CN112562857A - Method, device, processor and storage medium for realizing high-risk operation prediction based on K-means clustering - Google Patents
Method, device, processor and storage medium for realizing high-risk operation prediction based on K-means clustering Download PDFInfo
- Publication number
- CN112562857A CN112562857A CN202011578837.6A CN202011578837A CN112562857A CN 112562857 A CN112562857 A CN 112562857A CN 202011578837 A CN202011578837 A CN 202011578837A CN 112562857 A CN112562857 A CN 112562857A
- Authority
- CN
- China
- Prior art keywords
- risk
- clustering
- prediction based
- means clustering
- processor
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- 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
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
Abstract
The invention relates to a method for realizing high-risk operation prediction based on K-means clustering, which comprises the steps of collecting historical cases of operation patients, preprocessing and standardizing data; extracting characteristics of the data, and screening the characteristics; analyzing and storing the K mean value cluster; improving K mean value clustering; and evaluating the operation risk according to the clustering center and predicting the high-risk operation. The invention also relates to a device, a processor and a computer readable storage medium for realizing high-risk operation prediction based on K-means clustering. By adopting the method, the device, the processor and the computer readable storage medium for realizing high-risk operation prediction based on K-means clustering, the high-risk operation can be effectively predicted, and the flow efficiency of empirical hospital management is improved. In addition, the information of the high-risk patient is provided to the doctor before the operation, so that the doctor can obtain a comprehensive evaluation of the risk of the operation patient during the operation by fully combining the objective evaluation of the computer and the subjective judgment of the doctor.
Description
Technical Field
The invention relates to the field of clinical practice, in particular to the field of surgical risk assessment, and specifically relates to a method, a device, a processor and a computer-readable storage medium for realizing high-risk surgical prediction based on K-means clustering.
Background
The operation risk assessment has important significance in clinical practice, and generally, manual comprehensive judgment is carried out according to the medical history of an operation patient, physical examination, imaging and laboratory examination results, clinical diagnosis and the like. In the field of hospital management, there is also a definition of surgical difficulty/risk indicators. For example, the RBRVS index is the payment system for medical insurance (Medicare) in the United states in 1992 for paying physician labor fees. The method is characterized in that a relative score (point number) is given to each project completed by a doctor according to three factors of technical content, direct labor time (working intensity) required by the doctor and technical risk. The RBRVS evaluates the direct labor time, technical content and risks of each operation more accurately and gives a static score which is irrelevant to the price of medical service items per region and country. This makes it possible to have a lateral comparison between hospitals that calculate workload or service volume in terms of RBRVS points. However, since the score value does not take into account the payment of the resource for generating the total RBRVS points, including the number of doctors, the number of beds, and other factors, it is lopsided to directly evaluate the performance level of the operation project among hospitals and in different years of the same hospital. The method can not be used for objectively and quantitatively evaluating the difference of the surgical technical levels of the hospital A and the hospital B, and can also be used for objectively evaluating whether the surgical level of the same department is improved in two or three years or not and providing a service project with more technical difficulty for patients. At present, the system is only used for static evaluation of the performance of a doctor in China, and performance wages are issued to the doctor according to RBRVS points acquired by departments.
However, RBRVS and some of its derived payment-based metrics have not adequately considered causal relationships between pre-operatively occurring events and intra-operative risks for patients. For example, the RBRVS may provide a point of insurance liability (PLI) of the diagnosis and treatment project to indicate the risk of the diagnosis and treatment project causing high-risk situations; DRGs will provide a risk rating for the diagnostic group and calculate mortality. The other type of index, CD type rate, is classified into A, B, C, D types according to the age, basic vital signs, disease diagnosis and treatment of patients. As one of the methods for evaluating the severity of a disease, the CD-type ratio is a comprehensive evaluation and analysis method for the severity of a disease between qualitative evaluation and quantitative analysis, and since the result of the qualitative evaluation is strongly depended on, a relatively independent and objective analysis result cannot be obtained by fully automated quantitative analysis.
In addition, there are some disease prediction systems based on big data, which can also predict some serious diseases by using support vector machine. Since the problem solved by the present invention is to predict intraoperative risk. From the sampling data of the present invention, the incidence of intraoperative risk is approximately equal to 0.3%. Supervised learning algorithms are used, such as: and a support vector machine is extremely difficult to verify the prediction accuracy through data sampling.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides a method, a device, a processor and a computer readable storage medium for realizing high-risk operation prediction based on K-means clustering, which have the advantages of accuracy, low risk and wide application range.
