishment method | |
| CN112967803A (en) | Early mortality prediction method and system for emergency patients based on integrated model | |
| US20150269321A1 (en) | Personal health operating system | |
| Al-Mualemi et al. | A deep learning-based sepsis estimation scheme | |
| CN115798734B (en) | New burst infectious disease prevention and control method and device based on big data and storage medium | |
| CN114783607B (en) | Operation blood transfusion risk prediction model and construction method of network calculator thereof | |
| Moreno-Sánchez | Data-driven early diagnosis of chronic kidney disease: development and evaluation of an explainable AI model | |
| CN114613517A (en) | Prognosis prediction method and device, electronic equipment and storage medium | |
| Pal | Prediction for chronic kidney disease by categorical and non_categorical attributes using different machine learning algorithms | |
| Mena et al. | Machine learning approach to extract diagnostic and prognostic thresholds: application in prognosis of cardiovascular mortality | |
| CN109192312B (en) | Intelligent management system and method for adverse events of heart failure patients | |
| CN114038570A (en) | Sepsis related acute kidney injury patient death prediction method, system, apparatus and medium | |
| Zare et al. | A review of semantic similarity measures in biomedical domain using SNOMED-CT | |
| CN117133454A (en) | Dynamic interpretable type 2 diabetes patient contrast agent acute kidney injury prediction platform | |
| AU2021102593A4 (en) | A Method for Detection of a Disease | |
| Sumathi et al. | Machine learning based pattern detection technique for diabetes mellitus prediction | |
| CN113345584A (en) | Disease prognosis risk prediction model training method and device and electronic equipment | |
| Chadaga et al. | Severity prediction in COVID-19 patients using clinical markers and explainable artificial intelligence: A stacked ensemble machine learning approach |
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 |