CN115910323A - Treatment scheme selection method, device, equipment and storage medium - Google Patents
Treatment scheme selection method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN115910323A CN115910323A CN202211435174.1A CN202211435174A CN115910323A CN 115910323 A CN115910323 A CN 115910323A CN 202211435174 A CN202211435174 A CN 202211435174A CN 115910323 A CN115910323 A CN 115910323A
- Authority
- CN
- China
- Prior art keywords
- treatment
- case
- clustering
- data
- center
- 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
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention belongs to the technical field of computers, and discloses a treatment scheme selection method, a treatment scheme selection device, treatment scheme selection equipment and a storage medium. The method comprises the steps of obtaining physiological index data corresponding to a case to be recommended; comparing the physiological index data with the standard index data to determine abnormal index data; determining a case classification corresponding to a case to be recommended according to the abnormal index data through a preset classification model; searching a clustering result corresponding to case classification, and determining a target clustering center according to the clustering result and abnormal index data; and selecting a target treatment scheme from a plurality of treatment schemes corresponding to the target clustering center. Because similar target treatment schemes can be selected for recommendation according to abnormal index data corresponding to a case to be recommended in the modes of classification, clustering and the like, a doctor can be helped to select a proper treatment scheme, the workload of the doctor can be greatly reduced, and the phenomena of misdiagnosis or missed diagnosis and the like caused by too busy conditions are avoided.
Description
Technical Field
The present invention relates to the field of computer technologies, and in particular, to a method, an apparatus, a device, and a storage medium for selecting a treatment plan.
Background
At present, different treatment schemes are adopted for the same disease, the paid cost is not wanted, the obtained treatment effects are different, in the prior art, the treatment scheme can be selected only by the experience of a doctor, the reasonable treatment scheme is difficult to guarantee to be given depending on the experience of the doctor, the work of the doctor is busy at present, and the phenomenon of misdiagnosis or missed diagnosis is easy to occur in the diagnosis of the doctor under a high-load working mode.
The above is only for the purpose of assisting understanding of the technical solution of the present invention, and does not represent an admission that the above is the prior art.
Disclosure of Invention
The invention mainly aims to provide a treatment scheme selection method, a treatment scheme selection device, treatment scheme selection equipment and a storage medium, and aims to solve the technical problem that a reasonable treatment scheme is difficult to select in the prior art.
In order to achieve the above object, the present invention provides a treatment plan selection method, comprising the steps of:
acquiring physiological index data corresponding to a case to be recommended;
comparing the physiological index data with standard index data to determine abnormal index data;
determining a case classification corresponding to the case to be recommended according to the abnormal index data through a preset classification model;
searching a clustering result corresponding to the case classification, and determining a target clustering center according to the clustering result and the abnormal index data;
and selecting a target treatment scheme from a plurality of treatment schemes corresponding to the target clustering center.
Optionally, before the step of obtaining the physiological index data corresponding to the case to be recommended, the method further includes:
reading a plurality of diagnosis and treatment data from a case database to obtain a case diagnosis and treatment data set;
classifying the diagnosis and treatment data in the case diagnosis and treatment data set through a preset classification model, and setting a corresponding classification label;
splitting the case diagnosis and treatment data set based on the classification labels to obtain diagnosis and treatment data subsets corresponding to the classification labels;
and clustering the case diagnosis and treatment data in the diagnosis and treatment data subset to obtain a clustering result corresponding to each classification label.
Optionally, the step of clustering the case diagnosis and treatment data in the diagnosis and treatment data subset to obtain the clustering result corresponding to each classification label includes:
clustering case diagnosis and treatment data in the diagnosis and treatment data subset to obtain a plurality of clustering centers;
acquiring center case diagnosis and treatment data corresponding to each clustering center;
counting the diagnosis and treatment data of the central case to obtain a plurality of treatment schemes;
and storing the treatment scheme according to the center identification of the cluster center.
Optionally, the step of searching for the clustering result corresponding to the case classification and determining the target clustering center according to the clustering result and the abnormal index data includes:
searching in a preset classification label mapping table according to the case classification to obtain a target classification label;
searching a clustering result corresponding to the target classification label;
acquiring the spatial distance between the abnormal index data and each clustering center in the clustering result;
solving the minimum value in the space distance to obtain the minimum center distance;
and taking the clustering center corresponding to the minimum center distance as a target clustering center.
Optionally, before the step of taking the cluster center corresponding to the minimum center distance as the target cluster center, the method further includes:
calculating the difference between the space distance corresponding to each clustering center and the minimum center distance to obtain a center distance difference;
detecting whether a center distance difference smaller than a preset difference threshold exists or not;
and if the minimum center distance does not exist, the step of taking the cluster center corresponding to the minimum center distance as a target cluster center is executed.
Optionally, the step of selecting a target treatment scheme from a plurality of treatment schemes corresponding to the target cluster center includes:
acquiring a scheme ordering condition corresponding to the case to be recommended;
performing composite sequencing on a plurality of treatment schemes corresponding to the target clustering center based on the scheme sequencing conditions to obtain a sequencing result;
and selecting a target treatment scheme from the sequencing result.
Optionally, the step of obtaining the plan ranking condition corresponding to the case to be recommended includes:
acquiring a patient identifier corresponding to the case to be recommended;
searching historical patient diagnosis and treatment data according to the patient identification;
counting the historical patient diagnosis and treatment data to determine treatment preference information;
determining a regimen ordering metric based on the therapy preference information;
and generating a scheme sorting condition according to the scheme sorting index and the treatment preference information.
