Prediction information processing system

Abstract

The invention relates to the field of information processing, and discloses a prediction information processing system, which comprises a server, a user terminal and a detection terminal, and is characterized in that the server receives detection information sent by the detection terminal, classifies and stores the detection information, and dynamically predicts corresponding risk event information according to the detection information; different message type templates are configured in the server according to different disposal schemes, the same event is subjected to field generation and message identification and indexing, messages can be quickly generated, patient information is finely processed, and the communication efficiency is improved while safety is guaranteed.

Description

Technical Field

[0001] This invention relates to the field of information processing, and in particular to a predictive information processing system. Background Technology

[0002] Metabolic acidosis refers to a type of acidosis caused by a decrease in the body's pH value due to metabolic factors. Metabolic acidosis is generally considered to be a process caused by an increase in weak acids or a decrease in the strong ion difference (SID). However, in practice, there are many causes of metabolic acidosis, leading to methods that use SID and weak acids to quantify it. There are also methods that use plasma base excess to identify metabolic acidosis, but both are indirect methods and lack sufficient accuracy in predicting future trends.

[0003] Acute metabolic acidosis can occur within a few days, making communication regarding its management crucial during this phase. Since family members cannot enter the nursing area during ICU care, it is essential to establish different levels of communication with family members or hospital teams based on the specific stage of the critical illness or buffer period. In practice, metabolic acidosis presents numerous risk factors and requires communication with different departments. Due to the intermittent nature of communication and the presence of non-attending physicians, ensuring the secure flow of patient information across different stakeholders and terminals, while simultaneously improving communication efficiency, becomes a pressing need. Summary of the Invention

[0004] To address one of the aforementioned problems, this invention provides a predictive information processing system. The system includes a server, user terminals, and detection terminals. The server receives detection information sent from the detection terminals, categorizes and stores the detection information, and dynamically predicts corresponding risk event information based on the detection information. Based on the risk event information, the server generates different message type template information for different patients and pushes it to the user terminals. The message content of different user terminals varies due to different permission configurations.

[0005] The server includes a trigger event database, a handling plan database, and a user terminal permission configuration database.

[0006] The trigger event database is used to store configurable trigger events, which correspond to preset conditions set by the management terminal for different patients.

[0007] The treatment plan database is used to store configurable treatment plans. Each treatment plan includes multiple commands with a standard format. The commands correspond to the triggering events and are used to retrieve patient data or trigger the sending of messages to user terminals. The user terminal permission configuration database is used to authorize the permission information of all user terminals registered in the system.

[0008] Preferably, the treatment plan database is configured with an API interface, and the server updates the treatment plans in the treatment plan database through the API interface.

[0009] The preferred detection information includes at least: PaO2, PaCO2, lactic acid, blood glucose, blood ketones, blood potassium, creatinine, and blood urea nitrogen.

[0010] Preferably, the server is configured with different message type templates according to different handling schemes, and the same triggered event subscribes to user terminals and adopts different message type templates according to the authorization control policy.

[0011] Preferably, the message type template is filled in by fields, and the server fills in the fields according to the pre-stored patient information and test information in the database.

[0012] Preferably, the management user terminal corresponding to the patient adds or deletes fields according to the permission configuration information, and fills in the reserved empty fields in the message type template. The filled information takes the patient ID information pushed by the message template as the subject, and the filled message content is used as the group's conversation message content.

[0013] Preferably, the server sorts the feedback information of the message type template and the content of the session message by number, using the patient ID and the timestamp of the feedback information as indexes.

[0014] Preferably, the user terminal corresponding to the administrator configures a disable flag for sensitive fill information or fields, and the disable flag information prohibits the forwarding of the aforementioned flag information.

[0015] Preferably, the message type template sets permission information for different message content in different fields. When the message is presented to the user terminal, different permission information is set according to different elements in the message page. Specifically, the permission information is to configure a disable flag for sensitive fill information or fields. The disable flag information prohibits the forwarding of the above flag information. When the user performs message copying and forwarding, only the combination of different fields available to the authorized user terminal is presented.

[0016] This invention discloses a predictive information processing system, which includes a server, a user terminal, and a detection terminal. The server receives detection information sent by the detection terminal, classifies and stores the detection information, and dynamically predicts corresponding risk event information based on the detection information. The server is configured with different message type templates according to different treatment plans. For the same event, the system uses a field-based generation and identification / indexing method to generate messages quickly and perform refined processing of patient information, thereby improving communication efficiency while ensuring safety. Attached Figure Description

[0017] The features and advantages of the invention will be more clearly understood by referring to the accompanying drawings, which are illustrative and should not be construed as limiting the invention in any way.

