Method and device for recommending disease treatment plan, storage medium, and electronic device

Abstract

The present disclosure belongs to the field of medical artificial intelligence, and relates to a method and device for recommending disease treatment plans, a storage medium, and an electronic device. The method includes: obtaining target information corresponding to the patient; wherein the target information includes basic information of the patient and characteristic information of the disease suffered by the patient; based on the target information, clustering the treatment plans determined from multiple recommendation modules to obtain clustering results, and assigning corresponding recommendation levels to the clustering results according to the medical support evidence corresponding to the treatment plans in the clustering results; wherein the multiple recommendation modules are based on different medical support evidence respectively; sorting the clustering results according to the recommendation level to obtain sorting results, and displaying the treatment plans for the disease suffered by the patient according to the sorting results. In the present disclosure, the treatment plan is determined from multiple recommendation modules based on different medical support evidence, which combines the advantages of different recommendation modules and improves the accuracy of the displayed treatment plan.

Description

Technical Field

[0001] The present disclosure relates to the field of medical artificial intelligence, and in particular to a method for recommending a disease treatment plan, a device for recommending a disease treatment plan, a computer-readable storage medium, and an electronic device. Background Art

[0002] In the field of medical artificial intelligence, clinical decision support systems have always been a hot topic of research. Through clinical decision support systems, doctors can be recommended treatment plans for patients' diseases.

[0003] In the related art, there are three different clinical decision support systems. Among them, in the clinical decision support system based on clinical guidelines, the low frequency of clinical guideline updates and the lack of clinical research on specific patient groups in the clinical guidelines reduce the accuracy and timeliness of the recommended treatment plans. In the clinical decision support system based on references, the references may conflict with the clinical guidelines, or the therapeutic drugs in the references are not applicable in the country, so a standardized treatment plan cannot be recommended. In the clinical decision support system based on similar medical records, the treatment plans in the historical medical records are not the latest treatment plans, which reduces the timeliness of the recommended treatment plans.

[0004] In view of this, there is an urgent need in the art to develop a new method and device for recommending disease treatment plans.

[0005] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0006] The purpose of the present disclosure is to provide a method for recommending a disease treatment plan, a device for recommending a disease treatment plan, a computer-readable storage medium and an electronic device, thereby at least to a certain extent overcoming the problems of low standardization, low accuracy and low timeliness of the recommended treatment plans caused by related technologies.

[0007] Other features and advantages of the present disclosure will become apparent from the following detailed description, or may be learned in part by the practice of the present disclosure.

[0008] According to a first aspect of an embodiment of the present invention, a method for recommending a disease treatment plan is provided, the method comprising: obtaining target information corresponding to a patient; wherein the target information comprises basic information of the patient and characteristic information of the disease suffered by the patient; based on the target information, clustering treatment plans determined from a plurality of recommendation modules to obtain a clustering result, and according to medical supporting evidence corresponding to the treatment plan in the clustering result, assigning a corresponding recommendation level to the clustering result; wherein a plurality of the recommendation modules are respectively based on different medical supporting evidence; sorting the clustering results according to the recommendation level to obtain a sorting result, and displaying the treatment plan for the disease suffered by the patient according to the sorting result.

[0009] In an exemplary embodiment of the present invention, the multiple recommendation modules include a recommendation module based on clinical guidelines, a recommendation module based on medical literature, and a recommendation module based on historical medical records; based on the target information, clustering the treatment plans determined from the multiple recommendation modules to obtain a clustering result includes: based on the target information, using the recommendation module based on clinical guidelines to perform decision rule operations to determine a first treatment plan corresponding to the recommendation module based on clinical guidelines; matching target medical documents corresponding to the target information in the medical documents corresponding to the recommendation module based on medical literature, so as to use the second treatment plan corresponding to the target medical document as the treatment plan determined from the recommendation module based on medical literature; searching for the target medical record corresponding to the target information in the recommendation module based on historical medical records, so as to use the third treatment plan corresponding to the target medical record as the treatment plan determined from the recommendation module based on historical medical records; clustering the first treatment plan, the second treatment plan, and the third treatment plan to obtain a clustering result.

[0010] In an exemplary embodiment of the present invention, clustering the first treatment plan, the second treatment plan and the third treatment plan to obtain a clustering result includes: aggregating the first treatment plan, the second treatment plan and the third treatment plan to obtain a summary result; clustering the summary result according to the plan content of the first treatment plan, the plan content of the second treatment plan and the plan content of the third treatment plan to obtain a clustering result.

[0011] In an exemplary embodiment of the present invention, assigning a corresponding recommendation level to the clustering results based on the medical support data corresponding to the treatment plans in the clustering results includes: determining the medical support evidence corresponding to all the treatment plans in the clustering results, and determining the evidence priority corresponding to the medical support evidence; determining a target treatment plan in each category of the treatment plans based on the evidence priority, and determining the recommendation level corresponding to the target treatment plan, so as to assign the corresponding recommendation level to each category in the clustering results.

[0012] In an exemplary embodiment of the present invention, determining the recommendation level corresponding to the target treatment plan to assign the corresponding recommendation level to each category in the clustering results includes: determining the target medical support evidence for supporting the target treatment plan, and determining the evidence level corresponding to the target medical support evidence; determining a recommendation level having a level mapping relationship with the evidence level, to assign the corresponding recommendation level to each category in the clustering results.

[0013] In an exemplary embodiment of the present invention, determining the level of evidence corresponding to the target medical supporting evidence includes: if the target treatment plan is the first treatment plan, extracting the level of evidence corresponding to the target medical supporting evidence; if the target treatment plan is the second treatment plan, determining the target medical supporting evidence to be medical literature, so as to determine the level of evidence corresponding to the target medical supporting evidence based on the literature information corresponding to the medical literature; if the target treatment plan is the third treatment plan, determining the preset evidence level as the level of evidence corresponding to the target medical supporting evidence.

[0014] In an exemplary embodiment of the present invention, the method further comprises: determining the medical supporting evidence corresponding to the treatment plan, and displaying the medical supporting evidence.

