Diagnosis and treatment scheme recommendation and diagnosis and treatment equipment collaborative management system and method

Abstract

The invention provides a diagnosis and treatment scheme recommendation and diagnosis and treatment equipment collaborative management system and method. The system comprises a data acquisition module for acquiring symptom information, a diagnosis and treatment scheme recommendation module for generating a recommended diagnosis and treatment scheme based on the symptom information, a hospital server for sending the recommended diagnosis and treatment scheme to a hospital personnel client, and the hospital personnel client for confirming or adjusting the recommended diagnosis and treatment scheme. The hospital system server is used for collecting first equipment state information of the diagnosis and treatment equipment and sending the first equipment state information to the hospital server; the hospital server is also used for sending the first equipment state information to the cloud; and the equipment state monitoring module is used for monitoring the abnormity or use condition of the diagnosis and treatment equipment in the hospital and sending alarm information to the hospital server when the diagnosis and treatment equipment is confirmed to be abnormal or overused, so that the hospital server sends the alarm information to the hospital personnel client. The doctor seeing efficiency of patients and the equipment utilization rate can be improved, and the equipment operation and maintenance cost is reduced.

Description

Technical Field

[0001] The present invention relates to the field of smart medical technology, and in particular to a diagnosis and treatment plan recommendation and diagnosis and treatment equipment collaborative management system and method. Background Art

[0002] Medical equipment has been one of the fastest-growing assets at all levels of medical institutions in recent years. Improving the efficiency of medical equipment use, avoiding idle equipment, and rationally allocating equipment scale have become important ways to reduce operating costs and improve the economic benefits of medical institutions at all levels. On the other hand, the management challenges brought about by the influx of large numbers of equipment into medical institutions at all levels are becoming increasingly prominent. Furthermore, the device data storage at all levels of medical institutions is fragmented, lacking a unified management platform, leading to the phenomenon of data silos. Specifically, the following issues may exist: 1. Lack of coordinated management of equipment status, inability to identify equipment failures in a timely manner, resulting in excessively high equipment operation and maintenance costs; 2. The system cannot intelligently identify the utilization or idle rate of each device, resulting in some devices in the same batch being overused and some devices having low utilization rates within their product lifespan. 3. The diagnostic and treatment data of each device cannot be effectively combined for subsequent diagnosis and treatment. Summary of the Invention

[0003] The present invention aims to solve at least one of the technical problems existing in the prior art or related art.

[0004] In view of this, one or more embodiments of this specification provide a system and method for recommending treatment plans and coordinating the management of treatment equipment, which can improve the efficiency of patient treatment, equipment utilization, and reduce equipment operation and maintenance costs.

[0005] According to a first aspect of the present invention, a diagnosis and treatment plan recommendation and diagnosis and treatment equipment collaborative management system is provided, the system comprising a cloud and several hospital servers; the cloud comprises a data acquisition module, a diagnosis and treatment plan recommendation module, and an equipment status monitoring module; wherein: The hospital server is configured to, upon receiving a recommended treatment plan or warning information, send the recommended treatment plan or warning information to a hospital personnel client, and upon receiving first device status information, send the first device status information to the cloud; A data acquisition module is used to obtain the medical symptom information of the patient from the hospital server, wherein the medical symptom information includes medical history information and symptom information; A treatment plan recommendation module is used to generate a recommended treatment plan based on the symptom information and a pre-set trained treatment plan generation model, and return the recommended treatment plan to the hospital server or hospital staff client. The recommended treatment plan includes treatment mode, treatment intensity, treatment duration, and prescription validity period; The equipment status monitoring module is used to determine whether there is any abnormality or overuse of the diagnostic equipment based on the first equipment status information and pre-set alarm rules, and if so, send an alarm message to the hospital server or hospital staff client.

[0006] According to one embodiment of the present invention, the diagnosis and treatment plan recommendation module includes a data acquisition unit, a data processing unit, a model training unit, a diagnosis and treatment plan generation module and a diagnosis and treatment plan sending unit, wherein: a data collection unit, configured to collect training data, wherein the training data set includes historical disease symptom information obtained from a hospital server and diagnosis and treatment information corresponding to the historical disease symptom information; a data processing unit, configured to pre-process the training data to obtain a training data set; A model training unit is used to construct an initial diagnosis and treatment plan generation model, and use the training data set to train and optimize the initial diagnosis and treatment plan generation model to obtain a trained diagnosis and treatment plan generation model; a diagnosis and treatment plan generating unit, configured to generate a recommended diagnosis and treatment plan based on the disease symptom information and the trained diagnosis and treatment plan generating model; The diagnosis and treatment plan sending unit is used to send the recommended diagnosis and treatment plan to the hospital server or hospital staff client.

[0007] According to one embodiment of the present invention, the model training unit may further include: The model building subunit is used to build an initial diagnosis and treatment plan generation model; A data partitioning subunit, configured to divide the training data set into a training set, a validation set, and a test set; A model training subunit, configured to train the initial diagnosis and treatment plan generation model based on the training set to obtain a first diagnosis and treatment plan generation model; a model adjustment subunit, configured to adjust model parameters of the first diagnosis and treatment plan generation model based on the validation set to obtain a second diagnosis and treatment plan generation model; a model evaluation subunit, configured to determine whether the second diagnosis and treatment plan generation model reaches a preset model evaluation threshold based on the test set, and if so, set the second diagnosis and treatment plan generation model as a trained diagnosis and treatment plan generation model; and A model optimization subunit is used to adjust the model hyperparameters of the model generated by the second diagnosis and treatment plan.

[0008] According to one embodiment of the present invention, the system further comprises a hospital server, a hospital staff client and a patient client. Several hospital system servers are used to collect the first device status information of several diagnostic and treatment devices in the hospital and send it to the hospital server. The first device status information includes the device network status, device usage time, device key circuit monitoring and key component monitoring data.

[0009] The hospital staff client is used to prompt users to confirm or adjust the recommended treatment plan when receiving it, to obtain the best treatment plan, and to prompt users to confirm or adjust the status of the treatment equipment when receiving an alarm message.

[0010] The patient client is used to receive the best diagnosis and treatment plan and to feedback the diagnosis and treatment results to the cloud or hospital staff client.

[0011] According to one embodiment of the present invention, the system further includes several community system servers and several community personnel clients, wherein: The community system server is used to collect second device status information of diagnostic and treatment equipment in the community hospital and send it to the cloud, wherein the second device status information includes device network status, device usage time, device key circuit monitoring data, and key component monitoring data; The equipment status monitoring module is further configured to determine whether there is any abnormality or overuse of the diagnostic and treatment equipment in the community hospital based on the second equipment status information and pre-set alarm rules, and if so, send an alarm message to the community system server or the community personnel client; The community system server is also used to send the alarm information to the community personnel client when receiving the alarm information.

[0012] According to one embodiment of the present invention, in the case of including a community system server and a patient client, the training data set also includes the diagnosis and treatment results fed back by the patient client, the historical symptom information obtained from the community system server and the diagnosis and treatment information corresponding to the historical symptom information, as well as the publicly available historical symptom information and the diagnosis and treatment information corresponding to the historical symptom information.

[0013] According to one embodiment of the present invention, the hospital server communicates with the cloud or hospital staff client via a virtual private network interface.

