Medical data updating method, program product, equipment and storage medium

Abstract

The invention provides a medical data updating method, a program product, equipment and a storage medium. The method comprises the following steps: carrying out quantity statistics of curative effect feedback information on each syndrome type of each disease recorded in a syndrome type library; the syndrome type library is used for recording medical data of a plurality of syndrome types under a plurality of diseases; the curative effect feedback information comprises positive feedback information and negative feedback information; based on the quantity statistical result of the negative feedback information of each syndrome type, determining a to-be-optimized syndrome type, and obtaining update data of the to-be-optimized syndrome type; if the updated data comprises the newly-added target syndrome type and the newly-added medical data, adding a mapping relation between the target syndrome type and the newly-added medical data into a syndrome type library; and if the update data comprises the prescription update data, updating the prescription data in the medical data of the to-be-optimized syndrome type. Therefore, curative effect deficiency and adverse reactions after medicine taking can be summarized in time, and the prescription can be changed in time. Meanwhile, the syndromes in the syndrome library are effectively iteratively updated, and the diagnosis accuracy of doctors is improved in an auxiliary mode.

Description

Technical Field

[0001] The present application relates to the technical field of TCM-assisted diagnosis and treatment, and more specifically, to a medical data updating method, program product, device and storage medium. Background Art

[0002] At present, during the follow-up consultation process, most doctors will make manual adjustments to the follow-up medications based on the patient's feedback on the efficacy. However, some of the lack of efficacy, side effects and adverse reactions after taking the medication are not summarized in a timely manner, and a large number of follow-up prescriptions lack classification and summary. In addition, with the changes in environmental and climatic factors, the underlying medical data in the TCM system, including prescription data, also urgently needs to keep pace with the times and be updated iteratively, which has become a technical problem that needs to be solved in the field of TCM auxiliary diagnosis and treatment technology. Summary of the invention

[0003] The purpose of the embodiments of the present application is to provide a medical data update method, program product, device and storage medium to achieve the technical effect of iterative updating of medical data in the traditional Chinese medicine system.

[0004] A first aspect of an embodiment of the present application provides a medical data updating method based on efficacy feedback, the method comprising:

[0005] Performing statistics on the amount of therapeutic effect feedback information for each syndrome under each disease recorded in the syndrome database; wherein the syndrome database is used to record the medical data of multiple syndromes under multiple diseases; the therapeutic effect feedback information includes positive feedback information and negative feedback information;

[0006] Based on the statistical results of the quantity of the negative feedback information of each syndrome type, determining the syndrome type to be optimized, and obtaining the updated data of the syndrome type to be optimized;

[0007] If the updated data includes a newly added target syndrome type and newly added medical data, a mapping relationship between the target syndrome type and the newly added medical data is added to the syndrome type library;

[0008] If the update data includes prescription update data, the prescription data in the medical data of the syndrome to be optimized is updated.

[0009] In the above implementation process, by counting the number of medical feedback information for each syndrome under each disease in the syndrome library, the syndrome to be optimized is screened out based on the number of negative feedback information, and handed over to the TCM expert team to update the underlying medical data, add new syndromes to the disease or optimize the prescription data. On the one hand, the lack of efficacy, side effects and adverse reactions after taking the medicine can be summarized in time, so that the prescription can be changed in time. On the other hand, the diseases or syndromes in the syndrome library are effectively iterated and updated, which helps to improve the accuracy of doctors' diagnosis of patients, shorten the treatment course, and thus optimize the patient's medical experience.

[0010] Furthermore, the medical data of each syndrome type includes a symptom data set, and the symptom data set includes one or more of primary symptom data, secondary symptom data and concomitant symptom data; the efficacy feedback information is feedback information for each symptom data in the symptom data set;

[0011] The statistical analysis of the amount of therapeutic effect feedback information for each syndrome under each disease recorded in the syndrome database includes:

[0012] For each syndrome type recorded in the syndrome type library, respectively obtaining therapeutic effect feedback information of each symptom data corresponding to the syndrome type;

[0013] Performing statistics on the quantity of therapeutic effect feedback information for each symptom data of the syndrome type, and obtaining the statistical result of the quantity of negative feedback information corresponding to each symptom data;

[0014] Among them, the number of negative feedback information of at least one symptom data corresponding to the syndrome to be optimized exceeds a preset statistical threshold.

[0015] In the above implementation process, by statistically analyzing the efficacy feedback for each symptom in the syndrome type, when there is a lot of negative feedback for one or more symptoms, the syndrome type is optimized, so that the optimized treatment plan can specifically improve the efficacy of the negative feedback symptoms, greatly improve the patient's medical experience, and optimize the underlying medical data of the syndrome type library.

[0016] Furthermore, the statistical analysis of the amount of therapeutic effect feedback information for each syndrome under each disease recorded in the syndrome database includes:

[0017] For each of the syndromes recorded in the syndrome database, the efficacy feedback information is divided into a plurality of feedback groups corresponding to the patient attributes according to the patient attribute information carried in the efficacy feedback information; wherein the patient attribute information includes one or more of age, gender and region;

[0018] Perform quantitative statistics on the feedback groups corresponding to each patient attribute to obtain the quantitative statistical results of negative feedback information in each feedback group;

[0019] Among them, the syndrome type to be optimized corresponds to at least one target feedback group in which the number of negative feedback information exceeds a preset statistical threshold, and the updated data of the syndrome type to be optimized carries the patient attribute information corresponding to the target feedback group.

[0020] In the above implementation process, the efficacy feedback information is grouped and statistically analyzed based on one or more patient attributes such as age, gender, and region, and the updated data carries the patient attribute information corresponding to the target feedback group, realizing the precise segmentation of underlying medical data among different populations. Moreover, when different populations seek medical treatment, more precise medical data can be found based on the patient attribute information, and more precise auxiliary medical data can be recommended to physicians.