[0015] According to a second aspect of an embodiment of the present invention, a device for recommending disease treatment plans is provided, the device comprising: an acquisition module, configured to determine and acquire target information corresponding to a patient; wherein the target information comprises basic information of the patient and characteristic information of the disease suffered by the patient; a clustering module, configured to cluster treatment plans determined from a plurality of recommendation modules based on the target information to obtain clustering results, and assign corresponding recommendation levels to the clustering results according to medical supporting evidence corresponding to the treatment plans in the clustering results; wherein the plurality of recommendation modules are respectively based on different medical supporting evidence; a display module, configured to sort the clustering results according to the recommendation levels to obtain sorting results, and display the treatment plans for the disease suffered by the patient according to the sorting results.

[0016] According to a third aspect of an embodiment of the present invention, there is provided an electronic device, comprising: a processor and a memory; wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the method for recommending a disease treatment plan of any of the above exemplary embodiments is implemented.

[0017] According to a fourth aspect of an embodiment of the present invention, there is provided a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the method for recommending a disease treatment plan in any of the above exemplary embodiments is implemented.

[0018] It can be seen from the above technical solutions that the method for recommending a disease treatment plan, the device for recommending a disease treatment plan, the computer storage medium, and the electronic device in the exemplary embodiments of the present invention have at least the following advantages and positive effects:

[0019] In the method and apparatus provided by the exemplary embodiments of the present disclosure, on the one hand, the treatment plans determined from multiple recommendation modules are clustered to obtain clustering results, and the treatment plans in the clustering results are obtained by integrating the treatment plans in multiple recommendation modules, combining the advantages of multiple recommendation modules, thereby improving the standardization, accuracy and timeliness of the treatment plans displayed subsequently; on the other hand, the recommendation level corresponding to the clustering result is determined, and the clustering results are sorted according to the recommendation level, which helps doctors select a treatment plan from the treatment plans according to the recommendation level that is ultimately used to treat patients, thereby improving the auxiliary effect of assisting doctors in determining treatment plans, and thereby improving the efficiency of doctors in determining treatment plans.

[0020] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The accompanying drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the specification are used to explain the principles of the present disclosure. Obviously, the accompanying drawings described below are only some embodiments of the present disclosure, and for ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without creative work.

[0022] Figure 1 A schematic diagram schematically illustrates a flow chart of a method for recommending a disease treatment plan in an embodiment of the present disclosure;

[0023] Figure 2 A schematic diagram schematically shows a structure of clustering results obtained by clustering treatment plans determined from multiple recommendation modules in a method for recommending disease treatment plans in an embodiment of the present disclosure;

[0024] Figure 3 A schematic diagram schematically shows a process of clustering a first treatment plan, a second treatment plan, and a third treatment plan to obtain a clustering result in a method for recommending a disease treatment plan in an embodiment of the present disclosure;

[0025] Figure 4 A schematic diagram schematically shows a flow chart of assigning corresponding recommendation levels to clustering results in a method for recommending disease treatment plans in an embodiment of the present disclosure;

[0026] Figure 5 A schematic diagram schematically shows a flow chart of assigning a corresponding recommendation level to each category in the clustering results in the method for recommending a disease treatment plan in an embodiment of the present disclosure;

[0027] Figure 6 A schematic diagram schematically illustrates a flow chart of determining the level of evidence corresponding to target medical supporting evidence in a method for recommending a disease treatment plan in an embodiment of the present disclosure;

[0028] Figure 7 A schematic diagram schematically illustrates a flow chart of a method for recommending a disease treatment plan in an application scenario in an embodiment of the present disclosure;

[0029] Figure 8 A schematic diagram schematically shows the structure of a device for recommending a disease treatment plan in an embodiment of the present disclosure;

[0030] Fig. 9 An electronic device for recommending a disease treatment plan in an embodiment of the present disclosure is schematically shown;

[0031] Fig.10 A computer-readable storage medium for a method of recommending a disease treatment plan in an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0032] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as being limited to the examples set forth herein; on the contrary, these embodiments are provided so that the present disclosure will be more comprehensive and complete, and the concepts of the example embodiments are fully conveyed to those skilled in the art. The described features, structures, or characteristics may be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced while omitting one or more of the specific details, or other methods, components, devices, steps, etc. may be adopted. In other cases, known technical solutions are not shown or described in detail to avoid obscuring various aspects of the present disclosure.

[0033] The terms "a", "an", "the" and "said" are used in this specification to indicate the presence of one or more elements / components / etc.; the terms "including" and "having" are used to express an open-ended inclusion and mean that additional elements / components / etc. may exist in addition to the listed elements / components / etc.; the terms "first" and "second" etc. are used only as labels and are not intended to limit the quantity of their objects.

[0034] In addition, the accompanying drawings are only schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings represent the same or similar parts, and their repeated descriptions will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities.

[0035] In view of the problems existing in the related art, the present disclosure proposes a method for recommending a disease treatment plan. Figure 1 A flowchart showing a recommended method for disease treatment regimen is shown, such as Figure 1 As shown, the recommended approach to disease treatment includes at least the following steps:

[0036] Step S110. Obtain target information corresponding to the patient; wherein the target information includes basic information of the patient and characteristic information of the disease suffered by the patient.

[0037] Step S120. Based on the target information, the treatment plans determined from the multiple recommendation modules are clustered to obtain clustering results, and according to the medical support evidence corresponding to the treatment plans in the clustering results, a corresponding recommendation level is assigned to the clustering results; wherein the multiple recommendation modules are based on different medical support evidence.

[0038] Step S130: Sort the clustering results according to the recommendation level to obtain a sorting result, and display a treatment plan for the disease suffered by the patient according to the sorting result.