[0014] According to a second aspect of the present invention, a method for recommending treatment plans and coordinating management of treatment equipment is provided, which is applied to any of the treatment plan recommendation and coordinating management systems described in the first aspect, the method comprising: The cloud obtains the medical symptom information of the patient from the hospital server through the data acquisition module, wherein the medical symptom information includes medical history information and symptom information; The cloud generates a recommended treatment plan based on the symptom information and a pre-set trained treatment plan generation model through a treatment plan recommendation module, and returns the recommended treatment plan to the hospital server or the doctor client. The recommended treatment plan includes treatment mode, treatment intensity, treatment duration, and prescription validity period. The hospital system server collects first device status information of the diagnosis and treatment equipment in the hospital and sends it to the hospital server, wherein the first device status information includes device network status, device usage time, device key circuit monitoring data, and key component monitoring data; The cloud uses the device status monitoring module to determine whether there is any abnormality or overuse of the diagnostic and treatment equipment based on the first device status information and pre-set alarm rules. If so, an alarm message is sent to the hospital server or hospital staff client; Upon receiving the recommended diagnosis and treatment plan or the warning information, the hospital server sends the recommended diagnosis and treatment plan or the warning information to the hospital staff client, and upon receiving the first device status information, sends the first device status information to the cloud; When the hospital staff client receives a recommended treatment plan, it prompts the user to confirm or adjust the recommended treatment plan to obtain the best treatment plan. When it receives an alarm message, it prompts the user to confirm or adjust the status of the treatment equipment.

[0015] According to a third aspect of the present invention, a computer device is provided, comprising a memory, a processor, and computer instructions stored in the memory, wherein the processor executes the computer instructions to implement the method according to the second aspect.

[0016] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, on which computer instructions are stored. When the instructions are executed by a processor, the steps of the method described in the second aspect are implemented.

[0017] According to a fifth aspect of the present invention, a computer program product is provided, comprising computer instructions, which implement the steps of the method according to the second aspect when executed by a processor.

[0018] It can be seen from the above technical solutions that in one or more embodiments of the present specification, the diagnosis and treatment plan recommendation and diagnosis and treatment equipment collaborative management system includes a data acquisition module for acquiring the medical symptom information of the patient, a diagnosis and treatment plan recommendation module for generating recommended diagnosis and treatment plans based on the medical symptom information, a hospital server that sends the medical symptom information of the patient to the cloud and can send the recommended diagnosis and treatment plan to the hospital staff client, and a hospital staff client that confirms or adjusts the recommended diagnosis and treatment plan; when a patient goes to the hospital for treatment, the hospital server can send the medical symptom information of the patient to the cloud, and the data acquisition module in the cloud receives the medical symptom information of the patient, so that the diagnosis and treatment plan recommendation module generates a model based on the medical symptom information and a pre-set trained diagnosis and treatment plan, generates a recommended diagnosis and treatment plan, and sends the recommended diagnosis and treatment plan to the hospital server. After receiving the recommended diagnosis and treatment plan, the hospital server sends it to the hospital staff client, and then the doctor can confirm or adjust the recommended diagnosis and treatment plan through his hospital staff client. The plan can be confirmed or adjusted to obtain the best treatment plan suitable for the patient, thereby greatly improving the patient's treatment efficiency; in addition, the treatment plan recommendation and treatment equipment collaborative management system also includes a hospital system server for collecting first device status information of the hospital's treatment equipment and sending it to the hospital server; the hospital server is also used to send the first device status information to the cloud; the cloud is also provided with a device status monitoring module for monitoring the abnormality or usage of each treatment equipment in the hospital. When the device status monitoring module confirms that the treatment equipment has an abnormality or excessive use, it will send an alarm message to the hospital server, and the hospital server will send the alarm message to the hospital personnel client; thereby, multiple treatment equipment can be collaboratively managed, and when the treatment equipment has an abnormality or excessive use, it will be notified in time through an alarm message, which can improve the utilization rate of each treatment equipment, avoid sudden failure of the treatment equipment, and reduce the operation and maintenance cost of the treatment equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 This is a structural diagram of a diagnosis and treatment plan recommendation and diagnosis and treatment equipment collaborative management system provided in Example 1 of the present application.

[0020] Figure 2 This is a block diagram of a diagnosis and treatment plan recommendation module provided in Example 1 of the present application.

[0021] Figure 3 This is a block diagram of a data processing unit provided in Example 1 of the present application.

[0022] Figure 4 This is a block diagram of a model training unit provided in Example 1 of the present application.

[0023] Figure 5This is a structural diagram of a diagnosis and treatment plan recommendation and diagnosis and treatment equipment collaborative management system provided in Example 2 of the present application.

[0024] Figure 6 This is a flow chart of a method for recommending treatment plans and collaborative management of treatment equipment provided in Example 3 of the present application.

[0025] Figure 7 This is a schematic structural diagram of a computer device provided in Example 3 of the present application. DETAILED DESCRIPTION

[0026] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements, unless otherwise indicated. The specific aspects described in the following exemplary embodiments are not intended to be exhaustive and should not be construed as representing all possible implementations consistent with one or more embodiments of this specification. Rather, they are merely examples of apparatuses and methods consistent with certain aspects of one or more embodiments of this specification, as detailed in the appended claims. It should be noted that in other embodiments, the steps of the corresponding method are not necessarily performed in the order shown and described in this specification. In some other embodiments, the method may include more or fewer steps than those described in this specification. In addition, a single step described in this specification may be broken down into multiple steps for description in other embodiments, and multiple steps described in this specification may be combined into a single step for description in other embodiments.

[0027] Next, one or more embodiments of this specification are further described: Specific embodiment one: Figure 1 This is a schematic diagram of a diagnosis and treatment plan recommendation and diagnosis and treatment equipment collaborative management system provided by an exemplary embodiment of the present application. Figure 1 As shown, the diagnosis and treatment plan recommendation and diagnosis and treatment equipment collaborative management system may include a cloud, a hospital system server, a hospital server, diagnosis and treatment equipment, and a hospital staff client; the hospital system server is deployed within the hospital system and connected to the hospital server and several diagnosis and treatment equipment; the hospital server communicates with the outside world through a virtual private network (VPN, Virtual Private Network), and the outside world includes the cloud and hospital staff clients outside the hospital. Among them, the cloud further includes a data acquisition module, a diagnosis and treatment plan recommendation module, and an equipment status monitoring module. Specifically: The data acquisition module is used to receive the medical symptom information of the patient sent by the hospital server, and the medical symptom information includes medical history information and symptom information.

[0028] In this embodiment, to facilitate better diagnosis and treatment of patients, the patient's medical history and symptom information are obtained. The medical history information is used to better confirm the patient's physical condition, and the symptom information is used for targeted treatment. The source of the medical history information can be the patient's previous visit records and medical files stored in the hospital server, including the patient's allergies and contraindications; the source of the symptom information can be the patient's disease test results during the current visit.

[0029] In this embodiment, the medical symptom information of the patient is obtained from the hospital server, and the hospital server communicates with the cloud via VPN. In addition, in order to protect the privacy of the patient or hospital staff, the hospital server will filter the data before communicating with the cloud and send the medical symptom information related to the disease.

[0030] Preferably, in this embodiment, the data acquisition module can also obtain the patient number of the patient and the doctor number of the doctor who treats the patient, so as to facilitate the subsequent diagnosis and treatment doctor to confirm or adjust the recommended treatment plan, and the patient to obtain his own treatment plan.