[0018] Figure 1 This is a system schematic diagram of the present invention;

[0019] Figure 2 This is a schematic diagram of the risk matching interface of the present invention. Detailed Implementation

[0020] Referring to the following description and accompanying drawings, these and other features and characteristics, operating methods, functions of related elements of the structure, combinations of parts, and economics of manufacture of the present invention can be better understood, wherein the description and accompanying drawings form part of the specification. However, it is clearly understood that the drawings are for illustrative and descriptive purposes only and are not intended to limit the scope of protection of the present invention. It is understood that the drawings are not drawn to scale. Various structural diagrams are used in this invention to illustrate various modifications according to embodiments of the present invention.

[0021] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0022] It should be noted that the " / " in this article means "or". For example, A / B can mean A or B. The "and / or" in this article is only a description of the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, and B exists alone.

[0023] It should be noted that, in order to clearly describe the technical solutions of the embodiments of this application, the terms "first" and "second" are used in the embodiments of this application to distinguish the same or similar items with essentially the same function or effect. Those skilled in the art will understand that the terms "first" and "second" do not limit the quantity or execution order. For example, first information and second information are used to distinguish different information, rather than to describe a specific order of information.

[0024] It should be noted that in the embodiments of the present invention, the terms "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of the present invention should not be construed as being more preferred or advantageous than other embodiments or design schemes. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0025] Example 1

[0026] like Figure 1 As shown, the present invention provides a predictive information processing system, the system comprising a server, a user terminal, and a detection terminal, wherein the server receives detection information sent by the detection terminal, classifies and stores the detection information, and dynamically predicts corresponding risk event information based on the detection information;

[0027] Further, it includes a trigger event database, a treatment plan database, and a user terminal permission configuration database; wherein, the trigger event database is used to store configurable trigger events; the trigger events correspond to preset conditions set by the administrator's user terminal for different patients, and in an optional manner, the preset condition is that the predicted risk of metabolic acid poisoning exceeds a preset value; for example, when multiple physiological parameter values ​​exceed the preset value, a risk prediction matching mechanism is triggered, and the server can match and call the corresponding treatment plan according to the predicted risk event information level.

[0028] The treatment plan database is used to store configurable treatment plans. Each application treatment plan includes one or more commands with a standard format. The commands can correspond to the triggering events and are used to retrieve patient information or trigger the sending of messages to the corresponding user terminals.

[0029] like Figure 2 As shown, the matching prediction mechanism employs a Long Short-Term Memory (LSTM) network based on historical medical record data. First, it collects historical data related to moderate metabolic acidosis, such as PaO2, PaCO2, lactate, blood glucose, blood ketones, blood potassium, creatinine, and blood urea nitrogen from different medical records, and formats this data as time-series data for processing using an LSTM network. By controlling the forget gate, input gate, and output gate, it captures long-term and short-term dependencies in the time-series data. During model training, by adjusting network weights and biases, the model learns the key features of moderate metabolic acidosis data. It inputs the detected patient medical record data to identify risk trends within a set time period, associates these risk trends with corresponding risk event information, and generates message type templates for different user terminals based on the corresponding risk event information. This risk event information can correspond to the risk value of complications such as nephrotic metabolic syndrome.

[0030] The user terminal permission configuration database is used to authorize permission information for all user terminals registered in the system. The handling plan is associated with the corresponding controlled user terminal; the controlled terminal corresponds to an electronic device with functions such as information presentation, processing, and feedback.

[0031] The treatment plan database is configured with an API interface, and the server updates the treatment plans in the database through the API interface.

[0032] For example, the server receives user patient information data sent by the testing terminal. The patient's test data results are transmitted through a set message type. The message includes basic patient information, such as name and gender, and sample information, such as sample code (barcode), tester, and test time. After receiving the message, the server responds via an ACK message segment. The server configures query message types. The query sample test information message type consists of a message header, query definition information, and query filtering information.

[0033] For example, after receiving a query message from a user terminal, the server system calls the corresponding mapper to perform a database query operation. After logical judgment, it returns a response message, which includes a message header, a message response body, query error information, and the returned query results.

