A dynamic physical examination path generation method, system and terminal device based on disease discrimination value

Abstract

The application discloses a kind of dynamic physical examination path generation methods, system and terminal equipment based on disease identification value, it is related to intelligent medical technical field, its technical scheme main point is as follows: including the following steps: S1. obtain the symptom complaint information of patient;S2. according to the symptom complaint information of patient, generates initial disease candidate set, calculates the prior probability of each candidate disease, obtains disease candidate set with prior probability;S3. based on current disease candidate set, planning optimal physical examination item;S4. according to optimal physical examination item, execute inspection, output inspection result, form new evidence set;If inspection equipment is unavailable, return S3 and re-plan;S5. fusion new evidence set, update the probability of all candidate diseases;S6. judge whether it meets termination condition, if it meets, then output final diagnosis result and disease probability distribution;If it does not meet, then return S3 and re-plan.The application improves the accuracy and efficiency of diagnosis, provides complete solution.

Description

Technical Field

[0001] This invention relates to the field of intelligent medical technology, and more specifically, to a method, system, and terminal device for generating dynamic physical examination pathways based on disease identification value. Background Technology

[0002] With the deep integration of artificial intelligence and Internet of Things technologies in the medical field, various intelligent consultation systems and clinical decision support systems are emerging. These systems aim to assist doctors, especially medical practitioners in grassroots or resource-limited areas, in making disease diagnoses more efficiently and accurately.

[0003] Current mainstream intelligent consultation technology solutions typically follow one of the following two models:

[0004] Independent Consultation-Diagnosis Mode: After collecting patient symptom information through natural language interaction, the system directly outputs a ranked list of possible diseases based on a knowledge base or model. In this mode, the consultation process is completely separated from the subsequent physical examination, and the system cannot provide specific, personalized guidance on "what tests should be done next to verify or rule out a certain diagnosis."

[0005] Fixed physical examination template mode: After obtaining preliminary symptoms, the system will call a preset list of fixed physical examination items bound to the symptom category (for example, all patients with cough are advised to undergo "lung auscultation, chest X-ray, and blood routine examination"). Although this approach introduces physical examination, the examination items are static and rigid, and cannot be dynamically adjusted according to the specific disease probability distribution of each patient.

[0006] The existing solutions described above have the following core flaws and limitations:

[0007] The system fails to establish a closed-loop reasoning chain of "symptom hypothesis → targeted examination → verification / denial of hypothesis → updated decision," which is inconsistent with the actual differential diagnostic thinking process of clinicians.

[0008] The static and inefficient nature of physical examination strategies: Using a fixed checklist of examinations without differentiation fails to identify and prioritize the most valuable examinations for the current specific differential diagnosis, which may lead to unnecessary examinations (increasing patient costs and burden) or omission of key examinations.

[0009] Lack of multi-device collaboration and resource optimization: In scenarios involving multiple medical devices (such as stethoscopes, electrocardiographs, and ultrasound machines), existing systems typically lack a unified perception and scheduling capability for device status (available, busy, faulty), and cannot consider resource constraints when planning examination paths, thus affecting overall efficiency.

[0010] Unable to achieve progressive diagnostic optimization: The system provides all suggestions at once and does not support the iterative optimization process of dynamically adjusting the next examination plan based on the results of the previous examination. Therefore, it cannot simulate the dynamic diagnostic path of a doctor who "examines, thinks, and focuses simultaneously".

[0011] Clinical Practice Comparison: In actual clinical practice, experienced physicians do not order all possible tests at once. Instead, they form several preferred disease hypotheses (candidate diagnosis sets) based on initial information, and then purposefully select one or a few tests with the highest expected benefit (i.e., those that best distinguish different hypotheses or best rule out high-risk diseases). After obtaining the results, the physician updates their judgment and may re-plan subsequent tests until a diagnosis is clear or a decision threshold is reached. This dynamic, value-based selection of the examination path is a key capability that existing intelligent systems have failed to effectively simulate.