[0039] In the method and apparatus provided by the exemplary embodiments of the present disclosure, on the one hand, the treatment plans determined from multiple recommendation modules are clustered to obtain clustering results, and the treatment plans in the clustering results are obtained by integrating the treatment plans in multiple recommendation modules, combining the advantages of multiple recommendation modules, thereby improving the standardization, accuracy and timeliness of the treatment plans displayed subsequently; on the other hand, the recommendation level corresponding to the clustering result is determined, and the clustering results are sorted according to the recommendation level, which helps doctors select a treatment plan from the treatment plans according to the recommendation level that is ultimately used to treat patients, thereby improving the auxiliary effect of assisting doctors in determining treatment plans, and thereby improving the efficiency of doctors in determining treatment plans.

[0040] The following is a detailed description of each step of the recommended method for disease treatment.

[0041] In step S110, target information corresponding to the patient is acquired; wherein the target information includes basic information of the patient and characteristic information of the disease suffered by the patient.

[0042] In an exemplary embodiment of the present disclosure, each patient has corresponding patient information, and the patient information includes basic information of the patient and characteristic information of the disease suffered by the patient, wherein the basic information of the patient may include the patient's gender, the patient's age, the patient's race and all basic information that can describe the patient, and this exemplary embodiment does not make any special limitation to this. Characteristic information refers to information that describes the characteristics of the disease suffered by the patient. Specifically, if the disease suffered by the patient is A, then the characteristic information of the patient's disease may be the time when disease A was diagnosed, the period of disease A, the current symptoms of disease A, and may also be all information that describes disease A, and this exemplary embodiment does not make any special limitation to this.

[0043] For example, the doctor currently needs to obtain a treatment plan for the gastric tumor suffered by patient X. At this time, it is necessary to obtain target information corresponding to patient X. Specifically, the target information includes the basic information of patient X and the characteristic information of the gastric tumor. The basic information of the patient includes the gender of patient X, the blood type of patient X, the race of patient X and the age of patient X. The characteristic information includes the diagnosis time of the gastric tumor, whether the gastric tumor has metastasized, and the size of the gastric tumor.

[0044] In this exemplary embodiment, obtaining the patient's target information helps to subsequently determine a treatment plan for the patient's disease based on the target information and by utilizing multiple recommendation modules, thereby improving the standardization, accuracy, and timeliness of the determined recommended treatment plan.

[0045] In step S120, based on the target information, the treatment plans determined from the multiple recommendation modules are clustered to obtain clustering results, and the clustering results are assigned corresponding recommendation levels according to the medical support evidence corresponding to the treatment plans in the clustering results; wherein the multiple recommendation modules are based on different medical support evidence.

[0046] In an exemplary embodiment of the present disclosure, multiple recommendation modules are based on different medical supporting evidences, which may be a large amount of evidence-based evidence, medical literature, or historical medical records. This exemplary embodiment does not specifically limit this.

[0047] By utilizing multiple recommendation modules and target information, treatment plans for the patient's disease can be determined respectively. After the treatment plans are determined, the treatment plans can be clustered according to their contents, and the clustering results can be assigned corresponding recommendation levels based on the medical supporting evidence corresponding to the treatment plans.

[0048] For example, there are three recommendation modules. Based on this, according to the target information XX, treatment plan A1 can be determined from the first recommendation module, treatment plans A2 and A3 can be determined from the second recommendation module, and treatment plan A4 can be determined from the third recommendation module. Moreover, since the contents of treatment plans A1 and A2 are the same, the clustering results obtained are to cluster treatment plans A1 and A2 into one category, cluster treatment plan A3 into one category, and cluster treatment plan A4 into one category. On the basis of the above clustering results, the above clustering results are assigned recommendation levels according to the medical supporting evidence corresponding to the treatment plans.

[0049] In an alternative embodiment, Figure 2 A flowchart of clustering treatment plans determined from multiple recommendation modules to obtain clustering results in a method for recommending treatment plans for a disease is shown. The multiple recommendation modules include a recommendation module based on clinical guidelines, a recommendation module based on medical literature, and a recommendation module based on historical medical records. Figure 2 As shown, the method includes at least the following steps: In step S210, based on the target information, a decision rule operation is performed using a recommendation module based on clinical guidelines to determine a first treatment plan corresponding to the recommendation module based on clinical guidelines.

[0050] Among them, multiple recommendation modules specifically include a recommendation module based on clinical guidelines, wherein clinical guidelines are treatment plans for different patients summarized by experts based on a large amount of evidence-based evidence. Therefore, the authority of the recommendation module based on clinical guidelines is high enough, and, generally speaking, when constructing a recommendation module based on clinical guidelines, the diagnosis and treatment rules will be disassembled and the disassembled diagnosis and treatment rules will be represented in the form of a decision tree. Therefore, after obtaining the target information, it is necessary to perform decision rule operations on the recommendation module based on clinical guidelines to match the first treatment plan corresponding to the target information.

[0051] In addition, the recommendation module based on clinical guidelines also records the recommendation level and evidence level corresponding to each treatment plan. The evidence level refers to the level of medical supporting evidence for the first treatment plan, and the recommendation level refers to the recommendation index for recommending the first treatment plan for treating the patient's disease. There is a certain mapping relationship between the recommendation level and the evidence level. Generally speaking, the evidence level is divided into 1A, 1B, 2A, 2B and 3, and the recommendation level is divided into I, II, III and IV.

[0052] For example, the target information obtained is XX1, and the basic information XX1 is input into the recommendation module based on clinical guidelines, and then the decision rule operation is performed according to the target information XX1 to recommend the first treatment plan that can treat the patient's disease, and the number of the first treatment plans can be one or more.

[0053] In step S220, the target medical document corresponding to the target information is matched in the medical document corresponding to the medical document-based recommendation module, so that the second treatment plan corresponding to the target medical document is used as the treatment plan determined from the medical document-based recommendation module.

[0054] Among them, multiple recommendation modules also include a recommendation module based on medical literature. Usually, natural language processing technology can be used to extract PICO information in medical literature, where P represents basic patient information related to the patient in the medical literature, I represents intervention methods, such as the drugs used to treat the above patients or whether surgery is needed to treat the above patients, C represents the intervention method of the control group, and O represents the outcome, such as comparative information between the intervention method and the control group in terms of efficacy, safety, treatment cost, etc.