[0034] The server establishes a communication connection with the user terminal. When the user terminal sends a new sample monitoring task according to the trigger type scheme, the server actively sends the sample detection task information. After the detection instrument communication client receives the sample detection task information, it returns a message response and begins to wait for the sample reagent to be tested. After the test is completed, the test results are uploaded through a preset message body.

[0035] Based on the user's physiological parameters, the server matches the feature template information in the system. When a predicted risk event occurs, it generates different message types based on the corresponding patient information and sends them to different user terminals. The message content of different user terminals varies due to different permission configurations.

[0036] For example, the server system configures different message type templates according to different handling schemes. For the same triggered event, the user terminal subscribes to different message type template information according to the authorization control policy in the administrator.

[0037] The message template uses a field-based filling method, meaning that patient notifications and communication information are modularized, while information that family members can be informed about is filled using a field module filling method to achieve standardization and improve communication efficiency. The server fills the field modules based on pre-stored patient and test information in the database. For example, the automatically filled permission field information, when sent to the user terminal, adapts to the terminal's display capabilities and is presented in different ways, such as displaying physiological parameter data graphically.

[0038] In the preferred approach, administrators can add or delete modular fields based on permission configuration information and fill information into reserved empty fields in the message template. The filled message uses the patient ID information pushed by the message template as the main body, and the filled message content is used as the session message content. That is, when the server pushes the corresponding message template message according to the risk warning configuration, the feedback and communication for this message are indexed by the patient ID information and the corresponding message timestamp, and are numbered and sorted accordingly.

[0039] Administrators can configure disabled flags for sensitive fill-in information or fields. Disabled flags are set for sensitive information in the message template, prohibiting the forwarding of such flagged information. The message type template sets permission information for different message content fields. When a message is presented to a user terminal, different permission information can be set according to different elements on the message page. When a user performs message copying and forwarding, only combinations of different fields available to the authorized user terminal are displayed.

[0040] In a preferred embodiment, based on different permissions, administrators can group the user terminals (i.e., medical user terminals) within the hospital, uniformly identifying them as message template types within the group. The message template type, triggered by an event, is pushed to the corresponding treatment plan via an attachment suggestion identifier on the server and then to the medical terminal. The medical terminal within the hospital triggers a reading request by clicking the attachment identifier. The server processes the attachment online and uses the attachment identifier request to trigger verification to ensure the security of the attachment information. The server determines the level of information in the treatment plan; if high-risk information is present, a lock and self-destruct operation is performed within a set period, preventing the medical terminal from caching it.

[0041] In an optional approach, when the server detects a risk event, it pushes a template message to pre-defined medical terminal users. The message includes an attachment identifier to extract the corresponding treatment plan, retrieves the follow-up processing information from the plan, and pushes it to the corresponding medical terminal. The follow-up processing information is sent as an attachment to the user terminal, which then obtains viewing access to the relevant document by clicking a link.

[0042] The user terminal sends a viewing request to the server in response to the viewing operation of the attachment. The viewing request carries the attachment identifier and the visitor identifier. To ensure security and forwarding, the server performs verification. For example, the attachment file can be generated as an image and a watermark with the visitor identifier can be added to the image file for easy traceability.

[0043] In the optional method, the server performs verification of the control policy. The server successively authenticates the target user terminal and further judges the access permissions of the target user terminal based on the message status in the access control policy and the access permissions of the target user terminal, thus ensuring the privacy of user information and improving user experience.

[0044] In an optional approach, when creating a message template, the administrator can simultaneously set an access control policy to control access permissions to the message. This access control policy can be a separate access control policy for the message sent in this instance, or it can be a global access control policy. The global access control policy is the access control policy set for all messages created and sent by the source user.

[0045] In an optional approach, a feedback control is set in the message template. Based on the user terminal association relationship preset in different push messages, when the feedback control is triggered, the login information of the user terminal is verified. If the verification is successful, a feedback message is triggered on the user terminal, and the feedback message is directly sent to the associated user terminal.

[0046] The message session uses the patient ID as the session identifier. When different user terminals send feedback messages, the server automatically extracts the association between the feedback message and the previously sent messages, and presents the corresponding message context with the closest association to the corresponding user terminal in parallel.

[0047] Based on the association, the user terminal can locate previous messages. For example, when the user terminal clicks on the thumbnail-displayed associated message, a location instruction is triggered. The location instruction locates the target message in the session by including the sequence number of the session message in the thumbnail-displayed associated message. In response to the location instruction, the server obtains the context message of the target message in its respective session based on the session identifier of the session to which the target message belongs and the sequence number of the target message in its respective session, and pushes it to the corresponding user terminal.