In addition, in order to achieve the above object, the present invention further provides a treatment plan selection device, which includes the following modules:
the index acquisition module is used for acquiring physiological index data corresponding to a case to be recommended;
the abnormality determining module is used for comparing the physiological index data with standard index data to determine abnormal index data;
the case classification module is used for determining case classification corresponding to the case to be recommended according to the abnormal index data through a preset classification model;
the center determining module is used for searching a clustering result corresponding to the case classification and determining a target clustering center according to the clustering result and the abnormal index data;
and the scheme selection module is used for selecting a target treatment scheme from a plurality of treatment schemes corresponding to the target clustering center.
In addition, in order to achieve the above object, the present invention further provides a treatment plan selection apparatus, including: a processor, a memory, and a treatment plan selection program stored on the memory and executable on the processor, the treatment plan selection program when executed implementing the steps of the treatment plan selection method as described above.
In addition, to achieve the above object, the present invention further provides a computer readable storage medium, on which a treatment plan selection program is stored, and the treatment plan selection program realizes the steps of the treatment plan selection method as described above when executed by a processor.
The method comprises the steps of obtaining physiological index data corresponding to a case to be recommended; comparing the physiological index data with the standard index data to determine abnormal index data; determining a case classification corresponding to a case to be recommended according to the abnormal index data through a preset classification model; searching a clustering result corresponding to case classification, and determining a target clustering center according to the clustering result and abnormal index data; and selecting a target treatment scheme from a plurality of treatment schemes corresponding to the target clustering center. Because similar target treatment schemes can be selected for recommendation according to abnormal index data corresponding to a case to be recommended in the modes of classification, clustering and the like, a doctor can be helped to select a proper treatment scheme, the workload of the doctor can be greatly reduced, and the phenomena of misdiagnosis or missed diagnosis and the like caused by too busy conditions are avoided.
Drawings
Fig. 1 is a schematic structural diagram of an electronic device in a hardware operating environment according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of a first embodiment of a method of selecting a treatment regimen of the present invention;
FIG. 3 is a schematic flow chart of a second embodiment of a method of selecting a treatment regimen of the present invention;
fig. 4 is a block diagram showing the construction of a first embodiment of the treatment plan selection apparatus of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and do not limit the invention.
Referring to fig. 1, fig. 1 is a schematic structural diagram of a treatment plan selection device of a hardware operating environment according to an embodiment of the present invention.
As shown in fig. 1, the electronic device may include: a processor 1001, such as a Central Processing Unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Wherein a communication bus 1002 is used to enable connective communication between these components. The user interface 1003 may include a Display (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a Wireless interface (e.g., a Wireless-Fidelity (WI-FI) interface). The Memory 1005 may be a Random Access Memory (RAM) or a Non-Volatile Memory (NVM), such as a disk Memory. The memory 1005 may alternatively be a storage device separate from the processor 1001 described previously.
Those skilled in the art will appreciate that the configuration shown in fig. 1 does not constitute a limitation of the electronic device and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components.
As shown in fig. 1, the memory 1005, which is a storage medium, may include an operating system, a network communication module, a user interface module, and a treatment plan selection program.
In the electronic apparatus shown in fig. 1, the network interface 1004 is mainly used for data communication with a network server; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 in the electronic device of the present invention may be disposed in a treatment plan selection device, and the electronic device invokes a treatment plan selection program stored in the memory 1005 through the processor 1001 and executes the treatment plan selection method provided in the embodiment of the present invention.
An embodiment of the present invention provides a method for selecting a treatment plan, and referring to fig. 2, fig. 2 is a schematic flow chart of a first embodiment of the method for selecting a treatment plan according to the present invention.
In this embodiment, the method for selecting the treatment plan includes the following steps:
step S10: and acquiring physiological index data corresponding to the case to be recommended.
It should be noted that the execution main body of this embodiment may be the treatment scheme selection device, and the treatment scheme selection device may be an electronic device such as a personal computer, a server, and the like, or may be other devices that can implement the same or similar functions, such as a smart phone, a tablet computer, and the like.
It should be noted that the case to be recommended may be case data of a patient for whom a treatment plan needs to be recommended, and the case to be recommended may be specified by a user or a manager of the treatment plan selection device. The physiological index data may be index data for characterizing the physical state of the patient, including but not limited to body temperature, heart rate, respiratory rate, etc.
Step S20: and comparing the physiological index data with standard index data to determine abnormal index data.
It should be noted that the standard index data may be physiological index data of a physically healthy person. The standard indexes of people with different ages and weights may have certain deviation, so that when the standard index data are set, a plurality of sets of standard index data of different types can be set, when comparison is needed, data such as the age, the weight, the height and the like corresponding to a case to be recommended are obtained firstly, the corresponding standard index data are searched according to the data, and then the physiological index data are compared with the standard index data.
It can be understood that the physiological index data is compared with the standard index data to determine the abnormal physiological index, so as to obtain abnormal index data.
In practical use, the physiological index data which has a deviation from the standard index data and the deviation is greater than a preset deviation threshold value can be used as abnormal index data.
Step S30: and determining the case classification corresponding to the case to be recommended according to the abnormal index data through a preset classification model.
It should be noted that the preset classification model may be a Neural network model obtained by training in advance using a model training set, and the preset classification model may be a Convolutional Neural Network (CNN) model. The preset classification model can preliminarily classify the cases according to the abnormal index data and determine the case classification of the case to be recommended, wherein the case classification can comprise heart diseases, liver diseases, kidney diseases and the like.