[0055] After extracting the PICO information of the medical literature, a mapping relationship between the PICO information and the corresponding treatment plan will be established. In addition, a mapping relationship between the level of evidence and the treatment plan needs to be established. It is worth noting that in the recommendation module based on medical literature, the level of evidence is determined based on the effectiveness of the treatment plan derived from the medical literature, the impact factor of the journal that publishes the medical literature, and the content studied in the medical literature. Not only that, the recommendation module based on medical literature also records the recommendation level that has a mapping relationship with the level of evidence.

[0056] Based on this, when the target information is obtained, the recommendation module based on medical literature can be used to match the PICO information corresponding to the target information, and then determine a second treatment plan having a mapping relationship with the PICO information, so as to use the second treatment plan as the treatment plan determined from the recommendation module based on medical literature.

[0057] For example, the target information includes characteristic information of gastric cancer suffered by the patient. After obtaining the target information, three PICO information similar to the target information can be matched, and then three target medical documents with a mapping relationship with the above three PICO information can be queried, and the second treatment plan recorded in the above three target medical documents can be used as the treatment plan corresponding to the recommendation module based on medical documents.

[0058] In step S230, the target medical record corresponding to the target information is searched in the recommendation module based on historical medical records, so as to use the third treatment plan corresponding to the target medical record as the treatment plan determined from the recommendation module based on historical medical records.

[0059] Among them, the recommendation module also includes a recommendation module based on historical medical records. When constructing the recommendation module based on historical medical records, the patients, intervention methods, and outcomes corresponding to the medical records are added to the corresponding medical records as labels through natural language processing technology and medical logic reasoning. After obtaining the target information, the recommendation module based on historical medical records can be used to search for labels that are similar to the target information, and then the third treatment plan in the target medical record corresponding to the label is determined as the treatment plan determined from the recommendation module based on historical medical records.

[0060] For example, the target information is input into a recommendation module based on historical medical records. According to the basic information of the patient and the characteristic information of the patient's disease in the target information, the corresponding label can be matched, and then the target medical record C having a mapping relationship with the label can be searched in a large number of historical medical records, so that the third treatment plan recorded in the target medical record C can be used as the treatment plan determined from the recommendation module based on historical medical records.

[0061] In step S240, the first treatment plan, the second treatment plan, and the third treatment plan are clustered to obtain a clustering result.

[0062] After step S210, step S220 and step S230, the first treatment plan, the second treatment plan and the third treatment plan may be clustered to obtain a clustering result.

[0063] For example, the first treatment plan includes treatment plan A1, the second treatment plan includes treatment plans A2 and A3, and the third treatment plan includes treatment plan A4. Since the treatment plans A1 and A2 have the same content, the clustering results obtained after clustering the first treatment plan, the second treatment plan and the third treatment plan are that treatment plans A1 and A2 are clustered into one category, treatment plan A3 is clustered into one category, and treatment plan A4 is clustered into one category.

[0064] In this exemplary embodiment, the treatment plan is obtained from a recommendation module based on clinical guidelines, a recommendation module based on medical literature, and a recommendation module based on historical medical records, respectively, thereby avoiding the situation in the prior art where the treatment plan is obtained from only one of the above recommendation modules, improving the logic of determining the treatment plan, combining the advantages of the above three recommendation modules, and thereby improving the standardization, accuracy, and timeliness of the treatment plan displayed subsequently.

[0065] In an alternative embodiment, Figure 3 The flowchart of clustering the first treatment plan, the second treatment plan and the third treatment plan to obtain the clustering result in the method of recommending the disease treatment plan is shown as follows: Figure 3 As shown, the method includes at least the following steps: In step S310, the first treatment plan, the second treatment plan and the third treatment plan are summarized to obtain a summary result.

[0066] After respectively obtaining the first treatment plan, the second treatment plan and the third treatment plan by using the above three recommendation modules, the first treatment plan, the second treatment plan and the third treatment plan are firstly summarized.

[0067] For example, the first treatment plan obtained by the recommendation module based on clinical guidelines includes A1 and A2, the second treatment plan obtained by the recommendation module based on medical literature includes A7, A10 and A20, and the third treatment plan obtained by the recommendation module based on historical medical records includes A19. The treatment plans obtained after summary include A1, A2, A7, A10, A20 and A19.

[0068] In step S320, the summary results are clustered according to the content of the first treatment plan, the content of the second treatment plan, and the content of the third treatment plan to obtain a clustering result.

[0069] The content of the treatment plan refers to the treatment information covered by the treatment plan, specifically, the drugs used in the treatment, the use cycle of the drugs used in the treatment, and whether surgical treatment is required. This exemplary embodiment does not specifically limit this. If the content of multiple treatment plans is consistent, the multiple treatment plans can be clustered into one category to obtain a clustering result.

[0070] For example, the summarized treatment plans include A1, A2, A7, A10, A20 and A19. Since the content of treatment plan A1 is consistent with that of treatment plan A7, the content of treatment plan A2 is consistent with that of treatment plan A10, and the content of treatment plan A20 is consistent with that of treatment plan A19, the summary results are clustered and the clustering results are that treatment plan A1 and treatment plan A7 are clustered into one category, treatment plan A2 and treatment plan A10 are clustered into one category, and treatment plan A20 and treatment plan A19 are clustered into one category.

[0071] In this exemplary embodiment, on the one hand, the first treatment plan, the second treatment plan and the third treatment plan are summarized to ensure that the treatment plans in the subsequent clustering results come from multiple recommendation modules, avoiding the situation in the prior art that the treatment plans only come from a certain recommendation module, and combining the advantages of multiple recommendation modules; on the other hand, the summary results are clustered to obtain clustering results, which helps to subsequently determine the recommendation level corresponding to the clustering results, thereby improving the auxiliary effect of the treatment plan for doctors.

[0072] In an alternative embodiment, Figure 4 A flowchart of assigning corresponding recommendation levels to clustering results in a method for recommending disease treatment plans is shown, such as Figure 4 As shown, the method includes at least the following steps: In step S410, medical supporting evidence corresponding to all treatment plans in the clustering results is determined, and the evidence priority corresponding to the medical supporting evidence is determined.