[0031] The diagnosis and treatment plan recommendation module is used to generate a recommended diagnosis and treatment plan based on the symptom information and a pre-set trained diagnosis and treatment plan generation model, and send the recommended diagnosis and treatment plan to the hospital server. The recommended diagnosis and treatment plan includes treatment mode, treatment intensity, treatment duration, and prescription validity period.

[0032] In this embodiment, if Figure 2 As shown, the treatment plan recommendation module includes a data acquisition unit, a data processing unit, a model training unit, a treatment plan generation unit, and a treatment plan sending unit. Specifically, the data acquisition unit, the data processing unit, and the model training unit train and optimize the treatment plan generation model and obtain the trained treatment plan generation model; the treatment plan generation unit and the treatment plan sending unit generate and send the recommended treatment plan.

[0033] The process of obtaining the trained diagnosis and treatment plan generation model includes: Collecting training data through the data collection unit, wherein the training data set includes historical disease symptom information obtained from a hospital server and diagnosis and treatment information corresponding to the historical disease symptom information; Preprocessing the training data by the data processing unit to obtain a training data set; An initial diagnosis and treatment plan generation model is constructed by the model training unit, and the initial diagnosis and treatment plan generation model is trained and optimized using the training data set to obtain a trained diagnosis and treatment plan generation model.

[0034] In this embodiment, the data acquisition unit can obtain historical symptom information and diagnosis and treatment information corresponding to the symptom information from several hospital servers. There is a specific correlation between the diagnosis and treatment information and the symptom information, that is, the diagnosis and treatment information is for a certain disease of a certain patient, and may include treatment mode, treatment intensity, treatment duration, prescription validity period, number of prescriptions, etc.; the data processing unit further pre-processes the training data collected by the data acquisition unit to obtain a unified training data set; the model training unit can then use the training data set pre-processed by the data processing unit to train and optimize the constructed initial diagnosis and treatment plan generation model, obtain the trained diagnosis and treatment plan generation model and deploy it in the cloud.

[0035] More specifically, in this embodiment, Figure 3 As shown, the data processing unit may further include: The data cleaning subunit is used to clean the training data and remove duplicate, missing and erroneous data; Data normalization subunit, used to standardize the training data; A data desensitization subunit, configured to remove sensitive data from the training data, wherein the sensitive data includes the patient's personal identity information; The feature engineering subunit is used to extract important features from the training data.

[0036] In this embodiment, the data cleaning is mainly to remove duplicate, missing and erroneous data; the standardization of training data is mainly to standardize data from different sources, and the different sources may refer to data from different hospital servers; the data desensitization is mainly to desensitize the patient's personal information to protect the patient's privacy; the feature engineering is mainly used to extract useful features (important features) from the training data.

[0037] In this embodiment, the training data may include EEG (electroencephalogram) features, fMRI (functional magnetic resonance imaging) features, stimulation parameters, physiological indicators, and derived features obtained by further processing, analyzing, and calculating the original EEG features, fMRI features, physiological indicators, etc., and then useful features (important features) are extracted from the above data respectively. For EEG features, the extraction method may be time domain feature extraction, frequency domain feature extraction, or time-frequency domain feature extraction. For fMRI features, the extraction method may be voxel-based feature extraction or functional connectivity-based feature extraction. In this embodiment, important features can be determined by the bold signal mean and variance of specific fMRI brain regions (M1, DLPFC). For stimulation parameters, corresponding parameter features are extracted according to the specific stimulation type and research purpose. In this embodiment, stimulation intensity (the ratio relative to the resting motor threshold RMT), treatment frequency, and pulse train duration can be extracted. For physiological indicators, corresponding features are extracted according to different types of physiological indicators. In this embodiment, MEP (motor evoked potential) amplitude, cortical excitability index, etc. can be extracted. Preferably, in this embodiment, after feature extraction, each modality can be independently modeled according to multimodal feature fusion and then weighted or voted for integration; then a standardization strategy is performed, and the specific standardization method can be to standardize according to the entire data or to standardize according to individual groups in order to reduce individual deviations, so as to improve the quality of the data and the performance of the model.

[0038] More specifically, in this embodiment, Figure 4 As shown, the model training unit may further include: The model building subunit is used to build an initial diagnosis and treatment plan generation model; A data partitioning subunit, configured to divide the training data set into a training set, a validation set, and a test set; A model training subunit, configured to train the initial diagnosis and treatment plan generation model based on the training set to obtain a first diagnosis and treatment plan generation model; a model adjustment subunit, configured to adjust model parameters of the first diagnosis and treatment plan generation model based on the validation set to obtain a second diagnosis and treatment plan generation model; a model evaluation subunit, configured to determine, based on the test set, whether the second diagnosis and treatment plan generation model reaches a preset model evaluation threshold, and if so, set the second diagnosis and treatment plan generation model as a trained diagnosis and treatment plan generation model; A model optimization subunit is used to adjust the model hyperparameters of the model generated by the second diagnosis and treatment plan.

[0039] In this embodiment, the model building subunit can build a machine learning model, a deep learning model, and a reinforcement learning model. During the construction process, grid search or Bayesian optimization and other technologies can be used to fine-tune hyperparameters to obtain the best initial diagnosis and treatment plan generation model; the data division subunit divides the training data set obtained after preprocessing into a training set, a validation set, and a test set according to a preset ratio. The preset ratio can be 7:2:1, 6:2:2, or 6:3:1. This specification does not further limit the specific ratio and can be adjusted according to actual needs; if there are multiple data divisions, the division ratio of each division is 7:2:1, 6:2:2, or 6:3:1. The examples may be the same or different; the training set is used for the model training subunit to train the constructed initial diagnosis and treatment plan generation model, and the validation set is used for the model adjustment subunit to verify and adjust the parameters of the trained first diagnosis and treatment plan generation model to prevent overfitting. Specifically, the model can be optimized using an optimization algorithm; the test set is used for the model evaluation subunit to test the adjusted second diagnosis and treatment plan generation model to evaluate whether its performance reaches a preset model evaluation threshold. The preset model evaluation threshold may include prediction accuracy, and the prediction accuracy can be evaluated from aspects such as efficacy prediction, side effect prediction and treatment plan recommendation.

[0040] It should be noted that in this embodiment, the diagnosis and treatment plan generation model will continuously optimize and learn. For example, a time threshold can be set. After reaching the time threshold, the model training unit will execute the training optimization steps of the above model again. This is to facilitate the discovery of new diagnosis and treatment plans from new clinical data, new research evidence, or actual feedback from patients during treatment. For example, the area of ​​abnormal brain function can be determined through imaging data, and the treatment process can be more accurately mapped to the target area. For example, based on genetic information, the patient's sensitivity to TMS treatment can be predicted, and transcranial magnetic stimulation or other stimulation methods can be recommended.

[0041] During the continuous training and optimization of the model, the model prediction accuracy can be evaluated from the aspects of efficacy prediction, side effect prediction and treatment plan recommendation. The specific evaluation indicators can be: In terms of efficacy prediction, for short-term efficacy (4 weeks): AUC is 0.75-0.85, sensitivity ≥70%, specificity ≥80%; for long-term efficacy (12 weeks): AUC is 0.70-0.80.

[0042] In terms of side effect prediction, for overall accuracy: AUC is 0.70-0.80, recall rate ≥85%, precision rate ≥75%; for identification of high-risk populations: the prediction accuracy of patients susceptible to epilepsy is ≥90%.

