Intelligent evaluation and optimization method and system for osteoarthritis treatment plan

Abstract

This invention discloses an intelligent evaluation and optimization method and system for osteoarthritis treatment plans, relating to the field of medical technology. The intelligent evaluation and optimization method for osteoarthritis treatment plans includes the following steps: S1, collecting parameters and dividing them into time-series stages; S2, normalizing the data and constructing a task node index table and a resource dependency mapping table; S3, extracting treatment features and consumption features, and calculating weights to form a treatment efficacy feature parameter set; S4, associating the task node index table with the treatment efficacy feature parameter set to obtain the patient node treatment parameter set; S5, matching the patient parameter set with data of similar diseases based on a cosine similarity algorithm to evaluate treatment effectiveness and cost; S6, optimizing and adjusting the treatment parameters, verifying and dynamically updating medical resource consumption parameters. This invention achieves efficient monitoring and accurate evaluation by introducing a combination of time-series stage division and a task node index table.

Description

Technical Field

[0001] This invention relates to the field of medical technology, and more specifically, to a method and system for intelligent evaluation and optimization of treatment plans for osteoarthritis. Background Technology

[0002] Existing intelligent assessment and optimization methods and systems for osteoarthritis treatment lack intelligent decision support systems based on individual patient characteristics and historical treatment effects. Furthermore, traditional treatment effect assessments are mostly based on simple treatment results, such as pain scores or joint mobility, failing to fully consider the impact of the patient's overall treatment and medical resource consumption, resulting in an imbalance between treatment costs and efficacy. Currently, no effective solutions have been proposed to address the problems in related technologies. Summary of the Invention

[0003] In response to the problems in related technologies, this invention proposes an intelligent evaluation and optimization method and system for osteoarthritis treatment plans to overcome the aforementioned technical problems existing in the existing related technologies.

[0004] To achieve the above objectives, the specific technical solution adopted by the present invention is as follows:

[0005] According to one aspect of the present invention, a method for intelligent evaluation and optimization of osteoarthritis treatment plans is provided, comprising the following steps:

[0006] S1. Obtain osteoarthritis treatment parameters, medical resource consumption parameters, and similar disease treatment datasets for osteoarthritis patients, and divide the osteoarthritis treatment parameters and medical resource consumption parameters into time-series stages.

[0007] S2. Normalize the osteoarthritis treatment parameters and medical resource consumption parameters after the time-series stage division, and construct a treatment task node index table and a medical resource dependency mapping table.

[0008] As a preferred embodiment, the normalization of osteoarthritis treatment parameters and medical resource consumption parameters after time-series segmentation, and the construction of a treatment task node index table and a medical resource dependency mapping table, includes the following steps:

[0009] S21. Convert the pain score and joint range of motion in the osteoarthritis treatment parameters into standardized values ​​of 0-1, and unify the drug dosage and treatment frequency in the osteoarthritis treatment parameters into a quantitative format;

[0010] S22. Convert the consumption of consumables and treatment time in the medical resource consumption parameters into a unified standard consumption coefficient, and convert the treatment cost in the medical resource consumption parameters into a unified benchmark cost unit.

[0011] S23. Construct a treatment task node index table based on the time sequence of the normalized osteoarthritis treatment parameters.

[0012] S24. Perform treatment dependency association mapping on the normalized osteoarthritis treatment parameters and medical resource consumption parameters, and generate a medical resource dependency mapping table based on the treatment dependency association mapping results.

[0013] S3. Classify and extract treatment feature parameters and consumption feature parameters for osteoarthritis treatment parameters and medical resource consumption parameters, and calculate the weight ratio of treatment feature parameters and consumption feature parameters through cost-benefit algorithm to form a set of treatment efficacy feature parameters;

[0014] As a preferred embodiment, the step of classifying and extracting treatment feature parameters and consumption feature parameters from osteoarthritis treatment parameters and medical resource consumption parameters, and calculating the weight ratio of treatment feature parameters and consumption feature parameters using a cost-benefit algorithm to form a set of treatment efficacy feature parameters includes the following steps:

[0015] S31. Classify osteoarthritis treatment parameters according to efficacy indicators and intervention measures, and extract treatment characteristic parameters;

[0016] S32. Classify medical resource consumption parameters according to direct consumption and indirect consumption, and extract consumption characteristic parameters;

[0017] S33. Map the treatment characteristic parameters and consumption characteristic parameters to efficacy contribution values ​​and cost consumption values, and then perform quantitative weighting.

[0018] As a preferred embodiment, mapping the treatment characteristic parameters and consumption characteristic parameters to efficacy contribution values ​​and cost consumption values, and then performing quantitative weighting, includes the following steps:

[0019] S331. Preset consumption value mapping rules, and map treatment feature parameters and consumption feature parameters to efficacy contribution values ​​and cost consumption values ​​based on consumption value mapping rules;

[0020] S332. Set the weight adjustment coefficient and match the efficacy contribution value and cost consumption value based on the weight adjustment coefficient;

[0021] S333. Based on the matching results, the weighted efficacy contribution value is obtained by adjusting the weight of the matched efficacy contribution value, and the cost consumption value is obtained by combining the matched weighted weight adjustment value.

[0022] S334. Verify and output the weighted efficacy contribution value and weighted cost consumption value.

[0023] S34. Calculate the comprehensive weight ratio based on the quantitatively weighted efficacy contribution value and cost consumption value, and integrate them into a set of treatment efficacy characteristic parameters according to the time sequence stage.

[0024] S4. Establish a real-time monitoring association between the task node index table and the resource dependency mapping table and the treatment efficacy feature parameter set to obtain the patient node treatment parameter set.

[0025] As a preferred embodiment, the step of establishing a real-time monitoring association between the task node index table and the resource dependency mapping table and the treatment efficacy feature parameter set to obtain the patient node treatment parameter set includes the following steps:

[0026] S41. Preset feature association rules, and build a real-time monitoring association relationship between the treatment task node index table and the treatment efficacy feature parameter set based on the feature association rules;

[0027] S42. Based on real-time monitoring relationships, establish a mapping rule between a resource dependency relationship mapping table and a set of treatment efficacy feature parameters, and perform association matching;

[0028] As a preferred embodiment, the step of establishing a mapping rule between a resource dependency relationship mapping table and a set of treatment efficacy feature parameters based on real-time monitoring relationships, and performing association matching, includes the following steps:

[0029] S421. Based on real-time monitoring of the relationship, bind the resource dependency mapping table to the efficacy feature parameters in the treatment efficacy feature parameter set, and set efficacy parameter monitoring indicators and efficacy matching thresholds.

[0030] S422. Generate an association matching table based on the efficacy parameter monitoring indicators and efficacy matching thresholds, and establish a mapping rule between the resource dependency mapping table and the treatment efficacy feature parameter set based on the association matching table.

[0031] S423. The resource dependency mapping table is associated and matched with the set of therapeutic efficacy feature parameters through mapping rules.

[0032] S43. Construct a real-time monitoring data acquisition channel based on the correlation matching results, and perform data acquisition;

[0033] S44. Integrate the data collection results to generate a set of treatment parameters for patient nodes.

[0034] S5. Match the treatment parameter set of patient nodes with the treatment dataset of similar diseases using the cosine similarity algorithm, and evaluate the treatment effect and cost of osteoarthritis based on the matching results.

[0035] As a preferred embodiment, the step of matching the patient node treatment parameter set with a treatment dataset of similar diseases using a cosine similarity algorithm to determine treatment features, and evaluating the treatment effect and cost of osteoarthritis based on the matching results, includes the following steps:

[0036] S51. Extract patient feature vectors from the patient node treatment parameter set, and extract historical feature vectors from the treatment dataset of the same disease that correspond to the patient node treatment parameter set;

[0037] S52. Calculate the similarity value between the patient's feature vector and the historical feature vector using the cosine similarity algorithm, filter the similarity values, and perform treatment feature matching based on the filtering results;

[0038] S53. Establish efficacy evaluation model and cost evaluation model based on historical feature vectors, and input the patient node treatment parameter set into efficacy evaluation model and cost evaluation model to obtain treatment effect score and treatment cost evaluation value;

[0039] As a preferred embodiment, the step of establishing a treatment efficacy evaluation model and a cost evaluation model based on historical feature vectors, and inputting the patient node treatment parameter set into the treatment efficacy evaluation model and the cost evaluation model to obtain the treatment effect score and treatment cost evaluation value includes the following steps:

[0040] S531. Classify the extracted historical feature vectors according to the efficacy dimension and the cost dimension, and select the efficacy feature vector and cost feature vector from the historical feature vectors;

[0041] S532. Construct an efficacy evaluation model based on efficacy feature vectors and historical treatment effect data, and simultaneously construct a cost evaluation model based on cost feature vectors and historical treatment cost data;

[0042] S533. Perform feature decomposition on the patient node treatment parameter set to obtain the patient feature input vector, and input the patient feature input sub-vector into the efficacy evaluation model and cost evaluation model respectively to generate osteoarthritis treatment effect score and treatment cost evaluation value.