[0073] Among them, the treatment plan is determined based on medical supporting evidence. If the treatment plan is the first treatment plan, the medical supporting evidence is a large amount of evidence-based evidence. If the treatment plan is the second treatment plan, the medical supporting evidence is medical literature. If the treatment plan is the third treatment plan, the medical supporting evidence is historical medical records. Since the authority of treatment plans determined by different medical supporting evidence is different, different medical supporting evidence corresponds to different evidence priorities.

[0074] For example, the clustering result obtained by clustering the summary results is that treatment plan A1 and treatment plan A7 are clustered into one category, treatment plan A2 and treatment plan A10 are clustered into one category, and treatment plan A20 and treatment plan A19 are clustered into one category.

[0075] Since Treatment Plan A1 and Treatment Plan A2 both belong to the first treatment plan, the medical supporting evidence for Treatment Plan A1 and Treatment Plan A2 is a large amount of evidence-based evidence; since Treatment Plan A7, Treatment Plan A10 and Treatment Plan A20 all belong to the second treatment plan, the medical supporting evidence for Treatment Plan A7, Treatment Plan A10 and Treatment Plan A20 are all medical literature; since Treatment Plan A19 belongs to the third treatment plan, the medical supporting evidence for Treatment Plan A19 is historical medical records; and the priority of evidence corresponding to a large amount of evidence-based evidence is higher than the priority of evidence corresponding to medical literature, and the priority of evidence corresponding to medical literature is higher than the priority of evidence corresponding to historical medical records.

[0076] In step S420, a target treatment plan is determined in each type of treatment plan according to the evidence priority, and a recommendation level corresponding to the target treatment plan is determined to assign a corresponding recommendation level to each type in the clustering result.

[0077] Among them, by clustering the treatment plans determined from multiple recommendation modules, treatment plans belonging to different categories can be obtained. For example, the clustering result is that treatment plan A1 and treatment plan A7 are clustered into one category, treatment plan A2 and treatment plan A10 are clustered into one category, and treatment plan A20 and treatment plan A19 are clustered into one category.

[0078] Through step S410, it can be determined that the priority of evidence for treatment plan A1 belonging to the first category is higher than the priority of evidence for treatment plan A7 belonging to the first category. It can also be determined that the priority of evidence for treatment plan A2 belonging to the second category is higher than the priority of evidence for treatment plan A10 belonging to the second category. It can also be determined that the priority of evidence for treatment plan A20 belonging to the third category is higher than the priority of evidence for treatment plan A19 belonging to the third category.

[0079] Based on this, the target treatment plan belonging to the first category is determined to be A1, the target treatment plan belonging to the second category is determined to be A2, and the target treatment plan belonging to the third category is determined to be A20. Since there is a recommendation level that has a mapping relationship with the treatment plan, the recommendation level I corresponding to the target treatment plan A1 can be used as the recommendation level for the first category, the recommendation level IV corresponding to the target treatment plan A2 can be used as the recommendation level for the second category, and the recommendation level III corresponding to the target treatment plan A20 can be used as the recommendation level for the third category.

[0080] In this exemplary embodiment, the recommendation level of the target treatment plan in each category is used as the recommendation level of the category, which helps to subsequently display the treatment plan for the patient's disease based on the recommendation level, improves the logic of displaying the treatment plan, and increases the auxiliary effect of assisting doctors in determining the treatment plan.

[0081] In an alternative embodiment, Figure 5 A flowchart of assigning a corresponding recommendation level to each category in the clustering result in the method for recommending disease treatment plans is shown, such as Figure 5 As shown, the method includes at least the following steps: In step S510, target medical support evidence for supporting the target treatment plan is determined, and the evidence level corresponding to the target medical support evidence is determined.

[0082] Among them, after the target treatment plan is determined, it is necessary to determine the target medical support evidence corresponding to the target treatment plan, and then obtain the evidence level corresponding to the target medical support evidence.

[0083] For example, the target treatment plan corresponding to the first category is A1, the target treatment plan corresponding to the second category is A2, and the target treatment plan corresponding to the third category is A20. Based on this, since the target medical supporting evidence for target treatment plan A1 is XX-a study, the evidence level corresponding to target treatment plan A1 is 1A, since the target medical supporting evidence corresponding to target treatment plan A2 is XX-b study, the evidence level corresponding to target treatment plan A2 is 2B, and since the target medical supporting evidence corresponding to target treatment plan A20 is historical medical records, the evidence level corresponding to target treatment plan A20 is level 3.

[0084] In step S520, a recommendation level having a level mapping relationship with the evidence level is determined to assign a corresponding recommendation level to each class in the clustering result.

[0085] There is a level mapping relationship between different evidence levels and different recommendation levels, and the corresponding recommendation level can be determined according to the evidence level, so that the recommendation level is used as the recommendation level corresponding to each category in the clustering results.

[0086] For example, the recommendation level that has a level mapping relationship with evidence level 1A is Level I, the recommendation level that has a level mapping relationship with evidence level 2B is Level II, and the recommendation level that has a level mapping relationship with evidence level 3 is Level III. Based on this, the recommendation level corresponding to the first category in the clustering results is Level I, the recommendation level corresponding to the second category in the clustering results is Level II, and the recommendation level corresponding to the third category in the clustering results is Level III.

[0087] In this exemplary embodiment, the evidence level corresponding to the target medical supporting evidence is determined, and then the recommendation level having a level mapping relationship with the evidence level is determined. On the one hand, this improves the logic for determining the recommendation level of the target treatment plan; on the other hand, it helps to subsequently display the treatment plan according to the recommendation level, so as to enhance the auxiliary effect of assisting doctors in determining the treatment plan for the patient.

[0088] In an alternative embodiment, Figure 6 A flowchart of determining the level of evidence corresponding to the target medical support evidence in the method of recommending a disease treatment plan is shown, such as Figure 6 As shown, the method includes at least the following steps: In step S610, if the target treatment plan is the first treatment plan, extract the evidence level corresponding to the target medical support evidence.

