AI recommendation system and method for adaptively recommending surgical consumables meeting cost expectation

Abstract

The invention relates to an AI recommendation system and method for adaptively recommending surgical consumables meeting cost expectation, and the system carries out the training and learning of different types of DRGs big data through AI, thereby constructing a corresponding model, and putting the model into a consumable management system for use. According to the method, the corresponding consumable scheme can be identified and recommended according to the operation type, so that the patient can select the operation consumable information with the cost expectation, and the operation consumables meeting the cost expectation of the patient can be recommended by utilizing the model, so that the bearing capacity of the patient and the bearing pressure of a doctor can be considered. Therefore, the model is used for charging various surgical consumables, the workload of a surgeon is reduced, and delay and influence on surgical time and preparatory work are avoided. When the operation consumables are charged, the economic condition of the patient can be considered, the consumables meeting the cost expectation can be selected, adaptive cost can be brought to the patient, and medical burden caused by excess is avoided.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology, and in particular to an AI recommendation method for surgical consumables that adaptively recommends surgical consumables that meet cost expectations, a consumables recommendation system, and electronic equipment. Background Art

[0002] DRGs (Diagnosis-Related Groups) is a classification system used in the field of healthcare, especially in medical insurance payments. The DRGs system groups inpatient cases according to factors such as diagnosis, treatment, age, gender, and discharge status, and each group corresponds to a fixed payment amount. This system aims to control medical expenses, improve the efficiency of the use of medical resources, and encourage medical institutions to provide high-quality medical services.

[0003] DRGs have been gradually applied in most current hospital charging systems. Under this condition, each doctor can become an accountant and calculate medical expenses based on diagnosis information.

[0004] However, in medical surgery, because surgery requires a large number of different types of surgical consumables (surgical instruments, medicines, nursing supplies, etc.), even if doctors bill for various surgical consumables according to DRGs, this billing method still involves a lot of workload, which will delay and affect the operation time and preparation work.

[0005] In addition, when surgeons charge for surgical consumables, some consumables may come from different suppliers or have different qualities, types, varieties and prices, which may result in higher bills issued by doctors and overcharges for consumables that cannot meet the economic conditions of doctors or patients. In the early stages, traditional doctors rarely consider the economic conditions of patients, which may bring higher medical burdens to patients. Summary of the invention

[0006] In order to solve the above problems, the present application proposes an AI recommendation method, consumables recommendation system and electronic device for adaptively recommending surgical consumables that meet cost expectations.

[0007] On the one hand, this application proposes an AI recommendation method for adaptively recommending surgical consumables that meet cost expectations, including the following steps:

[0008] S1. Enter the current patient's surgical information, including the type of surgery and expected cost;

[0009] S2. Importing the surgical information into a preset surgical consumables AI recommendation model, and having the surgical consumables AI recommendation model identify and output a list of surgical consumables matching the surgical type;

[0010] S3, counting the consumable costs of the surgical consumables list, screening out the surgical consumables list that meets the expected cost, and using it as the target surgical consumables list for the current patient;

[0011] S4. Record the target surgical consumables list into the HIS medical record file of the current patient.

[0012] As an optional implementation scheme of the present application, optionally, the method for generating the surgical consumables AI recommendation model includes:

[0013] Collect DRGs big data of several surgical patients;

[0014] Preprocessing and classifying the DRGs big data, and dividing the DRGs big data into a plurality of DRGs data subsets corresponding to different surgical types according to the surgical types;

[0015] Performing feature engineering on each of the DRGs data subsets, extracting DRGs data features corresponding to the surgical type, and constructing a corresponding DRGs data feature set;

[0016] Dividing the DRGs data feature set into a training set and a validation set according to a preset ratio;

[0017] Importing the training set into a preset RNN model, performing model training and learning, and generating an initial surgical consumables AI recommendation model;

[0018] The surgical consumables AI recommendation model is verified using the verification set:

[0019] If the performance verification of the surgical consumables AI recommendation model passes, the surgical consumables AI recommendation model is deployed on the background server;

[0020] Otherwise, the DRGs big data is adjusted and the surgical consumables AI recommendation model is retrained and generated.

[0021] As an optional implementation scheme of the present application, optionally, the DRGs big data includes:

[0022] The type of surgery, surgical consumables used, and corresponding consumable costs of surgical patients in DRGs, including:

[0023] The surgical consumables used in the same type of surgery and the corresponding consumable costs remain consistent, or the surgical consumables used in the same type of surgery and the corresponding consumable costs remain inconsistent.

