CN111524598A - Perioperative complication prediction method and system - Google Patents
Perioperative complication prediction method and system Download PDFInfo
- Publication number
- CN111524598A CN111524598A CN202010316073.7A CN202010316073A CN111524598A CN 111524598 A CN111524598 A CN 111524598A CN 202010316073 A CN202010316073 A CN 202010316073A CN 111524598 A CN111524598 A CN 111524598A
- Authority
- CN
- China
- Prior art keywords
- complication
- perioperative
- prediction model
- prediction
- data
- 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
- G16H50/30—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
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Data Mining & Analysis (AREA)
- Biomedical Technology (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention discloses a perioperative complication prediction method and a perioperative complication prediction system, wherein the method comprises the following steps: acquiring existing perioperative complication data and constructing a perioperative complication database; carrying out layered random sampling from a complication database in the perioperative period according to three stages of preoperative, intraoperative and postoperative; dividing the sampling data of each stage into a training set, a verification set and a test set according to a proportion, and respectively training to obtain a complication occurrence probability prediction model and a complication occurrence time prediction model; and predicting the perioperative complication occurrence probability and complication occurrence time of the patient by adopting a complication occurrence probability prediction model and a complication occurrence time prediction model. The invention can avoid increasing the risk of perioperative complications due to the limitation of doctors, personal knowledge level and clinical experience, and can predict the occurrence probability and the occurrence time of the perioperative complications.
Description
Technical Field
The invention relates to the field of medical data processing, in particular to a perioperative complication prediction method and system.
Background
Perioperative refers to the entire process surrounding the operation, from the patient's decision to receive the surgical treatment, to the surgical treatment until the basic recovery, including a period of time before, during and after the operation, and specifically from the time the surgical treatment is determined until the treatment associated with the operation is substantially completed, from about 5-7 days before the operation to about 7-12 days after the operation.
The incidence of perioperative complications of different patients has many influencing factors, including the age, sex, nutritional status, diseases and operative modes of the patients, and the incidence of perioperative complications in different periods is different.
At present, perioperative complication prediction and prevention are determined by doctors according to experience, are limited by personal knowledge levels and clinical experience of the doctors, and often cannot judge the occurrence probability of perioperative complications in different periods and whether active prevention is needed, and particularly rare complications are often overlooked.
Therefore, a computer prediction method based on the existing database is needed to be researched to scientifically capture the occurrence probability and occurrence rule of complications in different periods of perioperative period.
Disclosure of Invention
The invention provides a perioperative complication prediction method and a perioperative complication prediction system, which are used for solving the technical problem that doctors cannot accurately predict and prevent perioperative complications.
In order to solve the technical problems, the technical scheme provided by the invention is as follows:
a perioperative complication prediction method comprises the following steps:
acquiring existing perioperative complication data and constructing a perioperative complication database;
carrying out layered random sampling from a complication database in the perioperative period according to three stages of preoperative, intraoperative and postoperative;
dividing the sampling data of each stage into a training set, a verification set and a test set according to a proportion, and respectively training to obtain a complication occurrence probability prediction model and a complication occurrence time prediction model of each stage;
and predicting the perioperative complication occurrence probability and complication occurrence time of the patient by adopting a complication occurrence probability prediction model and a complication occurrence time prediction model.
Preferably, the method further comprises: acquiring corresponding examination items and preventive measure data of various complications in the perioperative period, and establishing a perioperative complication preventive database;
after the perioperative complication occurrence probability and the complication occurrence time of the patient are obtained through prediction, ranking the first three complications according to the complication occurrence probability, and inquiring and returning corresponding examination items of the complications from a perioperative complication prevention database;
and after the inspection conclusion of the corresponding inspection item is obtained, determining whether to inquire and return preventive measure data from a perioperative complication prevention database according to the inspection conclusion.
Preferably, the sampling data of each stage is proportionally divided into a training set, a validation set and a test set, and the proportion is that the ratio of the training set to the validation set to the test set is 7: 2: 1.
preferably, the existing perioperative complication data comprises:
the basic conditions of a patient, including: age, gender, height, weight, nutritional status, mental status, past medical history, and family medical history;
various relevant medical examination data of the patient; a procedure to be performed by the patient; and the time of occurrence of the complication, the type of the complication, and the incidence rate corresponding to the type of the complication in the patient.