[0012] Therefore, the field of medical artificial intelligence urgently needs a dynamic and intelligent physical examination path generation method and system that can simulate the aforementioned clinical differential diagnostic thinking. This system needs to be able to comprehensively evaluate the differential diagnostic value, equipment availability, cost, and risk of various examinations based on real-time changes in disease hypothesis probabilities, thereby planning and executing the optimal examination sequence. Ultimately, this forms a closed-loop reasoning process of "medical history taking – physical examination – diagnosis," significantly improving the accuracy, efficiency, and resource utilization of assisted diagnosis. Summary of the Invention

[0013] The purpose of this invention is to provide a method, system, and terminal device for generating dynamic physical examination pathways based on disease identification value, thereby solving the above-mentioned problems.

[0014] The above-mentioned technical objective of the present invention is achieved through the following technical solution:

[0015] The first aspect of this invention provides a method for generating dynamic physical examination pathways based on disease identification value, comprising the following steps:

[0016] S1. Obtain the patient's symptom and chief complaint information;

[0017] S2. Based on the patient's symptom complaint information, generate an initial disease candidate set, calculate the prior probability of each candidate disease, and obtain a disease candidate set with prior probabilities;

[0018] S3. Based on the current disease candidate set, plan the optimal physical examination items;

[0019] S4. Perform the examination according to the optimal examination items, output the examination results, and form a new evidence set; if the examination equipment is unavailable, return to S3 to replan.

[0020] S5. Integrate the new evidence set and update the probabilities of all candidate diseases;

[0021] S6. Determine if the termination condition is met. If it is met, output the final diagnosis result and disease probability distribution; if it is not met, return to S3 to replan.

[0022] A second aspect of the present invention also provides an apparatus / device / system for generating dynamic physical examination pathways based on disease identification value, comprising a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the above method.

[0023] A third aspect of the present invention also provides a computer-readable storage medium having a computer program / instructions stored thereon, which, when executed by a processor, implement the steps of the above-described method.

[0024] A fourth aspect of the present invention also provides a computer program product, including a computer program / instructions that, when executed by a processor, implement the steps of the above-described method.

[0025] In summary, the present invention has the following beneficial effects:

[0026] This invention constructs a closed-loop dynamic decision-making system of "consultation-physical examination-diagnosis", realizing deep linkage between consultation information and physical examination decisions, simulating the complete process of progressive reasoning of clinicians, and forming a closed loop of intelligent assisted diagnosis;

[0027] This invention generates physical examination items dynamically based on real-time disease probability and optimizes them through value function evaluation, completely abandoning fixed physical examination templates. Each examination selection is based on the most likely disease hypothesis at present, which greatly improves the efficiency of physical examination and differential diagnosis ability, and reduces invalid examinations.

[0028] This invention employs a differential diagnosis-driven model and equipment status modeling to prioritize the examinations that best distinguish similar diseases, quickly narrowing down the candidate space; at the same time, it senses equipment availability to ensure the feasibility of the solution and optimize the collaborative utilization of multiple devices.

[0029] This invention establishes a safety constraint mechanism that forces the insertion of key examinations when candidate diseases contain a high-risk set, setting a safety baseline for the diagnostic process and ensuring that high-risk diseases (such as acute myocardial infarction) are prioritized for screening, significantly reducing the risk of missed diagnosis; Attached Figure Description

[0030] Figure 1 This is a flowchart of a dynamic physical examination path generation method based on disease identification value in an embodiment of the present invention. Detailed Implementation

[0031] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0032] In the embodiments provided in this application, it should be understood that the disclosed methods and systems can be implemented in other ways. The system embodiments described below are merely illustrative. For example, the division of units and modules is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple units or modules can be combined, or integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed may be through some interfaces; the indirect coupling or communication connection of devices or modules may be electrical, mechanical, or other forms.

[0033] In addition, each functional unit in the various embodiments of this application can be integrated into a single processor, or each unit can be a separate device, or two or more units can be integrated into a single device; each functional unit in the various embodiments of this application can be implemented in hardware or in the form of hardware plus software functional units.

[0034] Those skilled in the art will understand that all or part of the steps in the following method embodiments can be implemented by program instructions and related hardware. The aforementioned program instructions can be stored in a computer-readable storage medium. When executed, these program instructions perform the steps of the following method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, read-only memory (ROM), disks, or optical discs.

[0035] It should be understood that the use of terms such as "system," "device," "unit," and / or "module" in this application is merely one method of distinguishing different components, elements, parts, sections, or assemblies at different levels. However, if other terms can achieve the same purpose, they may be replaced by other expressions.