[0024] As an optional implementation scheme of the present application, optionally, each of the DRGs data subsets contains consistent surgical consumables used by several surgical patients under this type of surgery and corresponding consumable cost information, or contains inconsistent surgical consumables used by several surgical patients under this type of surgery and corresponding consumable cost information.

[0025] As an optional implementation scheme of the present application, optionally, S2, importing the surgical information into a preset surgical consumables AI recommendation model, and the surgical consumables AI recommendation model identifies and outputs a list of surgical consumables matching the surgical type, including:

[0026] Receive and identify the type of surgery for the current patient in the surgery information;

[0027] Identify DRGs data features that match the type of surgery through the surgical consumables AI recommendation model;

[0028] Output several groups of surgical consumables and consumable costs corresponding to the DRGs data features.

[0029] As an optional implementation scheme of the present application, optionally, S3, counting the consumables costs of the surgical consumables list, screening out the surgical consumables list that meets the expected costs, and using it as the target surgical consumables list for the current patient, including:

[0030] Writing the outputted groups of surgical consumables and consumables costs into a preset billing template to obtain corresponding surgical consumables lists, and counting the consumables costs of each surgical consumables list;

[0031] Record the list of each surgical consumables in the HIS medical record file of the current patient, and send a confirmation notice to the patient through the backend server;

[0032] The patient checks the consumables costs of each surgical consumables list through the patient terminal, makes a selection, and reports the selection information of the selected surgical consumables list to the backend server;

[0033] The backend server records the selected surgical consumables list according to the selection information and uses it as the target surgical consumables list for the current patient;

[0034] Print the target surgical consumables list and save it in the warehouse to generate the surgical bill for the current patient.

[0035] On the other hand, the present application proposes a consumables recommendation system for implementing the AI ​​recommendation method for surgical consumables that adaptively recommends surgical consumables that meet cost expectations, including:

[0036] The medical end is used to input the current patient's surgical information, including the type of surgery and expected cost;

[0037] The backend server is used to import the surgical information into a preset surgical consumables AI recommendation model, and the surgical consumables AI recommendation model identifies and outputs a list of surgical consumables that matches the surgical type; and, count the consumable costs of the surgical consumables list, screen out the surgical consumables list that meets the expected costs, and use it as the target surgical consumables list for the current patient; and, record the target surgical consumables list in the HIS medical record file of the current patient; and, send a confirmation notification to the patient; and, after the patient responds, generate the surgical bill for the current patient according to the selected information;

[0038] The patient end is used to view the consumables costs of each surgical consumables list, make a selection, and report the selection information of the selected surgical consumables list to the backend server; and respond to the surgical bill;

[0039] The medical end and the patient end are respectively connected to the backend server for communication.

[0040] On the other hand, the present application also proposes an electronic device, comprising:

[0041] processor;

[0042] a memory for storing processor-executable instructions;

[0043] Wherein, the processor is configured to implement the AI ​​recommendation method for surgical consumables that adaptively recommends and meets cost expectations when executing the executable instructions.

[0044] Technical effects of the present invention:

[0045] This application uses AI to train and learn different types of DRGs big data, so as to build corresponding models and put them into the consumables management system for use. It can identify and recommend corresponding consumables solutions according to the type of surgery, so that patients can choose surgical consumables information that meets their cost expectations. The model can be used to recommend surgical consumables that meet patients' cost expectations, thus taking into account both the patient's ability to bear and the doctor's pressure.

[0046] Therefore, the present invention utilizes the model to carry out billing for various surgical consumables, thereby reducing the workload of surgeons and avoiding delays and impacts on surgical time and preparation work.

[0047] In addition, when billing for surgical consumables, the patient's financial situation can be taken into consideration, and consumables that meet cost expectations can be selected, which will bring appropriate costs to the patient and avoid overages that create medical burdens.

[0048] Further features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate exemplary embodiments, features, and aspects of the disclosure and, together with the description, serve to explain the principles of the disclosure.

