Traceability method, device and equipment for clinical auxiliary decision-making and medium

Abstract

The application discloses a kind of clinical auxiliary decision's traceability method, device, equipment and medium, it is related to data processing technical field, the method comprises: obtaining clinical data, whether the rule trigger condition is satisfied according to the dynamic rule base constructed to judge clinical data;Dynamic rule base is associated with static knowledge base;When satisfying rule trigger condition, the dynamic traceability information matched with rule trigger condition is obtained from dynamic rule base;Dynamic traceability information includes: target rule item identification, target rule prompt content, target rule prompt basis content;According to target rule item identification, the static traceability information matched with target rule item identification is obtained from static knowledge base;Static traceability information includes: target knowledge item identification and target associated knowledge content;Receive and respond to operation instruction, mark target associated knowledge content.The scheme solves the trust degree problem caused by rule opacity, improves the accuracy of clinical decision.

Description

Technical Field

[0001] This invention generally relates to the field of clinical medical technology, and specifically to a traceability method, device, equipment and medium for clinical decision support. Background Technology

[0002] With the continuous development of medical technology and information processing technology, Clinical Decision Support System (CDSS), as a medical information technology application system based on human-computer interaction, has been increasingly used in the medical field because it can provide more and more auxiliary medical support.

[0003] Currently, clinical decision support systems primarily focus on expanding the number of rules to improve the system's coverage and usability. However, the resulting clinical decision support systems lack transparency, making it difficult for medical personnel to assess their accuracy and reliability. This reduces their trust in the system, impacts their judgment and decision-making processes, and ultimately lowers work efficiency. Summary of the Invention

[0004] In view of the above-mentioned defects or deficiencies in the prior art, it is desirable to provide a traceability method, device, equipment and medium for clinical decision support.

[0005] In a first aspect, the present invention provides a method for tracing the origins of clinical decision support, the method comprising:

[0006] Acquire clinical data, and determine whether the clinical data meets the rule triggering conditions based on the constructed dynamic rule base; the dynamic rule base is associated with the static knowledge base;

[0007] When the rule triggering condition is met, dynamic tracing information matching the rule triggering condition is obtained from the dynamic rule base; the dynamic tracing information includes: target rule entry identifier, target rule prompt content, and target rule prompt basis content;

[0008] Based on the target rule entry identifier, static tracing information matching the target rule entry identifier is obtained from the static knowledge base; the static tracing information includes: target knowledge entry identifier and target associated knowledge content, wherein the target associated knowledge content is the knowledge content that matches the target knowledge entry identifier to the highest degree;

[0009] Receive and respond to operation instructions to mark the target-related knowledge content.

[0010] In one embodiment, obtaining dynamic tracing information corresponding to the rule triggering condition from the dynamic rule base includes:

[0011] Obtain the rule entry identifier that matches the rule triggering condition from the dynamic rule base as the target rule entry identifier;

[0012] Obtain the rule prompt content that matches the target rule entry identifier from the dynamic rule base as the target rule prompt content;

[0013] The rule prompt content corresponding to the target rule entry identifier is used as the target rule prompt content.

[0014] In one embodiment, based on the target rule entry identifier, static tracing information matching the target rule entry identifier is obtained from the static knowledge base, including:

[0015] Based on the target rule entry identifier, obtain the target knowledge entry identifier that matches the target rule entry identifier from the static knowledge base;

[0016] The associated knowledge content corresponding to the target knowledge entry identifier is taken as the target associated knowledge content.

[0017] In one embodiment, before acquiring clinical data and determining whether the clinical data meets the rule triggering conditions based on the constructed dynamic rule base, the method further includes:

[0018] Build a static knowledge base and a dynamic rule base;

[0019] Establish a mapping relationship between the static knowledge base and the dynamic rule base.

[0020] In one embodiment, constructing a static knowledge base includes:

[0021] Acquire clinical auxiliary data; the clinical auxiliary data includes at least one of the following: literature data, medical experience data, and clinical data;

[0022] According to preset static conversion rules, the clinical auxiliary data is converted into static knowledge entries; the static knowledge entries include: knowledge entry identifier and knowledge content;

[0023] The static knowledge base is constructed based on the knowledge entry identifier and the knowledge content.

[0024] In one embodiment, constructing a dynamic rule base includes:

[0025] Obtain dynamic rule data;

[0026] According to preset dynamic conversion rules, the dynamic rule data is converted into dynamic rule entries; the dynamic rule entries include: rule entry identifier and rule content;

[0027] For each dynamic rule entry, construct the rule triggering conditions, rule prompt content, and rule prompt basis content;

[0028] The dynamic rule library is constructed based on the dynamic rule entries, the rule triggering conditions, the rule prompt content, and the rule prompt basis content.