Step S40: and searching a clustering result corresponding to the case classification, and determining a target clustering center according to the clustering result and the abnormal index data.
The clustering result corresponding to the case classification may be a clustering result obtained by clustering based on the case clinical data corresponding to the case classification. When clustering is performed, clustering can be performed according to data such as abnormal index data, case symptoms, confirmed disease types and the like included in the used case diagnosis and treatment data. Determining the target clustering center according to the clustering result and the abnormal index data may be calculating the similarity between the abnormal index data and each clustering center in the clustering result, and using the clustering center with the highest similarity as the target clustering center.
In a specific implementation, the similarity between the abnormal index data and the cluster center may be quantified by a spatial distance between the abnormal index data and the cluster center, and therefore, the step S40 in this embodiment may include:
searching in a preset classification label mapping table according to the case classification to obtain a target classification label;
searching a clustering result corresponding to the target classification label;
acquiring the spatial distance between the abnormal index data and each clustering center in the clustering result;
solving the minimum value in the space distance to obtain the minimum center distance;
and taking the clustering center corresponding to the minimum center distance as a target clustering center.
It should be noted that the preset classification label mapping table may include a mapping relationship between the case classification and the classification label, and the mapping relationship may be preset by a manager of the treatment plan selection device according to actual needs. And searching in a preset classification label mapping table according to the case classification, wherein the target classification label is obtained by searching a classification label corresponding to the case classification in the preset classification label mapping table and taking the searched classification label as the target classification label.
In a specific implementation, the spatial distance between the obtained abnormal index data and each cluster center in the cluster result may be a euclidean distance between the calculated abnormal index data and the abnormal index data corresponding to each cluster center in the cluster result. And calculating the minimum value in the spatial distances, wherein the minimum center distance is obtained by taking the minimum value of the spatial distances between the abnormal index data and the clustering centers in the clustering result as the minimum center distance.
It can be understood that the smaller the spatial distance between the abnormal index data and the cluster center, the higher the similarity with the cluster center, and the cluster center corresponding to the minimum center distance is actually the cluster center with the highest similarity with the abnormal index data, so that the cluster center corresponding to the minimum center distance can be used as the target cluster center.
Further, in an actual situation, the similarity between the abnormal index data corresponding to the case to be detected and the plurality of cluster centers may be higher, in this case, the subsequent steps are continuously executed, the selected treatment scheme may not be appropriate, and in order to avoid this phenomenon, before the step of using the cluster center corresponding to the minimum center distance as the target cluster center, the method may further include:
calculating the difference between the space distance corresponding to each clustering center and the minimum center distance to obtain a center distance difference;
detecting whether a center distance difference smaller than a preset difference threshold exists or not;
and if the target clustering center does not exist, executing the step of taking the clustering center corresponding to the minimum center distance as the target clustering center.
It should be noted that the preset difference threshold may be preset by a manager of the treatment plan selection device according to actual needs.
In a specific implementation, the difference between the spatial distance corresponding to each cluster center and the minimum center distance is calculated, and obtaining the center distance difference may be subtracting the spatial distances corresponding to each cluster center except the cluster center corresponding to the minimum center distance from the minimum center distance, respectively, to obtain a center distance difference.
It can be understood that, if there is a center distance difference smaller than the preset difference threshold, it indicates that the similarity between the abnormal index data and other cluster centers is higher except the cluster center corresponding to the minimum center distance, and at this time, in order to avoid selecting an inappropriate treatment plan, the execution of subsequent steps may be stopped, and the relevant data may be displayed to a doctor or a manager of the treatment plan selection device, so as to facilitate manual intervention. If the center distance difference value of the preset difference value threshold value does not exist, the fact that the similarity between the abnormal index data and other clustering centers is higher except the clustering center corresponding to the minimum center distance means that the clustering centers corresponding to the minimum center distance can be directly used as the target clustering center.
Step S50: and selecting a target treatment scheme from a plurality of treatment schemes corresponding to the target clustering center.
It should be noted that, the selecting of the target treatment plan from the plurality of treatment plans corresponding to the target cluster center may be to obtain plan feedback of each treatment plan in the target cluster center and occurrence times of each feedback, determine the cure ratio of each treatment plan according to the occurrence times of the plan feedback, calculate a recommended value of the plan according to the times of normal cure and the cure ratio fed back by the plan of each treatment plan, sort the plurality of treatment plans from large to small according to the recommended value, and select a preset number of treatment plans from the front to rear in the sorting result as the target treatment plan.
For example: assuming that four schemes a, B, and C coexist in the target clustering center, wherein the number of occurrences of the scheme a is 3000, the number of occurrences of normal healing is 2700, the number of occurrences of the scheme B is 1800, the number of occurrences of normal healing is 1200, the number of occurrences of the scheme C is 2100, and the number of occurrences of normal healing is 2000, then the cure ratio corresponding to the scheme a is 2700/3000=90%, the cure ratio corresponding to the scheme B is 1200/1800=66%, the cure ratio corresponding to the scheme C is 2000/2100=95%, then the recommendation score corresponding to the scheme a is = (2700 × α - (3000-2700) = β) =90%, where α and β are preset coefficients, α + β =1, α > β, and α >0.5.
In practical use, different users may have different requirements for the healing time due to different economic abilities, and in order to ensure that the selected treatment scheme can meet the actual needs of the users as much as possible, the step S50 in this embodiment may include:
acquiring a scheme ordering condition corresponding to the case to be recommended;
performing composite sequencing on a plurality of treatment schemes corresponding to the target clustering center based on the scheme sequencing conditions to obtain a sequencing result;
and selecting a target treatment scheme from the sequencing result.