[0050] Figure 1 It is shown as a schematic diagram of the implementation process of the present invention;

[0051] Figure 2 Shown is a schematic diagram of DRGs big data generation of the present invention;

[0052] Figure 3 Shown is a schematic diagram of the system composition of the present invention;

[0053] Figure 4 It is a schematic diagram showing the application of the electronic device of the present invention. DETAILED DESCRIPTION

[0054] Various exemplary embodiments, features and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. The same reference numerals in the accompanying drawings represent elements with the same or similar functions. Although various aspects of the embodiments are shown in the accompanying drawings, the drawings are not necessarily drawn to scale unless otherwise specified.

[0055] The word “exemplary” is used exclusively herein to mean “serving as an example, example, or illustration.” Any embodiment described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments.

[0056] In addition, in order to better illustrate the present disclosure, numerous specific details are given in the following specific embodiments. It should be understood by those skilled in the art that the present disclosure can also be implemented without certain specific details. In some examples, means, components and circuits well known to those skilled in the art are not described in detail in order to highlight the main purpose of the present disclosure.

[0057] The specific deployment and application of the DRGs system in this embodiment should be understood in conjunction with the application situation of each hospital, and this embodiment will not go into details.

[0058] The DRGs system can also be referred to as the "diagnosis related grouping system" or "diagnosis grouping system" and so on.

[0059] The billing rules for each consumable can be configured on the server according to the charging situation of each hospital.

[0060] For the form template of consumable bills or lists (provided by the system), you can fill in the data according to the template set up or configured by each hospital.

[0061] Example 1

[0062] like Figure 1 As shown, on the one hand, the present application proposes an AI recommendation method for adaptively recommending surgical consumables that meet cost expectations, including the following steps:

[0063] S1. Enter the current patient's surgical information, including the type of surgery and expected cost;

[0064] S2. Importing the surgical information into a preset surgical consumables AI recommendation model, and having the surgical consumables AI recommendation model identify and output a list of surgical consumables matching the surgical type;

[0065] S3, counting the consumable costs of the surgical consumables list, screening out the surgical consumables list that meets the expected cost, and using it as the target surgical consumables list for the current patient;

[0066] S4. Record the target surgical consumables list into the HIS medical record file of the current patient.

[0067] like Figure 2 As shown in the figure, in the hospital, after the doctor uses the diagnosis grouping system to generate the corresponding surgical consumables data for each surgical patient, the consumables application information for different surgical types can be formed. Therefore, the massive consumables application big data generated by the diagnosis grouping system can be stored in the background database. This information big data contains the consumables solutions used for different surgical types and the surgical costs involved according to the corresponding solutions.

[0068] Therefore, the present invention uses big data technology to train and learn solutions that meet different surgical cost requirements under different surgical types, and uses AI technology to recommend surgical consumable solutions that meet cost expectations for patients, and recommends a list of surgical consumables that meets patients' expectations, thereby reducing their medical expense burden. At the same time, the model can be used to recommend consumables, which can reduce the workload of surgeons and reduce their pressure.

[0069] Combined with Figure 3 As shown, there is a his system on the background server, which can record the surgical information of each surgical patient and store it in the background database. The surgical information of each surgical patient includes the corresponding surgical type, surgical consumables list, consumables cost, etc. Therefore, on the background server, the administrator can use the big data in the background database to train and generate the corresponding surgical consumables AI recommendation model. After the model is built and the performance is verified, the constructed surgical consumables AI recommendation model is installed and deployed on the background server.

[0070] When conducting preliminary preparations for surgical patients, medical staff can input the surgical type of the patient who currently needs surgery into the backend server through the medical terminal, such as EDA or PDA terminal, etc. The backend server imports the surgical type in the surgical information into the model, and the model identifies and outputs the lists of surgical consumables for that surgical type (because there are many types of consumables and their prices vary, although it is the same type of surgery, different patients may choose different consumables. Therefore, it is necessary to identify the surgical consumables lists composed of different consumables separately, and the bill costs corresponding to each surgical consumables list are different). The list will be billed later, and the backend server will recommend the corresponding target surgical consumables list based on the patient's choice.

[0071] Because the model can identify the different components of surgical consumables lists under different types of surgeries, when the model recommends, the model will output several surgical consumables lists under the type of surgery for the patient to choose from. The backend server will then select the surgical consumables list required for the final surgery based on the patient's choice of the cost of each surgical consumables list. After receiving the patient's selection, the backend server will generate the corresponding surgical consumables bill, which will be sent to the patient end (APP, etc.) by the billing system, and the patient end will respond and pay.