[0029] In one embodiment, establishing the mapping relationship between the static knowledge base and the dynamic rule base includes:

[0030] Obtain the associated knowledge entry identifier for each rule entry identifier, and establish a mapping relationship between the rule entry identifier and the associated knowledge entry identifier;

[0031] Based on the associated knowledge entry identifier, determine the knowledge content that matches the associated knowledge entry identifier;

[0032] The knowledge content with the highest matching degree is used as the associated knowledge content and bound to the rule entry identifier.

[0033] Secondly, embodiments of this application provide a traceability device for clinical decision support, the device comprising:

[0034] The judgment module is used to acquire clinical data and determine whether the clinical data meets the rule triggering conditions based on the constructed dynamic rule base; the dynamic rule base is associated with the static knowledge base.

[0035] The dynamic acquisition module is used to acquire dynamic tracing information matching the rule triggering condition from the dynamic rule base when the rule triggering condition is met; the dynamic tracing information includes: target rule entry identifier, target rule prompt content, and target rule prompt basis content;

[0036] The static acquisition module is used to acquire static tracing information that matches the target rule entry identifier from the static knowledge base based on the target rule entry identifier; the static tracing information includes: target knowledge entry identifier and target associated knowledge content, wherein the target associated knowledge content is the knowledge content that matches the target knowledge entry identifier with the highest degree of matching;

[0037] The tagging module is used to receive and respond to operation instructions to tag the target-related knowledge content.

[0038] Thirdly, embodiments of this application provide a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the clinical decision support traceability method provided in the above embodiments.

[0039] Fourthly, embodiments of this application provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the traceability method for clinical decision support provided in the above embodiments.

[0040] According to the specific embodiments provided in this application, the following technical effects are disclosed:

[0041] The clinical decision support traceability method, apparatus, device, and medium provided in this application include: acquiring clinical data; determining whether the clinical data meets rule triggering conditions based on a constructed dynamic rule base; when the rule triggering conditions are met, acquiring dynamic traceability information matching the rule triggering conditions from the dynamic rule base, the dynamic traceability information including: target rule entry identifier, target rule prompt content, target rule prompt basis content; and acquiring static traceability information matching the target rule entry identifier from a static knowledge base based on the target rule entry identifier, the static traceability information including: target knowledge entry identifier and target associated knowledge content, the target associated knowledge content being the knowledge content that matches the target knowledge entry with the highest degree of matching; and receiving and responding to an operation instruction to mark the target associated knowledge content. Compared with existing technologies, this technical solution can determine in real time whether clinical data meets the rule triggering conditions through a dynamic rule base. This allows medical staff to quickly and accurately obtain the matching target rule entry identifier, target rule prompt content, and target rule prompt basis content. By linking the dynamic rule base with the static knowledge base, it can quickly obtain the target knowledge entry identifier and target related knowledge content based on the target rule entry identifier. This provides data guidance information for medical staff to evaluate the accuracy and reliability of content and rules. After receiving operation instructions, it marks the target related knowledge content, making it easy for medical staff to quickly locate literature content closely related to the current rule. This not only solves the trust problem caused by the lack of rule transparency, but also improves the utilization efficiency of static medical literature knowledge and the accuracy and efficiency of clinical decision-making. Attached Figure Description

[0042] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0043] Figure 1 This is a diagram illustrating the application environment of the clinical decision support tracing method provided in one embodiment of this application.

[0044] Figure 2 This is a flowchart illustrating the traceability method for clinical decision support provided in one embodiment of this application;

[0045] Figure 3 A flowchart illustrating a method for establishing a mapping relationship between a static knowledge base and a dynamic rule base, provided in an embodiment of this application;

[0046] Figure 4 A flowchart illustrating a clinical decision support tracing method provided in an embodiment of this application;

[0047] Figure 5 A schematic diagram of the functional modules of a traceability device for clinical decision support provided in an embodiment of this application;

[0048] Figure 6 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0049] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0050] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0051] As mentioned in the background section, clinical decision support systems in related technologies lack transparency. Because the rules and prompts lack clear basis and source, it is difficult for medical personnel to assess their accuracy and reliability, which reduces their trust in the system, affects their judgment and decision-making process, and leads to reduced work efficiency.

[0052] To address the aforementioned shortcomings, this application provides a traceability method for clinical decision support. Compared to existing technologies, this solution utilizes a dynamic rule base to determine in real-time whether clinical data meets rule triggering conditions. This facilitates medical personnel in quickly and accurately obtaining matching target rule entry identifiers, target rule prompts, and the basis for those prompts. By linking the dynamic rule base with a static knowledge base, it can quickly retrieve target knowledge entry identifiers and related knowledge content based on the target rule entry identifiers. This provides data guidance for medical personnel to assess the accuracy and reliability of content and rules. Furthermore, upon receiving an operation instruction, it marks the target-related knowledge content, enabling medical personnel to quickly locate literature closely related to the current rule. This not only solves the trust issue caused by rule opacity but also improves the utilization efficiency of static medical literature knowledge and the accuracy and efficiency of clinical decision-making.