It should be noted that, the scheme ordering condition at least may include: treatment price weight, curing duration weight and the like.
In practical use, the multiple treatment schemes corresponding to the target cluster center are compositely sorted based on the scheme sorting conditions, and the sorting result can be obtained by firstly calculating the recommended value corresponding to each treatment scheme according to the above manner, then obtaining the scheme price, the scheme average recovery duration and the like of each treatment scheme to adjust the recommended value, and then sorting each treatment scheme according to the adjusted recommended value to obtain the sorting result.
For example: assuming that the recommendation score corresponding to the regimen a is 330, the treatment price is 300, the cure duration is 15 days, the weight of the treatment price contained in the regimen ranking condition is-0.3, and the weight of the cure duration is-3, the finally adjusted recommendation score is 330-300 x 0.3-3 x 15=195.
In a specific implementation, the selecting of the target treatment plan from the sorting results may be selecting, according to the sorting results, the first N treatment plans from the front to the back as the target treatment plans, where N is a preset number, and may be preset by a manager of the treatment plan selecting device according to actual needs.
Further, in order to accurately recommend a treatment plan according to the actual needs of the user, the step of obtaining the plan ranking condition corresponding to the case to be recommended in this embodiment may include:
acquiring a patient identifier corresponding to the case to be recommended;
searching historical patient diagnosis and treatment data according to the patient identification;
counting the historical patient diagnosis and treatment data to determine treatment preference information;
determining a regimen ranking indicator based on the therapy preference information;
and generating a scheme sorting condition according to the scheme sorting index and the treatment preference information.
It should be noted that the patient identifier may be a unique identifier set by the medical system for the user, and the historical patient diagnosis and treatment data may be diagnosis and treatment data recorded by the user when the user performs diagnosis and treatment in the past. The historical patient diagnosis and treatment data is counted, and the treatment preference information can be determined by reading the treatment schemes in the historical patient diagnosis and treatment data and determining the percentage interval in which the treatment schemes are sequenced in the same type of treatment schemes, so that the treatment preference information is obtained.
In practical use, determining the plan ranking index according to the treatment preference information may be determining the plan ranking index according to preference information having ranking significance in the treatment preference information.
For example: assuming that 4 treatment plans are recorded in the treatment preference information, the percentage intervals in which the prices corresponding to the treatment plans are ranked in the treatment plans of the same type are 0-10%, 30-60%, 10-30% and 0-10%, respectively, at this time, because the percentage intervals in which the prices are ranked are different each time, the preference information about the prices in the treatment preference information has no ranking significance, and therefore, the treatment prices should not be included in the plan ranking index;
if the percentage interval in which the corresponding cure time lengths are ranked in the same type of treatment scheme is 30-60%, the preference information about the cure time lengths in the treatment preference information has ranking significance, and the scheme ranking index should include the cure time lengths.
In a specific implementation, the step of generating the plan sorting condition according to the plan sorting index and the treatment preference information may be acquiring an interval weight mapping table corresponding to the plan sorting index, searching for a corresponding weight value in the interval weight mapping table according to preference information corresponding to the plan sorting index recorded in the treatment preference information, and then generating the plan sorting condition according to the weight value and the plan sorting index.
For example: assuming that the scheme ranking index only includes the healing duration, the percentage interval corresponding to the healing duration in the treatment preference information is 0-10%, and the data corresponding to the percentage interval of 0-10% in the interval weight mapping table corresponding to the healing duration is "0-10% @ -0.1", the scheme ranking condition generated at this time is the healing duration weight = -0.1.
The embodiment acquires physiological index data corresponding to a case to be recommended; comparing the physiological index data with the standard index data to determine abnormal index data; determining a case classification corresponding to a case to be recommended according to the abnormal index data through a preset classification model; searching a clustering result corresponding to case classification, and determining a target clustering center according to the clustering result and abnormal index data; and selecting a target treatment scheme from a plurality of treatment schemes corresponding to the target clustering center. Because similar target treatment schemes can be selected for recommendation according to abnormal index data corresponding to a case to be recommended in the modes of classification, clustering and the like, a doctor can be helped to select a proper treatment scheme, the workload of the doctor can be greatly reduced, and the phenomena of misdiagnosis or missed diagnosis and the like caused by over-busy cases are avoided.
Referring to fig. 3, fig. 3 is a schematic flow chart of a second embodiment of a treatment plan selection method according to the present invention.
Based on the first embodiment, before the step S10, the method for selecting a treatment plan of this embodiment further includes:
step S01: and reading a plurality of diagnosis and treatment data from the case database to obtain a case diagnosis and treatment data set.
It should be noted that the case database may be a database in which a large amount of diagnosis and treatment data is stored in advance, and a manager of the treatment plan selection device may collect data through a big data tool, collect data from various medical journals or professional medical information shared libraries, perform format conversion, cleaning, missing filling, and the like on the collected data, and store the collected data in the case database.
In practical use, the plurality of clinical data are read from the case database, and the case clinical data set is obtained by adding the plurality of clinical data read from the case database to a data set, and taking the data set as the case clinical data set after the addition is completed.
Step S02: and classifying the diagnosis and treatment data in the case diagnosis and treatment data set through a preset classification model, and setting a corresponding classification label.