Preferably, the method further comprises: after a perioperative complication database is constructed, preprocessing original data in the perioperative complication database, wherein the preprocessing comprises the following steps: cleaning, feature screening and feature combination.
Preferably, the training of the prediction model of the occurrence probability of complications and the prediction model of the occurrence time of complications in each stage respectively comprises the following steps:
training the training set in each stage by using a GBDT model to obtain a primary prediction model;
carrying out cross validation on the primary prediction model by using validation set data, and selecting a secondary prediction model with best prediction effect and a hyper-parameter combination;
testing the prediction result of the secondary prediction model by using the test set, and determining the secondary prediction model as a final prediction model if the prediction result of the secondary prediction model to the test set meets the requirement; otherwise, further adjusting the hyper-parameter combination until the prediction result of the secondary prediction model to the test set meets the requirement, and determining the model as a final prediction model; the final prediction models are a complication occurrence probability prediction model and a complication occurrence time prediction model.
The present invention also provides a computer system comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of any of the methods described above when executing the computer program.
The invention has the following beneficial effects:
1. the perioperative complication prediction method and the perioperative complication prediction system adopt a mode of training a prediction model, and can capture and learn the difference of the occurrence probability of complications of different patients in different operations from a massive complication database by means of strong computing power of a computer and an artificial intelligence algorithm, and construct the prediction model of the complications of different patients in different perioperative stages in different operations so as to predict the occurrence probability and the occurrence time of the complications.
2. In a preferred scheme, the perioperative complication prediction method and the perioperative complication prediction system can call existing corresponding data after the prediction result of the occurrence time and probability of complications is obtained, suggest to further improve medical examination, and give out relevant preventive measures according to the combination of the medical examination result and the relevant data of the previous patient.
In addition to the objects, features and advantages described above, other objects, features and advantages of the present invention are also provided. The present invention will be described in further detail below with reference to the accompanying drawings.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate embodiments of the invention and, together with the description, serve to explain the invention and not to limit the invention. In the drawings:
FIG. 1 is a schematic flow chart of a perioperative complication prediction method according to a preferred embodiment of the present invention.
Detailed Description
The embodiments of the invention will be described in detail below with reference to the drawings, but the invention can be implemented in many different ways as defined and covered by the claims.
Referring to fig. 1, the perioperative complication prediction method of the present invention comprises the following steps:
s1, obtaining the existing perioperative complication data, and constructing a perioperative complication database (which can also comprise various perioperative complication related influencing factors and preventive measures); in this embodiment, the existing perioperative complication data used includes: the basic conditions of a patient, including: age, gender, height, weight, nutritional status, mental status, past medical history, and family medical history; various relevant medical examination data of the patient; a procedure to be performed by the patient; and the time of occurrence of the complication, the type of the complication, and the incidence rate corresponding to the type of the complication in the patient.
In this embodiment, after the perioperative complication database is constructed, (before the database is called or sampled) the original data in the perioperative complication database may be preprocessed, where the preprocessing includes: cleaning, feature screening and feature combination. The data cleaning comprises the steps of removing or modifying abnormal data, removing or complementing missing data and removing repeated data. The feature screening is to select features with differences and relevance to model learning targets (for example, a patient has high blood sugar, high blood pressure, high density lipoprotein and high uric acid, and a complication (cerebral hemorrhage) is generated, but the high density lipoprotein and the high uric acid have no relevance to the cerebral hemorrhage and belong to the features without relevance to the cerebral hemorrhage). A combination of features is a multiplication of one feature by itself or another feature.
S2, performing layered random sampling from a perioperative complication database according to three stages of preoperative, intraoperative and postoperative; perioperative refers to the period of time during which the patient decides to begin surgical treatment until the surgical-related treatment is substantially completed. Preoperative means deciding on surgical treatment until surgery; the intraoperative refers to the operation process; postoperative refers to a closely related recovery time after the end of surgery, typically about 7-12 days. Every disease of a patient can cause risks, and the risks have different probabilities before, during and after the operation, and some risks only occur after the operation (some risks only occur before and some risks only occur during the operation), namely, the database can be divided into three sub-databases before sampling according to the situations before, during and after the operation.