[0043] As a preferred embodiment, the step of performing feature decomposition on the patient node treatment parameter set to obtain a patient feature input vector, and then inputting the patient feature input sub-vector into the efficacy evaluation model and the cost evaluation model respectively to generate an osteoarthritis treatment effect score and a treatment cost evaluation value, includes the following steps:

[0044] S5331. The patient node treatment parameter set is feature-splitting according to efficacy-related parameters and cost-related parameters to obtain the patient efficacy feature vector and the patient cost feature vector.

[0045] S5332. Preset management target rules, and filter patient efficacy feature vectors and patient cost feature vectors based on management target rules;

[0046] S5333: Input the screened patient efficacy feature vector and patient cost feature vector into the efficacy assessment model and cost assessment model respectively to obtain the treatment effect score and treatment cost assessment value;

[0047] S5334. Correct and output the treatment effect score and treatment cost assessment value by combining the management objective rules.

[0048] S54. Analyze treatment effect scores and treatment cost assessment values ​​to generate treatment effect and treatment cost for osteoarthritis.

[0049] S6. Based on the evaluated treatment effects and costs of osteoarthritis, optimize and adjust the treatment parameters for osteoarthritis, verify and output the optimized treatment parameters, and dynamically update the medical resource consumption parameters.

[0050] According to another aspect of the present invention, an intelligent evaluation and optimization system for osteoarthritis treatment plans is provided. The system includes: a parameter acquisition and partitioning module, a parameter processing and mapping module, a feature extraction and calculation module, a real-time monitoring and correlation module, a treatment effect and cost module, and a parameter optimization and adjustment module.

[0051] The parameter acquisition and partitioning module is used to acquire osteoarthritis treatment parameters, medical resource consumption parameters, and similar disease treatment datasets for osteoarthritis patients, and to partition the osteoarthritis treatment parameters and medical resource consumption parameters into time-series stages.

[0052] The parameter processing and mapping module is used to normalize the osteoarthritis treatment parameters and medical resource consumption parameters after the time-series stage division, and to construct a treatment task node index table and a medical resource dependency mapping table.

[0053] The feature extraction and calculation module is used to classify and extract treatment feature parameters and consumption feature parameters from osteoarthritis treatment parameters and medical resource consumption parameters, and to calculate the weight ratio of treatment feature parameters and consumption feature parameters through a cost-benefit algorithm to form a set of treatment efficacy feature parameters.

[0054] The real-time monitoring and association module is used to establish a real-time monitoring association between the task node index table and the resource dependency mapping table and the treatment efficacy feature parameter set, and to obtain the patient node treatment parameter set.

[0055] The treatment effect and cost module is used to match the treatment parameter set of patient nodes with the treatment dataset of similar diseases using the cosine similarity algorithm, and evaluate the treatment effect and cost of osteoarthritis based on the matching results.

[0056] The parameter optimization and adjustment module is used to optimize and adjust osteoarthritis treatment parameters based on the evaluated treatment effects and costs. It then verifies and outputs the optimized osteoarthritis treatment parameters and dynamically updates the medical resource consumption parameters.

[0057] The beneficial effects of this invention are as follows:

[0058] 1. This invention combines a time-series stage division with a task node index table, along with a medical resource dependency mapping table, to achieve efficient monitoring and accurate evaluation of the osteoarthritis treatment process. By dividing osteoarthritis treatment parameters and medical resource consumption parameters into stages, it dynamically adjusts treatment plans and resource allocation, optimizes the balance between treatment effectiveness and resource consumption, and avoids unsatisfactory treatment results or resource waste caused by delayed treatment plans. At the same time, through weighted calculation of treatment characteristics and consumption characteristics, it improves the accuracy and personalization of treatment efficacy, ensuring that patients receive the best treatment plan.

[0059] 2. This invention uses a cosine similarity algorithm to match historical treatment data to evaluate treatment effectiveness and costs in real time, ensuring the optimization of treatment plans. By quantifying and weighting treatment features and cost consumption, combined with real-time monitoring data collection and patient feature segmentation, it enables real-time adjustment of personalized treatment plans. Furthermore, the efficacy evaluation and cost evaluation models built based on historical treatment data make treatment effect prediction more accurate and treatment cost control more efficient, thereby improving the controllability and execution efficiency of the overall treatment process.

[0060] 3. This invention optimizes osteoarthritis treatment plans by dynamically updating medical resource consumption parameters and providing real-time feedback on treatment efficacy. By continuously tracking patients' treatment characteristics and medical resource consumption, it ensures that treatment plans and resource allocation are always kept in the optimal state, maximizing the improvement of patients' treatment effects and satisfaction. Furthermore, by combining cost-effectiveness algorithms and real-time data collection, it identifies potential problems and makes adjustments in real time, improving the responsiveness and flexibility of the treatment process. Attached Figure Description

[0061] To more clearly illustrate the technical solutions in the embodiments of the present invention 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 the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0062] Figure 1 This is a flowchart of a method for intelligent evaluation and optimization of osteoarthritis treatment plans according to an embodiment of the present invention;

[0063] Figure 2 This is a system block diagram of an intelligent evaluation and optimization system for osteoarthritis treatment plans according to an embodiment of the present invention.

[0064] In the picture:

[0065] 1. Parameter acquisition and partitioning module; 2. Parameter processing and mapping module; 3. Feature extraction and calculation module; 4. Real-time monitoring and correlation module; 5. Treatment effect and cost module; 6. Parameter optimization and adjustment module. Detailed Implementation

[0066] The specific embodiments of the present invention will be described in further detail below with reference to the accompanying drawings and examples. The following examples are for illustrative purposes only and are not intended to limit the scope of the invention.

[0067] Therefore, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention.

[0068] According to embodiments of the present invention, a method and system for intelligent evaluation and optimization of osteoarthritis treatment plans are provided.

[0069] The present invention will now be further described in conjunction with the accompanying drawings and specific embodiments. According to one embodiment of the present invention, such as... Figure 1 As shown, the intelligent evaluation and optimization method for osteoarthritis treatment according to an embodiment of the present invention includes the following steps:

[0070] S1. Obtain osteoarthritis treatment parameters, medical resource consumption parameters, and similar disease treatment datasets for osteoarthritis patients, and divide the osteoarthritis treatment parameters and medical resource consumption parameters into time-series stages.

[0071] Specifically, treatment data of patients is collected through medical information systems or databases, including basic patient information, treatment plans, medication use, treatment frequency, pain scores, joint mobility, and medical resource consumption (such as drugs, consumables, treatment duration, etc.). Relevant treatment parameters and medical resource consumption data are obtained through electronic medical record systems, hospital management systems, and patient self-reported data.

[0072] Furthermore, all treatment parameters and resource consumption parameters are divided into time-series stages. The purpose of this process is to subdivide the different treatment stages experienced by the patient and assign corresponding treatment parameters and resource consumption data to each stage. This time-series stage division is based on factors such as the cyclical nature of treatment, changes in treatment interventions, and the progression of the patient's condition. For example, the treatment process can be divided into acute, recovery, and maintenance phases, or further refined based on the specific changes in the patient's condition. Acquisition of treatment datasets for similar diseases is achieved by analyzing historical medical records, databases of similar disease treatments, or relevant clinical research data. These datasets not only provide a reference for the current patient's treatment plan but also offer necessary comparative information for subsequent treatment optimization.

[0073] S2. Normalize the osteoarthritis treatment parameters and medical resource consumption parameters after the time-series stage division, and construct a treatment task node index table and a medical resource dependency mapping table.

[0074] In this embodiment of the application, the normalization of osteoarthritis treatment parameters and medical resource consumption parameters after time-series stage division, and the construction of a treatment task node index table and a medical resource dependency mapping table, includes the following steps:

[0075] S21. Convert the pain score and joint range of motion in the osteoarthritis treatment parameters into standardized values ​​of 0-1, and unify the drug dosage and treatment frequency in the osteoarthritis treatment parameters into a quantitative format;

[0076] Specifically, converting pain scores and joint range of motion in osteoarthritis treatment parameters into standardized values ​​of 0-1 first requires determining their respective scoring ranges. Pain scores typically use a scale of 0 to 10, where 0 represents no pain and 10 represents extreme pain. Joint range of motion is assessed based on the joint's range of motion, usually between 0 and 180 degrees. These parameters are then converted into standardized values ​​within the 0-1 range using a min-max normalization method. Specifically, standardization is achieved by linearly transforming each score to between 0 and 1 using the minimum and maximum values ​​as benchmarks.

[0077] To achieve standardized quantification of drug dosage and treatment frequency, it is necessary to standardize the quantification of different drugs and treatment frequencies. Drug dosage should be standardized according to the conventional dosage unit of the drug, such as converting the dosage of different types of drugs into milligrams or other standard units. Treatment frequency should be standardized according to the number of times the drug is administered daily, weekly, or monthly. By standardizing drug dosage and treatment frequency, these parameters in different patients and treatment plans are unified into the same quantitative unit, making subsequent data processing and comparison more convenient. In the entire process of data normalization and quantification, the key is to ensure that the treatment parameters of all patients are compared under the same standard and to avoid data distortion caused by differences in different units or scoring systems.