[0021] Further, the efficacy feedback information includes efficacy feedback text. Before counting the number of efficacy feedback information for each syndrome type recorded in the syndrome type library, the method further includes:

[0022] Performing semantic extraction on the efficacy feedback text to determine whether the efficacy feedback text is positive feedback information or negative feedback information.

[0023] In the above implementation process, by performing semantic extraction on the efficacy feedback text to distinguish whether the efficacy feedback text is positive feedback or negative feedback, the syndrome types to be optimized can be screened out based on the statistical results of the number of negative feedback information subsequently.

[0024] Further, determining the syndrome type to be optimized based on the statistical result of the number of negative feedback information for each syndrome type includes:

[0025] Based on the statistical result, determining a first syndrome type to be optimized in which the negative feedback information exceeds a first statistical threshold and does not exceed a second statistical threshold; wherein the updated data of the first syndrome type to be optimized includes the target syndrome type and the new medical data, and / or includes the prescription update data;

[0026] Based on the statistical result, determining a second syndrome type to be optimized in which the negative feedback information exceeds the second statistical threshold, wherein the updated data of the second syndrome type to be optimized includes the prescription update data.

[0027] In the above implementation process, by setting the first statistical threshold and the second statistical threshold, the first syndrome type to be optimized and the second syndrome type to be optimized are divided. For the first syndrome type to be optimized, optimization processing such as adding a new syndrome type or optimizing prescription data is taken, while for the second syndrome type to be optimized, optimization processing of prescription data is taken, so as to make a more scientific optimization treatment for the syndrome types to be optimized with different negative feedback quantities, ensuring the scientificity and correctness of the update of underlying medical data.

[0028] Further, if the updated data includes a newly added target syndrome type and newly added medical data, adding the mapping relationship between the target syndrome type and the newly added medical data in the syndrome type library includes:

[0029] If the updated data includes a newly added primary syndrome type and the first newly added medical data of the primary syndrome type, adding the primary syndrome type to the primary syndrome type classification of the syndrome type library, and storing the mapping relationship between the primary syndrome type and the first newly added medical data in the syndrome type library;

[0030] If the updated data includes multiple secondary syndrome types obtained by splitting the syndrome type to be optimized and the second newly added medical data of each secondary syndrome type, adding the multiple secondary syndrome types to the secondary syndrome type classification under the syndrome type to be optimized in the syndrome type library, and storing the mapping relationship between each secondary syndrome type and the corresponding second newly added medical data in the syndrome type library.

[0031] In the above implementation process, by adding a primary syndrome type under a disease or splitting the syndrome type to be optimized to obtain multiple newly added secondary syndrome types, the defects of missing syndrome type classification or rough and incomplete classification can be gradually made up. At the same time, the hierarchical and infinite subdivision of syndrome types can be realized, so as to realize the standardization of prescriptions and syndrome types, and realize accurate syndrome differentiation.

[0032] Further, the method further includes:

[0033] Receiving the patient's medical treatment information;

[0034] If the medical treatment information does not carry the efficacy feedback information on the previous medical treatment, determining a recommended syndrome type that matches the medical treatment information from the primary syndrome type classification of the syndrome type library;

[0035] If the medical treatment information carries the efficacy feedback information on the previous medical treatment, determining a recommended syndrome type that matches the medical treatment information from the primary syndrome type classification or the target secondary syndrome type classification of the syndrome type library; wherein, the target secondary syndrome type is the secondary syndrome type classification under the historical syndrome type determined in the previous medical treatment;

[0036] Obtaining the recommended medical data of the recommended syndrome type from the syndrome type library, and outputting the recommended syndrome type and the recommended medical data to the physician.

[0037] In the above implementation process, when the syndrome types in the syndrome type library are continuously supplemented or continuously subdivided, different levels of syndrome types will be matched according to the first visit or follow-up visit situation when the patient seeks medical treatment to assist the physician in diagnosis, improving the diagnostic accuracy.

[0038] In the second aspect of the embodiments of the present application, a computer program product is provided. The computer program product includes a computer program, and when the computer program is executed by a processor, the methods described in any one of the first aspect are implemented.

[0039] In the third aspect of the embodiments of the present application, an electronic device is provided. The electronic device includes:

[0040] A processor;

[0041] A memory for storing executable instructions of the processor;

[0042] Wherein, when the processor calls the executable instructions, the operations of the methods described in any one of the first aspect are implemented.

[0043] In the fourth aspect of the embodiments of the present application, a computer-readable storage medium is provided, on which computer instructions are stored, and when the computer instructions are executed by a processor, the steps of the methods described in any one of the first aspect are implemented. Description of the Drawings

[0044] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required to be used in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present application, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0045] Figure 1 It is a schematic flowchart of a medical data update method based on efficacy feedback provided by the embodiments of the present application;

[0046] Figures 2 - 6 It is a schematic flowchart of another medical data update method based on efficacy feedback provided by the embodiments of the present application;

[0047] Figure 7 It is a hardware structure diagram of an electronic device provided by the embodiments of the present application. Detailed Embodiments

[0048] Next, the technical solutions in the embodiments of the present application will be described in conjunction with the drawings in the embodiments of the present application.

[0049] It should be noted that: similar reference numerals and letters denote similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of the present application, terms such as "first", "second", etc. are only used for distinguishing descriptions and cannot be understood as indicating or implying relative importance.

[0050] In the traditional Chinese medicine system, the iterative update of medical data involves at least the following two aspects:

[0051] The first aspect is the iterative update of treatment methods, and an important part of treatment methods is prescription data. In the related art, doctors often adjust prescriptions according to the curative effect feedback of patients during follow-up consultations. However, the curative effects, side effects, and adverse reactions after taking medicine are not summarized in a timely manner, and a large number of follow-up prescriptions lack classification and summary. At the same time, due to the huge amount of traditional Chinese medicine prescription data, the inheritance of traditional Chinese medicine schools is complex, and the expert experience is regional, fixed, and mutually exclusive to a certain extent, resulting in the difficulty of integrating and updating classical prescriptions. At the same time, the update and optimization of prescriptions require a large amount of clinical data support, and there is currently a lack of an effective prescription optimization method.