[0053] The clinical decision support traceability method provided in this application can be applied to, for example... Figure 1 In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be set up independently, integrated into server 104, or placed in the cloud or on other servers. Terminal 102 can send real-time monitored clinical data to server 104. After receiving the clinical data, server 104 determines whether the clinical data meets the rule triggering conditions based on a constructed dynamic rule base. When the rule triggering conditions are met, it retrieves the corresponding dynamic traceability information from the dynamic rule base and the corresponding static traceability information from the static knowledge base. Then, after receiving the operation instruction on terminal 102, it marks the target associated indication content and displays it on terminal 102. Furthermore, in some embodiments, the traceability method for clinical decision support can also be implemented independently by server 104 or terminal 102. For example, terminal 102 can directly perform traceability processing for the clinical decision support to be processed, or server 104 can retrieve clinical data from the data storage system and perform traceability processing on the clinical data.

[0054] Optionally, the aforementioned dynamic rule base and static knowledge base can be constructed by server 104 or terminal 102 based on clinical auxiliary data analysis.

[0055] The terminal 102 can be, but is not limited to, various desktop computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, and smart in-vehicle devices. Portable wearable devices can include smartwatches, smart bracelets, and head-mounted devices. The server 104 can be implemented using a standalone server or a server cluster composed of multiple servers, or it can be a cloud server.

[0056] In one exemplary embodiment, such as Figure 2 As shown, a traceability method for clinical decision support is provided. This method is executed by computer devices, specifically by a terminal or server alone, or by both a terminal and a server. In this embodiment, the method is applied to... Figure 1 Taking server 104 as an example, the explanation includes the following steps S201 to S204. Wherein:

[0057] Step S201: Obtain clinical data and determine whether the clinical data meets the rule triggering conditions based on the constructed dynamic rule base; the dynamic rule base is associated with the static knowledge base.

[0058] It should be noted that the aforementioned clinical data requires processing by a clinical decision support system and may include patient vital signs, diagnostic and treatment parameters, and basic information. The dynamic rule base and static knowledge base can be pre-built according to actual needs. The dynamic rule base includes multiple rule triggering conditions, each corresponding to a set of clinical data, which can be used to determine whether the rule triggering conditions are met.

[0059] The aforementioned clinical data can be obtained through public data sources, imported from external systems, or obtained through real-time monitoring. This embodiment does not limit the method of obtaining clinical data.

[0060] In this embodiment, after obtaining clinical data, a dynamic rule base can be invoked to determine whether the clinical data meets the rule triggering conditions in the dynamic rule base. Specifically, the corresponding condition parameters can be determined based on the clinical data, and the rule parameters for each rule triggering condition can be obtained. Then, the condition parameters and rule parameters can be matched. When the match is consistent, it indicates that the clinical data meets the rule triggering conditions; when the match is inconsistent, it indicates that the clinical data does not meet the rule triggering conditions.

[0061] For example, the triggering conditions of the above rules may include the patient's vital signs information and diagnostic parameters, such as: body temperature above 38.5°C for three consecutive days, white blood cell count above 10×109 / L, and lung imaging showing that the area of ​​inflammatory lesions has increased by 20% or more in the past week.

[0062] In this embodiment, after obtaining clinical data, the system determines whether the clinical data meets the rule triggering conditions based on the constructed dynamic rule base. This facilitates medical staff in querying the rules to further confirm the accuracy and reliability of the data in the clinical decision support system, thus solving the trust issue caused by the lack of rule transparency.

[0063] In one embodiment, before acquiring clinical data and determining whether the clinical data meets the rule triggering conditions based on the constructed dynamic rule base, please refer to [link to relevant documentation]. Figure 3 As shown, the above method also includes:

[0064] Step S301: Construct a static knowledge base and a dynamic rule base.

[0065] Step S302: Establish the mapping relationship between the static knowledge base and the dynamic rule base.

[0066] It should be noted that the aforementioned static knowledge base can be constructed based on clinical auxiliary data, while the dynamic rule base can be constructed based on dynamic rule data. The static knowledge base can include basic medical knowledge and clinical medical knowledge, such as knowledge related to human anatomy, physiology, and pathology. Knowledge related to human anatomy can include the structure, location, and physiological functions of various organs; physiological knowledge can cover the various functional operations of the human body under normal physiological conditions; and pathological knowledge can include the etiology, pathogenesis, and pathological changes of various diseases.