In order to achieve the above object, the method, apparatus, processor and computer readable storage medium for implementing high risk operation prediction based on K-means clustering of the present invention are as follows:
the method for realizing high-risk operation prediction based on K-means clustering is mainly characterized by comprising the following steps of:
(1) collecting historical cases of surgical patients, and preprocessing and standardizing data;
(2) extracting characteristics of the data, and screening the characteristics;
(3) analyzing and storing the K mean value cluster;
(4) improving K mean value clustering;
(5) and evaluating the operation risk according to the clustering center and predicting the high-risk operation.
Preferably, the characteristics screened in step (2) include preoperative test coverage, patient age, presence or absence of surgical history, rescue, BMI value, preoperative test positive rate, preoperative test coverage, preoperative test crisis value, anesthesia rating index, patient age index, surgical RVU index and doctor RVU index.
Preferably, the step (3) specifically includes the following steps:
(3.1) dividing the training samples into K clustering groups according to the similarity among the samples;
and (3.2) calculating the complication incidence rate of each cluster group, calculating the cluster center of each cluster group, and storing the obtained cluster centers, the complication incidence rates of the cluster groups and the mean values and standard deviations of all the characteristics, wherein the A-class patients in the cluster results are taken as high-risk patients.
Preferably, the step (4) is performed by K-Means + +, K-Means, Canopy algorithm, Mini-Batch K-Means algorithm, ISODATA algorithm, and Kernel K-Means algorithm.
Preferably, the step (5) specifically comprises the following steps:
(5.1) inquiring the serial number of the patient, collecting the data of the sample, and standardizing;
(5.2) comparing the distances between the data points and the clustering centers, and dividing the data points into groups in which the clustering centers with the minimum distances are located;
(5.3) if the division result is a group with the first complication occurrence rate, early warning is carried out, and a doctor is prompted to pay attention to the sample; otherwise, the evaluation is continued.
This device based on high-risk operation prediction is realized to K mean value clustering, its key feature is, the device include:
a processor configured to execute computer-executable instructions;
and the memory stores one or more computer-executable instructions, and when the computer-executable instructions are executed by the processor, the steps of the method for realizing high-risk operation prediction based on K-means clustering are realized.
The processor for realizing high-risk operation prediction based on K-means clustering is mainly characterized in that the processor is configured to execute computer executable instructions, and when the computer executable instructions are executed by the processor, the steps of the method for realizing high-risk operation prediction based on K-means clustering are realized.
The computer-readable storage medium is mainly characterized by storing a computer program thereon, wherein the computer program can be executed by a processor to realize the steps of the method for realizing high-risk operation prediction based on K-means clustering.
By adopting the method, the device, the processor and the computer readable storage medium for realizing high-risk operation prediction based on K-means clustering, the high-risk operation can be effectively predicted, and the flow efficiency of empirical hospital management is improved. In addition, the information of the high-risk patient is provided to the doctor before the operation, so that the doctor can obtain a comprehensive evaluation of the risk of the operation patient during the operation by fully combining the objective evaluation of the computer and the subjective judgment of the doctor.
Drawings
FIG. 1 is a model generation flow chart of the method for realizing high risk surgical prediction based on K-means clustering of the present invention.
FIG. 2 is a model usage flow chart of the method for realizing high risk surgical prediction based on K-means clustering of the present invention.
Fig. 3a is a probability distribution curve of the surgical risk index of each category of patients in the clustering result when K takes 3 in the method for realizing high risk surgical prediction based on K-means clustering of the present invention.
Fig. 3b is a probability distribution curve of the surgery risk index of each category of the patient in the clustering result when K takes 4 according to the method for realizing high-risk surgery prediction based on K-means clustering of the present invention.
Fig. 3c is a probability distribution curve of the surgery risk index of each category of the patient in the clustering result when K takes 5 in the method for realizing high risk surgery prediction based on K-means clustering of the present invention.
Fig. 3d is a probability distribution curve of the surgery risk index of each category of the patient in the clustering result when K takes 6 according to the method for realizing high risk surgery prediction based on K-means clustering of the present invention.
Detailed Description
In order to more clearly describe the technical contents of the present invention, the following further description is given in conjunction with specific embodiments.
The invention discloses a method for realizing high-risk operation prediction based on K-means clustering, which comprises the following steps:
(1) collecting historical cases of surgical patients, and preprocessing and standardizing data;
(2) extracting characteristics of the data, and screening the characteristics;
(3) analyzing and storing the K mean value cluster;
(4) improving K mean value clustering;
(5) and evaluating the operation risk according to the clustering center and predicting the high-risk operation.