It should be noted that the preset classification model may preliminarily classify diagnosis and treatment according to abnormal index data included in the diagnosis and treatment data, determine corresponding case classification, and then set a corresponding separation label for each diagnosis and treatment data according to a mapping relationship between classification and label in a preset classification label mapping table. The preset classification label mapping table may include a mapping relationship between the case classification and the classification label, and the mapping relationship may be preset by a manager of the treatment plan selection device according to actual needs.
Step S03: and splitting the case diagnosis and treatment data set based on the classification labels to obtain diagnosis and treatment data subsets corresponding to the classification labels.
It should be noted that, the case diagnosis and treatment data set is split based on the classification tags, and the diagnosis and treatment data subsets corresponding to the classification tags are obtained by dividing the diagnosis and treatment data with the same classification tag in the case diagnosis and treatment data set into the same set, and splitting the case diagnosis and treatment data set into a plurality of diagnosis and treatment data subsets, so as to obtain the diagnosis and treatment data subsets corresponding to the classification tags.
Step S04: and clustering the case diagnosis and treatment data in the diagnosis and treatment data subset to obtain a clustering result corresponding to each classification label.
It should be noted that, the case diagnosis and treatment data in the diagnosis and treatment data subsets are clustered, and the clustering result corresponding to each classification label is obtained by clustering each diagnosis and treatment data subset respectively by using a preset clustering algorithm according to data such as abnormal index data, case symptoms, confirmed disease types and the like included in the case diagnosis and treatment data, so as to obtain the clustering result corresponding to each classification label. The preset clustering algorithm may be preset by a manager of the treatment plan selection device, and the preset clustering algorithm may be a K-means clustering algorithm, and certainly, may also be other clustering algorithms with similar functions, which is not limited in this embodiment.
In practical use, in order to facilitate the selection of a treatment plan subsequently, step S04 in this embodiment may include:
clustering case diagnosis and treatment data in the diagnosis and treatment data subset to obtain a plurality of clustering centers;
acquiring center case diagnosis and treatment data corresponding to each clustering center;
counting the diagnosis and treatment data of the central case to obtain a plurality of treatment schemes;
and storing the treatment scheme according to the center identification of the cluster center.
It should be noted that, clustering the case diagnosis and treatment data in the diagnosis and treatment data subset to obtain a plurality of clustering centers may be performed according to data such as abnormal index data, case symptoms, confirmed disease types, and the like included in the case diagnosis and treatment data, and determining the corresponding position of each case diagnosis and treatment data to form a plurality of clustering centers.
In actual use, the step of obtaining the central case diagnosis and treatment data corresponding to each clustering center may be calculating a spatial distance between each case diagnosis and treatment data and the clustering center, and then taking the case diagnosis and treatment data of which the spatial distance corresponding to the clustering center is smaller than a preset judgment threshold value as the central case diagnosis and treatment data of the clustering center, so as to obtain the central case diagnosis and treatment data corresponding to each clustering center.
In a specific implementation, the central case diagnosis and treatment data is counted, and the plurality of treatment schemes are obtained by counting and summarizing treatment means, treatment feedback of each means, and occurrence times of each means which are determined to appear in each central case diagnosis and treatment data. Storing the treatment plan according to the center identifier of the cluster center may be to store the center identifier and the treatment plan in association, for example: and adding a column in the data table for storing the treatment scheme for storing the corresponding center identification.
The embodiment obtains a case diagnosis and treatment data set by reading a plurality of diagnosis and treatment data from a case database; classifying the diagnosis and treatment data in the case diagnosis and treatment data set through a preset classification model, and setting a corresponding classification label; splitting the case diagnosis and treatment data set based on the classification labels to obtain diagnosis and treatment data subsets corresponding to the classification labels; and clustering the case diagnosis and treatment data in the diagnosis and treatment data subset to obtain a clustering result corresponding to each classification label. Because a large amount of diagnosis and treatment data are collected in advance by means of big data and the like and stored in the case database, the abundance of the data is ensured, the diagnosis and treatment data are classified after the data are collected, the diagnosis and treatment data corresponding to the classification of each case are clustered respectively, and corresponding clustering results are generated, so that the treatment scheme can be quickly searched according to the clustering results when the treatment scheme needs to be recommended subsequently, and a realization basis is provided for the treatment scheme selection method.
In addition, an embodiment of the present invention further provides a storage medium, where a treatment plan selection program is stored, and the treatment plan selection program, when executed by a processor, implements the steps of the treatment plan selection method described above.
Referring to fig. 4, fig. 4 is a block diagram showing the structure of a first embodiment of the treatment plan selecting apparatus according to the present invention.
As shown in fig. 4, a treatment plan selecting apparatus according to an embodiment of the present invention includes:
the index acquisition module 10 is used for acquiring physiological index data corresponding to a case to be recommended;
an abnormality determination module 20, configured to compare the physiological index data with standard index data, and determine abnormal index data;
the case classification module 30 is configured to determine, according to the abnormal index data, a case classification corresponding to the case to be recommended through a preset classification model;
the center determining module 40 is configured to search a clustering result corresponding to the case classification, and determine a target clustering center according to the clustering result and the abnormal index data;
and the scheme selecting module 50 is used for selecting a target treatment scheme from a plurality of treatment schemes corresponding to the target clustering center.