[0072] As an optional implementation scheme of the present application, optionally, the method for generating the surgical consumables AI recommendation model includes:

[0073] Collect DRGs big data of several surgical patients;

[0074] Preprocessing and classifying the DRGs big data, and dividing the DRGs big data into a plurality of DRGs data subsets corresponding to different surgical types according to the surgical types;

[0075] Performing feature engineering on each of the DRGs data subsets, extracting DRGs data features corresponding to the surgical type, and constructing a corresponding DRGs data feature set;

[0076] Dividing the DRGs data feature set into a training set and a validation set according to a preset ratio;

[0077] Importing the training set into a preset RNN model, performing model training and learning, and generating an initial surgical consumables AI recommendation model;

[0078] The surgical consumables AI recommendation model is verified using the verification set:

[0079] If the performance verification of the surgical consumables AI recommendation model passes, the surgical consumables AI recommendation model is deployed on the background server;

[0080] Otherwise, the DRGs big data is adjusted and the surgical consumables AI recommendation model is retrained and generated.

[0081] The present invention utilizes neural networks to train AI models, and CNN, RNN, logistic regression, random forest models, etc. may be selected.

[0082] First, it is necessary to collect relevant DRGs big data from the background database. This can be done by the administrator himself, collecting data related to surgical consumables.

[0083] DRGs big data usually contains the patient's diagnosis information, treatment process, consumables usage information and consumables billing costs, etc. These data can be used to analyze and predict the patient's treatment effect and the use of medical resources. The following are the steps to build a recommendation model:

[0084] 1. Data collection and preprocessing: Collect DRGS-related medical data, including but not limited to patients’ diagnosis information, treatment plans, hospital stays, costs, etc. Clean the data, process missing values ​​and outliers, and ensure data quality.

[0085] As mentioned above, for different types of surgeries, different patients may choose different types, qualities, and prices of consumables. Therefore, different types of surgeries may correspond to several types of surgical consumables selection information. Therefore, this solution needs to classify the collected DRGs big data. According to the type of surgery, the DRGs big data is first divided into various DRGs data subsets corresponding to different types of surgeries. Feature recognition is performed on different groups of consumables selection information under the type of surgery in each DRGs data subset, and the corresponding DRGs data features are extracted, and the corresponding data feature set is constructed.

[0086] 2. Feature engineering: Based on professional knowledge in the medical field, extract features from the raw data that are helpful for model prediction. For example, diagnostic information can be converted into coded form, and treatment plans can be converted into quantifiable indicators. Feature engineering can also use machine learning models, deep learning models, or feature extraction algorithms to extract corresponding data features. Among them, the identified features can also be manually labeled or manually inspected to identify and extract the data features of the corresponding DRGs, such as the names and costs of various consumables selected for thyroid surgery.

[0087] 3. Model selection: Choose a suitable machine learning algorithm as the basis of the recommendation model. Common algorithms include logistic regression, random forest, gradient boosted tree (GBDT), neural networks such as RNN, etc.

[0088] 4. Training and validation: Use the collected data set to train the model and evaluate the performance of the model through methods such as cross-validation. Adjust the model parameters to optimize the accuracy and generalization ability of the model.

[0089] 5. Model evaluation: Use the test set to evaluate the prediction effect of the model. The main evaluation indicators may include accuracy, recall rate, F1 score, etc.

[0090] 6. Recommendation system integration: Integrate the trained model into the recommendation system to dynamically generate recommendations based on the patient’s real-time data. Recommendations can include treatment options, drug selection, rehabilitation advice, etc.

[0091] 7. Model iteration and optimization: Based on user feedback and system operation, new data is continuously collected to iterate and optimize the model to improve the accuracy and personalization of recommendations.

[0092] 8. Privacy and Compliance Compliance: Ensure compliance with relevant privacy protection regulations and medical ethics standards when processing patient data.

[0093] Through the above steps, an intelligent recommendation model based on DRGS big data can be built to provide support for medical decision-making and improve the quality and efficiency of medical services.

[0094] The general steps for model training based on RNN are as follows:

[0095] First, prepare the dataset, including data cleaning and formatting. Then, define the RNN model architecture and choose the appropriate recurrent neural network type, such as LSTM or GRU. Next, configure the model parameters, such as hidden layer size, learning rate, and optimizer. After that, divide the dataset into training and validation sets, and perform batch processing on the data.