[0078] S22. Convert the consumption of consumables and treatment time in the medical resource consumption parameters into a unified standard consumption coefficient, and convert the treatment cost in the medical resource consumption parameters into a unified benchmark cost unit.

[0079] Specifically, converting the consumption parameters of medical resources, such as consumable usage and treatment time, into standardized consumption coefficients hinges on establishing unified consumption standards. For consumable usage, a standardized consumption coefficient is assigned based on the type and frequency of use of each consumable. For example, the usage of each consumable is quantified according to its cost, frequency of use, and the importance of treatment effectiveness, converting it into a standard consumption coefficient. Similarly, treatment time is calculated based on the time allocation for each stage of the treatment process, converting the duration of each stage into a standardized coefficient. This ensures that the treatment time for all patients is quantified in the same unit, facilitating data comparison and optimization.

[0080] The next step, standardizing the conversion of treatment costs, is to ensure the comparability of costs between different treatment plans and medical institutions. Treatment costs include multiple aspects such as drug costs, consumable costs, and labor costs. To unify these into a benchmark cost unit, a standard cost calculation unit is selected, such as the cost per treatment cycle or the standard cost per treatment event. Then, based on the actual expenditure of various treatment costs, each cost is converted into a unified cost unit. Furthermore, by standardizing and uniformly converting consumable usage, treatment duration, and treatment costs, a comparative analysis of different treatment plans and medical resource consumption can be achieved, providing a scientific basis for subsequent treatment optimization.

[0081] S23. Construct a treatment task node index table based on the time sequence of the normalized osteoarthritis treatment parameters.

[0082] Specifically, normalized osteoarthritis treatment parameters need to be rationally divided according to time stages to ensure that the treatment parameters at each stage can reflect different clinical characteristics and changes in efficacy during the treatment process. For example, the treatment process can be divided into acute, recovery, and maintenance phases based on the progress of treatment, or further refined into multiple stages based on changes in the patient's specific condition, such as changes in arthritis range of motion and pain scores. The treatment parameters in each time stage, including pain scores, joint range of motion, and drug dosage, need to be normalized within each stage to ensure that all treatment parameters are compared under the same standards.

[0083] Next, by organizing the normalized treatment parameters for each time-series stage, a treatment task node index table is constructed. This index table maps the normalized treatment parameters for each treatment stage to the corresponding treatment task, forming a clear, structured data table. Each node represents a specific treatment task or stage, and the relationships between nodes reflect the dependencies between stages during the treatment process. For example, in the treatment task nodes during the acute phase, the focus is on drug dosage and pain scores, while in the treatment task nodes during the recovery phase, more attention is paid to parameters such as joint range of motion and physical therapy.

[0084] Finally, the completed treatment task node index table can provide a foundation for subsequent treatment effect evaluation and resource optimization. By systematically organizing and indexing treatment tasks and treatment parameters at different stages, accurate task tracking and effect analysis can be achieved, ensuring that each task in the treatment process is effectively monitored and evaluated.

[0085] S24. Perform treatment dependency association mapping on the normalized osteoarthritis treatment parameters and medical resource consumption parameters, and generate a medical resource dependency mapping table based on the treatment dependency association mapping results.

[0086] Specifically, the normalized osteoarthritis treatment parameters and medical resource consumption parameters need to undergo treatment dependency correlation mapping. The purpose of treatment dependency correlation mapping is to identify and establish the interrelationships between treatment tasks, ensuring that the implementation sequence and dependencies of different treatment tasks are reasonably reflected. For example, in the treatment of osteoarthritis, drug therapy depends on a specific treatment phase (such as the acute phase), while physical therapy may only begin in the recovery or maintenance phase. By performing correlation analysis on treatment tasks and resource consumption, the dependencies between various treatment tasks are identified, and mappings are established based on these relationships.

[0087] Next, the results of the treatment dependency mapping are transformed into a medical resource dependency mapping table. This table displays the medical resources required for each treatment task and their dependencies, including the consumption of resources such as medicines, treatment equipment, and medical personnel. In the mapping table, the relationship between treatment tasks and resources is presented in the form of a chart or matrix. Each resource consumption point is connected to the corresponding treatment task node. Through this mapping relationship, it is possible to clearly understand which resources each treatment task requires and the order of resource dependencies, thus providing a basis for subsequent resource optimization and adjustment.

[0088] Furthermore, the generated medical resource dependency mapping table will become one of the core tools for intelligent assessment and optimization. This table can not only help medical institutions and doctors to allocate resources rationally during the treatment process, but also provide a basis for real-time monitoring, so that resource consumption and task execution during the treatment process can be carried out simultaneously.

[0089] S3. Classify and extract treatment feature parameters and consumption feature parameters for osteoarthritis treatment parameters and medical resource consumption parameters, and calculate the weight ratio of treatment feature parameters and consumption feature parameters through cost-benefit algorithm to form a set of treatment efficacy feature parameters;

[0090] In this embodiment of the application, the step of classifying and extracting treatment feature parameters and consumption feature parameters from osteoarthritis treatment parameters and medical resource consumption parameters, and calculating the weight ratio of treatment feature parameters and consumption feature parameters using a cost-benefit algorithm to form a set of treatment efficacy feature parameters includes the following steps:

[0091] S31. Classify osteoarthritis treatment parameters according to efficacy indicators and intervention measures, and extract treatment characteristic parameters;

[0092] Specifically, when classifying osteoarthritis treatment parameters, they need to be categorized according to different treatment goals and interventions. Efficacy indicators include pain scores, joint range of motion, and functional recovery, which directly reflect treatment effectiveness. Interventions include drug therapy, physical therapy, and surgical intervention, each with corresponding treatment parameters. By classifying treatment parameters according to efficacy indicators and interventions, the specific impact of each treatment plan on the patient can be clearly analyzed, ensuring that the effects of different interventions are effectively evaluated during the treatment process.

[0093] Next, when extracting treatment characteristic parameters, it is necessary to extract core features that represent the treatment effect from the categorized efficacy indicators and interventions. For example, characteristic parameters for drug treatment may include drug dosage, frequency of use, and corresponding pain relief effect; characteristic parameters for physical therapy may include changes in joint range of motion, treatment frequency, and duration. These treatment characteristic parameters will provide data support for subsequent effect evaluation and treatment optimization.

[0094] Finally, by extracting treatment characteristic parameters, the resulting treatment characteristic parameter set provides a foundation for the quantitative evaluation of treatment effects. This set summarizes key parameters under different treatment methods and efficacy indicators, providing data support for further optimization and personalized treatment plans. This process not only helps optimize patient treatment plans but also provides important references for the rational allocation of medical resources and the efficient execution of treatment plans.

[0095] S32. Classify medical resource consumption parameters according to direct consumption and indirect consumption, and extract consumption characteristic parameters;

[0096] Specifically, when classifying medical resource consumption parameters, they need to be categorized into two types based on their nature: direct consumption and indirect consumption. Direct consumption refers to resources directly related to the treatment process, such as the amount of medication used, the duration of use of treatment equipment, and the use of surgical consumables. The consumption of these resources directly affects the treatment outcome and the patient's recovery speed. Indirect consumption includes resources that do not directly participate in the treatment process but play an auxiliary role in supporting it, such as the working hours of medical staff, hospital management costs, and the consumption of environmental facilities. This classification helps to clarify the specific types of resource consumption, providing a basis for subsequent optimization and adjustments.

[0097] Next, when extracting characteristic parameters of medical resource consumption, it is necessary to extract key parameters that reflect the degree of consumption based on the different characteristics of direct and indirect consumption. For example, for direct consumption parameters, characteristic parameters include drug dosage, usage time of treatment equipment, and the amount of consumables consumed in each treatment, while for indirect consumption parameters, characteristic parameters may include the working hours of medical staff, the length of hospital stay for patients, and the indirect costs of using hospital facilities.

[0098] By extracting consumption characteristic parameters, detailed data is provided for the assessment and optimization of medical resource consumption. These parameters help medical institutions comprehensively understand resource consumption during the treatment process, thereby optimizing resource allocation without affecting treatment outcomes. Through reasonable resource consumption analysis and adjustment, treatment efficiency can be improved, costs reduced, and the overall sustainability of treatment enhanced, as well as patient satisfaction increased.

[0099] S33. Map the treatment characteristic parameters and consumption characteristic parameters to efficacy contribution values ​​and cost consumption values, and then perform quantitative weighting.

[0100] In this embodiment of the application, mapping the treatment characteristic parameters and consumption characteristic parameters to efficacy contribution values ​​and cost consumption values, and then performing quantitative weighting, includes the following steps:

[0101] S331. Preset consumption value mapping rules, and map treatment feature parameters and consumption feature parameters to efficacy contribution values ​​and cost consumption values ​​based on consumption value mapping rules;

[0102] Specifically, the pre-defined consumption value mapping rules need to be based on the relationship between treatment characteristic parameters and consumption characteristic parameters. A standardized mapping mechanism should be designed, and the mapping rules should consider the degree of influence of each parameter on treatment effect and resource consumption. For example, treatment characteristic parameters such as pain score and joint range of motion are associated with the efficacy contribution value through weighted coefficients, while consumption characteristic parameters such as drug dosage and treatment frequency are associated with the cost consumption value through resource consumption coefficients. The setting of mapping rules needs to combine clinical experience, treatment effect analysis, and historical data statistics to ensure the scientific nature and practicality of the mapping.