As a preferred embodiment of the present invention, the characteristics screened in the step (2) include preoperative test coverage, patient age, presence or absence of surgical history, rescue, BMI value, preoperative test positive rate, preoperative test coverage, preoperative test crisis value, anesthesia rating index, patient age index, surgical RVU index and doctor RVU index.
As a preferred embodiment of the present invention, the step (3) specifically comprises the following steps:
(3.1) dividing the training samples into K clustering groups according to the similarity among the samples;
and (3.2) calculating the complication incidence rate of each cluster group, calculating the cluster center of each cluster group, and storing the obtained cluster centers, the complication incidence rates of the cluster groups and the mean values and standard deviations of all the characteristics, wherein the A-class patients in the cluster results are taken as high-risk patients.
As a preferred embodiment of the present invention, the step (4) is performed by K-Means + +, K-Means, Canopy algorithm, Mini-Batch K-Means algorithm, ISODATA algorithm, and Kernel K-Means algorithm.
As a preferred embodiment of the present invention, the step (5) specifically comprises the following steps:
(5.1) inquiring the serial number of the patient, collecting the data of the sample, and standardizing;
(5.2) comparing the distances between the data points and the clustering centers, and dividing the data points into groups in which the clustering centers with the minimum distances are located;
(5.3) if the division result is a group with the first complication occurrence rate, early warning is carried out, and a doctor is prompted to pay attention to the sample; otherwise, the evaluation is continued.
As a preferred embodiment of the present invention, the device for realizing high-risk surgical prediction based on K-means clustering includes:
a processor configured to execute computer-executable instructions;
and the memory stores one or more computer-executable instructions, and when the computer-executable instructions are executed by the processor, the steps of the method for realizing high-risk operation prediction based on K-means clustering are realized.
As a preferred embodiment of the present invention, the processor for implementing high-risk surgical prediction based on K-means clustering is configured to execute computer executable instructions, and when the computer executable instructions are executed by the processor, the steps of the method for implementing high-risk surgical prediction based on K-means clustering are implemented.
As a preferred embodiment of the present invention, the computer readable storage medium has a computer program stored thereon, and the computer program is executable by a processor to implement the steps of the method for implementing high risk surgical prediction based on K-means clustering as described above.
In the specific embodiment of the invention, in order to solve the problem that the surgical patient cannot be subjected to preoperative rapid and effective risk assessment, the intra-operative risk early warning based on the K-means clustering analysis is provided, and the potential high-risk patient surgical information can be exposed through accurate and efficient data analysis before an operation, so that a doctor has sufficient time to assess and avoid the potential risk through consultation and other ways.
The invention discloses a method for predicting high-risk operations based on K-means clustering, which comprises the following steps:
s1, analysis stage
S1.1 data acquisition and preparation, data preprocessing and standardization
Collecting the historical case of the operation patient, and preprocessing and standardizing the data.
S1.2 feature extraction
And performing characteristic engineering and characteristic screening on the data. The selected feature dimensions may include, but are not limited to: coverage of pre-operative tests, age of patient, presence or absence of surgical history, rescue, BMI value, positive rate of pre-operative tests, coverage of pre-operative tests, crisis value of pre-operative tests, index of anesthesia rating, age index of patient, RVU index of surgery, RVU index of doctor, etc.
S1.3K means clustering analysis and storage
And dividing the training samples into K clustering groups according to the similarity among the samples, wherein the similarity can be defined by a Euclidean distance function. Each cluster grouping calculates a complication rate and each cluster grouping calculates a cluster center. And storing the obtained cluster centers, the complication incidence rates of the cluster groups and the mean values and standard deviations of all the characteristics. The patients in class a of the clustering results were considered high risk patients.
S1.4K-means clustering improvement
S1.4.1K-Means + +, K-Means | |, and Canopy algorithm
The K-Means clustering algorithm is sensitive to the initial clustering center, the selection of initial particles can be improved by adopting a K-Means + + algorithm, and the initial conditions can be optimized by further adopting a K-Means | algorithm. In addition, the model construction can be carried out by adopting a Canopy + K-Means algorithm mixed form.
S1.4.2 Mini-Batch K-Means algorithm
The Mini-batch K-Means algorithm can be adopted to reduce the convergence time and improve the operation efficiency.
S1.4.3 ISODATA algorithm
When the data magnitude is large and the extracted feature dimension is high, an ISODATA algorithm can be adopted to select a proper K value.