[0043] Regarding treatment plan recommendations, parameter recommendation accuracy is: stimulation intensity error ≤ 5% RMT, frequency matching ≥ 90%. Clinical adoption rate: physician adoption rate of recommended plans ≥ 70%.

[0044] The process of generating and sending the recommended diagnosis and treatment plan includes: Generate a recommended treatment plan based on the disease symptom information and the trained treatment plan generation model through the treatment plan generation unit, wherein the recommended treatment plan includes treatment mode, treatment intensity, treatment duration, and prescription validity period; The recommended diagnosis and treatment plan is returned to the hospital server or the hospital staff client through the diagnosis and treatment plan sending unit.

[0045] Continuing with the above example, after receiving the symptom information of the patient sent by the hospital server, the treatment plan generation unit inputs the symptom information into a pre-trained treatment plan generation model (i.e., the trained treatment plan generation model) to obtain a recommended treatment plan. The treatment plan sending unit then returns the recommended treatment plan to the hospital server, which is the hospital server that sent the symptom information. Specifically, when the data acquisition module obtains the symptom information of the patient, the patient number, and the doctor number of the doctor who treated the patient from the hospital server, it can record the source of the data, that is, establish an association information table between the symptom information, the patient number, the doctor number, and the hospital server. After receiving the recommended treatment plan, the treatment plan sending unit can determine the symptom information corresponding to the recommended treatment plan, and then return the recommended treatment plan, the patient number, and the doctor number to the hospital server associated with the symptom information according to the association information table, so that the hospital server can send the recommended treatment plan to the corresponding hospital staff client, or directly return it to the hospital staff client associated with the symptom information.

[0046] The hospital server is used to send the recommended diagnosis and treatment plan to the hospital staff client when receiving the recommended diagnosis and treatment plan.

[0047] Continuing with the above example, after the hospital server receives the recommended treatment plan, patient number and doctor number, it can send the recommended treatment plan and patient number to the corresponding hospital staff client based on the doctor number; and if the hospital staff client is located outside the hospital, the hospital server sends the recommended treatment plan through VPN.

[0048] The hospital staff client is used to prompt doctors to confirm or adjust the recommended treatment plan upon receiving it, so as to obtain the best treatment plan.

[0049] Continuing with the above example, after the hospital staff client receives the recommended treatment plan and patient number, it can evaluate the recommended treatment plan based on the patient's condition to confirm whether the recommended treatment plan is the best treatment plan for the patient. If so, the recommended treatment plan is confirmed through the hospital staff client and set as the best treatment plan; if not, the recommended treatment plan is adjusted through the hospital staff client to generate the best treatment plan.

[0050] Preferably, in this embodiment, the hospital staff client can also send the best treatment plan to the hospital server and / or cloud after the doctor confirms the best treatment plan, so as to facilitate subsequent continuous optimization of the trained treatment plan generation model.

[0051] It should be noted that, in some other feasible embodiments, a table of association information between the medical symptom information, patient number, and doctor number of the patient may also be established on the hospital server; In this case, the data acquisition module can only obtain the medical symptom information and patient number of the patient, and the cloud can establish an association information table between the medical symptom information, patient number and hospital server. Then, the diagnosis and treatment plan sending unit can only return the recommended diagnosis and treatment plan and patient number to the hospital server. In this case, the recommended treatment plan generated by the treatment plan generation unit may include the patient number; thus, the treatment plan sending unit may only return the recommended treatment plan to the hospital server, and the hospital server determines the corresponding doctor number based on the recommended treatment plan and the association information table established by it between the patient's medical symptom information, patient number and doctor number.

[0052] It should be noted that, in some other feasible embodiments, the recommended treatment plan generated by the treatment plan generation unit may include the patient number and the doctor number. After the hospital server receives the recommended treatment plan, it can obtain the corresponding doctor number from it.

[0053] Preferably, in this embodiment, the diagnosis and treatment plan recommendation and diagnosis and treatment equipment collaborative management system also includes a patient client, and the patient client is used to receive the best diagnosis and treatment plan and feedback the diagnosis and treatment results to the cloud or hospital staff client.

[0054] Continuing with the above example, after the treating doctor determines the best treatment plan through the hospital staff client, the patient's client will receive the best treatment plan, so that the patient can view the treatment plan, use the treatment plan, etc.; and the patient client allows the patient to provide timely feedback on the treatment results during the treatment process, so that the treatment plan can be adjusted in time according to the treatment results to ensure the treatment effect of the patient.

[0055] In this embodiment, when the diagnosis and treatment results fed back by the patient are sent to the cloud, the trained diagnosis and treatment plan generation model pre-set in the cloud can regenerate the recommended diagnosis and treatment plan based on the feedback diagnosis and treatment results, and then send the regenerated recommended diagnosis and treatment plan to the hospital staff client for the treating doctor to confirm whether the diagnosis and treatment plan of the patient needs to be changed.

[0056] The hospital system server is used to collect the first device status information of the diagnosis and treatment equipment in the hospital and send it to the hospital server. The first device status information includes the device network status, device usage time, device key circuit monitoring and key component monitoring data.

[0057] The hospital server is also used to send the first device status information to the cloud.

[0058] In this embodiment, the hospital server can send the first device status information to the cloud according to a preset sending rule. The preset sending rule can be to upload the first device status information within the preset time interval every time a preset time interval is reached. The preset time interval can be two days, one week, or two weeks, and can also be dynamically adjusted according to actual conditions. For example, if the preset time interval is one week, and the hospital server sends the first device status information at 8:00 on April 20, the next time the first device status information is sent will be one week from the current time point, that is, at 8:00 on April 27. The first device status information sent is all the first device status information received from 8:00 on April 20 to 8:00 on April 27. Of course, the hospital system server can set the sending rules in the same way as the hospital server to send the first device status information regularly.

[0059] The equipment status monitoring module is used to determine whether there are any abnormalities or excessive use of the diagnostic and treatment equipment based on the first equipment status information and pre-set alarm rules. If so, an alarm message is sent to the hospital server and / or hospital staff client; the alarm information includes diagnostic and treatment equipment information and specific alarm status. After receiving the alarm information, the hospital staff client can determine the specific diagnostic and treatment equipment and its existing problems based on the alarm information.

[0060] In this embodiment, the device status monitoring module primarily determines whether the diagnostic and treatment equipment has circuit abnormalities, operational abnormalities, or high-frequency use based on the first device status information. Circuit abnormalities include overvoltage, overcurrent, overtemperature, or performance degradation of key components. For example, the module monitors the ESR (equivalent series resistance) of the high-voltage capacitor of device A in real time through high-frequency current injection or AC impedance testing. If the deviation is greater than 5%, the high-voltage capacitor is deemed abnormal and an alarm message indicating the abnormality of the high-voltage capacitor of device A is sent. Operational abnormalities include abnormal shutdown, performance degradation, and network interruption. For example, if device B experiences overload protection or program lockup, an abnormal shutdown is determined and an alarm message indicating the abnormal shutdown of device B is sent. High frequency is defined as being used five or more times within two hours. If device C is detected to have been used six times within two hours, an alarm message indicating that device C is overused and that another device should be used is sent. It should be noted that in other embodiments, the criteria for determining circuit abnormalities can be set based on different diagnostic and treatment equipment, and the high frequency can be adaptively modified based on the number of diagnostic and treatment equipment, hospital size, and other factors.