[0052] The second aspect is the iterative update of syndrome types. The so-called syndrome type refers to the syndromes that are relatively common, typical, with standardized or established syndrome names in clinical practice. Regarding the relationship between diseases and syndrome types, one disease can be divided into multiple syndrome types, and the symptoms and treatment methods of different syndrome types under the same disease are different. And the same syndrome type can correspond to multiple diseases. For example, the syndrome type of "syndrome of spleen yang deficiency" can correspond to multiple diseases such as diarrhea, constipation, and vomiting. With the changes of factors such as the environment and climate, new diseases have emerged, and new syndrome types may also appear in existing diseases, and new treatment methods need to be adopted to deal with them. In the related art, there are few studies on the update and iteration of disease syndrome types, resulting in the need for patients to repeatedly adjust treatment plans during multiple diagnoses and treatments to be cured, which prolongs the treatment course, reduces the treatment effect, and causes problems such as insufficient trust between patients and doctors.

[0053] In view of the above problems, there is an urgent need for a solution that can effectively perform iterative updates on medical data in the traditional Chinese medicine system. To solve at least one of the above-mentioned technical problems, the present application provides a medical data update method based on curative effect feedback, specifically including steps 110-step 140 as Figure 1 shown.

[0054] Step 110: Count the number of curative effect feedback information for each syndrome type under each disease recorded in the syndrome type library.

[0055] Among them, the syndrome type library is used to record medical data of multiple syndrome types under multiple diseases; the curative effect feedback information includes positive feedback information and negative feedback information.

[0056] Exemplarily, before performing step 110 - step 140, a syndrome type library for recording medical data of multiple syndrome types under multiple diseases can be established in advance. As described above, one disease can be subdivided into multiple syndrome types, and at the same time, one syndrome type can correspond to multiple diseases. Therefore, in the syndrome type library, the syndrome types are corresponded to different diseases and stored according to the corresponding relationship of "disease - syndrome type - medical data". The medical data may include, but is not limited to, treatment method data and symptom data sets. The treatment method data may include, but is not limited to, one or more of prescription data, acupuncture data, and doctor's advice data, etc. The symptom data set includes one or more of main symptom data, secondary symptom data, and accompanying symptom data. Exemplarily, the medical data corresponding to the syndrome type under each disease can be formulated by a team of traditional Chinese medicine experts based on historical experience to complete the establishment of the syndrome type library.

[0057] When a patient is diagnosed with a certain syndrome type under a certain disease during a certain visit, the efficacy feedback information of the patient can be collected after the patient receives treatment. By collecting a large amount of efficacy feedback information, the efficacy feedback information of each syndrome type under each disease can be obtained. On this basis, by regularly counting the quantity of the collected efficacy feedback information, or alternatively, when the quantity of the efficacy feedback information reaches a preset threshold, it can be determined that the efficacy feedback information is sufficient and representative, and then the quantity statistics is triggered.

[0058] Step 120: Based on the quantity statistical result of the negative feedback information of each syndrome type, determine the syndrome type to be optimized, and obtain the updated data of the syndrome type to be optimized.

[0059] The efficacy feedback information includes positive feedback information and negative feedback information. The so-called positive feedback information refers to the efficacy information feedback by the patient after the symptoms are relieved or cured after receiving treatment; the so-called negative feedback information refers to the efficacy information feedback by the patient when the symptoms are not relieved, or the symptoms are aggravated, or new symptoms appear, or side effects occur, or the patient is not cured after receiving treatment.

[0060] It should be noted that the efficacy feedback information or negative feedback information of each syndrome type mentioned in this embodiment refers to the feedback information of a certain syndrome type under a certain disease. Although one syndrome type can correspond to multiple diseases, due to the different symptoms and treatment methods of different diseases, the various syndrome types under different diseases are separately counted. For example, the syndrome type of "syndrome of spleen yang deficiency" under "diarrhea" and the syndrome type of "syndrome of spleen yang deficiency" under "constipation" are counted separately to obtain two quantity statistical results.

[0061] Subsequently, the syndrome to be optimized can be determined based on the statistical results of the number of negative feedback information of each syndrome under each disease. Optionally, the syndrome whose number of negative feedback information is greater than a quantity threshold can be determined as the syndrome to be optimized; optionally, the syndrome whose proportion of negative feedback information in the efficacy feedback information is greater than a proportion threshold can be determined as the syndrome to be optimized.

[0062] Among them, the reasons for more negative feedback information of syndromes may include: 1. There are problems with the prescription of the syndrome itself, the treatment effect is poor, and the prescription needs to be improved. 2. A new syndrome has appeared in the disease, but the underlying medical data has not been updated, resulting in the misdiagnosis of the patient as other existing syndromes and the wrong medicine. 3. The existing syndrome classification is relatively simple, and the classification is not comprehensive and accurate, resulting in poor prescription targeting.

[0063] Based on this, after the syndrome type to be optimized is screened out from the syndrome type library, the underlying medical data of the syndrome type to be optimized can be updated and optimized by the TCM expert team. The update optimization may include but is not limited to one or more of the optimization of prescription data, the addition of new syndrome types, and the splitting of existing syndrome types. In this way, after the TCM expert team completes the optimization, the updated data of the syndrome type to be optimized will be fed back, and the updated data includes one or more of the following: 1. The newly added target syndrome type and the corresponding newly added medical data; 2. The prescription update data of the syndrome type to be optimized. Then, according to the specific content of the updated data, step 130 and / or step 140 can be selected for execution.

[0064] Step 130: If the updated data includes a newly added target syndrome type and newly added medical data, a mapping relationship between the target syndrome type and the newly added medical data is added to the syndrome type library.

[0065] If the TCM expert team determines that a new syndrome type is needed for the disease, the new medical data includes but is not limited to the symptom data set of the new target syndrome type and the treatment method data for the new target syndrome type, etc. The treatment method data at least includes prescription data, and of course can also include other auxiliary treatment method data such as acupuncture, massage, etc.