S1.4.4 Kernel K-Means algorithm
And a Kernel K-Means algorithm can be adopted to map the samples to a high-dimensional feature space for clustering, so that the clustering effect is further improved.
S2, prediction stage
S2.1 evaluating operation risk according to clustering center and predicting high-risk operation
The serial number of the patient is inquired, the data of the sample is collected, the data dimension in the embodiment is 8 dimensions, and the standardization is carried out. The data points are compared to the distances of the 5 cluster centers and are divided into groups with the smallest distance of one cluster center. And when the division result is a group with the first complication incidence ranking, early warning is carried out, and a doctor is prompted to pay attention to the sample.
The embodiment discloses a method for predicting a high-risk operation based on K-means clustering, a flow diagram is shown in fig. 1 and fig. 2, and the method comprises the following steps:
s1, analysis stage
S1.1 data acquisition and preparation, data preprocessing and standardization
The historical cases of the operation patients are collected, the number of the case data adopted by the embodiment is about 11 ten thousand, and the data are preprocessed and standardized.
S1.2 feature extraction
And performing characteristic engineering and characteristic screening on the data. The characteristic dimensions used in this embodiment are 8 dimensions, which are:
coverage of pre-operative tests, positive rate of pre-operative tests, coverage of pre-operative tests, crisis values of pre-operative tests, index of anesthesia rating, patient age index, RVU index of surgery, RVU index of doctor.
S1.3K means clustering analysis and storage
In this embodiment, K is 5. And dividing the training samples into 5 clustering groups according to the similarity among the samples, wherein the similarity is defined by a Euclidean distance function. Each cluster grouping calculates a complication rate and each cluster grouping calculates a cluster center. And storing the obtained cluster centers, the complication incidence rates of cluster groups (table 1) and the mean values and standard deviations of all the characteristics (table 2).
The present example produced a cluster of patients in class a as high risk patients. The reason why K-5 is selected in this example is that when divided into 5 or 6 groups, the intraoperative risk index of class a patients approaches the maximum intraoperative risk index of all patients. Moreover, since the cluster centers are located far from all other cluster centers, the characteristics of patients in class a are more distinctive from the 5 or 6 groups than from the other groups. On the other hand, the probability distribution of patients in group 5 and the probability distribution of patients in group 6 both fit the normal distribution (as shown in fig. 3a to 3 d), and the kurtosis of the normal distribution of patients in group 5 is higher than that of patients in group 6. The higher the kurtosis, the more the patient training samples inside the cluster are, the closer to the cluster center, the more obvious the similar features of the training samples are. The group 5 patients were selected as high risk patients in view of the relatively high cohesion within the group a patients and the relatively low coupling with other patients.
S2, prediction stage
S2.1 evaluating operation risk according to clustering center and predicting high-risk operation
The serial number of the patient is inquired, the data of the sample is collected, the data dimension in the embodiment is 8 dimensions, and the standardization is carried out. The data points are compared to the distances of the 5 cluster centers and are divided into groups with the smallest distance of one cluster center. And when the division result is a group with the first complication incidence ranking, early warning is carried out, and a doctor is prompted to pay attention to the sample.
The clustering result obtained by the technical scheme can predict the corresponding high-risk operation possibility. Fig. 3a to 3d show probability distribution curves of the patient operation risk index for each category in the clustering results when K is different, where K is 3, 4, 5, and 6. Curve a identified by the mark "x" in the figure represents a high risk patient. The intraoperative risk index refers to a linear weighted sum of normalized values of eight-dimensional data of a patient, the normalization mode adopts mean value normalization, and the weight is the standard deviation of the normalized values of the data of each dimension.
For a specific implementation of this embodiment, reference may be made to the relevant description in the above embodiments, which is not described herein again.
It is understood that the same or similar parts in the above embodiments may be mutually referred to, and the same or similar parts in other embodiments may be referred to for the content which is not described in detail in some embodiments.
It should be noted that the terms "first," "second," and the like in the description of the present invention are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. Further, in the description of the present invention, the meaning of "a plurality" means at least two unless otherwise specified.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and alternate implementations are included within the scope of the preferred embodiment of the present invention in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present invention.
It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by suitable instruction execution devices. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware that is related to instructions of a program, and the program may be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.
In addition, functional units in the embodiments of the present invention may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a separate product, may also be stored in a computer readable storage medium.