[0048] In a preferred embodiment, for session messages where the empty fields in the message body template are edited by the user terminal, the server adaptively matches the user-edited session message content with the permission settings in the template fields of the message body. When a sensitive or disabled field is detected, a prompt message is issued or a replacement is performed. For example, messages containing specific keywords such as "high-risk complications" or "expected survival" are not allowed to be shared; in this case, the corresponding information is replaced or hidden.

[0049] Example 2

[0050] This invention provides a computer storage medium storing computer program instructions for implementing the above-described method. This invention also provides a system including a memory and a processor, wherein the memory stores a computer program that is executed by the processor to implement the above-described method.

[0051] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk drive (HDD), or solid-state drive (SSD), etc.; the storage medium can also include combinations of the above types of memory.

[0052] As used herein, the terms “component,” “module,” “system,” etc., are intended to refer to a computer-related entity, which may be hardware, firmware, a combination of hardware and software, software, or running software. For example, a component may be, but is not limited to, a process running on a processor, a processor, an object, an executable file, a running thread, a program, and / or a computer. As an example, an application running on a computing device and the computing device itself can both be components. One or more components may reside in a running process and / or thread, and components may be located in a single computer and / or distributed among two or more computers. Furthermore, these components are capable of execution from various computer-readable media having various data structures thereon. These components may communicate locally and / or remotely via signals, such as based on one or more data packets (e.g., data from a component that interacts with a local system, another component in a distributed system, and / or signals that interact with other systems via a network such as the Internet).

[0053] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A prediction information processing system, characterized in that: The system includes a server, a user terminal and a detection terminal. The server receives detection information sent by the detection terminal, classifies and stores the detection information, and the server dynamically predicts corresponding risk event information based on the detection information. Generates different message type template information corresponding to the patient based on risk event information and pushes it to the user terminal. The message content of different user terminals varies due to different permission configurations; The server further includes a trigger event database, a treatment plan database, and a user terminal authority configuration database; the trigger event database is used to store configurable trigger events, and the trigger events correspond to preset conditions set by the administrator for different patients; The treatment plan database is used to store configurable treatment plans, each treatment plan includes multiple commands in a standard format, the commands correspond to the trigger events, and are used to retrieve patient data information or trigger the sending of messages to user terminals; the user terminal authority configuration database is used to authorize the authority information of all user terminals registered in the system.

2. The system according to claim 1, characterized in that: The treatment solution database is configured with an API interface, and the server updates and sets the treatment solutions in the treatment solution database through the API interface.

3. The system of claim 2, further characterized in that: The detection information at least includes: Pa O2, PaCO2, lactic acid, blood sugar, blood ketone, blood potassium, creatinine and urea nitrogen.

4. The system of claim 3, further characterized in that: Different message type templates are configured in the server according to different handling schemes, and different message type templates are used for user terminals subscribing to the same trigger event according to the authorization control policy.

5. The system of claim 4, further characterized in that: The message type template is filled in a field-by-field manner, and the server fills in the fields according to the pre-stored patient information and test information in the database.

6. The system of claim 5, further characterized in that: The management user terminal corresponding to the patient adds or deletes fields according to the authority configuration information, and fills in information in the reserved empty fields of the message type template. The filled information takes the patient ID information pushed by the message template as the subject, and uses the filled message content as the group's conversation message content.

7. The system of claim 6, further characterized in that: The server performs number sorting processing on the feedback information and session message content of the message type template, using the patient ID and the timestamp of the feedback information as indexes.

8. The system of claim 7, further characterized in that: The user terminal corresponding to the administrator configures a disabling flag for sensitive filling information or fields, and the disabling flag information prohibits the forwarding of the above-mentioned flag information.

9. The system of claim 8, further characterized in that: The message type template sets permission information for different message body contents by field. When the message is presented to the user terminal, different permission information is set according to different elements in the message page. The permission information specifically configures a disable flag for sensitive fill information or fields. The disable flag information prohibits the forwarding of the above-mentioned flag information. When the user executes message copy and forwarding, only combinations of different fields available to authorized user terminals are presented.

10. The system according to any one of claims 1 to 9, further characterized in that: The system is applied to the risk detection of metabolic acidosis.

Images