CN111627533B - Active monitoring and management system and method for hospital-wide adverse events - Google Patents
Active monitoring and management system and method for hospital-wide adverse events Download PDFInfo
- Publication number
- CN111627533B CN111627533B CN202010305217.9A CN202010305217A CN111627533B CN 111627533 B CN111627533 B CN 111627533B CN 202010305217 A CN202010305217 A CN 202010305217A CN 111627533 B CN111627533 B CN 111627533B
- Authority
- CN
- China
- Prior art keywords
- event
- data
- module
- adverse
- hospital
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/20—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H80/00—ICT specially adapted for facilitating communication between medical practitioners or patients, e.g. for collaborative diagnosis, therapy or health monitoring
Abstract
The invention relates to a hospital-wide adverse event active monitoring and management system which comprises a data acquisition module, a data storage module, a data cleaning module, a semantic analysis module, an event early warning module, an event intervention module and an automatic learning module, wherein the data acquisition module acquires specific data of a data acquisition source and stores the data in the data storage module; the data in the data storage module is processed step by step through the data cleaning module, the semantic analysis module and the event analysis module, an analysis result with adverse event hidden danger is extracted, and then the analysis result is displayed to an adverse event manager through the event intervention module and the event early warning module, so that real-time monitoring and management of the overall adverse events are realized; in addition, the algorithm models of the data cleaning module, the semantic analysis module and the event analysis module are automatically optimized through the automatic learning module according to the processing result of the adverse event, so that the intelligent degree of monitoring the adverse event is improved.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a hospital-wide adverse event active monitoring and management system and method.
Background
Medical adverse events, which refer to the risk events that a patient has received injury or is likely to receive injury during medical care, have a significant negative impact on hospitals, medical staff, patients, family members, and the entire society. As early as 2005, the World Health Organization (WHO) realized that adverse medical events were a global problem of global severity. In 2007, the national hospital association also graded adverse medical events, and thus attention was paid to adverse medical events.
The patient safety problem is serious and complex, and needs to be considered in multiple dimensions and deep levels, so that the construction of a comprehensive, standardized and continuously developed patient safety monitoring management system is an effective guarantee for realizing the patient safety. However, at present, the monitoring and management method for medical safety events mainly depends on manual work, that is, the medical adverse events mainly adopt a manual reporting mode, the manual reporting mode is easy to cause the problems of missing report and hidden report of a large number of medical adverse events, effective, objective, comprehensive and accurate data cannot be provided for medical quality management, and the monitoring intelligence degree for adverse events is low.
Disclosure of Invention
The invention provides a primary hospital-wide adverse event active monitoring and management system, aiming at solving the technical problems that effective, objective, comprehensive and accurate data cannot be provided for medical quality management and the intelligent degree of adverse event monitoring is low in the related technology.
The first aspect of the embodiment of the invention discloses a hospital-wide adverse event active monitoring and management system, which comprises a data acquisition module, a data storage module, a data cleaning module, a semantic analysis module, an event early warning module, an event intervention module and an automatic learning module, wherein:
the data acquisition module is used for acquiring specific data in a data acquisition source;
the data storage module is used for storing the specific data;
the data cleaning module is used for cleaning the specific data to obtain effective data;
the semantic analysis module is used for performing semantic analysis on the effective data to obtain a semantic analysis result and determining a target event according to the semantic analysis result;
the event analysis module is used for identifying the event type of the target event, analyzing the target event based on the event type, judging whether the target event has the potential hazard of an adverse event according to an analysis result, and if so, extracting the analysis result of the potential hazard of the adverse event from the analysis result;
the event early warning module is used for determining the event grade of the target event according to the analysis result of the adverse event hidden danger, comparing the event grade of the target event with a preset grade threshold value, and triggering the event intervention module if the event grade of the target event is equal to or higher than the grade threshold value;
the event intervention module is used for sending the analysis result of the adverse event hidden danger to a management terminal for an adverse event manager to check;
the automatic learning module is used for respectively optimizing a first algorithm model corresponding to the data cleaning module, a second algorithm model corresponding to the semantic analysis module and a third algorithm model corresponding to the event analysis module according to a processing result fed back by an adverse event manager and aiming at the target event.
As an optional implementation manner, in the first aspect of the embodiment of the present invention, the data collection source includes a HIS (Hospital Information System) database, an EMR (Electronic Medical Record) database, an LIS (Laboratory Information Management System) database, an HRP (Hospital Resource Planning) database, a CIS (Clinical Information System) database, and a Medical complaint and dispute Management System database.
As an optional implementation manner, in the first aspect of the embodiment of the present invention, the data cleansing module includes:
the screening submodule is used for screening the original data by utilizing a preset adverse event risk value condition to obtain first data which accords with the adverse event risk value condition;
the searching submodule is used for searching second data, the correlation degree of which with the first data is greater than a preset correlation degree threshold value, from the original data;
and the determining submodule is used for determining valid data according to the first data and the second data.