[0061] In this embodiment, the diagnosis and treatment plan recommendation and diagnosis and treatment equipment collaborative management system also includes a hospital system server and an equipment status monitoring module for collaborative management of diagnosis and treatment equipment. The hospital system server is set up inside the hospital, and is connected to the diagnosis and treatment equipment inside the hospital and the hospital server through WIFI or optical fiber, etc., obtains the first device status information from each diagnosis and treatment device, and uploads the first device status information to the hospital server, so that the hospital server sends the first device status information to the cloud; after receiving the first device status information, the cloud-based device status monitoring module will judge the status of each diagnosis and treatment device based on the pre-set alarm rules. If it is determined that one or some diagnosis and treatment devices are abnormal or overused, an alarm message will be generated and sent to the hospital server, and then the hospital server will send the alarm message to the hospital staff client; the alarm message can also be sent directly to the hospital staff client.

[0062] In this embodiment, an association table between hospital staff clients and medical equipment can be established in the hospital server. After receiving the alarm information, the hospital server can send it to the corresponding hospital staff client based on the association table between the hospital staff client and medical equipment, so that the client can perform abnormal processing on the medical equipment. Specific embodiment two: Figure 5 This is a schematic diagram of a diagnosis and treatment plan recommendation and diagnosis and treatment equipment collaborative management system provided by an exemplary embodiment of the present application. Figure 5As shown, the diagnosis and treatment plan recommendation and diagnosis and treatment equipment collaborative management system may include a cloud, a hospital system server, a hospital server, diagnosis and treatment equipment, a hospital staff client, a community system server, a community staff client, and a patient client; the hospital system server is deployed in the hospital system, connected to the hospital server and the diagnosis and treatment equipment in the hospital; the hospital server communicates with the outside world through a virtual private network (VPN), and the outside world includes the cloud and the hospital staff client outside the hospital; the community system server is deployed in the community hospital system, connected to the diagnosis and treatment equipment in the community hospital and the cloud; wherein the cloud further includes a data acquisition module, a diagnosis and treatment plan recommendation module, and an equipment status monitoring module. Compared with the specific embodiment 1, the difference between this embodiment and the specific embodiment 1 is that after obtaining the best diagnosis and treatment plan, the diagnosis and treatment plan recommendation and diagnosis and treatment equipment system management system of this embodiment can also obtain the diagnosis and treatment information of the patients from the community hospital, and collaboratively manage the diagnosis and treatment equipment in the community hospital. Specifically, in this embodiment, the diagnosis and treatment plan recommendation and diagnosis and treatment equipment system management system includes: A data acquisition module is used to obtain the medical symptom information of the patient from the hospital server, wherein the medical symptom information includes medical history information and symptom information; A diagnosis and treatment plan recommendation module is used to generate a recommended diagnosis and treatment plan based on the symptom information and a pre-set trained diagnosis and treatment plan generation model, and return the recommended diagnosis and treatment plan to the hospital server or hospital staff client; A hospital system server is configured to collect first device status information of diagnostic and treatment equipment in the hospital and send the information to the hospital server, wherein the first device status information includes device network status, device usage time, device key circuit monitoring data, and key component monitoring data; An equipment status monitoring module is used to determine whether there is any abnormality or overuse of the diagnostic and treatment equipment based on the first equipment status information and pre-set alarm rules, and if so, send an alarm message to the hospital server or hospital staff client; The hospital server is configured to, upon receiving the recommended diagnosis and treatment plan or the warning information, send the recommended diagnosis and treatment plan or the warning information to the hospital personnel client, and upon receiving the first device status information, send the first device status information to the cloud; The hospital staff client is used to prompt users to confirm or adjust the recommended treatment plan when receiving it, to obtain the best treatment plan, and to prompt users to confirm or adjust the status of the diagnosis and treatment equipment when receiving an alarm message; The community system server is used to collect second device status information of diagnostic and treatment equipment in the community hospital and send it to the cloud, wherein the second device status information includes device network status, device usage time, device key circuit monitoring data, and key component monitoring data; The equipment status monitoring module is further configured to determine whether there is any abnormality or overuse of the diagnostic and treatment equipment in the community hospital based on the second equipment status information and pre-set alarm rules, and if so, send an alarm message to the community system server or the community personnel client; The community system server is also used to send the alarm information to the community personnel client when receiving the alarm information.

[0064] In this embodiment, the diagnosis and treatment plan recommendation module includes: a data collection unit, configured to collect training data, the training data set including historical medical symptom information and diagnosis and treatment information corresponding to the historical medical symptom information obtained from a hospital server, historical medical symptom information and diagnosis and treatment information corresponding to the historical medical symptom information obtained from a community system server, diagnosis and treatment results fed back by a patient client, and publicly available historical medical symptom information and diagnosis and treatment information corresponding to the historical medical symptom information; A data processing unit, configured to pre-process the training data to obtain a training data set; A model training unit is used to construct an initial diagnosis and treatment plan generation model, and use the training data set to train and optimize the initial diagnosis and treatment plan generation model to obtain a trained diagnosis and treatment plan generation model; a diagnosis and treatment plan generating unit, configured to generate a recommended diagnosis and treatment plan based on the disease symptom information and the trained diagnosis and treatment plan generating model; The diagnosis and treatment plan sending unit is used to send the recommended diagnosis and treatment plan to the hospital server or hospital staff client.

[0065] Based on the same application concept as the above-mentioned diagnosis and treatment plan recommendation and diagnosis and treatment equipment collaborative management system, this specification also provides a diagnosis and treatment plan recommendation and diagnosis and treatment equipment collaborative management method applied to the above-mentioned diagnosis and treatment plan recommendation and diagnosis and treatment equipment collaborative management system.

[0066] Furthermore, in this embodiment, the model training unit includes: The model building subunit is used to build an initial diagnosis and treatment plan generation model; A data partitioning subunit, configured to divide the training data set into a training set, a validation set, and a test set; A model training subunit, configured to train the initial diagnosis and treatment plan generation model based on the training set to obtain a first diagnosis and treatment plan generation model; a model adjustment subunit, configured to adjust model parameters of the first diagnosis and treatment plan generation model based on the validation set to obtain a second diagnosis and treatment plan generation model; a model evaluation subunit, configured to determine, based on the test set, whether the second diagnosis and treatment plan generation model reaches a preset model evaluation threshold, and if so, set the second diagnosis and treatment plan generation model as a trained diagnosis and treatment plan generation model; A model optimization subunit is used to adjust the model hyperparameters of the model generated by the second diagnosis and treatment plan.

[0067] In this embodiment, the model training unit is used to construct at least two different initial diagnosis and treatment plan generation models, and use the training data set to train and optimize each of the initial diagnosis and treatment plan generation models to obtain at least two different trained diagnosis and treatment plan generation models; the diagnosis and treatment plan generation unit includes: a diagnosis and treatment plan generation subunit, configured to generate a plurality of initial diagnosis and treatment plans based on the disease symptom information and each of the trained diagnosis and treatment plan generation models; The diagnosis and treatment plan fusion subunit is used to fuse the initial diagnosis and treatment plans to generate a recommended diagnosis and treatment plan.