[0103] Next, based on the consumption value mapping rule, the treatment characteristic parameters and consumption characteristic parameters are mapped to efficacy contribution values ​​and cost consumption values. The core of this process is to quantify the treatment characteristic parameters and consumption characteristic parameters to obtain the corresponding efficacy contribution value and cost consumption value for each parameter. For example, for drug dosage, the mapping rule is used to correlate it with the degree of improvement in treatment effect, thereby obtaining the efficacy contribution value of drug treatment; similarly, for medical resource consumption (such as the amount of consumables used, treatment time, etc.), the corresponding cost consumption value is calculated according to the consumption value mapping rule.

[0104] By mapping treatment and consumption characteristic parameters to efficacy contribution and cost consumption values, clear quantitative indicators can be provided for subsequent treatment effect evaluation and resource optimization. These values ​​provide clinicians with intuitive feedback on treatment effectiveness, enabling treatment plans to be adjusted in real time based on actual efficacy and resource consumption.

[0105] S332. Set the weight adjustment coefficient and match the efficacy contribution value and cost consumption value based on the weight adjustment coefficient;

[0106] Specifically, the key to setting weight adjustment coefficients is to determine the weight of each treatment task or parameter based on the relative importance of different treatment characteristics and resource consumption. For both efficacy contribution and cost consumption values, the weight adjustment coefficients need to reflect the degree of influence of each treatment plan or resource consumption on the final treatment effect and cost. For example, treatment characteristic parameters such as drug dosage and treatment frequency have a significant impact on efficacy contribution values, while consumption characteristic parameters such as equipment usage time and hospitalization duration dominate cost consumption values. The setting of weight coefficients should be based on clinical experience, historical data analysis, and expert evaluation to ensure the rationality and effectiveness of the weights.

[0107] Next, based on the set weight adjustment coefficients, the efficacy contribution value and cost consumption value are matched. The core of the matching process is to perform a weighted calculation of the efficacy contribution value and corresponding cost consumption value of each treatment task. By applying the weight coefficients of the treatment characteristic parameters and consumption characteristic parameters to their respective contribution values ​​and consumption values, the adjusted efficacy and cost matching value is obtained. For example, for a certain treatment stage, the efficacy contribution value and cost consumption value after weight adjustment more accurately reflect the true effect and required resources of the treatment at that stage.

[0108] Finally, by matching the weighted efficacy contribution value and cost consumption value, a more precise basis is provided for optimizing treatment effects and adjusting resource allocation. This process enables medical institutions to adjust treatment plans in real time based on actual treatment effects and resource consumption, in order to achieve better treatment results and lower treatment costs.

[0109] S333. Based on the matching results, the weighted efficacy contribution value is obtained by adjusting the weight of the matched efficacy contribution value, and the cost consumption value is obtained by combining the matched weighted weight adjustment value.

[0110] Specifically, based on the matching results of efficacy contribution values, the efficacy contribution value of each treatment task or parameter is weighted and adjusted using a matching weight adjustment coefficient. The weighted efficacy contribution value is calculated by multiplying the efficacy contribution value of each treatment task by its corresponding weight adjustment coefficient, thus obtaining the weighted contribution of that task in the overall treatment plan. For example, if a treatment task has a high efficacy contribution value and a large weight adjustment coefficient, then the weighted efficacy contribution value of that treatment task will also be high, reflecting the importance of that task to the overall treatment effect. The weighted efficacy contribution value allows for a more accurate assessment of the treatment plan's effectiveness, providing a reference for optimizing the treatment plan.

[0111] Next, based on the matching results of cost consumption values, the cost consumption value of each treatment task or consumption parameter is weighted and adjusted using the matching weight adjustment coefficient. The weighted cost consumption value is calculated by multiplying the cost consumption value of each consumption parameter by its corresponding weight adjustment coefficient to obtain the weighted cost consumption value for that task. For example, if the corresponding weight coefficient for certain medical resources consumed in a treatment process, such as consumables or treatment time, is larger, then the weighted cost consumption value of that resource will also be higher. This helps to accurately reflect the overall cost of the treatment plan. Through the weighted cost consumption value, medical institutions can more clearly understand the resources and costs consumed by each treatment task, providing data support for resource allocation and cost control.

[0112] By combining weighted efficacy contribution values ​​and weighted cost consumption values, a balance can be optimized between treatment effectiveness and resource consumption. These weighted values ​​provide medical institutions with more precise evaluation criteria, enabling treatment plans to not only maximize efficacy but also effectively control costs. In practice, doctors and medical administrators adjust treatment plans based on the weighted results to ensure that the effectiveness and resource consumption of each treatment task are within a reasonable range, thereby improving treatment efficiency, reducing unnecessary costs, and increasing overall patient satisfaction.

[0113] S334. Verify and output the weighted efficacy contribution value and weighted cost consumption value.

[0114] Specifically, the first step in validating the weighted efficacy contribution value and weighted cost consumption value is to perform data validation and consistency checks. This process needs to ensure that there are no errors or inconsistencies in the calculation of the weighted efficacy contribution value and cost consumption value. The accuracy of the weighted value is verified by comparing it with historical data, expert evaluations, or clinical trial results. If the weighted value deviates significantly from the actual treatment effect or resource consumption data, the weighting coefficients need to be readjusted or the correctness of the data input needs to be checked.

[0115] Next, the weighted efficacy contribution value and weighted cost consumption value are validated based on actual clinical feedback and treatment results. By collecting actual implementation data of the treatment plan, including patient treatment effects and actual resource consumption during treatment, the weighted data is verified to accurately reflect the effects and costs of the treatment process. If the weighted value can accurately predict the improvement in treatment effect and the actual resource consumption, then the weighted results are proven to be effective.

[0116] Statistical analysis methods are used to further validate the weighted efficacy contribution value and weighted cost consumption value. For example, regression analysis or correlation analysis can be used to determine the relationship between the weighted values ​​and actual treatment outcomes and costs. If the analysis results show a significant statistical correlation between the weighted efficacy contribution value and weighted cost consumption value and treatment effectiveness and cost consumption, then these weighted values ​​are confirmed to be practically feasible and accurate in optimizing treatment plans and resource allocation. Through this validation output process, treatment plans can be continuously adjusted and optimized to improve the accuracy and cost-effectiveness of treatment.

[0117] S34. Calculate the comprehensive weight ratio based on the quantitatively weighted efficacy contribution value and cost consumption value, and integrate them into a set of treatment efficacy characteristic parameters according to the time sequence stage.

[0118] Specifically, the steps for calculating the overall weighted proportion involve merging the weighted efficacy contribution value and the weighted cost consumption value, and quantifying them according to their importance in the treatment process. By assigning an overall weighted proportion to each treatment task, the relative contribution of that task in the entire treatment process is reflected. For example, the efficacy contribution value and the cost consumption value each occupy a certain proportion, and finally, an overall weighted proportion is calculated. This ratio is used to measure the balance between treatment effectiveness and resource consumption. In this process, the proportion of efficacy contribution value is higher if the treatment goal focuses on effectiveness, while the proportion of cost consumption value is higher if the treatment goal focuses on cost control.

[0119] Next, based on the treatment tasks and resource consumption parameters at each time stage, the weighted efficacy contribution value and cost consumption value are integrated to form the comprehensive weight ratio for each treatment stage. In each treatment stage (e.g., acute phase, recovery phase, maintenance phase), a set of treatment efficacy characteristic parameters for that stage is integrated based on the weighted value and the comprehensive weight ratio calculation. This set of characteristic parameters not only includes efficacy contribution values ​​and cost consumption values, but also incorporates other treatment characteristics, such as treatment methods and medication regimens, to form the treatment characteristic parameters for that stage. Through this stage-based integration of characteristic parameters, the effectiveness and resource consumption of each treatment stage are comprehensively grasped, ensuring the optimization of the treatment plan.

[0120] The final integrated set of treatment efficacy characteristic parameters will serve as the basis for subsequent treatment optimization and adjustment. This set of characteristic parameters provides clinicians with a global perspective, enabling real-time monitoring of the dynamic changes in treatment effectiveness and resource consumption during the treatment process. By tracking and analyzing the comprehensive weighting of each stage and the treatment efficacy characteristic parameters, medical institutions can make more precise adjustments to treatment plans, maximizing treatment effectiveness and optimizing resource allocation.

[0121] S4. Establish a real-time monitoring association between the task node index table and the resource dependency mapping table and the treatment efficacy feature parameter set to obtain the patient node treatment parameter set.