As an optional implementation manner, in the first aspect of the embodiment of the present invention, the manner in which the event analysis module identifies the event type of the target event specifically is:
extracting the event characteristics of the target event, and identifying the event type by using a pre-constructed third algorithm model; wherein the third algorithm model is a deep neural network model.
The second aspect of the embodiment of the invention discloses a hospital-wide adverse event active monitoring and management method, which is applied to a hospital-wide adverse event active monitoring and management system, wherein the system comprises a data cleaning module, a semantic analysis module and an event analysis module, wherein:
collecting specific data in a data collection source and storing the specific data;
cleaning the specific data to obtain effective data;
performing semantic analysis on the effective data to obtain a semantic analysis result, and determining a target event according to the semantic analysis result;
identifying the event type of the target event, analyzing the target event based on the event type, judging whether the target event has the adverse event hidden danger according to an analysis result, and if so, extracting the analysis result of the adverse event hidden danger from the analysis result;
determining the event grade of the target event according to the analysis result of the adverse event hidden danger, comparing the event grade of the target event with a preset grade threshold, and if the event grade of the target event is equal to or higher than the grade threshold, sending the analysis result of the adverse event hidden danger to a management terminal for an adverse event manager to check;
and respectively optimizing a first algorithm model corresponding to the data cleaning module, a second algorithm model corresponding to the semantic analysis module and a third algorithm model corresponding to the event analysis module according to a processing result fed back by an adverse event manager and aiming at the target event.
As an alternative implementation manner, in the second aspect of the embodiment of the present invention, the data collection source includes a HIS (Hospital Information System) database, an EMR (Electronic Medical Record) database, an LIS (Laboratory Information Management System) database, an HRP (Hospital Resource Planning) database, a CIS (Clinical Information System) database, and a Medical complaint dispute Management System database.
As an optional implementation manner, in the second aspect of the embodiment of the present invention, the performing a cleaning process on the specific data to obtain valid data includes:
screening the original data by using a preset adverse event risk value condition to obtain first data meeting the adverse event risk value condition;
searching second data of which the correlation degree with the first data is greater than a preset correlation degree threshold value from the original data;
and determining valid data according to the first data and the second data.
As an optional implementation manner, in the second aspect of the embodiment of the present invention, the identifying an event type of the target event includes:
extracting the event characteristics of the target event, and identifying the event type by using a pre-constructed third algorithm model; wherein the third algorithm model is a deep neural network model.
The technical scheme provided by the embodiment of the invention can have the following beneficial effects:
in the embodiment of the invention, the system comprises a data acquisition module, a data storage module, a data cleaning module, a semantic analysis module, an event early warning module, an event intervention module and an automatic learning module, wherein the data acquisition module acquires specific data in a data acquisition source, stores the specific data in the data storage module, processes the specific data in the data storage module step by step through the data cleaning module, the semantic analysis module and the event analysis module, extracts an analysis result with a potential hazard of an adverse event, and displays the analysis result to an adverse event manager through the event intervention module and the event early warning module, so that real-time monitoring and management of the adverse event of the whole hospital are realized; in addition, the algorithm models of the data cleaning module, the semantic analysis module and the event analysis module are automatically optimized through the automatic learning module according to the processing result of an adverse event manager, so that the aim of intelligently monitoring adverse events of a whole hospital more accurately is achieved, and the effects of continuously improving the medical safety management level of the hospital and effectively guaranteeing the safety of patients are achieved.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention, as claimed.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.
FIG. 1 is a block diagram illustrating an active monitoring and management system for hospital wide adverse events according to an exemplary embodiment;
FIG. 2 is a block diagram illustrating another active monitoring and management system for hospital wide adverse events according to an exemplary embodiment;
fig. 3 is a flowchart illustrating a method for controlling a smart campus hub based on internet of things according to an exemplary embodiment.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It is to be noted that the terms "comprises" and "comprising" and any variations thereof in the embodiments and drawings of the present invention are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus.
The embodiment of the invention discloses a hospital-wide adverse event active monitoring and management system, which can realize real-time monitoring and management of hospital-wide adverse events and improve the intelligent degree of adverse event monitoring through the mutual cooperation of all modules. The following are detailed below.
Example one
Referring to fig. 1, fig. 1 is a schematic structural diagram of a system for actively monitoring and managing hospital-wide adverse events according to an embodiment of the present invention. As shown in fig. 1, the active monitoring and management system for hospital-wide adverse events may include:
the data acquisition module 10 is configured to acquire specific data from a data acquisition source and provide the specific data to the data storage module 20.
As an alternative embodiment, the data collection source may include, but is not limited to, a HIS (Hospital Information System) database, an EMR (Electronic Medical Record) database, an LIS (Laboratory Information Management System) database, an HRP (Hospital Resource Planning) database, a CIS (Clinical Information System) database, and a Medical complaint dispute Management System database.