[0066] A mapping relationship between the newly added target syndrome and the newly added medical data is added to the syndrome library, so that when the patient is diagnosed with the target syndrome, the treatment method data in the corresponding medical data can be found based on the mapping relationship and output to the physician, providing auxiliary reference information for the physician.

[0067] Step 140: If the update data includes prescription update data, the prescription data in the medical data of the syndrome to be optimized is updated.

[0068] If it is determined by a team of traditional Chinese medicine experts that the prescription for the syndrome type to be optimized needs to be optimized, then the updated data includes the prescription update data for the syndrome type to be optimized, and the prescription data in the medical data of the syndrome type to be optimized is updated to the prescription update data. Among them, prescription optimization includes, but is not limited to, changes in the medicinal flavors and / or dosages.

[0069] It can be seen that a medical data update method based on efficacy feedback provided in this embodiment counts the number of medical feedback information for each syndrome type under each disease in the syndrome type library, screens out the syndrome types to be optimized based on the number of negative feedback information, and hands them over to a team of traditional Chinese medicine experts for underlying medical data update to add new syndrome types or optimize prescription data for diseases. On the one hand, it can timely summarize the situations of missing efficacy, side effects and adverse reactions after taking medicine, so that the prescription can be changed in time. On the other hand, it effectively iteratively updates the diseases or syndrome types in the syndrome type library, helps improve the diagnostic accuracy of doctors for patients, shortens the treatment course, and thus optimizes the patient's medical experience.

[0070] The above steps are introduced in detail below.

[0071] As described above, the medical data includes a symptom data set. And the symptom data set includes one or more of main symptom data, secondary symptom data and accompanying symptom data.

[0072] Among them, the main symptom data is the manifestation data of the main symptom. The main symptom is the main symptom, which refers to the symptom that is decisive for the diagnosis of a certain disease among many symptoms shown when a certain disease occurs. It includes the main symptoms and signs when the patient seeks medical treatment, etc., and is the symptom that can best reflect the cause, pathology and nature of the disease. It is the main contradiction and also the key factor in clinical syndrome differentiation. Each disease has specific main symptoms. The number of main symptoms can be one or more.

[0073] The secondary symptom data is the manifestation data of the secondary symptom. The secondary symptom is the secondary symptom, which is a symptom closely related to the main symptom, and its reflected pathogenesis is the same as that of the main symptom, and it can also be called a concurrent symptom.

[0074] The accompanying symptom data is the manifestation data of the accompanying symptom. In a symptom group (symptoms and signs), the pathogenesis reflected by the accompanying symptom is less related or even opposite to the pathological cold-heat nature of the "main symptom" and "secondary symptom", and it can also be called a mixed symptom or a complex symptom.

[0075] Based on this, the efficacy feedback information described in this embodiment is feedback information for each symptom data in the symptom data set. That is, for a certain syndrome of a certain disease, its efficacy feedback information includes one or more of feedback information on the main symptom, feedback information on the secondary symptom, and feedback information on the accompanying symptom. For example, the feedback information on the main symptom indicates improvement, but the feedback information on the secondary symptom may indicate aggravation. In this way, the quantitative statistics of the efficacy feedback information in step 110 may specifically include the following: Figure 2 Steps 210 to 220 are shown.

[0076] Step 210: for each syndrome type recorded in the syndrome type library, respectively obtain the therapeutic effect feedback information of each symptom data corresponding to the syndrome type;

[0077] Step 220: Count the amount of therapeutic effect feedback information for each symptom data of the syndrome type, and obtain the statistical result of the amount of negative feedback information corresponding to each symptom data.

[0078] For example, if the syndrome symptom data set includes the above three symptom data, the efficacy feedback information corresponding to each symptom data is obtained respectively, and the efficacy feedback information of each symptom data is quantitatively counted to obtain the negative feedback statistical results of each symptom data.

[0079] Finally, it can be determined that the syndrome type corresponding to the symptom data whose number of negative feedback information exceeds the preset statistical threshold is the syndrome type to be optimized. That is, the syndrome type to be optimized corresponds to at least one symptom data whose number of negative feedback information exceeds the preset statistical threshold. For example, if the negative feedback information of the main symptom data and the secondary symptom data of a certain syndrome type does not exceed the statistical threshold, but the negative feedback information of its accompanying symptom data exceeds the statistical threshold, then the syndrome type is the syndrome type to be optimized. Among them, the negative feedback information exceeding the preset statistical threshold may include that the number of negative feedback information is greater than the quantity threshold, and / or the proportion of negative feedback information in the efficacy feedback information is greater than the proportion threshold.

[0080] It can be seen that this embodiment performs efficacy feedback statistics for each symptom in the syndrome type. When one or more symptoms have more negative feedback, the syndrome type is optimized, so that the optimized treatment plan can specifically improve the efficacy of the negative feedback symptoms, greatly improve the patient's medical experience, and optimize the medical data at the bottom of the syndrome type library.

[0081] In addition, Figure 1 or Figure 2 Based on the embodiment shown, the quantitative statistics of the therapeutic effect feedback information in step 110 may also specifically include the following: Figure 3 Steps 310 to 320 are shown.

[0082] Step 310: For the efficacy feedback information of each syndrome type recorded in the syndrome type library, divide the efficacy feedback information into multiple feedback groups corresponding to the patient attributes according to the patient attribute information carried by the efficacy feedback information. The patient attribute information includes one or more of age, gender, and region.

[0083] Affected by factors such as region and climate, the types of diseases and specific syndrome types may change in different regions or different climates. Also, the types of diseases and specific syndrome types vary among different genders and age groups. To achieve accurate classification of syndrome types and accurate prescription medication, in this embodiment, multiple feedback groups can be pre-divided based on age, gender, and region. The region can be, for example, the southern region and the northern region, or other region division methods can be used, which are not limited in this embodiment.