[0089] Among them, since there are three recommendation modules, the determined target treatment plan may be the first treatment plan, the second treatment plan, or the third treatment plan.

[0090] When the target treatment plan is the first treatment plan, the level of evidence is determined based on the target medical support evidence corresponding to the first treatment plan. For example, the clinical guideline evidence category published in 2018 stipulates that when the first treatment plan is determined through a large-scale randomized controlled clinical study and the expert consensus on the first treatment plan is greater than 80%, the level of evidence corresponding to the target medical support evidence is determined to be 1A; when the first treatment plan is determined through a large-scale randomized controlled clinical study, but the expert consensus on the first treatment plan is greater than 60% and less than 80%, the level of evidence corresponding to the target medical support evidence is determined to be 1B.

[0091] In step S620, if the target treatment plan is the second treatment plan, the target medical supporting evidence is determined to be a medical document, so as to determine the evidence level corresponding to the target medical supporting evidence according to the document information corresponding to the medical document.

[0092] Among them, if the target treatment plan is the second treatment plan, obviously, the target medical supporting evidence corresponding to the second treatment plan is medical literature. In this case, the evidence level corresponding to the target medical supporting evidence is determined based on the literature information. Specifically, the literature information can be the content of the medical literature research, the impact factor of the journal that publishes the medical literature, the research field to which the medical literature belongs, the therapeutic effect of the medical literature, or all information related to the medical literature. This exemplary embodiment does not make any special limitations on this.

[0093] For example, if the target medical treatment plan is the second treatment plan, the target medical supporting evidence corresponding to the target treatment plan is determined to be medical document a. Based on this, the impact factor b of the journal that publishes the medical document a is obtained, the content xx studied by the medical document is determined, the treatment effect c of the second treatment plan recorded in the medical document is determined, and the evidence level corresponding to the medical document a is determined based on the impact factor b, the research content xx and the treatment effect c.

[0094] In step S630, if the target treatment plan is the third treatment plan, the preset evidence level is determined as the evidence level corresponding to the target medical supporting evidence.

[0095] Among them, if the target treatment plan is the third treatment plan, the target medical support evidence corresponding to the third treatment plan can be determined as the historical medical record. Since the historical medical records all use existing treatment plans, the third treatment plan is often too old. Therefore, the lower-level preset evidence level is determined as the evidence level corresponding to the historical medical record.

[0096] For example, if the target treatment plan is the third treatment plan, the preset evidence level 3 is determined as the evidence level corresponding to the historical medical record.

[0097] In this exemplary embodiment, different ways of determining the level of evidence are provided for different treatment plans. On the one hand, the logic for determining the level of evidence is improved; on the other hand, the clustering results can be subsequently assigned a corresponding recommendation level based on the level of evidence, and the treatment plans can be displayed based on the recommendation level, thereby improving the auxiliary effect for doctors.

[0098] In step S130, the clustering results are sorted according to the recommendation levels to obtain sorting results, and a treatment plan for the disease suffered by the patient is displayed according to the sorting results.

[0099] Among them, the treatment plans belonging to different categories in the clustering results can be sorted according to the recommendation level to obtain a sorting result, and then the treatment plans are displayed according to the sorting result to assist doctors in determining the treatment plan for treating patients.

[0100] For example, the clustering result is that treatment plan Aa and treatment plan Ab belong to Class A treatment plan, treatment plan Ba, treatment plan Bb and treatment plan Bc belong to Class B treatment plan, and treatment plan Ca, treatment plan Cb and treatment plan Cc belong to Class C treatment plan. Among them, in Class A treatment plan, treatment plan Aa belongs to the target treatment plan, and treatment plan Aa belongs to the first treatment plan, and the recommended level of target medical support evidence corresponding to the first treatment plan is Level I. In Class B treatment plan, treatment plan Ba ​​belongs to the target treatment plan, and target treatment plan Ba ​​belongs to the first treatment plan, and the recommended level of target medical support evidence corresponding to the first treatment plan is Level II. In Class C treatment plan, treatment plan Cc belongs to the third treatment plan, and the recommended level of target medical support evidence corresponding to the third treatment plan is Level III.

[0101] Based on this, the clustering results are sorted according to the above recommendation levels, and the sorting results are in the order of Class A treatment plan, Class B treatment plan, and Class C treatment plan. Then, based on the sorting results, the above treatment plans are displayed in the order of Class A treatment plan, Class B treatment plan, and Class C treatment plan.

[0102] It is worth noting that when displaying each type of treatment plan, it can be displayed in the order of the target treatment plan and other treatment plans in each category. For example, in Category A treatment plans, since Treatment Plan Aa is the target treatment plan, the Category A treatment plans are displayed in the order of Treatment Plan Aa and Treatment Plan Ab.

[0103] In an optional embodiment, the method further includes: determining medical supporting evidence corresponding to the treatment plan, and displaying the medical supporting evidence.

[0104] In addition to displaying the treatment plan, the medical supporting evidence corresponding to the treatment plan also needs to be displayed, and usually the medical supporting evidence is displayed at a position corresponding to the treatment plan. Specifically, the medical supporting evidence can be displayed on the corresponding side of the treatment plan while the treatment plan is displayed, or a control can be displayed on the corresponding side of the treatment plan while the treatment plan is displayed. When the doctor touches the control, the medical supporting evidence corresponding to the treatment plan is displayed.

[0105] For example, after displaying the treatment plan for the patient's disease according to the sorting results, it is necessary to determine the medical supporting evidence corresponding to the treatment plan and display the medical supporting evidence on the right side of the treatment plan.

[0106] In this exemplary embodiment, in addition to displaying the treatment plan, the medical supporting evidence corresponding to the treatment plan is also displayed, allowing doctors to select the displayed treatment plan from two dimensions: recommendation level and medical supporting evidence, further enhancing the auxiliary effect of assisting doctors in determining the treatment plan.