[0067] A dynamic rule base can include rule triggering conditions, rule prompts, and the basis for those prompts. Rule triggering conditions are typically related to a patient's vital signs, laboratory test results, and imaging results. Rule prompts can refer to the guided actions performed by medical personnel after a rule is triggered. The basis for those prompts is the rule reference information corresponding to the prompts, i.e., the theoretical or practical basis supporting the rule's formulation.

[0068] As one feasible approach, during the construction of a static knowledge base, clinical auxiliary data is acquired, which includes at least one of the following: literature data, medical experience data, and clinical data. The clinical auxiliary data is then converted into static knowledge entries according to a preset static conversion rule. Each static knowledge entry includes a knowledge entry identifier and knowledge content. Finally, a static knowledge base is constructed based on the knowledge entry identifier and knowledge content.

[0069] It should be noted that the aforementioned clinical auxiliary data can be imported from external devices, obtained from public data sources, or compiled after consulting relevant materials. This application embodiment does not impose any limitations on the method of acquiring clinical auxiliary data. Clinical auxiliary data can include original materials such as medical literature guidelines, expert consensus, clinical pathways, and medical textbooks. The preset static conversion rules are customized according to actual needs.

[0070] After acquiring clinical auxiliary data, it can be transformed into static knowledge entries according to preset static transformation rules. Each static knowledge entry includes: a knowledge entry identifier and knowledge content. The knowledge entry identifier is used to uniquely identify the knowledge entry, such as a "knowledge ID," while the knowledge content includes specific literature information. Each knowledge entry identifier uniquely corresponds to one or more associated knowledge content entries.

[0071] Optionally, the static knowledge base can be configured with an index structure, which is used to associate knowledge IDs with knowledge content. The index structure may include, for example, a hash tree or a B-tree. After obtaining the target knowledge ID, the corresponding target knowledge content can be quickly found in the static knowledge base according to the index structure, allowing the system to quickly locate the target entry in constant or logarithmic time, thereby significantly improving the retrieval speed of rule-based data.

[0072] In this embodiment of the application, by constructing a static knowledge base, a database that can be consulted by clinical medical personnel can be proposed, providing good data guidance information for the subsequent application of dynamic rules.

[0073] As another possible approach, in the process of building a dynamic rule base, dynamic rule data can be acquired first, and then converted into dynamic rule entries according to preset dynamic transformation rules. The dynamic rule entries include: rule entry identification information and rule content. For each dynamic rule entry, rule triggering conditions, rule prompt content, and rule prompt basis content are constructed. Based on the dynamic rule entries, rule triggering conditions, rule prompt content, and rule prompt basis content, a dynamic rule base is constructed.

[0074] It should be noted that the aforementioned dynamic rule data can be imported from external devices, obtained from public data sources, or compiled after consulting relevant materials. This application embodiment does not impose any limitations on the method of obtaining dynamic rule data. Dynamic rule data refers to the data required for dynamic rules, such as multiple cases, medication guidelines, clinical operation guidelines, etc. The preset dynamic conversion rules are customized according to actual needs.

[0075] After acquiring dynamic rule data, it can be converted into dynamic rule entries according to preset dynamic transformation rules. Each dynamic rule entry includes a rule entry identifier and specific rule content, and defines rule triggering conditions, including specific patient population characteristics and clinical operation scenarios, to ensure that the rule is triggered and activated at the appropriate time and in the appropriate context. Rule prompt content is also defined, which may include specific information displayed to medical personnel after the rule triggering condition is triggered. The basis for the rule prompt is then defined, which may include literature, historical experience, etc. The rule entry identifier can be a "rule ID," and the rule content includes specific rule information, thus constructing a dynamic rule base. Each rule entry identifier uniquely corresponds to one or more associated rule contents, rule triggering conditions, rule prompt content, and rule prompt basis content.

[0076] The triggering conditions for the aforementioned rules could be set, for example, as follows: when a patient's blood pressure is higher than 180 / 110 mmHg and accompanied by symptoms such as headache and dizziness, the triggered rule would be: Hypertensive Emergency Management Rule. Trigger thresholds for different disease scenarios would specify the exact values ​​of various indicators or the specific conditions under which the corresponding rule is activated. For example, when monitoring blood glucose in diabetic patients, a fasting blood glucose level higher than 13.9 mmol / L accompanied by positive ketone bodies would trigger the Diabetic Ketoacidosis Management Rule.