[0122] In this embodiment of the application, the step of establishing a real-time monitoring association between the task node index table and the resource dependency mapping table and the treatment efficacy feature parameter set to obtain the patient node treatment parameter set includes the following steps:

[0123] S41. Preset feature association rules, and build a real-time monitoring association relationship between the treatment task node index table and the treatment efficacy feature parameter set based on the feature association rules;

[0124] Specifically, the key to pre-setting feature association rules lies in determining the correlation between different treatment task nodes and treatment efficacy feature parameters. Feature association rules analyze the relationship between key parameters during the treatment process (such as treatment methods, drug dosage, pain scores, and joint mobility) and treatment effects to determine which features are interrelated. For example, drug dosage is closely related to the degree of improvement in pain scores and joint mobility, while treatment duration and the amount of treatment equipment used may be related to resource consumption and treatment progress. These rules construct the logical relationship between each treatment task and treatment efficacy feature parameters, laying the foundation for subsequent real-time monitoring.

[0125] Next, based on these pre-defined feature association rules, the treatment task node index table is combined with the treatment efficacy feature parameter set to construct a real-time monitoring association. Each task node in the treatment task node index table represents a specific task or stage in the treatment process, while the treatment efficacy feature parameter set contains treatment effect data related to each task node. By applying feature association rules, task nodes and efficacy parameters are matched to form an association model for the real-time monitoring system. For example, in the acute phase, treatment task nodes may be directly associated with feature parameters such as drug dosage and pain score, while in the recovery phase, treatment task nodes are associated with joint range of motion and physical therapy parameters.

[0126] Finally, the establishment of real-time monitoring relationships enables medical institutions to assess the execution status of each stage and task node in the treatment process in real time. Through real-time correlation analysis between treatment tasks and performance parameters, medical institutions can promptly identify potential problems in treatment, such as unsatisfactory treatment results or excessive resource consumption, and then adjust treatment plans or resource allocation accordingly.

[0127] S42. Based on real-time monitoring relationships, establish a mapping rule between a resource dependency relationship mapping table and a set of treatment efficacy feature parameters, and perform association matching;

[0128] In this embodiment of the application, the step of establishing a mapping rule between a resource dependency relationship mapping table and a set of treatment efficacy feature parameters based on real-time monitoring relationships, and performing association matching, includes the following steps:

[0129] S421. Based on real-time monitoring of the relationship, bind the resource dependency mapping table to the efficacy feature parameters in the treatment efficacy feature parameter set, and set efficacy parameter monitoring indicators and efficacy matching thresholds.

[0130] Specifically, based on real-time monitoring of relationships, a resource dependency mapping table is bound to efficacy feature parameters in a treatment efficacy feature parameter set. The resource dependency mapping table displays the medical resources required for different treatment tasks and their interdependencies, while the treatment efficacy feature parameter set contains various parameters related to treatment effectiveness (such as pain scores, joint range of motion, etc.). By combining these two, the correlation between the resource consumption required for each treatment task and the treatment effect is clarified. The execution status of each treatment task node is reflected through real-time monitoring of efficacy feature parameters, while simultaneously referring to the resource dependency mapping table to ensure that resource utilization and treatment effectiveness remain at an optimal level.

[0131] The purpose of setting efficacy parameter monitoring indicators and efficacy matching thresholds is to ensure the monitoring and evaluation of various efficacy indicators during treatment. Efficacy parameter monitoring indicators typically include key indicators such as the patient's pain score, range of motion, and functional recovery during treatment, which are tracked in real time. Efficacy matching thresholds are the ideal ranges set for various efficacy parameters during treatment; exceeding or falling below these ranges is considered an unsatisfactory treatment outcome, requiring adjustment. For example, if the pain score threshold is set at 0-3, a score exceeding 3 indicates insufficient pain control, necessitating a reassessment of medication or treatment plans.

[0132] Finally, based on the setting of efficacy parameter monitoring indicators and efficacy matching thresholds, the medical team promptly identified problems that arose during treatment and made corresponding adjustments. This binding mechanism and monitoring system provide a real-time feedback mechanism, enabling any deviations or abnormalities during treatment to be quickly identified and corrected.

[0133] S422. Generate an association matching table based on the efficacy parameter monitoring indicators and efficacy matching thresholds, and establish a mapping rule between the resource dependency mapping table and the treatment efficacy feature parameter set based on the association matching table.

[0134] Specifically, an association matching table is generated based on efficacy parameter monitoring indicators and efficacy matching thresholds. The core of this table is to match the efficacy parameters of each treatment task node with the set thresholds, thereby forming real-time monitoring results of the efficacy parameters. For example, for the efficacy parameter of pain score, the set thresholds are 0-3 (low pain), 4-6 (moderate pain), and 7-10 (high pain). Through real-time monitoring, the generated association matching table will display the efficacy changes of each treatment task node during implementation and indicate whether they exceed the preset thresholds.

[0135] Next, based on the generated association matching table, mapping rules are established between the resource dependency mapping table and the set of treatment efficacy feature parameters. The mapping rules aim to clarify the relationship between treatment tasks and resource consumption, while combining efficacy feature parameters with actual resource consumption. Through the association matching table, the medical team can identify which resource consumptions are closely related to specific treatment outcomes. For example, if a treatment task at a certain stage fails to meet efficacy targets (such as pain scores exceeding a threshold), it is necessary to adjust the relevant treatment resources (such as increasing drug dosage or changing the treatment method).

[0136] Finally, through the established mapping rules, medical institutions dynamically adjust resource allocation and treatment plans based on the association matching table. The mapping rules provide clear guidance on the relationship between resource consumption and efficacy at different stages of the treatment process, ensuring a reasonable match between the resource consumption required for each treatment task and the expected treatment effectiveness.

[0137] S423. The resource dependency mapping table is associated and matched with the set of therapeutic efficacy feature parameters through mapping rules.

[0138] Specifically, the key to associating and matching the resource dependency mapping table with the treatment efficacy feature parameter set through mapping rules is to clearly define the dependencies between treatment tasks and resources. The resource dependency mapping table displays the resources required for different treatment tasks, such as medications, equipment, and manpower, while the treatment efficacy feature parameter set contains efficacy indicators for each treatment task, such as pain scores and joint mobility. The establishment of mapping rules needs to ensure that the resources consumed by each treatment task node during implementation are closely related to the corresponding treatment effect. For example, in treating acute osteoarthritis, certain resources (such as analgesics and physical therapy equipment) directly affect pain relief and improvement in joint mobility; therefore, the mapping rules should establish a close association between these resources and efficacy parameters.

[0139] Next, by applying mapping rules, each resource consumption item in the resource dependency mapping table is matched with each efficacy parameter in the treatment efficacy feature parameter set. During this process, the interaction between resource consumption and efficacy parameters is analyzed based on the actual needs of the treatment plan. For example, if a treatment requires a significant number of medical personnel and has a substantial impact on the treatment outcome, the changes in resource consumption and treatment effectiveness should be reflected in the mapping. Through this matching process, the correlation between resource consumption and efficacy parameters corresponding to each treatment task node is established, ensuring the rational allocation of resources and the achievement of treatment goals.

[0140] S43. Construct a real-time monitoring data acquisition channel based on the correlation matching results, and perform data acquisition;

[0141] Specifically, based on the correlation matching results, the data acquisition channel needs to be able to seamlessly connect to the medical resource management system, treatment record system, and patient monitoring equipment to collect patient treatment data and efficacy parameters in real time. For example, data such as pain scores, joint range of motion, and treatment equipment usage time need to be obtained in real time from clinical monitoring equipment, patient feedback systems, and treatment plans. Through preset data acquisition protocols and interfaces, data can flow between different systems and platforms, ensuring the timeliness and accuracy of monitoring data.

[0142] Next, during data collection, it's crucial to ensure that all relevant performance parameters and resource consumption data are recorded promptly and correlated with treatment task nodes. The data collection system should be able to automatically capture performance changes and related resource consumption at each treatment stage based on correlation matching rules. For example, during drug therapy, it should automatically record the dosage of each medication, changes in the patient's pain score, and the usage of treatment equipment. This data is transmitted to the data processing platform through a real-time monitoring channel, ensuring that every key data point during treatment is accurately collected and providing support for subsequent effect evaluation and resource adjustments.

[0143] The collected real-time data will be analyzed through a dedicated data processing system to generate actionable feedback and adjustment suggestions. The real-time monitoring data acquisition channel not only needs to collect performance parameters and resource consumption data, but also needs to ensure the accuracy and completeness of the data. Through data cleaning and real-time verification, abnormal data is filtered out to ensure the stability and reliability of the system in practical applications.

[0144] S44. Integrate the data collection results to generate a set of treatment parameters for patient nodes.

[0145] S5. Match the treatment parameter set of patient nodes with the treatment dataset of similar diseases using the cosine similarity algorithm, and evaluate the treatment effect and cost of osteoarthritis based on the matching results.