[0084] The efficacy feedback information can carry patient attribute information, that is, one or more of age, gender, and region. Among them, the region information can be determined by the IP address of the efficacy feedback information. After collecting the efficacy feedback information of each syndrome type under each disease, the efficacy feedback information can be classified into the corresponding feedback group based on the carried patient attribute information.

[0085] For example, the feedback groups based on age can include the feedback group for 0 - 14 years old, the feedback group for 15 - 59 years old, and the feedback group for 60 years old and above. The feedback groups based on gender can include the female feedback group and the male feedback group. The feedback groups based on region can include the southern feedback group and the northern feedback group. If a total of 3 patients have provided efficacy feedback for the "syndrome of spleen yang deficiency" syndrome type of the "diarrhea" disease, including patient A (male, 45 years old, from the south), patient B (female, 11 years old, from the north), and patient C (female, 60 years old, from the south), then the efficacy feedback information of the three patients is divided into the corresponding feedback groups.

[0086] Optionally, the feedback groups divided based on different patient attribute information can be independent of each other, and the efficacy feedback information of the same patient may be divided into multiple groups. For example, the efficacy feedback information of patient A can be divided into the feedback group for 15 - 59 years old, the male feedback group, and the southern feedback group.

[0087] Optionally, the feedback groups divided based on different patient attribute information are interrelated. For example, within each feedback group based on age, a next-level feedback group is divided based on gender, and then a next-next-level feedback group is divided based on region. For example, the efficacy feedback information of patient A can be divided into the feedback group of "southern male, 15 - 59 years old", the efficacy feedback information of patient B can be divided into the feedback group of "northern female, 0 - 14 years old", and the efficacy feedback information of patient C can be divided into the feedback group of "southern female, 60 years old and above".

[0088] In addition, if the efficacy feedback information includes feedback information corresponding to multiple symptom data, then multiple feedback groups can also be divided for each symptom data based on age, gender, and region. For example, for the main symptom data, it includes the feedback groups corresponding to the above three age groups, the feedback groups corresponding to the two genders, and the feedback groups corresponding to the two regions. The same applies to other symptom data. In this way, the efficacy feedback information of the patient can be divided into the feedback groups corresponding to various symptom data respectively.

[0089] Step 320: Conduct a quantity statistics for the feedback groups corresponding to each patient attribute to obtain the quantity statistics result of the negative feedback information for each feedback group.

[0090] After the group division of the feedback data is completed, the efficacy feedback data in each feedback group can be statistically analyzed in units of each feedback group to obtain the statistical result of the negative feedback information for each group.

[0091] Subsequently, the target feedback groups with the quantity of negative feedback information exceeding the preset statistical threshold can be determined, and the syndrome type corresponding to the target feedback group can be determined as the syndrome type to be optimized. That is, there is at least one target feedback group corresponding to the syndrome type to be optimized with the quantity of negative feedback information exceeding the preset statistical threshold. For example, in a certain syndrome type, the quantity of negative feedback information in the feedback groups of 0 - 14 years old and 15 - 59 years old does not exceed the statistical threshold, but the quantity of negative feedback in the feedback group of 60 years old and above exceeds the statistical threshold, then this syndrome type can be determined as the syndrome type to be optimized. Among them, the negative feedback information exceeding the preset statistical threshold can include that the quantity of negative feedback information is greater than the quantity threshold, and / or the proportion of negative feedback information in the efficacy feedback information is greater than the proportion threshold.

[0092] Finally, after the TCM expert team completes the optimization of the syndrome type, the returned updated data can carry the patient attribute information corresponding to the target feedback group, so that when subsequent corresponding patients seek medical treatment, the medical data corresponding to the patient attribute information can be referred to specifically. For example, in the above example, since the quantity of negative feedback in the feedback group of 60 years old and above exceeds the statistical threshold, after the TCM expert team completes the optimization of the syndrome type, the updated data, such as the prescription update data, carries the patient attribute information of "60 years old and above", indicating that the updated prescription is applicable to patients of 60 years old and above with this syndrome type.

[0093] It can be seen that in this embodiment, the efficacy feedback information is grouped and statistically analyzed based on one or more patient attributes such as age, gender, and region, and the patient attribute information corresponding to the target feedback group is carried in the updated data, realizing the precise segmentation of the underlying medical data among different populations. Moreover, when different populations seek medical treatment, more precise medical data can be found based on the patient attribute information, and more precise auxiliary medical data can be recommended to physicians.

[0094] Regarding the efficacy feedback information, based on any of the embodiments described above Figures 1 - 3 The efficacy feedback information of patients can be classified according to "cured", "improved", "no change", "worsened", and "others". Of course, the efficacy feedback information can also be classified in other ways, which will not be elaborated in this application. In addition, patients or physicians can directly check the options of "cured", "improved", "no change", or "worsened" in the device, or patients or physicians can input the efficacy feedback information in the form of voice or video. Subsequently, the voice recognition technology is used to recognize the efficacy feedback information input by voice or video to obtain the efficacy feedback text. Or, patients or physicians input the efficacy feedback information in text form, and at this time, the efficacy feedback information is also called the efficacy feedback text.

[0095] After obtaining the efficacy feedback text, semantic extraction can be performed on the efficacy feedback text to determine whether the efficacy feedback text is positive feedback information or negative feedback information.

[0096] In addition, the efficacy feedback information can also include new symptoms that appear after the patient receives treatment. For example, the "other" category can be used to record the new symptoms that appear after the patient receives treatment. For example, efficacy feedback information such as "diarrhea after taking medicine", "constipation after taking medicine", "abdominal pain after eating something cold", and "abdominal pain and diarrhea after getting angry". For the efficacy feedback information of a certain syndrome type of a disease, if there is feedback information about new symptoms that appear after the patient receives treatment, semantic extraction is performed on each efficacy feedback information carrying the new symptoms that appear after the patient receives treatment to obtain the new symptom information. Subsequently, the quantity of all new symptom information is counted. If there is target new symptom information whose quantity exceeds the preset threshold, the syndrome type corresponding to the target new symptom information is determined as the syndrome type to be optimized, and the syndrome type to be optimized carrying the target new symptom information is output and handed over to the traditional Chinese medicine expert team for optimization. Or, after determining the syndrome type to be optimized based on the quantity of negative feedback information, the occurrence times of the new symptom information of this syndrome type are sorted from high to low, and the first several new symptom information are determined as the target new symptom information, and the syndrome type to be optimized carrying the target new symptom information is output and handed over to the traditional Chinese medicine expert team for optimization.