[0096] Start training the model and iteratively update the model weights using the training set data. At the end of each epoch, use the validation set to evaluate the model performance and adjust the hyperparameters as needed. During the training process, monitor the loss function and accuracy indicators to ensure that the model converges.

[0097] After training is complete, save the model and perform a final evaluation on the test set to verify the generalization ability of the model. Based on the test results, you may need to return to adjust the model architecture or parameters for further optimization. Finally, deploy the trained model to the actual application.

[0098] In the present invention, the administrator can perform relevant model training and adjust the model training parameters. For the feature set division ratio, for example, 7:3, the corresponding data is randomly extracted from the verification set and imported into the model to verify the model performance.

[0099] Verification decisions are made at the administrator's discretion.

[0100] As an optional implementation scheme of the present application, optionally, the DRGs big data includes:

[0101] The type of surgery, surgical consumables used, and corresponding consumable costs of surgical patients in DRGs, including:

[0102] The surgical consumables used in the same type of surgery and the corresponding consumable costs remain consistent, or the surgical consumables used in the same type of surgery and the corresponding consumable costs remain inconsistent.

[0103] That is, the same type of surgery will have different consumables selection information.

[0104] As an optional implementation scheme of the present application, optionally, each of the DRGs data subsets contains consistent surgical consumables used by several surgical patients under this type of surgery and corresponding consumable cost information, or contains inconsistent surgical consumables used by several surgical patients under this type of surgery and corresponding consumable cost information.

[0105] In the divided subsets, there will also be different surgical consumables selection information for the same surgery type.

[0106] Because there are many types of consumables in hospitals, this embodiment defaults to at least two lists of surgical consumables for each type of surgery.

[0107] As an optional implementation scheme of the present application, optionally, S2, importing the surgical information into a preset surgical consumables AI recommendation model, and the surgical consumables AI recommendation model identifies and outputs a list of surgical consumables matching the surgical type, including:

[0108] Receive and identify the type of surgery for the current patient in the surgery information;

[0109] Identify DRGs data features that match the type of surgery through the surgical consumables AI recommendation model;

[0110] Output several groups of surgical consumables and consumable costs corresponding to the DRGs data features.

[0111] The model can automatically identify the type of surgery the current patient is undergoing and match and output several sets of corresponding surgical consumables selection information.

[0112] The backend server can generate several medical bills for consumables based on several groups of surgical consumables and consumables costs output by the model (each group of consumables information includes the name of the consumables used for the corresponding type of surgery, unit price, etc.), allowing patients to confirm and select the bill that meets their cost expectations. The backend generates the final consumables bill based on the patient's choice. Therefore, it is possible to recommend consumables bills that meet the patient's financial strength, and make quantitative recommendations in a more humane way, avoiding the drawback of doctors blindly recommending without considering the patient's financial ability.

[0113] As an optional implementation scheme of the present application, optionally, S3, counting the consumables costs of the surgical consumables list, screening out the surgical consumables list that meets the expected costs, and using it as the target surgical consumables list for the current patient, including:

[0114] Writing the outputted groups of surgical consumables and consumables costs into a preset billing template to obtain corresponding surgical consumables lists, and counting the consumables costs of each surgical consumables list;

[0115] Record the list of each surgical consumables in the HIS medical record file of the current patient, and send a confirmation notice to the patient through the backend server;

[0116] The patient checks the consumables costs of each surgical consumables list through the patient terminal, makes a selection, and reports the selection information of the selected surgical consumables list to the backend server;

[0117] The backend server records the selected surgical consumables list according to the selection information and uses it as the target surgical consumables list for the current patient;

[0118] Print the target surgical consumables list and save it in the warehouse to generate the surgical bill for the current patient.

[0119] Generally, hospitals deploy their own billing systems on their backend servers, and configure corresponding billing templates or billing rules in the billing systems. Therefore, the backend server can write several groups of surgical consumables and consumables costs output by the model into the preset billing templates and perform cost statistics.

[0120] For generating different consumable bills under this type of surgery, the backend can record these surgical consumable lists of different costs in the HIS system and send a confirmation notification to the patient. The patient receives and views different medical bills through the patient end, and after viewing the consumable costs of each list, makes a choice and reports the selection information of the list that meets his or her economic expectations to the backend server, so that the backend server can generate the corresponding medical bill according to the bill selected by the patient that meets his or her economic expectations.