[0146] In this embodiment of the application, the step of matching the patient node treatment parameter set with the treatment dataset of similar diseases using a cosine similarity algorithm, and evaluating the treatment effect and cost of osteoarthritis based on the matching results, includes the following steps:

[0147] S51. Extract patient feature vectors from the patient node treatment parameter set, and extract historical feature vectors from the treatment dataset of the same disease that correspond to the patient node treatment parameter set;

[0148] Specifically, the key to extracting patient feature vectors from the patient node treatment parameter set is selecting core feature parameters related to the patient's treatment process and transforming them into standardized numerical forms. The patient node treatment parameter set typically contains various data related to the patient's treatment process, such as medication usage, treatment frequency, pain score, joint range of motion, and treatment equipment usage. By preprocessing these treatment parameters—removing outliers and standardizing them—these parameters are transformed into a unified feature vector representing the patient's treatment status and individual needs. For example, medication dosage, treatment duration, and pain relief level are quantified and standardized into various dimensions of the feature vector, providing foundational data for subsequent treatment effectiveness evaluation.

[0149] Next, when extracting historical feature vectors corresponding to the patient node's treatment parameter set from the treatment dataset for similar diseases, it is necessary to extract case features with similar treatment plans and diseases from historical case data. These historical feature vectors should include data such as the treatment process, resource consumption, and efficacy indicators of similar patients in the past. By matching them with the patient's current treatment parameter set, feature vectors similar to the patient's current treatment situation are extracted from the historical data. This process uses similarity measures (such as Euclidean distance, cosine similarity, etc.) to determine the degree of similarity between historical cases and current patient treatment data, thereby ensuring that the extracted historical feature vectors can provide effective support for predicting and optimizing the treatment effect of the current patient.

[0150] By comparing patient feature vectors with historical feature vectors, a basis for developing personalized treatment plans is provided. By analyzing treatment effects and resource consumption similar to the current patient's treatment in historical feature vectors, the medical team predicts the current patient's possible treatment outcome and adjusts the treatment plan based on experience gained from historical data.

[0151] S52. Calculate the similarity value between the patient's feature vector and the historical feature vector using the cosine similarity algorithm, filter the similarity values, and perform treatment feature matching based on the filtering results;

[0152] Specifically, the similarity value between the patient's feature vector and historical feature vectors is calculated using a cosine similarity algorithm. Then, based on the calculated similarity value, a selection process is conducted to ensure optimized and personalized treatment plans. Typically, a similarity threshold is set, selecting only historical feature vectors with high similarity. For example, a similarity threshold of 0.8 might be set; when the similarity value is higher than this threshold, the historical case is considered to be closely related to the current patient's treatment and has high reference value.

[0153] Finally, treatment feature matching is performed based on the screening results. By matching historical feature vectors with high similarity to the current patient's feature vector, personalized treatment plans are developed for the patient. For example, treatment plans, resource consumption, and efficacy indicators in the historical feature vectors can serve as a reference to help doctors choose treatment strategies more suitable for the current patient. Simultaneously, by analyzing multiple similar historical cases, the medical team identifies the most effective treatment methods and resource allocations, thereby improving treatment outcomes and reducing resource waste.

[0154] S53. Establish efficacy evaluation model and cost evaluation model based on historical feature vectors, and input the patient node treatment parameter set into efficacy evaluation model and cost evaluation model to obtain treatment effect score and treatment cost evaluation value;

[0155] In this embodiment of the application, the step of establishing a treatment efficacy evaluation model and a cost evaluation model based on historical feature vectors, and inputting the patient node treatment parameter set into the treatment efficacy evaluation model and the cost evaluation model to obtain the treatment effect score and treatment cost evaluation value includes the following steps:

[0156] S531. Classify the extracted historical feature vectors according to the efficacy dimension and the cost dimension, and select the efficacy feature vector and cost feature vector from the historical feature vectors;

[0157] Specifically, the first step in classifying the extracted historical feature vectors according to efficacy and cost dimensions is to clarify the different dimensions contained in each feature vector. Historical feature vectors contain treatment data across multiple dimensions, such as efficacy-related features (e.g., pain scores, joint range of motion, functional recovery) and cost-related features (e.g., medication usage, treatment equipment consumption, length of hospital stay). Based on these dimensions, the historical feature vectors are classified, and efficacy-related feature vectors and cost-related feature vectors are extracted separately.

[0158] During the screening process, it is necessary to separate the efficacy feature vector and the cost feature vector from the historical feature vector based on specific screening criteria. For the efficacy feature vector, the screening criteria are typically based on relevant indicators of treatment effectiveness, such as the degree of pain relief, changes in functional recovery, and patient self-assessment. These indicators reflect treatment effectiveness and align with the patient's clinical treatment goals. For the cost feature vector, the screening criteria focus on the resource consumption during treatment, such as medication costs, usage of treatment equipment, and hospitalization expenses.

[0159] The selected efficacy and cost feature vectors provide strong support for optimizing treatment plans. The efficacy feature vector helps medical teams assess the effectiveness of different treatment options, identify the optimal treatment method, and ensure that the treatment plan maximizes the improvement of the patient's health. Simultaneously, the cost feature vector helps medical institutions optimize resource allocation and control unnecessary expenses during the treatment process. By analyzing and comparing these two types of feature vectors, medical teams can balance treatment effectiveness and cost based on actual needs, developing personalized treatment plans for patients that meet both efficacy requirements and reasonable cost control.

[0160] S532. Construct an efficacy evaluation model based on efficacy feature vectors and historical treatment effect data, and simultaneously construct a cost evaluation model based on cost feature vectors and historical treatment cost data;

[0161] Specifically, the key to building an efficacy evaluation model based on efficacy feature vectors and historical treatment effect data lies in selecting appropriate machine learning methods or statistical models to handle the relationship between efficacy feature vectors and treatment effects. Efficacy feature vectors contain multi-dimensional treatment data, such as drug dosage, treatment frequency, pain scores, and functional recovery. These features may have a certain non-linear relationship with treatment outcomes; therefore, algorithms such as regression analysis, support vector machines, and random forests are chosen to build the efficacy evaluation model. By training the model using historical treatment effect data as the training set, the model will learn the association between different features and efficacy and be able to predict the effects of future patient treatment plans. After model training, the accuracy and generalization ability of the model are evaluated using a validation set to ensure its reliability in practical applications.

[0162] The method for constructing a cost assessment model based on cost feature vectors and historical treatment cost data is similar to that for the efficacy assessment model. Cost feature vectors primarily reflect the consumption of various resources during treatment, such as drug costs, equipment usage costs, and hospitalization costs. To establish an accurate cost assessment model, a suitable algorithm (such as linear regression, decision tree regression, or neural networks) needs to be selected, and historical treatment cost data should be used as the training set. The model will predict the costs required for different treatment options by learning resource consumption patterns from historical data. Like the efficacy assessment model, the cost assessment model also needs to be validated using a test set to ensure the accuracy and applicability of its predictions, helping medical institutions optimize resource allocation and reduce treatment costs.

[0163] By combining the outputs of efficacy assessment models and cost assessment models, medical institutions can achieve comprehensive optimization of efficacy and cost. In practical applications, medical teams use the results of these two models to balance treatment effectiveness and cost, ensuring that treatment plans maximize efficacy while controlling costs. For example, if the efficacy assessment model predicts a good outcome for a certain treatment plan, but the cost assessment model indicates high costs, the medical team can adjust the treatment plan, selecting a lower-cost alternative with similar effectiveness. By continuously optimizing these two models, medical institutions can tailor efficient and economical treatment plans for each patient, improving the overall quality of treatment and patient satisfaction.

[0164] S533. Perform feature decomposition on the patient node treatment parameter set to obtain the patient feature input vector, and input the patient feature input sub-vector into the efficacy evaluation model and cost evaluation model respectively to generate osteoarthritis treatment effect score and treatment cost evaluation value.

[0165] In this embodiment of the application, the step of performing feature decomposition on the patient node treatment parameter set to obtain a patient feature input vector, and then inputting the patient feature input sub-vector into the efficacy evaluation model and the cost evaluation model respectively to generate an osteoarthritis treatment effect score and a treatment cost evaluation value includes the following steps:

[0166] S5331. The patient node treatment parameter set is feature-splitting according to efficacy-related parameters and cost-related parameters to obtain the patient efficacy feature vector and the patient cost feature vector.

[0167] Specifically, the first step in feature-splitting the patient node treatment parameter set into efficacy-related parameters and cost-related parameters is to determine which treatment parameters are related to efficacy and cost, respectively. Efficacy-related parameters include patient treatment outcome data, such as pain scores, joint range of motion, functional recovery status, and quality of life scores. These parameters directly reflect the treatment effect and are obtained through patient self-reports, clinical assessments, and monitoring devices. Cost-related parameters include data related to treatment resource consumption, such as medication usage, duration of treatment equipment use, length of hospital stay, medical staff working hours, and the cost of treatment materials.