The embodiment acquires physiological index data corresponding to a case to be recommended; comparing the physiological index data with the standard index data to determine abnormal index data; determining a case classification corresponding to a case to be recommended according to the abnormal index data through a preset classification model; searching a clustering result corresponding to case classification, and determining a target clustering center according to the clustering result and abnormal index data; and selecting a target treatment scheme from a plurality of treatment schemes corresponding to the target clustering center. Because similar target treatment schemes can be selected for recommendation according to abnormal index data corresponding to a case to be recommended in the modes of classification, clustering and the like, a doctor can be helped to select a proper treatment scheme, the workload of the doctor can be greatly reduced, and the phenomena of misdiagnosis or missed diagnosis and the like caused by too busy conditions are avoided.
Further, the index obtaining module 10 is further configured to read a plurality of diagnosis and treatment data from a case database to obtain a case diagnosis and treatment data set; classifying the diagnosis and treatment data in the case diagnosis and treatment data set through a preset classification model, and setting corresponding classification labels; splitting the case diagnosis and treatment data set based on the classification labels to obtain diagnosis and treatment data subsets corresponding to the classification labels; and clustering the case diagnosis and treatment data in the diagnosis and treatment data subset to obtain a clustering result corresponding to each classification label.
Further, the index obtaining module 10 is further configured to cluster the case diagnosis and treatment data in the diagnosis and treatment data subset to obtain a plurality of clustering centers; acquiring center case diagnosis and treatment data corresponding to each clustering center; counting the diagnosis and treatment data of the central case to obtain a plurality of treatment schemes; and storing the treatment scheme according to the center identification of the cluster center.
Further, the center determining module 40 is further configured to search in a preset classification label mapping table according to the case classification to obtain a target classification label; searching a clustering result corresponding to the target classification label; acquiring the spatial distance between the abnormal index data and each clustering center in the clustering result; solving the minimum value in the space distance to obtain the minimum center distance; and taking the clustering center corresponding to the minimum center distance as a target clustering center.
Further, the center determining module 40 is further configured to calculate a difference between a spatial distance corresponding to each clustering center and the minimum center distance, so as to obtain a center distance difference; detecting whether a center distance difference smaller than a preset difference threshold exists or not; and if the target clustering center does not exist, executing the step of taking the clustering center corresponding to the minimum center distance as the target clustering center.
Further, the plan selecting module 50 is further configured to obtain a plan ranking condition corresponding to the case to be recommended; performing composite sequencing on a plurality of treatment schemes corresponding to the target clustering center based on the scheme sequencing conditions to obtain a sequencing result; and selecting a target treatment scheme from the sequencing result.
Further, the scheme selection module 50 is further configured to obtain a patient identifier corresponding to the case to be recommended; searching historical patient diagnosis and treatment data according to the patient identification; counting the historical patient diagnosis and treatment data to determine treatment preference information; determining a regimen ordering metric based on the therapy preference information; and generating a scheme sorting condition according to the scheme sorting index and the treatment preference information.
It should be understood that the above is only an example, and the technical solution of the present invention is not limited in any way, and in a specific application, a person skilled in the art may set the technical solution as needed, and the present invention is not limited thereto.
It should be noted that the above-described work flows are only exemplary, and do not limit the scope of the present invention, and in practical applications, a person skilled in the art may select some or all of them to achieve the purpose of the solution of the embodiment according to actual needs, and the present invention is not limited herein.
In addition, the technical details that are not described in detail in this embodiment can be referred to the method for selecting a treatment plan provided in any embodiment of the present invention, and are not described herein again.
Further, it is to be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrases "comprising a," "8230," "8230," or "comprising" does not exclude the presence of other like elements in a process, method, article, or system comprising the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present invention or portions thereof that contribute to the prior art may be embodied in the form of a software product, where the computer software product is stored in a storage medium (e.g. a Read Only Memory (ROM)/RAM, a magnetic disk, and an optical disk), and includes several instructions for enabling a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. A treatment scheme selection method is characterized by comprising the following steps:
acquiring physiological index data corresponding to a case to be recommended;
comparing the physiological index data with standard index data to determine abnormal index data;
determining a case classification corresponding to the case to be recommended according to the abnormal index data through a preset classification model;
searching a clustering result corresponding to the case classification, and determining a target clustering center according to the clustering result and the abnormal index data;
and selecting a target treatment scheme from a plurality of treatment schemes corresponding to the target clustering center.
2. The method for selecting a treatment plan according to claim 1, wherein the step of obtaining the physiological index data corresponding to the case to be recommended further comprises:
reading a plurality of diagnosis and treatment data from a case database to obtain a case diagnosis and treatment data set;
classifying the diagnosis and treatment data in the case diagnosis and treatment data set through a preset classification model, and setting corresponding classification labels;
splitting the case diagnosis and treatment data set based on the classification labels to obtain diagnosis and treatment data subsets corresponding to the classification labels;
and clustering the case diagnosis and treatment data in the diagnosis and treatment data subset to obtain a clustering result corresponding to each classification label.
3. The treatment plan selection method according to claim 2, wherein the step of clustering the case clinical data in the clinical data subset to obtain the clustering result corresponding to each classification label includes:
clustering case diagnosis and treatment data in the diagnosis and treatment data subset to obtain a plurality of clustering centers;
acquiring center case diagnosis and treatment data corresponding to each clustering center;
counting the diagnosis and treatment data of the central case to obtain a plurality of treatment schemes;
and storing the treatment scheme according to the center identification of the cluster center.