[0121] The backend can print and save the bills of the consumables selected by the patient. At the same time, the generated surgical bill for the current patient will be sent to the patient end to notify the patient to pay. The patient can respond and pay through the APP on the patient end, and notify the billing system after payment.

[0122] Therefore, the present invention uses AI to train and learn different types of DRGs big data, thereby building a corresponding model and putting it into use in the consumables management system. According to the type of surgery, the corresponding consumables plan can be identified and recommended for patients to choose surgical consumables information that meets their cost expectations. The model can be used to recommend surgical consumables that meet patients' cost expectations, thus taking into account both the patient's ability to bear and the doctor's pressure.

[0123] Obviously, those skilled in the art should understand that the implementation of all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above-mentioned embodiments. Those skilled in the art can understand that the implementation of all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above-mentioned embodiments. Among them, the storage medium can be a disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory (Flash Memory), a hard disk (Hard Disk Drive, abbreviated as: HDD) or a solid-state drive (SSD), etc.; the storage medium can also include a combination of the above-mentioned types of memory.

[0124] Example 2

[0125] like Figure 3 As shown, based on the implementation principle of Example 1, on the other hand, the present application proposes a consumables recommendation system for implementing the AI ​​recommendation method for adaptively recommending surgical consumables that meet cost expectations described in Example 2, including:

[0126] The medical end is used to input the current patient's surgical information, including the type of surgery and expected cost;

[0127] The backend server is used to import the surgical information into a preset surgical consumables AI recommendation model, and the surgical consumables AI recommendation model identifies and outputs a list of surgical consumables that matches the surgical type; and, count the consumable costs of the surgical consumables list, screen out the surgical consumables list that meets the expected costs, and use it as the target surgical consumables list for the current patient; and, record the target surgical consumables list in the HIS medical record file of the current patient; and, send a confirmation notification to the patient; and, after the patient responds, generate the surgical bill for the current patient according to the selected information;

[0128] The patient end is used to view the consumables costs of each surgical consumables list, make a selection, and report the selection information of the selected surgical consumables list to the backend server; and respond to the surgical bill;

[0129] The medical end and the patient end are respectively connected to the backend server for communication.

[0130] The interaction of the above-mentioned systems can be understood in conjunction with Example 1, and will not be described in detail in this example.

[0131] The modules or steps of the present invention described above can be implemented by a general-purpose computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, and optionally, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0132] Example 3

[0133] like Figure 4 As shown, further, in another aspect, the present application also proposes an electronic device, including:

[0134] processor;

[0135] a memory for storing processor-executable instructions;

[0136] Among them, the processor is configured to implement the AI ​​recommendation system and method for adaptively recommending surgical consumables that meet cost expectations as described in Example 2 when executing the executable instructions.

[0137] The electronic device of the embodiment of the present disclosure includes a processor and a memory for storing instructions executable by the processor. The processor is configured to implement the AI ​​recommendation method for adaptively recommending surgical consumables that meet cost expectations as described in the above embodiment 2 when executing the executable instructions.

[0138] Here, it should be noted that the number of processors can be one or more. At the same time, the electronic device in the embodiment of the present disclosure may also include an input device and an output device. Among them, the processor, memory, input device and output device may be connected through a bus or in other ways, which are not specifically limited here.

[0139] As a computer-readable storage medium, the memory can be used to store software programs, computer executable programs and various modules, such as: the program or module corresponding to the AI ​​recommendation method for adaptively recommending surgical consumables that meet cost expectations in an embodiment of the present disclosure. The processor executes various functional applications and data processing of the electronic device by running the software programs or modules stored in the memory.

[0140] The input device can be used to receive input numbers or signals. The signal can be a key signal related to user settings and function control of the device / terminal / server. The output device can include a display device such as a display screen.

[0141] The embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or technical improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. An AI recommendation method for adaptively recommending surgical consumables that meet cost expectations, characterized in that: The steps include: S1. Enter the current patient's surgical information, including the type of surgery and expected cost; S2. Importing the surgical information into a preset surgical consumables AI recommendation model, and having the surgical consumables AI recommendation model identify and output a list of surgical consumables matching the surgical type; S3, counting the consumable costs of the surgical consumables list, screening out the surgical consumables list that meets the expected cost, and using it as the target surgical consumables list for the current patient; S4. Record the target surgical consumables list into the HIS medical record file of the current patient.