[0168] Next, the split efficacy and cost parameters are transformed into feature vectors. The patient efficacy feature vector includes parameters directly related to treatment effectiveness. After standardization and normalization, it forms a unified numerical vector that describes the changes in patient efficacy at various stages of treatment. The dimensions of these feature vectors can include the degree of pain relief, the extent of functional improvement, and the speed of recovery. For example, pain scores and joint range of motion are used as different dimensions of the vector to quantitatively express the patient's treatment effect. The patient cost feature vector includes parameters related to resource consumption, such as drug dosage, treatment frequency, and the use of medical equipment. These parameters, after quantification and standardization, also form a feature vector that describes the resource consumption during treatment.

[0169] S5332. Preset management target rules, and filter patient efficacy feature vectors and patient cost feature vectors based on management target rules;

[0170] Specifically, the key to setting management objectives lies in clearly defining the efficacy and cost control targets to be achieved during the treatment process. This includes specific treatment effectiveness standards (such as the reduction in pain scores and functional recovery) and resource consumption standards (such as the range of treatment cost control and the usage time of treatment equipment). For example, management objectives may require that the pain score be reduced by at least 50% during the treatment period or that the treatment cost not exceed a certain set budget limit.

[0171] Next, based on management objective rules, when screening patient efficacy feature vectors and patient cost feature vectors, the data in each feature vector are compared to select those that meet the management objective requirements. For example, when screening patient efficacy feature vectors, according to management objective rules, it is checked whether the patient's treatment effect has met the target, such as whether the pain score has reached the expected decrease within the specified time. If the patient's efficacy feature vector shows that the treatment effect has not met the predetermined standard, the feature vector is excluded or the treatment plan is adjusted. When screening patient cost feature vectors, it is necessary to check whether the resource consumption during the treatment process meets the budget limit, such as whether the amount of medication used or the duration of treatment equipment use exceeds the preset range. Finally, the patient efficacy feature vectors and patient cost feature vectors that meet the management objective rules provide a basis for the formulation and optimization of personalized treatment plans.

[0172] S5333: Input the screened patient efficacy feature vector and patient cost feature vector into the efficacy assessment model and cost assessment model respectively to obtain the treatment effect score and treatment cost assessment value;

[0173] Specifically, the selected patient efficacy feature vectors are input into the efficacy assessment model to score the treatment effect. This model is a predictive model built based on historical treatment effect data and patient efficacy feature vectors. By inputting the selected efficacy feature vectors into this model, the model calculates a treatment effect score based on the patient's specific treatment data (such as drug dosage, treatment frequency, pain score, etc.). This score reflects the effectiveness of the treatment plan on the current patient, such as the degree of pain relief or functional recovery.

[0174] Next, the filtered patient cost feature vectors are input into the cost assessment model to obtain the treatment cost assessment value. This cost assessment model is a predictive model built based on historical treatment cost data and patient cost feature vectors. After inputting the filtered patient cost feature vectors, the model calculates the total resource consumption during the treatment process, including drug costs, treatment equipment usage costs, and hospitalization costs. This assessment value reflects the economic cost of the treatment plan in actual implementation, helping medical institutions predict the budget consumption for each treatment plan. This is then combined with the treatment effectiveness score obtained from the efficacy assessment model and the treatment cost assessment value obtained from the cost assessment model.

[0175] S5334. Correct and output the treatment effect score and treatment cost assessment value by combining the management objective rules.

[0176] S54. Analyze treatment effect scores and treatment cost assessment values ​​to generate treatment effect and treatment cost for osteoarthritis.

[0177] Specifically, a treatment effectiveness score is generated for each patient through a treatment efficacy assessment model. This score primarily reflects the improvement in joint function recovery, pain relief, and quality of life during treatment. By inputting the patient's treatment parameters into the model and considering their individual characteristics, the actual treatment effect is evaluated. For example, for patients with osteoarthritis, the model generates a treatment effectiveness score based on factors such as improved joint mobility and reduced pain scores. A high score indicates that the treatment plan has achieved the expected therapeutic effect for the patient; conversely, a low score suggests that the treatment plan needs to be adjusted.

[0178] The next step is to analyze the key to generating treatment cost estimates for osteoarthritis by calculating resource consumption during the treatment process using a cost assessment model. The treatment cost estimate is a prediction of the resources consumed during osteoarthritis treatment, including medication costs, physical therapy costs, medical equipment usage costs, and costs for inpatient or outpatient treatment. The cost assessment model evaluates the economic input required to implement the treatment plan by inputting the patient's cost characteristic vector. A high cost estimate indicates that the treatment plan may involve significant resource consumption, requiring optimization of resource allocation to control treatment costs. By monitoring and assessing treatment costs, medical institutions can better manage budgets and allocate resources.

[0179] S6. Based on the evaluated treatment effects and costs of osteoarthritis, optimize and adjust the treatment parameters for osteoarthritis, verify and output the optimized treatment parameters, and dynamically update the medical resource consumption parameters.

[0180] Specifically, the first step in optimizing osteoarthritis treatment parameters based on assessed treatment effectiveness and costs is a comprehensive analysis of existing treatment protocols. For example, if treatment outcomes are unsatisfactory or costs are too high, the medical team considers adjusting key parameters such as medication dosage, treatment frequency, and treatment duration. The goal of this optimization is to improve treatment effectiveness while reducing costs through refined treatment protocols. Through this data-driven optimization, the medical team can ensure that each treatment parameter maximizes efficacy while controlling resource consumption.

[0181] Next, the optimized osteoarthritis treatment parameters will be validated and output. The optimized treatment plan needs to undergo rigorous validation to ensure it produces the expected results in actual treatment. The validation process includes applying the adjusted treatment plan to a real patient population, monitoring whether it improves efficacy, reduces costs, and meets individual patient needs. By comparing treatment effects and cost data before and after treatment, the medical team validates the actual effectiveness of the optimized plan. If the validation results show that both treatment effectiveness and costs are effectively improved or controlled, the optimized plan is considered feasible and can be formally applied in clinical treatment.

[0182] Based on the validation results, medical institutions need to dynamically update medical resource consumption parameters. Optimizing treatment plans involves not only adjusting treatment effectiveness and costs but also considering changes in resource consumption. As treatment plans are optimized, resource consumption may change, such as the amount of medication used or the frequency of use of treatment equipment. Through real-time monitoring and data collection, the medical team can dynamically track changes in resource consumption to ensure the rational allocation of resources during treatment. If resource consumption changes significantly, the medical team should adjust resource allocation based on the new consumption data to avoid overconsumption or resource waste.

[0183] According to another aspect of the invention, such as Figure 2 The system shown provides an intelligent evaluation and optimization system for osteoarthritis treatment plans. The system includes: a parameter acquisition and partitioning module 1, a parameter processing and mapping module 2, a feature extraction and calculation module 3, a real-time monitoring and correlation module 4, a treatment effect and cost module 5, and a parameter optimization and adjustment module 6.

[0184] The parameter acquisition and partitioning module 1 is used to acquire osteoarthritis treatment parameters, medical resource consumption parameters and similar disease treatment datasets of osteoarthritis patients, and to divide the osteoarthritis treatment parameters and medical resource consumption parameters into time-series stages.

[0185] The parameter processing and mapping module 2 is used to normalize the osteoarthritis treatment parameters and medical resource consumption parameters after the time-series stage division, and to construct a treatment task node index table and a medical resource dependency mapping table.

[0186] Feature extraction and calculation module 3 is used to classify and extract treatment feature parameters and consumption feature parameters from osteoarthritis treatment parameters and medical resource consumption parameters, and calculate the weight ratio of treatment feature parameters and consumption feature parameters through cost-benefit algorithm to form a set of treatment efficacy feature parameters;

[0187] Real-time monitoring and association module 4 is used to establish a real-time monitoring association between the task node index table and the resource dependency mapping table and the treatment efficacy feature parameter set, and to obtain the patient node treatment parameter set.

[0188] The treatment effect and cost module 5 is used to match the treatment parameter set of patient nodes with the treatment dataset of similar diseases using the cosine similarity algorithm, and evaluate the treatment effect and cost of osteoarthritis based on the matching results.

[0189] The parameter optimization and adjustment module 6 is used to optimize and adjust the osteoarthritis treatment parameters based on the evaluated treatment effect and treatment cost, verify and output the optimized osteoarthritis treatment parameters, and dynamically update the medical resource consumption parameters.