The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
By adopting the method, the device, the processor and the computer readable storage medium for realizing high-risk operation prediction based on K-means clustering, the high-risk operation can be effectively predicted, and the flow efficiency of empirical hospital management is improved. In addition, the information of the high-risk patient is provided to the doctor before the operation, so that the doctor can obtain a comprehensive evaluation of the risk of the operation patient during the operation by fully combining the objective evaluation of the computer and the subjective judgment of the doctor.
In this specification, the invention has been described with reference to specific embodiments thereof. It will, however, be evident that various modifications and changes may be made thereto without departing from the broader spirit and scope of the invention. The specification and drawings are, accordingly, to be regarded in an illustrative rather than a restrictive sense.
Claims (8)
1. A method for realizing high-risk operation prediction based on K-means clustering is characterized by comprising the following steps:
(1) collecting historical cases of surgical patients, and preprocessing and standardizing data;
(2) extracting characteristics of the data, and screening the characteristics;
(3) analyzing and storing the K mean value cluster;
(4) improving K mean value clustering;
(5) and evaluating the operation risk according to the clustering center and predicting the high-risk operation.
2. The method for realizing high risk surgical prediction based on K-means clustering according to claim 1, wherein the features screened in step (2) comprise preoperative test coverage, patient age, presence or absence of surgical history, rescue, BMI value, preoperative test positive rate, preoperative examination coverage, preoperative test crisis value, anesthesia rating index, patient age index, surgical RVU index and doctor RVU index.
3. The method for realizing high risk surgical prediction based on K-means clustering according to claim 1, wherein the step (3) specifically comprises the following steps:
(3.1) dividing the training samples into K clustering groups according to the similarity among the samples;
and (3.2) calculating the complication incidence rate of each cluster group, calculating the cluster center of each cluster group, and storing the obtained cluster centers, the complication incidence rates of the cluster groups and the mean values and standard deviations of all the characteristics, wherein the A-class patients in the cluster results are taken as high-risk patients.
4. The method for realizing high risk surgical prediction based on K-Means clustering according to claim 1, wherein the step (4) is realized by K-Means + +, K-Means, Canopy algorithm, Mini-Batch K-Means algorithm, ISODATA algorithm and Kernel K-Means algorithm.
5. The method for realizing high risk surgical prediction based on K-means clustering according to claim 1, wherein the step (5) specifically comprises the following steps:
(5.1) inquiring the serial number of the patient, collecting the data of the sample, and standardizing;
(5.2) comparing the distances between the data points and the clustering centers, and dividing the data points into groups in which the clustering centers with the minimum distances are located;
(5.3) if the division result is a group with the first complication occurrence rate, early warning is carried out, and a doctor is prompted to pay attention to the sample; otherwise, the evaluation is continued.
6. The utility model provides a device for realize high-risk operation prediction based on K mean value clustering which characterized in that, the device include:
a processor configured to execute computer-executable instructions;
a memory storing one or more computer-executable instructions that, when executed by the processor, perform the steps of the method for performing high risk surgical prediction based on K-means clustering of any one of claims 1 to 5.
7. A processor for realizing high-risk operation prediction based on K-means clustering, wherein the processor is configured to execute computer executable instructions, and when the computer executable instructions are executed by the processor, the steps of the method for realizing high-risk operation prediction based on K-means clustering in any one of claims 1 to 5 are realized.