And S3, dividing the sampling data of each stage into a training set, a verification set and a test set according to the proportion (in the embodiment, the ratio of the training set to the verification set to the test set is 7: 2: 1), and respectively training to obtain a complication occurrence probability prediction model and a complication occurrence time prediction model of each stage. The following steps can be preferably employed:
s301, training the training set in each stage by using a GBDT (Gradient Boosting Decision Tree) model to obtain a primary prediction model;
s302, cross validation is carried out on the primary prediction model by using validation set data, and a secondary prediction model of a hyper-parameter combination with the best prediction effect is selected; the hyper-parameter is a parameter value set before the learning is started, for example: learning rate, iteration times, the number of hidden layers, and the like.
S303, testing the prediction result of the secondary prediction model by using the test set, and determining the prediction model as the final prediction model if the prediction result of the secondary prediction model to the test set meets the requirements (in the model training optimization process, the error is used as the optimization basis, the smaller the error is, the better the error is, and the iteration can be stopped when the error meets the set requirement; otherwise, further adjusting the hyper-parameter combination until the prediction result of the secondary prediction model to the test set meets the requirement, and determining the model as a final prediction model; the final prediction models are a complication occurrence probability prediction model and a complication occurrence time prediction model.
After the final prediction model is obtained, the prediction model can be packaged into application software or a webpage, only the user (usually a doctor inputs from a terminal) needs to extract or input the relevant data of the patient, and the trainer automatically captures the difference between the occurrence probabilities of the complications of different patients, so that the relation among all indexes of the patients with the occurrence rates of the complications at all stages can be learned, and the prediction result can be obtained. The patient provides the indices in the database as comprehensively as possible, and generally the more comprehensive the indices of the patient are, the more accurate the prediction is.
And S4, predicting the perioperative complication occurrence probability and complication occurrence time of the patient by adopting the complication occurrence probability prediction model and the complication occurrence time prediction model.
By means of training the prediction model and with the help of powerful computing capacity of a computer and an artificial intelligence algorithm, the difference of the occurrence probability of complications of different patients during different operations can be captured and learned from a massive complication database, and the prediction model of the complications of different patients during different operations in different perioperative stages is constructed so as to predict the occurrence probability and the occurrence time of the complications.
In practical application, on the basis of the steps, the perioperative complication prediction method can be optimized by adding the following steps:
s5, acquiring corresponding examination items and preventive measure data of various perioperative complications, and establishing a perioperative complication prevention database; this step may be performed together with step S1;
s6, after the perioperative complication occurrence probability and complication occurrence time of the patient are predicted, ranking the first three complications according to the complication occurrence probability, and inquiring and returning corresponding examination items of the complications from the perioperative complication prevention database; or directly inquiring and returning preventive measure data from a perioperative complication preventive database (see fig. 1, in case of not making corresponding examination items or not making subsequent examination items, step S7 is not performed any more);
s7, after the inspection conclusion of the corresponding inspection item is obtained, determining whether to inquire and return preventive measure data from a perioperative complication preventive database according to the inspection conclusion; if necessary, the process may return to step S6 to predict the complication occurrence probability and complication occurrence time of the complication again based on the newly added examination findings.
Through the steps, the existing corresponding data can be called after the occurrence time and probability prediction results of the complications are obtained, further improvement of medical examination is suggested, and relevant preventive measures are suggested according to the combination of the medical examination results and the relevant data of the previous patient.
The present embodiment also provides a computer system, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the steps of the method of the above embodiment are implemented.
The invention has the following beneficial effects:
1. the perioperative complication prediction method and the perioperative complication prediction system can capture and learn the difference of the occurrence probability of the complications of different patients during different operations from a massive complication database by means of the powerful computing power of a computer and an artificial intelligence algorithm,
2. in a preferred scheme, the perioperative complication prediction method and the perioperative complication prediction system can call existing corresponding data after the prediction result of the occurrence time and probability of complications is obtained, suggest to further improve medical examination, and give out relevant preventive measures according to the combination of the medical examination result and the relevant data of the previous patient.