[0190] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for intelligent evaluation and optimization of osteoarthritis treatment plans, characterized in that, Includes the following steps: S1. Obtain osteoarthritis treatment parameters, medical resource consumption parameters, and similar disease treatment datasets for osteoarthritis patients, and divide the osteoarthritis treatment parameters and medical resource consumption parameters into time-series stages. S2. Normalize the osteoarthritis treatment parameters and medical resource consumption parameters after the time-series stage division, and construct a treatment task node index table and a medical resource dependency mapping table. S3. Classify and extract treatment feature parameters and consumption feature parameters for osteoarthritis treatment parameters and medical resource consumption parameters, and calculate the weight ratio of treatment feature parameters and consumption feature parameters through cost-benefit algorithm to form a set of treatment efficacy feature parameters; S4. Establish a real-time monitoring association between the task node index table and the resource dependency mapping table and the treatment efficacy feature parameter set to obtain the patient node treatment parameter set. S5. Match the treatment parameter set of patient nodes with the treatment dataset of similar diseases using the cosine similarity algorithm, and evaluate the treatment effect and cost of osteoarthritis based on the matching results. S6. Based on the evaluated treatment effects and costs of osteoarthritis, optimize and adjust the treatment parameters for osteoarthritis, verify and output the optimized treatment parameters, and dynamically update the medical resource consumption parameters. The process of classifying and extracting treatment feature parameters and consumption feature parameters for osteoarthritis treatment parameters and medical resource consumption parameters, and calculating the weight ratio of treatment feature parameters and consumption feature parameters using a cost-benefit algorithm to form a set of treatment efficacy feature parameters includes the following steps: S31. Classify osteoarthritis treatment parameters according to efficacy indicators and intervention measures, and extract treatment characteristic parameters; S32. Classify medical resource consumption parameters according to direct consumption and indirect consumption, and extract consumption characteristic parameters; S33. Map the treatment characteristic parameters and consumption characteristic parameters to efficacy contribution values ​​and cost consumption values, and then perform quantitative weighting. S34. Calculate the comprehensive weight ratio based on the quantified weighted efficacy contribution value and cost consumption value, and integrate them according to time sequence stages to form a treatment efficacy feature parameter set; the step of matching the patient node treatment parameter set with the treatment dataset of similar diseases using a cosine similarity algorithm, and evaluating the treatment effect and cost of osteoarthritis based on the matching results includes the following steps: S51. Extract patient feature vectors from the patient node treatment parameter set, and extract historical feature vectors from the treatment dataset of the same disease that correspond to the patient node treatment parameter set; S52. Calculate the similarity value between the patient's feature vector and the historical feature vector using the cosine similarity algorithm, filter the similarity values, and perform treatment feature matching based on the filtering results; S53. Establish efficacy evaluation model and cost evaluation model based on historical feature vectors, and input the patient node treatment parameter set into efficacy evaluation model and cost evaluation model to obtain treatment effect score and treatment cost evaluation value; S54. Analyze treatment effect scores and treatment cost assessment values ​​to generate treatment effect and treatment cost for osteoarthritis.

2. The intelligent evaluation and optimization method for osteoarthritis treatment plans according to claim 1, characterized in that, The normalization of osteoarthritis treatment parameters and medical resource consumption parameters after time-series segmentation, and the construction of a treatment task node index table and a medical resource dependency mapping table, includes the following steps: S21. Convert the pain score and joint range of motion in the osteoarthritis treatment parameters into standardized values ​​of 0-1, and unify the drug dosage and treatment frequency in the osteoarthritis treatment parameters into a quantitative format; S22. Convert the consumption of consumables and treatment time in the medical resource consumption parameters into a unified standard consumption coefficient, and convert the treatment cost in the medical resource consumption parameters into a unified benchmark cost unit. S23. Construct a treatment task node index table based on the time sequence of the normalized osteoarthritis treatment parameters. S24. Perform treatment dependency association mapping on the normalized osteoarthritis treatment parameters and medical resource consumption parameters, and generate a medical resource dependency mapping table based on the treatment dependency association mapping results.

3. The intelligent evaluation and optimization method for osteoarthritis treatment plans according to claim 1, characterized in that, The step of establishing a real-time monitoring association between the task node index table and the resource dependency mapping table and the treatment efficacy feature parameter set to obtain the patient node treatment parameter set includes the following steps: S41. Preset feature association rules, and build a real-time monitoring association relationship between the treatment task node index table and the treatment efficacy feature parameter set based on the feature association rules; S42. Based on real-time monitoring relationships, establish a mapping rule between a resource dependency relationship mapping table and a set of treatment efficacy feature parameters, and perform association matching; S43. Construct a real-time monitoring data acquisition channel based on the correlation matching results, and collect data; S44. Integrate the data collection results to generate a set of treatment parameters for patient nodes.

4. The intelligent evaluation and optimization method for osteoarthritis treatment plans according to claim 1, characterized in that, The process of mapping treatment characteristic parameters and consumption characteristic parameters to efficacy contribution values ​​and cost consumption values, and then performing quantitative weighting, includes the following steps: S331. Preset consumption value mapping rules, and map treatment feature parameters and consumption feature parameters to efficacy contribution values ​​and cost consumption values ​​based on consumption value mapping rules; S332. Set the weight adjustment coefficient and match the efficacy contribution value and cost consumption value based on the weight adjustment coefficient; S333. Based on the matching results, the weighted efficacy contribution value is obtained by adjusting the weight of the matched efficacy contribution value, and the cost consumption value is obtained by combining the matched weighted weight adjustment value. S334. Verify and output the weighted efficacy contribution value and weighted cost consumption value.

5. The intelligent evaluation and optimization method for osteoarthritis treatment plans according to claim 3, characterized in that, The process of establishing a resource dependency mapping table and a set of treatment efficacy feature parameters based on real-time monitoring relationships, and performing association matching, includes the following steps: S421. Based on real-time monitoring of the relationship, bind the resource dependency mapping table to the efficacy feature parameters in the treatment efficacy feature parameter set, and set efficacy parameter monitoring indicators and efficacy matching thresholds. S422. Generate an association matching table based on the efficacy parameter monitoring indicators and efficacy matching thresholds, and establish a mapping rule between the resource dependency mapping table and the treatment efficacy feature parameter set based on the association matching table. S423. The resource dependency mapping table is associated and matched with the set of therapeutic efficacy feature parameters through mapping rules.

6. The intelligent evaluation and optimization method for osteoarthritis treatment plans according to claim 1, characterized in that, The process of establishing efficacy evaluation and cost evaluation models based on historical feature vectors, and inputting patient node treatment parameter sets into these models to obtain treatment effect scores and treatment cost evaluation values ​​includes the following steps: S531. Classify the extracted historical feature vectors according to the efficacy dimension and the cost dimension, and select the efficacy feature vector and cost feature vector from the historical feature vectors; S532. Construct an efficacy evaluation model based on efficacy feature vectors and historical treatment effect data, and simultaneously construct a cost evaluation model based on cost feature vectors and historical treatment cost data; S533. Perform feature decomposition on the patient node treatment parameter set to obtain the patient feature input vector, and input the patient feature input sub-vector into the efficacy evaluation model and cost evaluation model respectively to generate osteoarthritis treatment effect score and treatment cost evaluation value.

7. The intelligent evaluation and optimization method for osteoarthritis treatment plans according to claim 6, characterized in that, The step of performing feature decomposition on the patient node treatment parameter set to obtain the patient feature input vector, and then inputting the patient feature input sub-vector into the efficacy evaluation model and the cost evaluation model respectively to generate osteoarthritis treatment effect score and treatment cost evaluation value, includes the following steps: S5331. The patient node treatment parameter set is feature-splitting according to efficacy-related parameters and cost-related parameters to obtain patient efficacy feature vector and patient cost feature vector; S5332. Preset management target rules, and filter patient efficacy feature vectors and patient cost feature vectors based on management target rules; S5333: Input the screened patient efficacy feature vector and patient cost feature vector into the efficacy assessment model and cost assessment model respectively to obtain the treatment effect score and treatment cost assessment value; S5334. Correct and output the treatment effect score and treatment cost assessment value by combining the management objective rules.

8. An intelligent evaluation and optimization system for osteoarthritis treatment plans is used to implement the intelligent evaluation and optimization method for osteoarthritis treatment plans according to any one of claims 1-7, characterized in that, The system includes: a parameter acquisition and partitioning module, a parameter processing and mapping module, a feature extraction and calculation module, a real-time monitoring and correlation module, a treatment effect and cost module, and a parameter optimization and adjustment module; The parameter acquisition and partitioning module is used to acquire osteoarthritis treatment parameters, medical resource consumption parameters, and similar disease treatment datasets for osteoarthritis patients, and to partition the osteoarthritis treatment parameters and medical resource consumption parameters into time-series stages. The parameter processing and mapping module is used to normalize the osteoarthritis treatment parameters and medical resource consumption parameters after the time-series stage division, and to construct a treatment task node index table and a medical resource dependency mapping table. The feature extraction and calculation module is used to classify and extract treatment feature parameters and consumption feature parameters from osteoarthritis treatment parameters and medical resource consumption parameters, and to calculate the weight ratio of treatment feature parameters and consumption feature parameters through a cost-benefit algorithm to form a set of treatment efficacy feature parameters. The real-time monitoring and association module is used to establish a real-time monitoring association between the task node index table and the resource dependency mapping table and the treatment efficacy feature parameter set, and to obtain the patient node treatment parameter set. The treatment effect and cost module is used to match the treatment parameter set of patient nodes with the treatment dataset of similar diseases using the cosine similarity algorithm, and evaluate the treatment effect and cost of osteoarthritis based on the matching results. The parameter optimization and adjustment module is used to optimize and adjust osteoarthritis treatment parameters based on the evaluated treatment effects and costs. It then verifies and outputs the optimized osteoarthritis treatment parameters and dynamically updates the medical resource consumption parameters.

Images