[0077] The above rule prompts provide immediate guidance after a rule is triggered, indicating to healthcare professionals what initial actions to take and subsequent treatment recommendations. For example, after triggering the hypertensive emergency management rule, the prompts might include "Immediately administer antihypertensive medication, place the patient in a quiet environment, and closely monitor blood pressure changes, etc." Treatment recommendations provide healthcare professionals with directions for subsequent treatment activities after initial intervention. For instance, in managing diabetic ketoacidosis, subsequent recommendations might include "Complete laboratory tests such as blood gas analysis as soon as possible, and adjust fluid resuscitation and insulin treatment plans based on the results, etc."

[0078] The basis for rule suggestions can be presented as links or summaries, providing the theoretical support source behind each rule. This support can be linked to relevant medical research papers, clinical guidelines, or other literature, or summaries of these documents can be extracted and stored in a dynamic rule base. For example, a rule for managing hypertensive emergencies might be based on an authoritative research paper on the management of hypertension; the link or summary of that paper could be stored so that medical personnel can access the scientific validity of the rule.

[0079] After constructing the static knowledge base and the dynamic rule base, a mapping relationship is established between the static knowledge base and the dynamic rule base. This is done by obtaining the associated knowledge entry identifier for each rule entry identifier and establishing a mapping relationship between the rule entry identifier and the associated knowledge entry identifier. Based on the associated knowledge entry identifier, the knowledge content that matches the associated knowledge entry identifier is determined. Then, the content with the highest matching degree is selected from the knowledge content as the associated knowledge content and bound to the rule entry identifier.

[0080] Specifically, taking rule entries identified as "Rule ID" and knowledge entries identified as "Knowledge ID" as an example, a binding relationship is established between the Knowledge IDs in the static knowledge base and the Rule IDs in the dynamic rule base. For each Rule ID, a corresponding associated Knowledge ID can be determined. Each dynamic rule is then linked to a relevant Knowledge ID in the static knowledge base. Based on the associated Rule ID, the knowledge content matching the associated Rule ID is determined. The content with the highest degree of matching is then selected as the associated knowledge content, and this associated knowledge content is treated as strongly associated content and bound to the Rule ID. The associated knowledge content can be the paragraph content most closely related to the Rule ID among all knowledge content. For example, it can be in text format, table format, or diagram format. Text format could include, for example, a summary.

[0081] Optionally, the aforementioned associated knowledge content can be determined by performing in-depth analysis of all knowledge content using a preset algorithm. The preset algorithm can be, for example, a natural language processing (NLP) algorithm. By pre-binding knowledge IDs with associated knowledge content, it can ensure that medical personnel can quickly obtain key information and improve the accuracy and relevance of the rule basis.

[0082] In this embodiment, by constructing a static knowledge base and a dynamic rule base, and establishing a mapping relationship between the static knowledge base and the dynamic rule base, it is ensured that each rule can accurately find specific related knowledge content, accurately determine dynamic traceability information and static traceability information, avoid confusion and incorrect matching that may be caused by many-to-many or one-to-many relationships, thereby improving the accuracy of recognition.

[0083] Step S202: When the rule triggering condition is met, obtain the dynamic traceability information that matches the rule triggering condition from the dynamic rule base; the dynamic traceability information includes: target rule entry identifier, target rule prompt content, and target rule prompt basis content.

[0084] Step S203: Based on the target rule entry identifier, obtain static traceability information that matches the target rule entry identifier from the static knowledge base; the static traceability information includes: target knowledge entry identifier and target associated knowledge content, the target associated knowledge content being the knowledge content that matches the target knowledge entry identifier to the highest degree.

[0085] Step S204: Receive and respond to the operation instruction, and mark the associated knowledge content.

[0086] Specifically, please see Figure 4 As shown, Figure 4The flowchart illustrating the traceability method for clinical decision support provided in this application includes a database construction phase and an application phase. In the construction phase, a static knowledge base and a dynamic rule base are first defined. Specifically, after defining the static knowledge base, data such as medical literature guidelines and medical experience data are received and processed. This data is then converted into static knowledge entries according to static transformation rules. Each static knowledge entry includes a knowledge ID and corresponding knowledge content. After defining the dynamic rule base, dynamic rule entries can be defined, obtaining rule IDs and rule names. Then, for each rule ID, corresponding rule triggering conditions, rule prompt content, and rule prompt basis content are defined. A binding relationship is established between the static knowledge base and the dynamic rule base by establishing a binding relationship based on knowledge IDs and rule IDs. Then, the knowledge content with the highest correlation to the rule ID is obtained as strongly correlated content, copied, and stored.