8. A computer-readable storage medium, having a computer program stored thereon, the computer program being executable by a processor to implement the steps of the method for achieving high risk surgical prediction based on K-means clustering according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011578837.6A CN112562857A (en) | 2020-12-28 | 2020-12-28 | Method, device, processor and storage medium for realizing high-risk operation prediction based on K-means clustering |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011578837.6A CN112562857A (en) | 2020-12-28 | 2020-12-28 | Method, device, processor and storage medium for realizing high-risk operation prediction based on K-means clustering |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112562857A true CN112562857A (en) | 2021-03-26 |
Family
ID=75033780
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011578837.6A Pending CN112562857A (en) | 2020-12-28 | 2020-12-28 | Method, device, processor and storage medium for realizing high-risk operation prediction based on K-means clustering |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112562857A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116052887A (en) * | 2023-03-01 | 2023-05-02 | 联仁健康医疗大数据科技股份有限公司 | Method and device for detecting excessive inspection, electronic equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106709252A (en) * | 2016-12-26 | 2017-05-24 | 重庆星空云医疗科技有限公司 | Intelligent decision-making assistance system for predicting, diagnosing, treating and controlling hospital infection |
| CN106778042A (en) * | 2017-01-26 | 2017-05-31 | 中电科软件信息服务有限公司 | Cardio-cerebral vascular disease patient similarity analysis method and system |
| 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 |
| CN111180067A (en) * | 2019-12-05 | 2020-05-19 | 济宁市第一人民医院 | Pre-operation risk assessment early warning method and device |
| CN111742061A (en) * | 2017-12-21 | 2020-10-02 | 皇家飞利浦有限公司 | Pre-operative risk stratification based on PDE4D7 expression and pre-operative clinical variables |
-
2020
- 2020-12-28 CN CN202011578837.6A patent/CN112562857A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106709252A (en) * | 2016-12-26 | 2017-05-24 | 重庆星空云医疗科技有限公司 | Intelligent decision-making assistance system for predicting, diagnosing, treating and controlling hospital infection |
| CN106778042A (en) * | 2017-01-26 | 2017-05-31 | 中电科软件信息服务有限公司 | Cardio-cerebral vascular disease patient similarity analysis method and system |
| CN111742061A (en) * | 2017-12-21 | 2020-10-02 | 皇家飞利浦有限公司 | Pre-operative risk stratification based on PDE4D7 expression and pre-operative clinical variables |
| 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 |
| CN111180067A (en) * | 2019-12-05 | 2020-05-19 | 济宁市第一人民医院 | Pre-operation risk assessment early warning method and device |
Non-Patent Citations (1)
| Title |
|---|
| DANIEL RANTI等: "K-Means Clustering to Elucidate Vulnerable Subpopulations Among Medicare Patients Undergoing Total Joint Arthroplasty", THE JOURNAL OF ARTHROPLASTY, vol. 35 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116052887A (en) * | 2023-03-01 | 2023-05-02 | 联仁健康医疗大数据科技股份有限公司 | Method and device for detecting excessive inspection, electronic equipment and storage medium |
| CN116052887B (en) * | 2023-03-01 | 2023-06-27 | 联仁健康医疗大数据科技股份有限公司 | Method and device for detecting excessive inspection, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10340040B2 (en) | Method and system for identifying diagnostic and therapeutic options for medical conditions using electronic health records | |
| Aakre et al. | Prospective validation of a near real-time EHR-integrated automated SOFA score calculator | |
| US20190156947A1 (en) | Automated information collection and evaluation of clinical data | |
| Peissig et al. | Relational machine learning for electronic health record-driven phenotyping | |
| JP2006500075A (en) | Patient data mining for lung cancer discrimination | |
| US10886025B2 (en) | Drug adverse event extraction method and apparatus | |
| CN106462662A (en) | Method and system for computer-aided patient stratification based on case difficulty | |
| JP2007524461A (en) | Mammography automatic diagnosis and decision support system and method | |
| Mohanty et al. | Machine learning for predicting readmission risk among the frail: Explainable AI for healthcare | |
| Chuck | Cost-effectiveness of 21 alternative cervical cancer screening strategies | |
| Thalji et al. | Risk assessment methods for cardiac surgery and intervention | |
| Thomassin-Naggara et al. | Artificial intelligence and breast screening: French Radiology Community position paper | |
| Pruitt et al. | A natural language processing algorithm to extract characteristics of subdural hematoma from head CT reports | |
| Fisher et al. | Dementia Population Risk Tool (DemPoRT): study protocol for a predictive algorithm assessing dementia risk in the community | |
| JP2019510317A (en) | Filtering by test value context | |
| CN112562857A (en) | Method, device, processor and storage medium for realizing high-risk operation prediction based on K-means clustering | |
| US20120253834A1 (en) | Methods, apparatuses and computer program products for facilitating display of relevant quality measures based on diagnoses | |
| de Haan et al. | Patient-specific workup of adrenal incidentalomas | |
| CN116682565A (en) | Digital medical information on-line monitoring method, terminal and medium | |
| CN113948180A (en) | Method, device, processor and computer readable storage medium for realizing mental disease image report generation processing | |
| Shi et al. | Clinical decision modeling system | |
| GUMUS | ELECTRONIC HEALTH RECORD AND PATIENT SATISFACTION IN PUBLIC HOSPITALS: MODERATING ROLE OF OPERATIONAL EFFICIENCY | |
| KR20160136875A (en) | Apparatus and method for management of performance assessment | |
| JP2020064642A (en) | Detecting device, recording medium, detecting method, and detecting program | |
| JP7333549B2 (en) | Disease risk assessment method, disease risk assessment system, and health information processing device |
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 |