In conclusion, the invention constructs the prediction model of the complications occurring in different perioperative stages when different patients carry out different operations by adopting the mode of training the prediction model so as to predict the occurrence probability and the occurrence time of the complications. Can avoid the limitation of doctors, personal knowledge level and clinical experience or increase the risk of perioperative complications by neglecting. Furthermore, the medical examination is further improved according to the prediction result, so that the problem of insufficient experience of doctors is solved, and the scientificity and pertinence of subsequent suggestions can be ensured. Through the prediction of the complications, the vigilance of doctors can be improved, and corresponding preventive measures are taken, so that the occurrence of the complications is reduced, and the perioperative risk is reduced.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (7)
1. A perioperative complication prediction method is characterized by comprising the following steps:
acquiring existing perioperative complication data and constructing a perioperative complication database;
carrying out layered random sampling from a complication database in the perioperative period according to three stages of preoperative, intraoperative and postoperative;
dividing the sampling data of each stage into a training set, a verification set and a test set according to a proportion, and respectively training to obtain a complication occurrence probability prediction model and a complication occurrence time prediction model of each stage;
and predicting the perioperative complication occurrence probability and complication occurrence time of the patient by adopting the complication occurrence probability prediction model and the complication occurrence time prediction model.
2. The perioperative complication prediction method according to claim 1, characterized in that it further comprises: acquiring corresponding examination items and preventive measure data of various complications in the perioperative period, and establishing a perioperative complication preventive database;
after the perioperative complication occurrence probability and the complication occurrence time of the patient are obtained through prediction, ranking the first three complications according to the complication occurrence probability, and inquiring and returning corresponding examination items of the complications from a perioperative complication prevention database;
and after the inspection conclusion of the corresponding inspection item is obtained, determining whether to inquire and return preventive measure data from a perioperative complication prevention database according to the inspection conclusion.
3. The perioperative complication prediction method according to claim 1, characterized in that the sampled data of each stage is proportionally divided into a training set, a validation set and a test set, the proportion being the ratio of the training set, the validation set and the test set is 7: 2: 1.
4. the perioperative complication prediction method according to claim 1, characterized in that the existing perioperative complication data comprises:
the basic conditions of a patient, including: age, gender, height, weight, nutritional status, mental status, past medical history, and family medical history;
various relevant medical examination data of the patient; a procedure to be performed by the patient; and the time of occurrence of the complication, the type of the complication, and the incidence rate corresponding to the type of the complication in the patient.
5. The perioperative complication prediction method according to claim 1, characterized in that it further comprises: after a perioperative complication database is constructed, preprocessing original data in the perioperative complication database, wherein the preprocessing comprises the following steps: cleaning, feature screening and feature combination.
6. The perioperative complication prediction method according to any of claims 1 to 5, wherein the training of the respective complication occurrence probability prediction model and complication occurrence time prediction model for each stage comprises the following steps:
training the training set in each stage by using a GBDT model to obtain a primary prediction model;
carrying out cross validation on the primary prediction model by using validation set data, and selecting a secondary prediction model with best prediction effect and a hyper-parameter combination;
testing the prediction result of the secondary prediction model by using a test set, and determining the secondary prediction model as a final prediction model if the prediction result of the secondary prediction model to the test set meets the requirement; otherwise, further adjusting the hyper-parameter combination until the prediction result of the secondary prediction model to the test set meets the requirement, and determining the model as a final prediction model; the final prediction model is the complication occurrence probability prediction model and the complication occurrence time prediction model.
7. A computer system comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the steps of the method of any of the preceding claims 1 to 6 are performed when the computer program is executed by the processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010316073.7A CN111524598A (en) | 2020-04-21 | 2020-04-21 | Perioperative complication prediction method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010316073.7A CN111524598A (en) | 2020-04-21 | 2020-04-21 | Perioperative complication prediction method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111524598A true CN111524598A (en) | 2020-08-11 |
Family
ID=71904085