[0107] In the method and apparatus provided by the exemplary embodiments of the present disclosure, on the one hand, the treatment plans determined from multiple recommendation modules are clustered to obtain clustering results, and the treatment plans in the clustering results are obtained by integrating the treatment plans in multiple recommendation modules, combining the advantages of multiple recommendation modules, thereby improving the standardization, accuracy and timeliness of the treatment plans displayed subsequently; on the other hand, the recommendation level corresponding to the clustering result is determined, and the clustering results are sorted according to the recommendation level, which helps doctors select a treatment plan from the treatment plans according to the recommendation level that is ultimately used to treat patients, thereby improving the auxiliary effect of assisting doctors in determining treatment plans, and thereby improving the efficiency of doctors in determining treatment plans.

[0108] The following is a detailed description of the method for recommending a disease treatment plan in the embodiment of the present disclosure in conjunction with an application scenario.

[0109] Figure 7 A flowchart of a method for recommending a disease treatment plan in an application scenario is shown, such as Figure 7 As shown, information 710 is the target information corresponding to the patient, module 720 is a recommendation module based on clinical guidelines, module 730 is a recommendation module based on medical literature, and module 740 is a recommendation module based on historical medical records. After the treatment plan is determined by the above three modules, step S750 is first executed to cluster the treatment plans determined from multiple recommendation modules to obtain clustering results, and according to the medical support evidence corresponding to the treatment plan in the clustering results, the clustering results are assigned corresponding recommendation levels, and then step S760 is executed to sort the clustering results according to the recommendation level to obtain sorted results, and the treatment plan for the patient's disease is displayed according to the sorted results, and finally step S770 is executed to determine the medical support evidence corresponding to the treatment plan, and the medical support evidence is displayed.

[0110] In this application scenario, on the one hand, the treatment plans determined from multiple recommendation modules are clustered to obtain clustering results, and the treatment plans in the clustering results are obtained by integrating the treatment plans in multiple recommendation modules, combining the advantages of multiple recommendation modules, thereby improving the standardization, accuracy and timeliness of the subsequent displayed treatment plans; on the other hand, the recommendation level corresponding to the clustering result is determined, and the clustering results are sorted according to the recommendation level, which helps doctors select a treatment plan from the treatment plans according to the recommendation level that will ultimately be used to treat patients, thereby improving the auxiliary effect of assisting doctors in determining treatment plans, thereby improving the efficiency of doctors in determining treatment plans.

[0111] In addition, in an exemplary embodiment of the present disclosure, a device for recommending a disease treatment plan is also provided. Figure 8 A schematic diagram of the structure of a recommended device for disease treatment is shown, such as Figure 8 As shown, the device 800 for recommending a disease treatment plan may include: an acquisition module 810, a clustering module 820 and a display module 830. Among them:

[0112] The acquisition module 810 is configured to acquire target information corresponding to the patient; wherein the target information includes basic information of the patient and characteristic information of the disease suffered by the patient; the clustering module 820 is configured to cluster the treatment plans determined from multiple recommendation modules based on the target information to obtain clustering results, and assign corresponding recommendation levels to the clustering results according to the medical support evidence corresponding to the treatment plans in the clustering results; wherein the multiple recommendation modules are based on different medical support evidence respectively; wherein the multiple recommendation modules are based on different medical support evidence respectively; the display module 830 is configured to sort the clustering results according to the recommendation level to obtain sorting results, and display the treatment plans for the disease suffered by the patient according to the sorting results.

[0113] The specific details of the above-mentioned disease treatment plan recommendation device 800 have been described in detail in the corresponding disease treatment plan recommendation method, so they are not repeated here.

[0114] It should be noted that, although several modules or units of the device for recommending a disease treatment plan 800 are mentioned in the above detailed description, such division is not mandatory. In fact, according to an embodiment of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided into multiple modules or units to be embodied.

[0115] In addition, in an exemplary embodiment of the present disclosure, an electronic device capable of implementing the above method is also provided.

[0116] Refer to the following Fig. 9 An electronic device 900 according to such an embodiment of the present invention will be described. Fig. 9 The electronic device 900 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0117] like Fig. 9 As shown, the electronic device 900 is in the form of a general computing device. The components of the electronic device 900 may include, but are not limited to: the at least one processing unit 910, the at least one storage unit 920, a bus 930 connecting different system components (including the storage unit 920 and the processing unit 910), and a display unit 940.

[0118] The storage unit stores program codes, which can be executed by the processing unit 910, so that the processing unit 910 executes the steps according to various exemplary embodiments of the present invention described in the above “Exemplary Method” section of this specification.

[0119] The storage unit 920 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 921 and / or a cache memory unit 922 , and may further include a read-only memory unit (ROM) 923 .

[0120] The storage unit 920 may also include a program / utility 924 having a set (at least one) of program modules 925, such program modules 925 including but not limited to: an operating system, one or more application programs, other program modules and program data, each of which or some combination may include the reality of a network environment.

[0121] Bus 930 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0122] The electronic device 900 may also communicate with one or more external devices 970 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 900, and / or communicate with any device that enables the electronic device 900 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 950. Furthermore, the electronic device 900 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter 960. As shown, the network adapter 960 communicates with other modules of the electronic device 900 via a bus 930. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 900, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAI systems, tape drives, and data backup storage systems, etc.

[0123] Through the description of the above embodiments, it is easy for those skilled in the art to understand that the example embodiments described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the embodiment of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the embodiment of the present disclosure.

[0124] In an exemplary embodiment of the present disclosure, a computer-readable storage medium is also provided, on which a program product capable of implementing the above method of the present specification is stored. In some possible embodiments, various aspects of the present invention can also be implemented in the form of a program product, which includes a program code, and when the program product is run on a terminal device, the program code is used to enable the terminal device to perform the steps according to various exemplary embodiments of the present invention described in the above "Exemplary Method" section of the present specification.

[0125] refer to Fig.10 As shown, a program product 1000 for implementing the above method according to an embodiment of the present invention is described, which can adopt a portable compact disk read-only memory (CD-ROM) and include program code, and can be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited thereto. In this document, a readable storage medium can be any tangible medium containing or storing a program, which can be used by or in combination with an instruction execution system, an apparatus or a device.