[0087] After establishing a binding relationship between the static knowledge base and the dynamic rule base, the application phase can be executed. During the application phase, clinical data is monitored in real time, and it is determined whether the clinical data meets the rule triggering conditions. When the rule triggering conditions are met, the target rule ID matching the rule triggering conditions is retrieved from the dynamic rule base. Then, the target rule prompt content corresponding to the target rule ID is found and displayed on the clinical information system interface. This target rule prompt content can provide medical staff with immediate guidance data. Then, based on the target rule ID, the target rule prompt basis content displayed on the clinical information system interface is retrieved. This target rule prompt basis content can be represented in the form of a link or summary, enabling medical staff to understand the theoretical support data corresponding to the rule.

[0088] For example, the target rule prompt displayed on the clinical information system interface might include: "The patient's current pneumonia symptoms have worsened, and adjustments to the treatment plan should be considered. It is recommended to reassess the effectiveness of the antibiotics being used, and drug sensitivity testing could be considered to guide more precise medication selection. Simultaneously, closely monitor changes in the patient's respiratory function and other vital signs." The basis for the target rule prompt could be, for example, the basis for rules governing hypertensive emergencies. This basis could be derived from an authoritative research paper on the management of hypertensive crises, and the link or abstract of this paper could be stored for medical personnel to access and understand the scientific validity of the rule.

[0089] Furthermore, after obtaining the target rule ID, if medical staff want to gain a deeper understanding of static traceability information, they can call and display the static knowledge base. From the static knowledge base, they can find the target knowledge ID that matches the target rule ID. When medical staff open the static literature knowledge and need to further obtain strongly related content, they can perform a trigger operation on the interface, so that medical staff can receive and respond to the operation command, obtain the target related knowledge content related to the target rule, and mark it after obtaining the target related knowledge content. For example, the target related knowledge content can be highlighted, underlined, or bolded.

[0090] The aforementioned target-related knowledge content can be the paragraph with the highest degree of matching with the current rule, or the keyword or key sentence with the highest degree of matching with the current rule.

[0091] In this embodiment, when clinical data meets the rule triggering conditions in the dynamic rule base, the corresponding rule can be matched immediately, and the target rule entry identifier, target rule prompt content, and target rule prompt basis content can be displayed. This allows medical staff to quickly obtain guidance information without spending a lot of time searching through materials. Furthermore, the rule prompt content in the dynamic rule base is combined with the literature knowledge in the static knowledge base, providing medical staff with a more accurate direction for diagnosis and treatment, thereby formulating more personalized treatment plans that are more in line with the specific situation of patients. Through rule identifiers, medical staff can easily obtain dynamic traceability information from the dynamic rule base and static traceability information from the static knowledge base, saving time and effort in knowledge acquisition and providing medical staff with a more convenient way to acquire knowledge. When medical staff open relevant literature, they can quickly focus on the key content closely related to the current rule, highlighting key knowledge and improving the efficiency and quality of medical decision-making.

[0092] The clinical decision support traceability method provided in this application includes: acquiring clinical data; determining whether the clinical data meets the rule triggering conditions based on a constructed dynamic rule base; when the rule triggering conditions are met, acquiring dynamic traceability information matching the rule triggering conditions from the dynamic rule base, the dynamic traceability information including: target rule entry identifier, target rule prompt content, target rule prompt basis content; and acquiring static traceability information matching the target rule entry identifier from a static knowledge base based on the target rule entry identifier, the static traceability information including: target knowledge entry identifier and target associated knowledge content, the target associated knowledge content being the knowledge content that matches the target knowledge entry with the highest degree of matching; receiving and responding to operation instructions, and marking the target associated knowledge content. Compared to existing technologies, this technical solution, through a dynamic rule base, can determine in real time whether clinical data meets the rule triggering conditions. This allows medical staff to quickly and accurately obtain the matching target rule entry identifier, target rule prompt content, and the basis for the target rule prompt. By linking the dynamic rule base with the static knowledge base, it can quickly obtain the target knowledge entry identifier and related knowledge content based on the target rule entry identifier. This provides data guidance for medical staff to evaluate the accuracy and reliability of content and rules. Furthermore, after receiving operation instructions, it marks the target related knowledge content, making it easy for medical staff to quickly locate literature content closely related to the current rule. This not only solves the trust problem caused by the lack of rule transparency but also improves the utilization efficiency of static medical literature knowledge and the accuracy and efficiency of clinical decision-making. It also helps rule management personnel and prevents prompts without rule basis from being applied in clinical practice, further enhancing the practicality and reliability of the clinical auxiliary decision-making system.

[0093] Based on the same inventive concept, this application also provides a traceability device for clinical decision support, used to implement the traceability method for clinical decision support described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more embodiments of the traceability device for clinical decision support provided below can be found in the limitations of the traceability method for clinical decision support described above, and will not be repeated here.