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010316073.7A Pending CN111524598A (en) | 2020-04-21 | 2020-04-21 | Perioperative complication prediction method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111524598A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111986761A (en) * | 2020-09-03 | 2020-11-24 | 平安国际智慧城市科技股份有限公司 | Multi-dimensional complication information extraction method and device, electronic equipment and medium |
| CN112863692A (en) * | 2021-01-12 | 2021-05-28 | 宁波大学医学院附属医院 | Perioperative drug adverse reaction assessment model construction method |
| 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 |
| CN113517077A (en) * | 2021-06-18 | 2021-10-19 | 东莞市人民医院 | Control method, system and storage medium for predicting efficacy of hip external inversion |
| CN115995298A (en) * | 2023-03-21 | 2023-04-21 | 中国医学科学院阜外医院 | Method and system for determining occurrence probability of AKI after heart operation and auxiliary decision-making 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 |
| CN116825356A (en) * | 2023-07-12 | 2023-09-29 | 中国医学科学院基础医学研究所 | Multi-association surgery complication risk assessment method, system and computing equipment |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111009322A (en) * | 2019-10-21 | 2020-04-14 | 四川大学华西医院 | Perioperative risk assessment and clinical decision intelligent auxiliary system |
-
2020
- 2020-04-21 CN CN202010316073.7A patent/CN111524598A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111009322A (en) * | 2019-10-21 | 2020-04-14 | 四川大学华西医院 | Perioperative risk assessment and clinical decision intelligent auxiliary system |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111986761A (en) * | 2020-09-03 | 2020-11-24 | 平安国际智慧城市科技股份有限公司 | Multi-dimensional complication information extraction method and device, electronic equipment and medium |
| CN112863692A (en) * | 2021-01-12 | 2021-05-28 | 宁波大学医学院附属医院 | Perioperative drug adverse reaction assessment model construction method |
| 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 |
| CN113517077A (en) * | 2021-06-18 | 2021-10-19 | 东莞市人民医院 | Control method, system and storage medium for predicting efficacy of hip external inversion |
| 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 |
| CN115995298A (en) * | 2023-03-21 | 2023-04-21 | 中国医学科学院阜外医院 | Method and system for determining occurrence probability of AKI after heart operation and auxiliary decision-making system |
| CN115995298B (en) * | 2023-03-21 | 2023-06-09 | 中国医学科学院阜外医院 | Method and system for determining occurrence probability of AKI after heart operation and auxiliary decision-making system |
| CN116825356A (en) * | 2023-07-12 | 2023-09-29 | 中国医学科学院基础医学研究所 | Multi-association surgery complication risk assessment method, system and computing equipment |
| CN116825356B (en) * | 2023-07-12 | 2024-02-06 | 中国医学科学院基础医学研究所 | Multi-association surgery complication risk assessment method, system and computing equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111524598A (en) | Perioperative complication prediction method and system | |
| US20210249138A1 (en) | Disease risk prediction device, disease risk prediction method, and disease risk prediction program | |
| JP2020513615A (en) | Decentralized diagnostic workflow training of deep learning neural networks | |
| CN108784655A (en) | Rapid evaluation for medical patient and consequences analysis | |
| JP2012221508A (en) | System and computer readable medium for predicting patient outcomes | |
| CN113066574B (en) | Neural network-based aneurysm rupture prediction method, device and storage medium | |
| US20240331813A1 (en) | Computer-implemented method and device for carrying out a medical laboratory value analysis | |
| Simon et al. | Survival association rule mining towards type 2 diabetes risk assessment | |
| CN112967803A (en) | Early mortality prediction method and system for emergency patients based on integrated model | |
| CN116052882A (en) | Pheochromocytoma postoperative hypertension complication prediction system based on machine learning | |
| CN117152827A (en) | Training method of myopia prediction model, myopia prediction method and device | |
| CN108595432A (en) | Medical document error correction method | |
| CN116825359A (en) | VTE risk early warning method, system, electronic equipment and computer readable medium | |
| CN115862850A (en) | Modeling method and device of hepatocellular carcinoma monitoring model based on longitudinal multidimensional data | |
| Gupta et al. | Towards an AI-based objective prognostic model for quantifying wound healing | |
| CN113066531B (en) | Risk prediction method, risk prediction device, computer equipment and storage medium | |
| CN117238522B (en) | Febuxostat curative effect prediction system, febuxostat curative effect prediction equipment and febuxostat curative effect prediction medium | |
| CN114203306A (en) | Medical event prediction model training method, medical event prediction method and device | |
| CN114864093B (en) | Apparatus, method and storage medium for disease prediction based on fundus image | |
| CN115954102A (en) | Artificial joint prosthesis peripheral infection diagnosis model and diagnosis system | |
| CN114420298A (en) | Multi-stage prediction system and equipment for ineffective recanalization in acute ischemic stroke intravascular treatment | |
| US20220068485A1 (en) | Computing system that generates patient-specific outcome predictions | |
| Kavya et al. | Heart Disease Prediction Using Logistic Regression | |
| KR102358841B1 (en) | Electronic device for predicting side effects of joint replacement surgery based on pre-operative data and operation method thereof | |
| JP5796319B2 (en) | Inspection result management apparatus, inspection result management program, and inspection result management method |
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 |