[0068] In this embodiment, the model building subunit can construct a variety of machine learning models, deep learning models, and reinforcement learning models. Specifically, machine learning models such as support vector machine (SVM), random forest (RF), gradient boosting decision tree (GBDT), etc. can be used to predict the therapeutic efficacy and side effects of disease treatment plans; deep learning models include convolutional neural networks (CNN), recurrent neural networks (RNN), etc., which can process complex imaging and time series data, for example, analyzing fMRI (functional magnetic resonance imaging) data to identify brain network abnormalities related to the disease; reinforcement learning models can dynamically adjust the treatment plan based on the treatment results fed back by the patients to achieve personalized treatment. Different models have different advantages and functions. By constructing multiple models and using each model to recommend treatment plans, multiple initial treatment plans can be obtained. All initial treatment plans can then be integrated through the treatment plan fusion sub-unit to obtain recommended treatment plans, which can further improve the accuracy of the recommended treatment plans.

[0069] Specifically, in this embodiment, the process of integrating diagnosis and treatment plans may include the following steps: Standardize features across multiple initial diagnosis and treatment plans, including unified dimensions and temporal alignment; Identify parameter conflicts among multiple initial diagnosis and treatment plans, and determine the selection of conflicting parameters or trigger manual review based on preset priorities; Generate recommended diagnosis and treatment plans based on pre-set dynamic fusion algorithms.

[0070] In the above steps, parameter conflict identification refers to identifying whether conflicting values ​​are given for the same parameter in multiple initial treatment plans. Preset priorities can be set based on clinical safety guidelines. For example, if one initial treatment plan recommends high-frequency stimulation (≥5Hz) to improve depression, and another initial treatment plan recommends low-frequency stimulation (≤1Hz) due to the patient's history of epilepsy, the preset priority will determine that the epilepsy patient should use low-frequency stimulation.

[0071] In the above steps, the dynamic fusion algorithm includes a multi-objective optimization framework and knowledge-guided fusion. The multi-objective optimization framework aims to maximize the objective function: Maximize: α⋅Efficacy Score + β⋅Safety Score + γ⋅Patient Compliance Score. Specifically, the objective function includes the efficacy score, safety score, and patient compliance score. The weights of the three in the objective function are α, β, and γ, respectively, and are determined through SHAP value analysis or expert voting. Pareto frontier screening is then performed using algorithms such as NSGA-II to obtain a set of non-dominated solutions, from which the optimal trade-off solution is determined. Knowledge-guided fusion includes clinical rule embedding and evidence-level weighting. Clinical rule embedding encodes certain clinical treatment contraindications as rules in the form of logical constraints, such as contraindications for specific target areas in patients with skull defects. Evidence-level weighting involves assigning appropriate weights based on factors such as the quality and reliability of evidence when evaluating and integrating evidence from different sources. For example, a higher weight may be assigned to regimens based on RCT studies. Specifically, this can be achieved by assigning a weight of +0.3 to the NRETT guideline-recommended regimen.

[0072] Preferably, in some embodiments, after the recommended diagnosis and treatment plan is generated, the generated recommended diagnosis and treatment plan can also be verified, and the verified recommended diagnosis and treatment plan is sent to the hospital server or hospital staff client as the final recommended diagnosis and treatment plan.

[0073] In this embodiment, a community system server is provided in the community hospital, and the community system server can collect the second device status information of the diagnosis and treatment equipment in the community hospital, and can further send the second device status information to the cloud according to preset sending rules.

[0074] In this embodiment, other parts not specifically described can be referred to the description of the specific embodiment 1 and will not be repeated here. Specific embodiment three: Medical institutions at all levels are equipped with a wide variety of medical devices, such as transcranial magnetic stimulators (TMS). A transcranial magnetic stimulator (TMS) is a therapeutic device that uses pulsed magnetic fields to noninvasively regulate brain neural activity. It works by using the physical phenomenon of rapidly changing magnetic fields to induce electric fields in conductive media (such as brain tissue). The core principle of TMS is that the magnetic field penetrates the skull, inducing currents in cortical neurons and triggering neural depolarization. This device is widely used in the treatment of psychiatric disorders, neurorehabilitation, and brain science research.

[0076] In this embodiment, a transcranial magnetic stimulator is taken as an example to further illustrate a diagnosis and treatment plan recommendation and a diagnosis and treatment equipment collaborative management method provided by this embodiment.

[0077] Please refer to Figure 6 As shown, Figure 6 This is a flowchart of a method for recommending treatment plans and coordinating management of treatment equipment provided by an exemplary embodiment of the present application, including: Step 601: The cloud obtains the medical symptom information of the patient from the hospital server through the data acquisition module, wherein the medical symptom information includes medical history information and symptom information; In step 602, the cloud generates a recommended treatment plan based on the symptom information and a pre-set trained treatment plan generation model through a treatment plan recommendation module, and returns the recommended treatment plan to the hospital server or the doctor client; Step 603: The hospital system server collects first device status information of the diagnosis and treatment equipment in the hospital and sends it to the hospital server. The first device status information includes device network status, device usage time, device key circuit monitoring data, and key component monitoring data. In step 604, the cloud uses the device status monitoring module to determine whether there is abnormality or overuse of the diagnostic and treatment equipment based on the first device status information and pre-set alarm rules. If so, an alarm message is sent to the hospital server or hospital staff client; Step 605: Upon receiving the recommended diagnosis and treatment plan, the hospital server sends the recommended diagnosis and treatment plan to the client of the hospital staff; Step 6051: Upon receiving the alarm information, the hospital server sends the alarm information to the hospital staff client; Step 6052: Upon receiving the first device status information, the hospital server sends the first device status information to the cloud. Step 606: Upon receiving the recommended treatment plan, the hospital staff client prompts the user to confirm or adjust the recommended treatment plan to obtain the best treatment plan, and upon receiving an alarm message, prompts the user to confirm or adjust the status of the treatment equipment.

[0078] In this embodiment, before executing step 602, the following steps may be used but are not limited to obtain a trained diagnosis and treatment plan generation model: Collecting training data through the data collection unit, wherein the training data set includes historical disease symptom information obtained from a hospital server and diagnosis and treatment information corresponding to the historical disease symptom information; Preprocessing the training data by the data processing unit to obtain a training data set; An initial diagnosis and treatment plan generation model is constructed by the model training unit, and the initial diagnosis and treatment plan generation model is trained and optimized using the training data set to obtain a trained diagnosis and treatment plan generation model.

[0079] In this embodiment, the data acquisition unit can obtain the patient's clinical data, TMS treatment data, public data, patient questionnaires, etc. from hospital servers, community system servers, patient clients, medical staff clients, and public network platforms; wherein the clinical data mainly includes medical history, diagnostic information, imaging data, genetic information, previous treatment and efficacy, expert consensus and clinical guidelines, etc.; the TMS treatment data includes detailed TMS treatment parameters, prescription information and patient treatment response (efficacy, side effects, etc.); the public data includes integrated public TMS treatment data sets; wherein the patient questionnaire includes questions about contraindications for TMS treatment.

[0080] Specifically, in this embodiment, the training data set includes physiological function index data, functional imaging data, clinical behavior and scale data, and treatment parameter and response data; different types of data are used to train and optimize the model from different aspects. For example, For physiological indicator data, the motor threshold (RMT / AMT) is used to evaluate the excitability of the corticospinal tract and verify whether the model's prediction of stimulation intensity is consistent with the actual threshold; the motor evoked potential (MEP), including amplitude, latency, and area under the curve, is used to verify the model's ability to predict changes in cortical excitability; the central conduction time (CMCT) is used to calculate through cervical nerve root stimulation to verify the accuracy of the model's assessment of motor pathway integrity; and the cortical quiet period (CSP) is used to verify the model's prediction of intracortical inhibitory function.