[0097] For example, for the syndrome type of "syndrome of spleen-kidney yang deficiency" under the disease of "diarrhea", if semantic extraction is performed on the efficacy feedback information to determine the top 3 target new symptom information of "constipation after taking medicine", "abdominal pain after eating cold food", and "abdominal pain and diarrhea after getting angry", and the syndrome type of "syndrome of spleen-kidney yang deficiency" to be optimized carrying these target new symptom information is output to the traditional Chinese medicine expert team. According to the expert experience, the original prescription can be modified. For example, the stir-fried atractylodes macrocephala in the original prescription is changed from 30 g to 20 g, and at the same time, 12 g of white peony root and 10 g of prepared ginger are added to obtain the prescription update data of the syndrome type of "syndrome of spleen-kidney yang deficiency" to be optimized under the disease of "diarrhea".

[0098] It can be seen that in this embodiment, semantic extraction is performed on the efficacy feedback text to distinguish whether the efficacy feedback text is positive feedback or negative feedback, so that the syndrome type to be optimized can be screened out based on the statistical result of the quantity of negative feedback information subsequently.

[0099] Regarding the screening process of the syndrome type to be optimized in step 120, in some embodiments, it includes steps 410-step 420 as shown in Figure 4 shown.

[0100] Step 410: Based on the statistical result, determine the first syndrome type to be optimized for which the negative feedback information exceeds the first statistical threshold and does not exceed the second statistical threshold.

[0101] In this embodiment, a first statistical threshold and a second statistical threshold are set, and the second statistical threshold is greater than the first statistical threshold. The first statistical threshold can be a first quantity threshold or a first proportion threshold; the second statistical threshold can be a second quantity threshold or a second proportion threshold. Specifically, that the negative feedback information exceeds the first statistical threshold and does not exceed the second statistical threshold may include that the quantity of negative feedback information exceeds the first quantity threshold but does not exceed the second quantity threshold, or may include that the proportion of negative feedback information in the efficacy feedback information exceeds the first proportion threshold but does not exceed the second proportion threshold. As an example, the first proportion threshold can be 25%, and the second proportion threshold can be 75%.

[0102] In this embodiment, the syndrome type for which the statistical result of the negative feedback information falls within the range from the first statistical threshold to the second statistical threshold is determined as the first syndrome type to be optimized. Among them, the update data of the first syndrome type to be optimized includes the target syndrome type and the newly added medical data, and / or includes the prescription update data. That is, for the first syndrome type to be optimized, the traditional Chinese medicine expert team may add the target syndrome type and supplement the newly added medical data, or may perform prescription update adjustment on the first syndrome type to be optimized.

[0103] Step 420: Based on the statistical result, determine the second syndrome type to be optimized for which the negative feedback information exceeds the second statistical threshold.

[0104] Specifically, that the negative feedback information exceeds the second statistical threshold may include that the quantity of the negative feedback information exceeds the second quantity threshold, or may include that the proportion of the negative feedback information in the efficacy feedback information exceeds the second proportion threshold. In this embodiment, the syndrome type for which the statistical result of the negative feedback information is determined to exceed the second statistical threshold is the second syndrome type. Among them, the update data of the second syndrome type to be optimized includes prescription update data. It can be understood that when the statistical result of the negative feedback information of a certain syndrome type exceeds a relatively large second statistical threshold, such as 75%, it indicates that most of the patients confirmed with this disease syndrome type have not been cured after treatment. At this time, it can be considered that there is a deviation in the treatment data of this disease syndrome type, resulting in the wrong prescription. Therefore, the traditional Chinese medicine expert team should consider optimizing and adjusting the prescription data instead of blindly adding new syndrome types.

[0105] It can be seen that in this embodiment, by setting the first statistical threshold and the second statistical threshold, the first syndrome type to be optimized and the second syndrome type to be optimized are divided, and for the first syndrome type to be optimized, optimization processing such as adding a new syndrome type or optimizing prescription data is adopted, while for the second syndrome type to be optimized, optimizing prescription data processing is adopted, so as to make a more scientific optimization processing for the syndrome types to be optimized with different negative feedback quantities, and ensure the scientificity and correctness of the update of the underlying medical data.

[0106] Regarding step 130, based on any of the above embodiments, it specifically includes steps 510 - 520 as Figure 5 shown.

[0107] Step 510: If the update data includes a newly added first-level syndrome type and the first new medical data of the first-level syndrome type, add the first-level syndrome type to the first-level syndrome type classification of the syndrome type library, and store the mapping relationship between the first-level syndrome type and the first new medical data in the syndrome type library.

[0108] As described above, the reasons for more negative feedback information of the syndrome type may include: 1. There are problems with the prescription of the syndrome type itself. 2. New syndrome types of the disease appear but the underlying medical data has not been updated. 3. The existing syndrome type classification is relatively simple and not comprehensive and accurate. For reasons 2 and 3, the optimization processing done by the traditional Chinese medicine expert team is to add new syndrome types, that is, the newly added target syndrome type and new medical data in step 130. However, for the newly added target syndrome type due to reason 2, it is to add a target syndrome type under a certain disease, and it is in a parallel relationship with other existing syndrome types (including the syndrome types to be optimized) of this disease. Such a newly added target syndrome type is also called a newly added first-level syndrome type. Therefore, a first-level syndrome type will be added to the first-level syndrome type classification of the syndrome type library, and the mapping relationship between the first-level syndrome type and the first new medical data will be stored in the syndrome type library.