[0094] In one exemplary embodiment, such as Figure 5 As shown, a traceability device for clinical decision support is provided, which includes:

[0095] The judgment module 510 is used to acquire clinical data and determine whether the clinical data meets the rule triggering conditions based on the constructed dynamic rule base; the dynamic rule base is associated with the static knowledge base;

[0096] The dynamic acquisition module 520 is used to obtain dynamic traceability information matching the rule triggering conditions from the dynamic rule base when the rule triggering conditions are met; the dynamic traceability information includes: target rule entry identifier, target rule prompt content, and target rule prompt basis content;

[0097] The static acquisition module 530 is used to obtain static traceability information that matches the target rule entry identifier from the static knowledge base based on the target rule entry identifier. The static traceability information includes: target knowledge entry identifier and target associated knowledge content, where the target associated knowledge content is the knowledge content that matches the target knowledge entry identifier with the highest degree of matching.

[0098] The tagging module 540 is used to receive and respond to operation instructions to tag the target-related knowledge content.

[0099] As an optional implementation, the dynamic acquisition module 520 is specifically used for:

[0100] Obtain the rule entry identifier that matches the rule triggering condition from the dynamic rule base as the target rule entry identifier;

[0101] Retrieve the rule suggestion content that matches the target rule entry identifier from the dynamic rule base as the target rule suggestion content;

[0102] Use the rule prompt content corresponding to the target rule entry identifier as the target rule prompt content.

[0103] As an optional implementation, the static acquisition module 530 is specifically used for:

[0104] Based on the target rule entry identifier, retrieve the target knowledge entry identifier that matches the target rule entry identifier from the static knowledge base;

[0105] The associated knowledge content corresponding to the target knowledge item identifier is taken as the target associated knowledge content.

[0106] As an optional implementation, the above-described apparatus is further used for:

[0107] Build a static knowledge base and a dynamic rule base;

[0108] Establish a mapping relationship between the static knowledge base and the dynamic rule base.

[0109] As an optional implementation, the above-described apparatus is further used for:

[0110] Acquire clinical auxiliary data; clinical auxiliary data includes at least one of the following: literature data, medical experience data, and clinical data;

[0111] According to the preset static transformation rules, clinical auxiliary data is transformed into static knowledge entries; static knowledge entries include: knowledge entry identifier and knowledge content;

[0112] A static knowledge base is constructed based on knowledge entry identifiers and knowledge content.

[0113] As an optional implementation, the above-described apparatus is further used for:

[0114] Obtain dynamic rule data;

[0115] According to the preset dynamic conversion rules, the dynamic rule data is converted into dynamic rule entries; the dynamic rule entries include: rule entry identifier and rule content;

[0116] For each dynamic rule entry, construct the rule triggering conditions, rule prompt content, and rule prompt basis content;

[0117] A dynamic rule library is constructed based on dynamic rule entries, rule triggering conditions, rule prompts, and the basis for rule prompts.

[0118] As an optional implementation, the above-described apparatus is further used for:

[0119] Obtain the associated knowledge entry identifier for each rule entry identifier, and establish a mapping relationship between the rule entry identifier and the associated knowledge entry identifier;

[0120] Based on the associated knowledge entry identifier, determine the knowledge content that matches the associated knowledge entry identifier;

[0121] The knowledge content with the highest matching degree is used as the associated knowledge content and bound to the rule entry identifier.

[0122] This implementation method allows the technical solution to determine in real time whether clinical data meets the rule triggering conditions through a dynamic rule base. This enables medical personnel to quickly and accurately obtain the matching target rule entry identifier, target rule prompt content, and target rule prompt basis content. By linking the dynamic rule base with the static knowledge base, the target knowledge entry identifier and target-related knowledge content can be quickly obtained based on the target rule entry identifier. This provides data guidance information for medical personnel to evaluate the accuracy and reliability of content and rules. Furthermore, after receiving operation instructions, the target-related knowledge content is marked, making it easy for medical personnel to quickly locate literature content closely related to the current rule. This not only solves the trust problem caused by the lack of rule transparency but also improves the utilization efficiency of static medical literature knowledge and the accuracy and efficiency of clinical decision-making.

[0123] In one exemplary embodiment, a computer device is provided, which may be a server or a terminal, and its internal structure diagram may be as follows. Figure 6 As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores video tag processing data. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network connection. When executed by the processor, the computer program implements a traceability method for clinical decision support.