[0081] For functional imaging data, task-based fMRI is used to validate the model's predictions about brain activation patterns during specific tasks (such as working memory). Structural MRI, including gray matter volume and white matter integrity (FA values), is used to validate the model's predictions about long-term efficacy. Currently, numerous studies have collected functional or structural MRI data from patients before TMS treatment. After treatment, these studies process and summarize the common features of pre-treatment MRI data from patients with significant therapeutic effects, using this data as a model to predict and identify patients suitable for TMS treatment, thereby avoiding ineffective treatment.

[0082] For clinical behavior and scale data, symptom scales include the Hamilton Depression Rating Scale (HAMD) and the Montreal Cognitive Assessment (MoCA), which are used to verify the consistency between the model's prediction of efficacy and clinical scores; side effect records include the incidence of adverse reactions such as headache and scalp discomfort, which are used to verify the accuracy of the side effect prediction model.

[0083] For treatment parameters and response data, stimulation parameters include frequency (Hz), intensity (%RMT), and pulse train duration, which are used to verify the rationality of the model's recommended parameters; the patient response curve includes the dynamic changes of MEP amplitude and CSP duration during treatment, which is used to verify the model's ability to predict individualized responses.

[0084] Preferably, in this embodiment, when executing step 602, the recommended treatment plan generated by the trained treatment plan generation model includes the optimal transcranial magnetic stimulation (TMS) treatment plan, including parameters such as stimulation site, frequency, intensity and pattern, to improve treatment effects and reduce side effects.

[0085] In this embodiment, when executing step 603, the first device status data collected includes: device network status, device usage time, device key circuit (pulse overvoltage monitoring, pulse number) monitoring, and key component (such as high-voltage capacitor ESR timing monitoring to determine whether its capacitance has decayed) monitoring data; the device status is uploaded to the cloud via the hospital server at regular intervals, and the device status monitoring module is used to predict the life of the device key data, and timely alarms are issued for abnormal data to remind relevant personnel to pay attention to the equipment operation status.

[0086] In this embodiment, the method further includes: In step 607, the community system server collects the second device status information of the diagnostic and treatment equipment in the community hospital and sends it to the cloud. The second device status information includes the device network status, device usage time, device key circuit monitoring and key component monitoring data.

[0087] In step 608, the cloud uses the device status monitoring module to determine whether there is any abnormality or overuse of the diagnostic and treatment equipment in the community hospital based on the second device status information and pre-set alarm rules. If so, an alarm message is sent to the community system server or the community personnel client; Step 6081: Upon receiving the alarm information, the community system server sends the alarm information to the community personnel client.

[0088] Step 609: The patient client receives the best diagnosis and treatment plan; In step 610, the patient client feeds back the diagnosis and treatment results to the cloud or the hospital staff client.

[0089] In this embodiment, the patient client receives the best diagnosis and treatment plan from the hospital staff client. In other embodiments, the patient client can also obtain the best diagnosis and treatment plan from the cloud or hospital server.

[0090] It should be noted that, in this embodiment, there is no timing requirement between step 601 and step 610. Step 607 can be executed synchronously with step 603 or in its entirety. Step 608 and step 604 can be executed synchronously. Step 601 can also be executed synchronously with step 603 and step 607. The feedback of diagnosis and treatment results in step 610 can be executed in its entirety.

[0091] It can be seen from one or more of the above embodiments that this specification provides a diagnosis and treatment plan recommendation and diagnosis and treatment equipment collaborative management system, including a data acquisition module for acquiring the medical symptom information of the patient, a diagnosis and treatment plan recommendation module for generating a recommended diagnosis and treatment plan based on the medical symptom information, a hospital server for sending the recommended diagnosis and treatment plan to the hospital staff client, and a hospital staff client for confirming or adjusting the recommended diagnosis and treatment plan; when a patient goes to the hospital for treatment, the hospital server can send the medical symptom information of the patient to the cloud, and the data acquisition module in the cloud receives the medical symptom information of the patient, so that the diagnosis and treatment plan recommendation module generates a recommended diagnosis and treatment plan based on the medical symptom information and a pre-set trained diagnosis and treatment plan generation model, and sends the recommended diagnosis and treatment plan to the hospital server. After receiving the recommended diagnosis and treatment plan, the hospital server sends it to the hospital staff client, and then the doctor can confirm or adjust the recommended diagnosis and treatment plan through his hospital staff client. The best diagnosis and treatment plan suitable for the patient is obtained, thereby greatly improving the patient's diagnosis and treatment efficiency; in addition, the diagnosis and treatment plan recommendation and diagnosis and treatment equipment collaborative management system also includes a hospital system server for collecting the first device status information of the diagnosis and treatment equipment in the hospital and sending it to the hospital server; the hospital server is also used to send the first device status information to the cloud; the cloud is also provided with a device status monitoring module for monitoring the abnormality or usage of each diagnosis and treatment equipment in the hospital. When the device status monitoring module confirms that the diagnosis and treatment equipment has an abnormality or excessive use, the hospital server will send an alarm message to the hospital staff client; thereby, multiple diagnosis and treatment equipment can be collaboratively managed, and when the diagnosis and treatment equipment has an abnormality or excessive use, it will be notified in time through an alarm message, which can improve the utilization rate of each diagnosis and treatment equipment, avoid sudden failure of the diagnosis and treatment equipment, and reduce the operation and maintenance costs of the diagnosis and treatment equipment.

[0092] Based on the same application concept as the above-mentioned method for recommending treatment plans and coordinating the management of treatment equipment, and corresponding to the example of the above-mentioned method for recommending treatment plans and coordinating the management of treatment equipment, this specification also provides an embodiment of a computer device.

[0093] Figure 7 This is a schematic diagram of a computer device provided by an exemplary embodiment of the present application. Figure 7, at the hardware level, the computer device includes a processor, an internal bus, a network interface, a memory, and a non-volatile memory, and of course may also include hardware required for other services. The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it, forming a diagnosis and treatment plan recommendation and diagnosis and treatment equipment collaborative management device at the logical level. One or more embodiments of this specification can be implemented based on software, such as the processor reading the corresponding diagnosis and treatment plan recommendation and diagnosis and treatment equipment collaborative management computer program from the non-volatile memory into the memory and then running it. Of course, in addition to software implementation methods, this application does not exclude other implementation methods, such as logic devices or a combination of software and hardware, etc., that is, the execution subject of the processing flow is not limited to each logical unit, but can also be hardware or logic devices. The systems, terminals, modules, or units described in the above embodiments may be implemented by computer chips or entities, or by products having certain functions. A typical implementation device is a computer, which may be in the form of a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email transceiver, game console, tablet computer, wearable device, or any combination of these devices. In a typical configuration, a computer includes one or more processors (CPU), input / output interfaces, network interfaces, and memory. Memory may include non-permanent storage in a computer-readable medium, in the form of random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium. Computer-readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic disk storage, quantum memory, graphene-based storage media or other magnetic storage devices, or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media such as modulated data signals and carrier waves. It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element. The foregoing description of this specification describes specific embodiments. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0094] The terms used in one or more embodiments of this specification are for the purpose of describing specific embodiments only and are not intended to limit one or more embodiments of this specification. The singular forms "a," "an," "the," and "the" used in one or more embodiments of this specification and the appended claims are also intended to include plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items. It should be understood that although the terms first, second, third, etc. may be used to describe various information in one or more embodiments of this specification, such information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of one or more embodiments of this specification, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when..." or "when..." or "in response to determining." The above description is merely a preferred embodiment of one or more embodiments of this specification and is not intended to limit one or more embodiments of this specification. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of one or more embodiments of this specification shall be included in the scope of protection of one or more embodiments of this specification.