[0036] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, "a plurality of" or "several" means two or more, unless otherwise explicitly specified.

[0037] If a flowchart is used in this application, it is used to illustrate the operations performed by the system according to embodiments of this application. It should be understood that the preceding or following operations are not necessarily performed in exact order. Instead, the steps can be processed in reverse order or simultaneously. Furthermore, other operations can be added to these processes, or one or more steps can be removed from them.

[0038] It should also be noted that, in this document, terms such as “comprising,” “including,” or any other variations thereof are intended to cover non-exclusive inclusion, such that an article or device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such an article or device. Without further limitation, an element defined by the phrase “comprising one…” does not exclude the presence of other identical elements in the article or device that includes the aforementioned element.

[0039] Example 1:

[0040] A method for generating dynamic physical examination pathways based on disease identification value, such as Figure 1 As shown, it includes the following steps:

[0041] S1. Obtain the patient's symptom and chief complaint information;

[0042] S2. Based on the patient's symptom complaint information, generate an initial disease candidate set, calculate the prior probability of each candidate disease, and obtain a disease candidate set with prior probabilities;

[0043] S3. Based on the current disease candidate set, plan the optimal physical examination items;

[0044] S4. Perform the examination according to the optimal examination items, output the examination results, and form a new evidence set; if the examination equipment is unavailable, return to S3 to replan.

[0045] S5. Integrate the new evidence set and update the probabilities of all candidate diseases;

[0046] S6. Determine if the termination condition is met. If it is met, output the final diagnosis result and disease probability distribution; if it is not met, return to S3 to replan.

[0047] In step S2, the patient's symptom complaint information is received, and an initial disease candidate set is generated through knowledge base matching and reasoning. ;

[0048] For each candidate disease Calculate a prior probability To form a prior probability distribution Example: , , Output a set of disease candidate sets with prior probabilities. .

[0049] To provide more precise guidance for physical examinations, candidate diseases are divided into two categories:

[0050]

[0051] Main candidate set Diseases with a high probability of occurrence and considered as the primary suspected target.

[0052] Differential Diagnosis Collection These are diseases with a relatively low probability of occurrence, but which need to be distinguished from the primary candidate disease. This structure ensures that the physical examination plan can focus on high-probability diseases while proactively excluding easily confused diagnoses.

[0053] In step S3, the step of planning the optimal physical examination items based on the current disease candidate set includes the following steps: screening all candidate physical examination items related to the candidate diseases, calculating the comprehensive value of each candidate physical examination item, and planning the optimal physical examination items. Specifically, this includes the following:

[0054] Based on the current This generates a set of physical examination items to be evaluated.

[0055] Define the body set ,

[0056] For example, among them, Lung auscultation; Heart sound auscultation; Blood oxygen saturation test; Blood glucose testing; Blood lipid test; Body temperature detection; Electrocardiogram (ECG) monitoring; Ultrasound examination.

[0057] From all the physical examination items In the process, all physical examination items related to the candidate diseases are selected to form a candidate action set:

[0058]

[0059] For each candidate check Calculate its comprehensive value :

[0060] ;

[0061] Disease differentiation ability, quantifying the ability of test results to change the current disease probability distribution. Its core calculation method is: ;

[0062] in, Based on historical statistics, Measurement results For disease The distinction of contributions.

[0063] Risk coverage capability, with a focus on identification. The ability to manage medium- and high-risk diseases.

[0064] Device availability rating depends on device status. :

[0065] ;

[0066] Cost rating (time, economy, etc.).

[0067] : This is an adjustable weight parameter.

[0068] Based on the value assessment, the final physical examination route is planned.

[0069] Safety constraint injection: Defining a high-risk disease set ,like Regardless of the value score, the corresponding key check (such as an electrocardiogram) will be forcibly inserted into the planned path.

[0070] Path optimization modeling:

[0071] A physical examination path is defined as an ordered sequence. .

[0072] The value of this path is

[0073] In order to meet equipment availability Under conditions such as safety constraints, find the optimal path:

[0074] ;

[0075] Here, Ω is the set of all feasible paths.

[0076] In step S4, the physical examination is performed and evidence is obtained.

[0077] Device collaboration: The medical device management module is based on the path Schedule the appropriate equipment to perform checks. Monitor equipment status in real time. If the planned equipment is unavailable, immediately trigger a return to step 3 for rescheduling.