[0124] Those skilled in the art will understand that Figure 6 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0125] In one exemplary embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0126] In one exemplary embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0127] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0128] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0129] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0130] The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0131] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0132] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for tracing the origins of clinical decision support, characterized in that, The methods for tracing the origins of clinical decision support include: Acquire clinical data, and determine whether the clinical data meets the rule triggering conditions based on the constructed dynamic rule base; the dynamic rule base is associated with the static knowledge base; When the rule triggering condition is met, dynamic tracing information matching the rule triggering condition is obtained from the dynamic rule base; the dynamic tracing information includes: target rule entry identifier, target rule prompt content, and target rule prompt basis content; Based on the target rule entry identifier, static tracing information matching the target rule entry identifier is obtained from the static knowledge base; the static tracing information includes: target knowledge entry identifier and target associated knowledge content, wherein the target associated knowledge content is the knowledge content that matches the target knowledge entry identifier to the highest degree; Receive and respond to operation instructions to mark the target-related knowledge content; Before acquiring clinical data and determining whether the clinical data meets the rule triggering conditions based on the constructed dynamic rule base, the method further includes: Build a static knowledge base and a dynamic rule base; Establish a mapping relationship between the static knowledge base and the dynamic rule base; The process of establishing the mapping relationship between the static knowledge base and the dynamic rule base includes: Obtain the associated knowledge entry identifier for each rule entry identifier, and establish a mapping relationship between the rule entry identifier and the associated knowledge entry identifier; Based on the associated knowledge entry identifier, determine the knowledge content that matches the associated knowledge entry identifier; The knowledge content with the highest matching degree is used as the associated knowledge content and bound to the rule entry identifier.

2. The method for tracing the source of clinical decision support according to claim 1, characterized in that, Retrieving dynamic tracing information corresponding to the rule triggering condition from the dynamic rule base includes: Obtain the rule entry identifier that matches the rule triggering condition from the dynamic rule base as the target rule entry identifier; Obtain the rule prompt content that matches the target rule entry identifier from the dynamic rule base as the target rule prompt content; The rule prompt content corresponding to the target rule entry identifier is used as the target rule prompt content.

3. The method for tracing the source of clinical decision support according to claim 1, characterized in that, Based on the target rule entry identifier, static source information matching the target rule entry identifier is obtained from the static knowledge base, including: Based on the target rule entry identifier, obtain the target knowledge entry identifier that matches the target rule entry identifier from the static knowledge base; The associated knowledge content corresponding to the target knowledge entry identifier is taken as the target associated knowledge content.

4. The method for tracing the source of clinical decision support according to claim 1, characterized in that, Building a static knowledge base includes: Acquire clinical auxiliary data; the clinical auxiliary data includes at least one of the following: literature data, medical experience data, and clinical data; According to preset static conversion rules, the clinical auxiliary data is converted into static knowledge entries; the static knowledge entries include: knowledge entry identifier and knowledge content; The static knowledge base is constructed based on the knowledge entry identifier and the knowledge content.

5. The method for tracing the source of clinical decision support according to claim 1, characterized in that, Building a dynamic rule base includes: Obtain dynamic rule data; According to preset dynamic conversion rules, the dynamic rule data is converted into dynamic rule entries; the dynamic rule entries include: rule entry identifier and rule content; For each dynamic rule entry, construct the rule triggering conditions, rule prompt content, and rule prompt basis content; The dynamic rule library is constructed based on the dynamic rule entries, the rule triggering conditions, the rule prompt content, and the rule prompt basis content.

6. A traceability device for clinical decision support, characterized in that, The traceability device for clinical decision support includes: The judgment module is used to acquire clinical data and determine whether the clinical data meets the rule triggering conditions based on the constructed dynamic rule base; the dynamic rule base is associated with the static knowledge base. The dynamic acquisition module is used to acquire dynamic tracing information matching the rule triggering condition from the dynamic rule base when the rule triggering condition is met; the dynamic tracing information includes: target rule entry identifier, target rule prompt content, and target rule prompt basis content; The static acquisition module is used to acquire static tracing information that matches the target rule entry identifier from the static knowledge base based on the target rule entry identifier; the static tracing information includes: target knowledge entry identifier and target associated knowledge content, wherein the target associated knowledge content is the knowledge content that matches the target knowledge entry identifier with the highest degree of matching; The tagging module is used to receive and respond to operation instructions to tag the target-related knowledge content; The device is also used for: Build a static knowledge base and a dynamic rule base; Establish a mapping relationship between the static knowledge base and the dynamic rule base; The device is further configured to: obtain the associated knowledge entry identifier of each rule entry identifier, and establish a mapping relationship between the rule entry identifier and the associated knowledge entry identifier; Based on the associated knowledge entry identifier, determine the knowledge content that matches the associated knowledge entry identifier; The knowledge content with the highest matching degree is used as the associated knowledge content and bound to the rule entry identifier.

7. A computer device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the traceability method for clinical decision support according to any one of claims 1-5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the traceability method for clinical decision support as described in any one of claims 1-5.

Images