Claims

1. A diagnosis and treatment plan recommendation and diagnosis and treatment equipment collaborative management system, characterized in that: The system includes a cloud and several hospital servers; wherein: The hospital server is configured to, upon receiving a recommended treatment plan or warning information, send the recommended treatment plan or warning information to a hospital personnel client, and upon receiving first device status information, send the first device status information to the cloud; The cloud includes: A data acquisition module is used to obtain the medical symptom information of the patient from the hospital server, wherein the medical symptom information includes medical history information and symptom information; a diagnosis and treatment plan recommendation module, configured to generate a recommended diagnosis and treatment plan based on the symptom information and a pre-set trained diagnosis and treatment plan generation model, and return the recommended diagnosis and treatment plan to the hospital server or hospital personnel client, wherein the recommended diagnosis and treatment plan includes treatment mode, treatment intensity, treatment duration, and prescription validity period; and, The equipment status monitoring module is used to determine whether there is any abnormality or overuse of the diagnostic equipment based on the first equipment status information and pre-set alarm rules, and if so, send an alarm message to the hospital server or hospital staff client.

2. The diagnosis and treatment plan recommendation and diagnosis and treatment equipment collaborative management system according to claim 1, characterized in that: The diagnosis and treatment plan recommendation module includes: a data collection unit, configured to collect training data, wherein the training data set includes historical disease symptom information obtained from a hospital server and diagnosis and treatment information corresponding to the historical disease symptom information; a data processing unit, configured to pre-process the training data to obtain a training data set; A model training unit is used to construct an initial diagnosis and treatment plan generation model, and use the training data set to train and optimize the initial diagnosis and treatment plan generation model to obtain a trained diagnosis and treatment plan generation model; a diagnosis and treatment plan generating unit, configured to generate a recommended diagnosis and treatment plan based on the disease symptom information and a trained diagnosis and treatment plan generating model; and The diagnosis and treatment plan sending unit is used to send the recommended diagnosis and treatment plan to the hospital server or hospital staff client.

3. The diagnosis and treatment plan recommendation and diagnosis and treatment equipment collaborative management system according to claim 2, characterized in that: The model training unit further includes: The model building subunit is used to build an initial diagnosis and treatment plan generation model; A data partitioning subunit, configured to divide the training data set into a training set, a validation set, and a test set; A model training subunit, configured to train the initial diagnosis and treatment plan generation model based on the training set to obtain a first diagnosis and treatment plan generation model; a model adjustment subunit, configured to adjust model parameters of the first diagnosis and treatment plan generation model based on the validation set to obtain a second diagnosis and treatment plan generation model; a model evaluation subunit, configured to determine whether the second diagnosis and treatment plan generation model reaches a preset model evaluation threshold based on the test set, and if so, set the second diagnosis and treatment plan generation model as a trained diagnosis and treatment plan generation model; and A model optimization subunit is used to adjust the model hyperparameters of the model generated by the second diagnosis and treatment plan.

4. The diagnosis and treatment plan recommendation and diagnosis and treatment equipment collaborative management system according to claim 3, characterized in that: The system further comprises: Several hospital system servers are used to collect first device status information of each of several diagnostic and treatment devices in the hospital and send it to the hospital server, wherein the first device status information includes device network status, device usage time, device key circuit monitoring data, and key component monitoring data; Several hospital staff clients are used to prompt users to confirm or adjust the recommended treatment plan to obtain the best treatment plan when receiving a recommended treatment plan, and to prompt users to confirm or adjust the status of the treatment equipment when receiving an alarm message; and The patient client is used to receive the best diagnosis and treatment plan and to feedback the diagnosis and treatment results to the cloud or hospital staff client.

5. The diagnosis and treatment plan recommendation and diagnosis and treatment equipment collaborative management system according to claim 4, characterized in that: The system also includes several community system servers and several community personnel clients, among which: The community system server is used to collect and send to the cloud the second device status information of a plurality of diagnostic and treatment devices in the community hospital, wherein the second device status information includes device network status, device usage time, device key circuit monitoring data, and key component monitoring data; The equipment status monitoring module is further configured to determine whether there is any abnormality or overuse of the diagnostic and treatment equipment in the community hospital based on the second equipment status information and pre-set alarm rules, and if so, send an alarm message to the community system server or the community personnel client; The community system server is also used to send the alarm information to the community staff client when receiving the alarm information; Among them, the training data set also includes the diagnosis and treatment results fed back by the patient client, the historical symptom information obtained from the community system server and the diagnosis and treatment information corresponding to the historical symptom information, as well as the public historical symptom information and the diagnosis and treatment information corresponding to the historical symptom information.

6. The diagnosis and treatment plan recommendation and diagnosis and treatment equipment collaborative management system according to any one of claims 1 to 5, characterized in that: The hospital server communicates with the cloud or hospital staff client through a virtual private network interface.

7. A method for recommending treatment plans and coordinating management of treatment equipment, applied to the treatment plan recommendation and coordinating management system according to any one of claims 1 to 6, characterized in that: The method comprises: The cloud obtains the medical symptom information of the patient from the hospital server through the data acquisition module, wherein the medical symptom information includes medical history information and symptom information; The cloud generates a recommended treatment plan based on symptom information and a pre-set trained treatment plan generation model through a treatment plan recommendation module, and returns the recommended treatment plan to the hospital server or the doctor client. The recommended treatment plan includes treatment mode, treatment intensity, treatment duration, and prescription validity period. The hospital system server collects first device status information of the diagnosis and treatment equipment in the hospital and sends it to the hospital server, wherein the first device status information includes device network status, device usage time, device key circuit monitoring data, and key component monitoring data; The cloud uses the device status monitoring module to determine whether there is any abnormality or overuse of the diagnostic and treatment equipment based on the first device status information and pre-set alarm rules. If so, an alarm message is sent to the hospital server or hospital staff client; Upon receiving the recommended diagnosis and treatment plan or the warning information, the hospital server sends the recommended diagnosis and treatment plan or the warning information to the hospital staff client, and upon receiving the first device status information, sends the first device status information to the cloud; When the hospital staff client receives a recommended treatment plan, it prompts the user to confirm or adjust the recommended treatment plan to obtain the best treatment plan. When it receives an alarm message, it prompts the user to confirm or adjust the status of the treatment equipment.

8. A computer device comprising a memory, a processor, and computer instructions stored in the memory, characterized in that: The processor executes the computer instructions to implement the steps of the method according to claim 7.

9. A computer-readable storage medium having computer instructions stored thereon, characterized in that: When the instruction is executed by a processor, the steps of the method according to claim 7 are implemented.

10. A computer program product comprising computer instructions, characterized in that When the computer instructions are executed by a processor, the steps of the method according to claim 7 are implemented.

Images