[0126] The program product may use any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0127] Computer readable signal media may include data signals propagated in baseband or as part of a carrier wave, in which readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Readable signal media may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0128] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.

[0129] Program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., through the Internet using an Internet service provider).

[0130] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary technical means in the art that are not disclosed in the present disclosure. The specification and examples are to be considered as exemplary only, and the true scope and spirit of the present disclosure are indicated by the claims.

Claims

1. A method for recommending a disease treatment regimen, characterized in that: The method comprises: Acquire target information corresponding to the patient; wherein the target information includes basic information of the patient and characteristic information of the disease suffered by the patient; Based on the target information, clustering the treatment plans determined from the multiple recommendation modules to obtain a clustering result, and assigning a corresponding recommendation level to the clustering result according to the medical support evidence corresponding to the treatment plan in the clustering result; wherein the multiple recommendation modules are respectively based on different medical support evidence; Sorting the clustering results according to the recommendation level to obtain a sorting result, and displaying the treatment plan for the disease suffered by the patient according to the sorting result; The assigning of a corresponding recommendation grade to the clustering results according to the medical support evidence corresponding to the treatment scheme in the clustering results comprises: determining the medical support evidence corresponding to all the treatment schemes in the clustering results, and determining the evidence priority corresponding to the medical support evidence; determining a target treatment scheme in each category of the treatment scheme according to the evidence priority, determining the target medical support evidence for supporting the target treatment scheme, and determining the evidence grade corresponding to the target medical support evidence, and determining a recommendation grade having a grade mapping relationship with the evidence grade, so as to assign the corresponding recommendation grade to each category in the clustering results; The multiple recommendation modules include a recommendation module based on clinical guidelines, a recommendation module based on medical literature, and a recommendation module based on historical medical records; based on the target information, clustering the treatment plans determined from the multiple recommendation modules to obtain a clustering result, including: based on the target information, using the recommendation module based on clinical guidelines to perform decision rule operations to determine a first treatment plan corresponding to the recommendation module based on clinical guidelines; matching target medical documents corresponding to the target information in the medical documents corresponding to the recommendation module based on medical literature, so as to use the second treatment plan corresponding to the target medical document as the treatment plan determined from the recommendation module based on medical literature; searching for the target medical record corresponding to the target information in the recommendation module based on historical medical records, so as to use the third treatment plan corresponding to the target medical record as the treatment plan determined from the recommendation module based on historical medical records; clustering the first treatment plan, the second treatment plan, and the third treatment plan to obtain a clustering result.

2. The method for recommending a disease treatment plan according to claim 1, characterized in that: The clustering of the first treatment plan, the second treatment plan, and the third treatment plan to obtain a clustering result includes: Summarizing the first treatment plan, the second treatment plan, and the third treatment plan to obtain a summary result; According to the content of the first treatment plan, the content of the second treatment plan and the content of the third treatment plan, the summary results are clustered to obtain a clustering result.

3. The method for recommending a disease treatment plan according to claim 1, characterized in that: Determine the level of evidence corresponding to the medical support for the objective, including: If the target treatment plan is the first treatment plan, extracting the level of evidence corresponding to the target medical supporting evidence; If the target treatment plan is the second treatment plan, determining the target medical supporting evidence to be a medical document, so as to determine the evidence level corresponding to the target medical supporting evidence according to the document information corresponding to the medical document; If the target treatment regimen is the third treatment regimen, the preset evidence level is determined as the evidence level corresponding to the target medical supporting evidence.

4. The method for recommending a disease treatment plan according to claim 1, characterized in that: The method further comprises: The medical supporting evidence corresponding to the treatment plan is determined and displayed.

5. A device for recommending disease treatment plans, characterized in that: include: An acquisition module is configured to determine and acquire target information corresponding to the patient; wherein the target information includes basic information of the patient and characteristic information of the disease suffered by the patient; a clustering module configured to cluster the treatment plans determined from the plurality of recommendation modules based on the target information to obtain a clustering result, and assign a corresponding recommendation level to the clustering result according to the medical supporting evidence corresponding to the treatment plan in the clustering result; wherein the plurality of recommendation modules are respectively based on different medical supporting evidence; a display module configured to sort the clustering results according to the recommendation level to obtain a sorting result, and display the treatment plan for the disease suffered by the patient according to the sorting result; The assigning of a corresponding recommendation grade to the clustering results according to the medical support evidence corresponding to the treatment scheme in the clustering results comprises: determining the medical support evidence corresponding to all the treatment schemes in the clustering results, and determining the evidence priority corresponding to the medical support evidence; determining a target treatment scheme in each category of the treatment scheme according to the evidence priority, determining the target medical support evidence for supporting the target treatment scheme, and determining the evidence grade corresponding to the target medical support evidence, and determining a recommendation grade having a grade mapping relationship with the evidence grade, so as to assign the corresponding recommendation grade to each category in the clustering results; The multiple recommendation modules include a recommendation module based on clinical guidelines, a recommendation module based on medical literature, and a recommendation module based on historical medical records; based on the target information, clustering the treatment plans determined from the multiple recommendation modules to obtain a clustering result, including: based on the target information, using the recommendation module based on clinical guidelines to perform decision rule operations to determine a first treatment plan corresponding to the recommendation module based on clinical guidelines; matching target medical documents corresponding to the target information in the medical documents corresponding to the recommendation module based on medical literature, so as to use the second treatment plan corresponding to the target medical document as the treatment plan determined from the recommendation module based on medical literature; searching for the target medical record corresponding to the target information in the recommendation module based on historical medical records, so as to use the third treatment plan corresponding to the target medical record as the treatment plan determined from the recommendation module based on historical medical records; clustering the first treatment plan, the second treatment plan, and the third treatment plan to obtain a clustering result.

6. An electronic device, characterized in that: include: processor; A memory, configured to store executable instructions of the processor; The processor is configured to execute the method for recommending a disease treatment plan according to any one of claims 1 to 4 by executing the executable instructions.

7. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method for recommending a disease treatment plan according to any one of claims 1 to 4 is implemented.

Images