[0078] Results collection: Obtain examination results and form the evidence set for this round of physical examinations. .

[0079] In step S5, the new evidence is combined with historical evidence (symptoms, etc.):

[0080] Update the probabilities of all candidate diseases using Bayes' theorem:

[0081]

[0082] in, It is the prior probability from the previous round. It is the posterior probability after this round of updates.

[0083] Based on the updated probability distribution, regenerate and ,renew .

[0084] In step S6, the termination condition is determined: the integrated diagnostic agent module evaluates whether the output conditions are met. These conditions may include:

[0085] Presence of disease satisfy (Threshold, such as 95%).

[0086] The candidate disease set has been sufficiently narrowed. ;

[0087] The expected value gain of the planned next round of optimal inspections is below a threshold.

[0088] Reach the preset maximum number of loops or time limit.

[0089] Decision: If the termination condition is met, exit the loop and output the final diagnosis and disease probability distribution. If not, proceed based on the updated probability distribution. Return to step S3, replan, and start a new cycle of "physical examination planning-execution-update".

[0090] Example 2:

[0091] The present invention also provides a device / equipment / system for generating dynamic physical examination pathways based on disease identification value, comprising a memory, a processor, and a computer program stored in the memory, characterized in that the processor executes the computer program to implement the steps of the above method.

[0092] The present invention also provides a computer-readable storage medium having a computer program / instructions stored thereon, which, when executed by a processor, implement the steps of the above-described method.

[0093] The present invention also provides a computer program product, including a computer program / instructions that, when executed by a processor, implement the steps of the above-described method.

[0094] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to in the method section.

[0095] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0096] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0097] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0098] The technical solutions provided in this application have been described in detail above. Specific examples have been used 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. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for generating dynamic physical examination pathways based on disease identification value, characterized by: Includes the following steps: S1. Obtain the patient's symptom and chief complaint information; S2. Based on the patient's symptom complaint information, generate an initial disease candidate set, calculate the prior probability of each candidate disease, and obtain a disease candidate set with prior probabilities; S3. Based on the current disease candidate set, plan the optimal physical examination items; S4. Perform the examination according to the optimal examination items, output the examination results, and form a new evidence set; if the examination equipment is unavailable, return to S3 to replan. S5. Integrate the new evidence set and update the probabilities of all candidate diseases; S6. Determine if the termination condition is met. If it is met, output the final diagnosis result and disease probability distribution; if it is not met, return to S3 to replan.

2. The dynamic physical examination path generation method according to claim 1, characterized in that: in In step S3, the step of planning the optimal physical examination items based on the current disease candidate set includes the following steps: All candidate physical examination items related to the candidate disease are screened out. For each candidate physical examination item, its comprehensive value is calculated, and the optimal physical examination item is planned.

3. The dynamic physical examination path generation method according to claim 2, characterized in that: in Step S3 also includes the following step: if there are high-risk diseases in the disease candidate set, insert the examination of the high-risk diseases into the planned path.

4. The dynamic physical examination path generation method according to claim 3, characterized in that: Step S3 also includes the following step: device constraint.

5. The dynamic physical examination path generation method according to claim 4, characterized in that: The comprehensive value is calculated as follows: ; ； in, For comprehensive value, Risk coverage capability Disease differentiation ability Equipment availability rating Cost rating : This is an adjustable weight parameter.

6. The dynamic physical examination path generation method according to claim 5, characterized in that: The optimal physical examination items planned, under the conditions of satisfying equipment availability and safety constraints, have the following optimal path: ； Here, Ω is the set of all feasible paths.

7. The dynamic physical examination path generation method according to claim 1, characterized in that: The probability of updating all candidate diseases is performed using Bayesian updating.

8. A device / equipment / system for generating dynamic physical examination pathways based on disease identification value, comprising a memory, a processor, and a computer program stored in the memory, characterized in that, The processor executes the computer program to implement the steps of the method according to any one of claims 1-7.

9. A computer-readable storage medium having a computer program / instructions stored thereon, characterized in that, When the computer program / instructions are executed by the processor, they implement the steps of the method described in any one of claims 1-7.

10. A computer program product comprising a computer program / instructions, characterized in that, When the computer program / instructions are executed by the processor, they implement the steps of the method described in any one of claims 1-7.

Images