4. The treatment plan selection method according to claim 1, wherein the step of searching for the clustering result corresponding to the case classification and determining the target clustering center according to the clustering result and the abnormal index data includes:
searching in a preset classification label mapping table according to the case classification to obtain a target classification label;
searching a clustering result corresponding to the target classification label;
acquiring the spatial distance between the abnormal index data and each clustering center in the clustering result;
solving the minimum value in the space distance to obtain the minimum center distance;
and taking the clustering center corresponding to the minimum center distance as a target clustering center.
5. The method of claim 4, wherein the step of using the cluster center corresponding to the minimum center distance as the target cluster center further comprises:
calculating the difference between the space distance corresponding to each clustering center and the minimum center distance to obtain a center distance difference;
detecting whether a center distance difference smaller than a preset difference threshold exists or not;
and if the target clustering center does not exist, executing the step of taking the clustering center corresponding to the minimum center distance as the target clustering center.
6. The method of claim 1-5, wherein the step of selecting a target treatment plan from a plurality of treatment plans corresponding to the target cluster center comprises:
acquiring a scheme ordering condition corresponding to the case to be recommended;
performing composite sequencing on a plurality of treatment schemes corresponding to the target clustering center based on the scheme sequencing conditions to obtain a sequencing result;
and selecting a target treatment scheme from the sequencing result.
7. The treatment plan selection method according to claim 6, wherein the step of obtaining the plan ranking condition corresponding to the case to be recommended includes:
acquiring a patient identifier corresponding to the case to be recommended;
searching historical patient diagnosis and treatment data according to the patient identification;
counting the historical patient diagnosis and treatment data to determine treatment preference information;
determining a regimen ranking indicator based on the therapy preference information;
and generating a scheme sorting condition according to the scheme sorting index and the treatment preference information.
8. A treatment scheme selection device is characterized by comprising the following modules:
the index acquisition module is used for acquiring physiological index data corresponding to a case to be recommended;
the abnormality determining module is used for comparing the physiological index data with standard index data to determine abnormal index data;
the case classification module is used for determining case classification corresponding to the case to be recommended according to the abnormal index data through a preset classification model;
the center determining module is used for searching a clustering result corresponding to the case classification and determining a target clustering center according to the clustering result and the abnormal index data;
and the scheme selection module is used for selecting a target treatment scheme from a plurality of treatment schemes corresponding to the target clustering center.
9. A treatment plan selection device, the treatment plan selection device comprising: a processor, a memory, and a treatment plan selection program stored on the memory and executable on the processor, the treatment plan selection program when executed implementing the steps of the treatment plan selection method of any one of claims 1-7.
10. A computer-readable storage medium, wherein a treatment plan selection program is stored on the computer-readable storage medium, and when executed by a processor, the treatment plan selection program implements the steps of the treatment plan selection method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211435174.1A CN115910323B (en) | 2022-11-16 | 2022-11-16 | Treatment scheme selection method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211435174.1A CN115910323B (en) | 2022-11-16 | 2022-11-16 | Treatment scheme selection method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115910323A true CN115910323A (en) | 2023-04-04 |
| CN115910323B CN115910323B (en) | 2023-09-29 |
Family
ID=86487286
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211435174.1A Active CN115910323B (en) | 2022-11-16 | 2022-11-16 | Treatment scheme selection method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115910323B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116665871A (en) * | 2023-08-02 | 2023-08-29 | 上海迎智正能文化发展有限公司 | Monitoring scheme optimization method and system based on big data |
| CN116798646A (en) * | 2023-08-17 | 2023-09-22 | 四川互慧软件有限公司 | Snake injury prognosis prediction method and device based on clustering algorithm and electronic equipment |
| CN117542536A (en) * | 2024-01-10 | 2024-02-09 | 中国人民解放军海军青岛特勤疗养中心 | Intelligent nursing method and system based on physical examination data |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150131867A1 (en) * | 2013-11-08 | 2015-05-14 | Institute For Information Industry | Treatment recommending system of plant symptoms, method and non-transitory computer-readable medium |
| US20160267235A1 (en) * | 2015-03-12 | 2016-09-15 | Wayne State University | PINS: A Perturbation Clustering Approach for Data Integration and Disease Subtyping |
| US20180211012A1 (en) * | 2017-01-25 | 2018-07-26 | Ucb Biopharma Sprl | Method and system for predicting optimal epilepsy treatment regimes |
| CN109785928A (en) * | 2018-12-25 | 2019-05-21 | 平安科技（深圳）有限公司 | Diagnosis and treatment proposal recommending method, device and storage medium |
| CN109859851A (en) * | 2018-12-27 | 2019-06-07 | 平安科技（深圳）有限公司 | A kind of therapeutic scheme recommended method and device |
| CN110610761A (en) * | 2018-06-14 | 2019-12-24 | 胡盛寿 | Hypertension auxiliary diagnosis method and system |