[0109] Step 520: If the updated data includes multiple secondary syndromes obtained by splitting the syndrome to be optimized and the second newly added medical data for each of the secondary syndromes, add the multiple secondary syndromes to the secondary syndrome classification under the syndrome to be optimized in the syndrome library, and store the mapping relationship between each secondary syndrome and the corresponding second newly added medical data in the syndrome library.

[0110] For the newly added target syndrome made for Reason 3, multiple secondary syndromes are obtained by splitting the syndrome to be optimized. For example, after splitting the syndrome to be optimized, "syndrome of spleen-kidney yang deficiency", two secondary syndromes can be obtained, namely "syndrome of spleen-kidney yang deficiency - partial spleen yang deficiency" and "syndrome of spleen-kidney yang deficiency - partial kidney yang deficiency". The secondary syndromes of the syndrome to be optimized belong to the sub-syndromes under the syndrome to be optimized. Therefore, the multiple split secondary syndromes will be added to the secondary syndrome classification under the syndrome to be optimized, and the mapping relationship between the secondary syndromes and the corresponding second newly added medical data will be stored in the syndrome library.

[0111] It should be noted that the syndrome library includes multiple levels of syndrome classification, such as primary syndrome classification, secondary syndrome classification, tertiary syndrome classification, and so on. The number of multiple levels of syndrome classification in this application is not limited. With the development of traditional Chinese medicine technology, the number of subsequent multiple levels of syndrome classification will be more and more. Among them, the syndrome to be optimized described in this embodiment can be a syndrome under any level of syndrome classification in the multiple levels of syndrome classification. For example, if the syndrome to be optimized is any syndrome in the primary syndrome classification, then the secondary syndrome is a syndrome in the secondary syndrome classification. If the syndrome to be optimized is any syndrome in the tertiary syndrome classification, then the secondary syndrome is any syndrome in the quaternary syndrome classification, and so on. In this way, by continuously refining the syndromes, a sub-syndrome hierarchy such as "primary syndrome - secondary syndrome - tertiary syndrome... nth-level syndrome" can be finally formed.

[0112] It can be seen that in this embodiment, by adding a primary syndrome under the disease or splitting the syndrome to be optimized to obtain multiple newly added secondary syndromes, the defect of missing or rough and incomplete syndrome classification can be gradually made up. At the same time, the syndrome can be infinitely subdivided step by step, so as to realize the standardization of prescriptions and syndromes, and realize accurate syndrome differentiation.

[0113] In addition, on the basis of the Figure 5 shown embodiment, the method may further include steps 610 - 640 as Figure 6 shown.

[0114] Step 610: Receive the patient's medical treatment information.

[0115] Among them, the medical visit information may include patient attribute information and disease information. The patient attribute information includes, for example, but is not limited to, age, region, gender, etc. The disease information includes, for example, disease information, main symptom information, secondary symptom information, accompanying symptom information, and so on.

[0116] In addition, if the patient is visiting the doctor for the first time, the medical visit information will not carry the efficacy feedback information on the previous medical visit. On the contrary, if the patient is not visiting the doctor for the first time, the medical visit information may carry the efficacy feedback information on the previous medical visit. Based on whether the efficacy feedback information is carried in the medical visit information, step 620 or step 630 is selected for execution.

[0117] Step 620: If the medical visit information does not carry the efficacy feedback information on the previous medical visit, determine the recommended syndrome type that matches the medical visit information from the first-level syndrome type classification in the syndrome type library.

[0118] Exemplarily, if the medical visit information does not carry the efficacy feedback information, the recommended syndrome type is determined from the first-level syndrome type classification in the syndrome type library according to the disease information in the medical visit information.

[0119] Step 630: If the medical visit information carries the efficacy feedback information on the previous medical visit, determine the recommended syndrome type that matches the medical visit information from the first-level syndrome type classification or the target secondary syndrome type classification in the syndrome type library. Among them, the target secondary syndrome type is the secondary syndrome type classification under the historical syndrome type determined in the previous medical visit.

[0120] Exemplarily, if the medical visit information carries the efficacy feedback information, first determine the historical syndrome type diagnosed in the previous medical visit, and determine all secondary syndrome types belonging to the historical syndrome type from the syndrome type library. Of course, if the historical syndrome type is not subdivided into secondary syndrome types, directly determine the historical syndrome type as the recommended syndrome type. If the historical syndrome type has secondary syndrome types, determine the recommended syndrome type from all secondary syndrome types based on the disease information in the medical visit information.

[0121] Step 640: Obtain the recommended medical data of the recommended syndrome type from the syndrome type library, and output the recommended syndrome type and the recommended medical data to the doctor.

[0122] Finally, based on the mapping relationship between the syndrome type and the medical data, obtain the recommended medical data corresponding to the recommended syndrome type from the syndrome type library, and output the recommended syndrome type and the recommended medical data to the doctor to assist the doctor in making a diagnosis and treatment decision.

[0123] It can be seen that in this embodiment, when the syndrome types in the syndrome type library are continuously supplemented or continuously subdivided, different levels of syndrome types will be matched for the first visit or follow-up visit of the patient to assist the doctor in diagnosis, improving the diagnostic accuracy.

[0124] Based on the medical data update method based on efficacy feedback described in any of the above embodiments, the present application also provides a computer program product, which includes one or more computer programs or instructions. The computer program or instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. When the computer program is executed by a processor, the method described in any of the above embodiments is implemented.

[0125] Based on the medical data update method based on efficacy feedback described in any of the above embodiments, the present application also provides a Figure 7 structural schematic diagram of an electronic device as shown. As Figure 7 , at the hardware level, the electronic device includes a processor, an internal bus, a network interface, a memory, and a non-volatile memory. Of course, there may also be other hardware required for other services. The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it to implement the medical data update method based on efficacy feedback described in any of the above embodiments.

[0126] The present application also provides a computer storage medium, which stores a computer program. When the computer program is executed by a processor, it can be used to execute the medical data update method based on efficacy feedback described in any of the above embodiments.