2. The method for adaptively recommending surgical consumables that meet cost expectations according to claim 1, characterized in that: The method for generating the surgical consumables AI recommendation model comprises: Collect DRGs big data of several surgical patients; Preprocessing and classifying the DRGs big data, and dividing the DRGs big data into a plurality of DRGs data subsets corresponding to different surgical types according to the surgical types; Performing feature engineering on each of the DRGs data subsets, extracting DRGs data features corresponding to the surgical type, and constructing a corresponding DRGs data feature set; Dividing the DRGs data feature set into a training set and a validation set according to a preset ratio; Importing the training set into a preset RNN model, performing model training and learning, and generating an initial surgical consumables AI recommendation model; The surgical consumables AI recommendation model is verified using the verification set: If the performance verification of the surgical consumables AI recommendation model passes, the surgical consumables AI recommendation model is deployed on the background server; Otherwise, the DRGs big data is adjusted and the surgical consumables AI recommendation model is retrained and generated.

3. The method for adaptively recommending surgical consumables that meet cost expectations according to claim 2, characterized in that: The DRGs big data includes: The type of surgery, surgical consumables used, and corresponding consumable costs of surgical patients in DRGs, including: The surgical consumables used in the same type of surgery and the corresponding consumable costs remain consistent, or the surgical consumables used in the same type of surgery and the corresponding consumable costs remain inconsistent.

4. The method for adaptively recommending surgical consumables that meet cost expectations according to claim 2, characterized in that: Each of the DRGs data subsets contains consistent surgical consumables used by several surgical patients under this type of surgery and corresponding consumable cost information, or contains inconsistent surgical consumables used by several surgical patients under this type of surgery and corresponding consumable cost information.

5. The method for adaptively recommending surgical consumables that meet cost expectations according to claim 2, characterized in that: S2. Importing the surgical information into a preset surgical consumables AI recommendation model, and having the surgical consumables AI recommendation model identify and output a list of surgical consumables matching the surgical type, including: Receive and identify the type of surgery for the current patient in the surgery information; Identify DRGs data features that match the type of surgery through the surgical consumables AI recommendation model; Output several groups of surgical consumables and consumable costs corresponding to the DRGs data features.

6. The method for adaptively recommending surgical consumables that meet cost expectations according to claim 5, characterized in that: S3, counting the consumable costs of the surgical consumables list, screening out the surgical consumables list that meets the expected cost, and using it as the target surgical consumables list for the current patient, including: Writing the outputted groups of surgical consumables and consumables costs into a preset billing template to obtain corresponding surgical consumables lists, and counting the consumables costs of each surgical consumables list; Record the list of each surgical consumables in the HIS medical record file of the current patient, and send a confirmation notice to the patient through the backend server; The patient checks the consumables costs of each surgical consumables list through the patient terminal, makes a selection, and reports the selection information of the selected surgical consumables list to the backend server; The backend server records the selected surgical consumables list according to the selection information and uses it as the target surgical consumables list for the current patient; Print the target surgical consumables list and save it in the warehouse to generate the surgical bill for the current patient.

7. A consumables recommendation system, used to implement the AI ​​recommendation method for adaptively recommending surgical consumables that meet cost expectations as described in any one of claims 1-6, characterized in that: include: The medical end is used to input the current patient's surgical information, including the type of surgery and expected cost; A backend server is used to import the surgical information into a preset surgical consumables AI recommendation model, and the surgical consumables AI recommendation model identifies and outputs a list of surgical consumables that matches the surgical type; and to count the consumable costs of the surgical consumables list, screen out the surgical consumables list that meets the expected costs, and use it as the target surgical consumables list for the current patient; And, recording the target surgical consumables list into the HIS medical record file of the current patient; and, sending a confirmation notification to the patient; and, after the patient responds, generating a surgery bill for the current patient according to the selected information; The patient end is used to view the consumable costs of each surgical consumable list, make a selection, and report the selection information of the selected surgical consumable list to the backend server; and, responding to said surgical bill; The medical end and the patient end are respectively connected to the backend server for communication.

8. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; Wherein, the processor is configured to implement the AI ​​recommendation method for surgical consumables that adaptively recommends and meets cost expectations as described in any one of claims 1-6 when executing the executable instructions.

Images