| CN112700838A (en) * | 2020-12-30 | 2021-04-23 | 平安科技（深圳）有限公司 | Big data-based medication scheme recommendation method and device and related equipment |
| WO2021139241A1 (en) * | 2020-05-13 | 2021-07-15 | 平安科技（深圳）有限公司 | Artificial intelligence-based patient classification method and apparatus, device, and storage medium |
| CN114366030A (en) * | 2021-12-31 | 2022-04-19 | 中国科学院苏州生物医学工程技术研究所 | Intelligent auxiliary system and method for anesthesia operation |
| CN114743632A (en) * | 2022-03-18 | 2022-07-12 | 中山大学肿瘤防治中心 | Disease treatment scheme recommendation method and device, storage medium and electronic equipment |
-
2022
- 2022-11-16 CN CN202211435174.1A patent/CN115910323B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150131867A1 (en) * | 2013-11-08 | 2015-05-14 | Institute For Information Industry | Treatment recommending system of plant symptoms, method and non-transitory computer-readable medium |
| US20160267235A1 (en) * | 2015-03-12 | 2016-09-15 | Wayne State University | PINS: A Perturbation Clustering Approach for Data Integration and Disease Subtyping |
| US20180211012A1 (en) * | 2017-01-25 | 2018-07-26 | Ucb Biopharma Sprl | Method and system for predicting optimal epilepsy treatment regimes |
| CN110610761A (en) * | 2018-06-14 | 2019-12-24 | 胡盛寿 | Hypertension auxiliary diagnosis method and system |
| CN109785928A (en) * | 2018-12-25 | 2019-05-21 | 平安科技（深圳）有限公司 | Diagnosis and treatment proposal recommending method, device and storage medium |
| CN109859851A (en) * | 2018-12-27 | 2019-06-07 | 平安科技（深圳）有限公司 | A kind of therapeutic scheme recommended method and device |
| WO2021139241A1 (en) * | 2020-05-13 | 2021-07-15 | 平安科技（深圳）有限公司 | Artificial intelligence-based patient classification method and apparatus, device, and storage medium |
| CN112700838A (en) * | 2020-12-30 | 2021-04-23 | 平安科技（深圳）有限公司 | Big data-based medication scheme recommendation method and device and related equipment |
| CN114366030A (en) * | 2021-12-31 | 2022-04-19 | 中国科学院苏州生物医学工程技术研究所 | Intelligent auxiliary system and method for anesthesia operation |
| CN114743632A (en) * | 2022-03-18 | 2022-07-12 | 中山大学肿瘤防治中心 | Disease treatment scheme recommendation method and device, storage medium and electronic equipment |
Non-Patent Citations (2)
| Title |
|---|
| 冷安明;杨静;周佐涛;张葵;: "新型冠状病毒肺炎中医诊疗方案用药规律数据挖掘", 世界科学技术-中医药现代化, no. 03 * |
| 李鹏飞;鲁法明;包云霞;曾庆田;朱冠烨;: "基于医疗过程挖掘与患者体征的药物推荐方法", 计算机集成制造系统, no. 06 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116665871A (en) * | 2023-08-02 | 2023-08-29 | 上海迎智正能文化发展有限公司 | Monitoring scheme optimization method and system based on big data |
| CN116665871B (en) * | 2023-08-02 | 2023-11-03 | 上海迎智正能文化发展有限公司 | Monitoring scheme optimization method and system based on big data |
| CN116798646A (en) * | 2023-08-17 | 2023-09-22 | 四川互慧软件有限公司 | Snake injury prognosis prediction method and device based on clustering algorithm and electronic equipment |
| CN116798646B (en) * | 2023-08-17 | 2023-11-24 | 四川互慧软件有限公司 | Snake injury prognosis prediction method and device based on clustering algorithm and electronic equipment |
| CN117542536A (en) * | 2024-01-10 | 2024-02-09 | 中国人民解放军海军青岛特勤疗养中心 | Intelligent nursing method and system based on physical examination data |
| CN117542536B (en) * | 2024-01-10 | 2024-04-12 | 中国人民解放军海军青岛特勤疗养中心 | Intelligent nursing method and system based on physical examination data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115910323B (en) | 2023-09-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115910323B (en) | Treatment scheme selection method, device, equipment and storage medium | |
| US20200027539A1 (en) | Systems and Methods for Predicting Medications to Prescribe to a Patient Based on Machine Learning | |
| CN111191020A (en) | Prescription recommendation method and system based on machine learning and knowledge graph | |
| CN111260448A (en) | Artificial intelligence-based medicine recommendation method and related equipment | |
| US10636515B2 (en) | Medical or health information search support apparatus and medical or health information search support system | |
| WO2017037103A1 (en) | Pmedia unit retrieval and related processes | |
| CN105453093A (en) | Modeling of patient risk factors at discharge | |
| CN111986744B (en) | Patient interface generation method and device for medical institution, electronic equipment and medium | |
| CN112614578B (en) | Doctor intelligent recommendation method and device, electronic equipment and storage medium | |
| CN111710429A (en) | Information pushing method and device, computer equipment and storage medium | |
| CN114334169B (en) | Medical object category decision method and device, electronic equipment and storage medium | |
| CN111639077B (en) | Data management method, device, electronic equipment and storage medium | |
| CN114416967A (en) | Method, device and equipment for intelligently recommending doctors and storage medium | |
| CN112214515A (en) | Data automatic matching method and device, electronic equipment and storage medium | |
| CN111785383A (en) | Data processing method and related equipment | |
| CN109710802B (en) | Video classification method and device | |
| CN114862140A (en) | Behavior analysis-based potential evaluation method, device, equipment and storage medium | |
| US10832822B1 (en) | Methods and systems for locating therapeutic remedies | |
| Huang et al. | Study on patient similarity measurement based on electronic medical records | |
| CN111415760A (en) | Doctor recommendation method, system, computer equipment and storage medium | |
| CN116303922A (en) | Consultation message response method, consultation message response device, computer equipment, storage medium and product | |
| CN112561935B (en) | Intelligent classification method, device and equipment for brain images | |
| WO2018081703A1 (en) | Extracting patient data to provide provider and patient data similarity scoring | |
| CN110473636B (en) | Intelligent medical advice recommendation method and system based on deep learning | |
| US10910112B2 (en) | Apparatus for patient record identification |
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 |