[0127] In several embodiments provided by the present application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the drawings show the possible architectures, functions, and operations of devices, methods, and computer program products according to multiple embodiments of the present application. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code, and the module, program segment, or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than marked in the drawings. For example, two consecutive blocks can actually be executed substantially in parallel, and they can sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, as well as the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

[0128] In addition, in each embodiment of the present application, the functional modules can be integrated together to form an independent part, or each module can exist alone, or two or more modules can be integrated to form an independent part.

[0129] When the above-mentioned functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of this application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.

[0130] The above are only the embodiments of this application and are not used to limit the protection scope of this application. For those skilled in the art, this application can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of this application shall be included in the protection scope of this application. It should be noted that similar reference numerals and letters represent similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings.

[0131] The above is only the specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed by this application, and all should be covered by the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claims.

[0132] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "including a..." does not exclude the existence of additional identical elements in the process, method, article or device including the said element.

Claims

1. A medical data updating method based on efficacy feedback, characterized in that: The method comprises: Performing statistics on the amount of therapeutic effect feedback information for each syndrome under each disease recorded in the syndrome database; wherein the syndrome database is used to record the medical data of multiple syndromes under multiple diseases; the therapeutic effect feedback information includes positive feedback information and negative feedback information; Based on the statistical results of the quantity of the negative feedback information of each syndrome type, determining the syndrome type to be optimized, and obtaining the updated data of the syndrome type to be optimized; If the updated data includes a newly added target syndrome type and newly added medical data, a mapping relationship between the target syndrome type and the newly added medical data is added to the syndrome type library; If the update data includes prescription update data, the prescription data in the medical data of the syndrome to be optimized is updated.

2. The method according to claim 1, characterized in that The medical data of each syndrome type includes a symptom data set, and the symptom data set includes one or more of primary symptom data, secondary symptom data and concomitant symptom data; the efficacy feedback information is feedback information for each symptom data in the symptom data set; The statistical analysis of the amount of therapeutic effect feedback information for each syndrome under each disease recorded in the syndrome database includes: For each syndrome type recorded in the syndrome type library, respectively obtaining therapeutic effect feedback information of each symptom data corresponding to the syndrome type; Performing statistics on the quantity of therapeutic effect feedback information for each symptom data of the syndrome type, and obtaining the statistical result of the quantity of negative feedback information corresponding to each symptom data; Among them, the number of negative feedback information of at least one symptom data corresponding to the syndrome to be optimized exceeds a preset statistical threshold.

3. The method according to claim 1, characterized in that The statistical analysis of the amount of therapeutic effect feedback information for each syndrome under each disease recorded in the syndrome database includes: For each of the syndromes recorded in the syndrome database, the efficacy feedback information is divided into a plurality of feedback groups corresponding to the patient attributes according to the patient attribute information carried in the efficacy feedback information; wherein the patient attribute information includes one or more of age, gender and region; Perform quantitative statistics on the feedback groups corresponding to each patient attribute to obtain the quantitative statistical results of negative feedback information in each feedback group; Among them, the syndrome type to be optimized corresponds to at least one target feedback group whose amount of negative feedback information exceeds a preset statistical threshold, and the update data of the syndrome type to be optimized carries the patient attribute information corresponding to the target feedback group.

4. The method according to claim 1, characterized in that: The efficacy feedback information includes efficacy feedback text. Before counting the amount of efficacy feedback information for each syndrome recorded in the syndrome database, the method further includes: Semantic extraction is performed on the therapeutic effect feedback text to determine whether the therapeutic effect feedback text is positive feedback information or negative feedback information.

5. The method according to claim 1, characterized in that The determining of the syndrome type to be optimized based on the statistical result of the quantity of the negative feedback information of each syndrome type includes: Based on the quantitative statistical result, determining a first syndrome type to be optimized whose negative feedback information exceeds a first statistical threshold and does not exceed a second statistical threshold; wherein the update data of the first syndrome type to be optimized includes the target syndrome type and the newly added medical data, and / or includes the prescription update data; Based on the quantitative statistical result, a second syndrome type to be optimized whose negative feedback information exceeds the second statistical threshold is determined, wherein the update data of the second syndrome type to be optimized includes the prescription update data.

6. The method according to any one of claims 1 to 5, characterized in that: If the updated data includes a newly added target syndrome type and newly added medical data, adding a mapping relationship between the target syndrome type and the newly added medical data in the syndrome type library includes: If the updated data includes a newly added primary syndrome type and first newly added medical data of the primary syndrome type, the primary syndrome type is added to the primary syndrome type classification of the syndrome type library, and the mapping relationship between the primary syndrome type and the first newly added medical data is stored in the syndrome type library; If the updated data includes multiple secondary syndromes obtained after splitting the syndrome to be optimized and the second newly added medical data of each secondary syndrome, the multiple secondary syndromes are added to the secondary syndrome classification under the syndrome to be optimized in the syndrome library, and the mapping relationship between each secondary syndrome and the corresponding second newly added medical data is stored in the syndrome library.

7. The method according to claim 6, characterized in that The method further comprises: Receive patient consultation information; If the medical information does not carry any therapeutic effect feedback information for the historical medical treatment, determining a recommended syndrome matching the medical information from the primary syndrome classification of the syndrome library; If the medical information carries the therapeutic effect feedback information of the historical medical visit, a recommended syndrome type matching the medical information is determined from the primary syndrome type classification or the target secondary syndrome type classification of the syndrome type library; wherein the target secondary syndrome type is a secondary syndrome type classification under the historical syndrome type determined in the historical medical visit; The recommended medical data of the recommended syndrome type is acquired from the syndrome type library, and the recommended syndrome type and the recommended medical data are output to the physician.

8. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

9. An electronic device, characterized in that: The electronic device comprises: processor; a memory for storing processor-executable instructions; Wherein, when the processor calls the executable instructions, the operation of any method described in claims 1-7 is implemented.

10. A computer-readable storage medium, characterized in that: Computer instructions are stored thereon, and when the computer instructions are executed by a processor, the steps of any method described in claims 1-7 are implemented.

Images