As another alternative, the data type of the data included in the data acquisition source may include, but is not limited to, text, image, text and image combination, and the like. The data acquisition module 10 may acquire specific data in a data acquisition source based on a web service technology, and particularly, when the data type of the data to be acquired (the specific data) is an image, the data acquisition module 10 may also acquire the specific data in the data acquisition source in a manner of directly reading a view, which is not limited in the embodiment of the present invention.
The data storage module 20 is configured to store specific data and trigger the data cleansing module 30 to perform a cleansing operation.
The data cleaning module 30 is configured to perform cleaning processing on the specific data to obtain valid data, and provide the valid data to the semantic analysis module 40.
The semantic analysis module 40 is configured to perform semantic analysis on the valid data to obtain a semantic analysis result, determine a target event according to the semantic analysis result, and provide the target event to the event analysis module 50.
In the embodiment of the present invention, the semantic analysis module 40 performs semantic analysis on the valid data to obtain a semantic analysis result, specifically, training pre-collected word segmentation materials with different classifiers to obtain an N-gram model, a CRF model and an HMM model, and performing sentence segmentation, word segmentation and part-of-speech tagging on the valid data according to the N-gram model, the CRF model and the HMM model to obtain a current preprocessed sentence; and determining the core key words according to the current preprocessing statement. The word segmentation material determination method specifically may be: constructing a data acquisition model according to preset adverse event template characteristics (for example, a falling adverse event, a falling event is uploaded as long as a patient falls in a hospital, a nurse records the situation in a nursing system registry, an adverse event system provides a data warehouse function, information about the falling of the patient in the nursing system registry is acquired from a nursing system by using an ETL (extract transform and load) tool, and the information is stored in an adverse event system data warehouse), and acquiring a large amount of system information data generated in the daily operation process of the hospital by using the data acquisition model; and analyzing and auditing the data acquired by the data acquisition model by adopting a manual mode according to the classification characteristics of the adverse events, and determining the data meeting the classification characteristics of the adverse events as word segmentation materials. Further, the semantic module 40 may determine a target event according to the core keyword and provide the target event to the event analysis module 50.
The event analysis module 50 is configured to identify an event type of the target event, analyze the target event based on the event type of the target event, determine whether the target event has an adverse event hidden danger according to an analysis result, if yes, extract an analysis result of the adverse event hidden danger from the analysis result, and provide the analysis result of the adverse event hidden danger to the event early warning module 60.
As an optional implementation manner, the manner of identifying the event type of the target event by the event analysis module 50 may specifically be:
extracting the event characteristics of the target event, and identifying the event type by using a pre-constructed third algorithm model; wherein the third algorithm model is a deep neural network model.
In the embodiment of the invention, event classification modeling can be carried out by utilizing event classification materials and data classification tools which are collected in advance to obtain the third algorithm model; the data classification tool includes, but is not limited to, using a two-string bigram as a feature unit, and using a feature dimension reduction method Chi-square, a weight calculation method tfidf, a classification model LibSVM or LibLinear, and the like, which is not limited in the embodiment of the present invention.
The event early warning module 60 is configured to determine an event level of the target event according to an analysis result of the adverse event hidden danger, compare the event level of the target event with a preset level threshold, and trigger the event intervention module 70 to start if the event level of the target event is equal to or higher than the level threshold.
As an alternative embodiment, if the event grade of the target event is lower than the preset grade threshold, the target event is stored in the medical event database.
In the embodiment of the invention, the system can classify different types of medical events (target events) into event grades in advance, and the level of the event grade is proportional to the importance (severity), namely the higher the event grade of the medical event is, the higher the importance of the medical event is, and conversely, the lower the event grade of the medical event is, the lower the importance of the medical event is. For example, the system may divide the event level of the medical event into an e-class and an e-class from high to low, the level threshold may be preset as a b-class, and then, if the event level of the target event is equal to or higher than the e-class, the event intervention module 70 is triggered to start; if the target event is lower than the second level, the target event can be stored in a medical event database, and the target events stored in the medical event database within a preset time length can be summarized into a list and sent to a management terminal for being checked by a manager.
The event intervention module 70 is configured to send an analysis result of the adverse event hidden danger to the management terminal for an adverse event manager to check.
In the embodiment of the present invention, the event intervention module 70 may be configured to send a notification message containing an analysis result of an adverse event hidden danger to a management terminal for an adverse event manager to check; the notification message is sent by a method including, but not limited to, mail, short message, WeChat message, enterprise WeChat message, and nailing notification message.
In the embodiment of the present invention, the event intervention module 70 may further trigger the automatic learning module 80 to start after sending the analysis result of the adverse event hidden danger to the management terminal for the adverse event manager to check.
The automatic learning module 80 is configured to optimize the first algorithm model corresponding to the data cleaning module 30, the second algorithm model corresponding to the semantic analysis module 40, and the third algorithm model corresponding to the event analysis module 50 according to the processing result fed back by the adverse event manager for the target event.
In an embodiment of the present invention, optionally, the automatic learning module 80 may be configured to obtain a processing result for the target event, which is fed back by an adverse event manager through a management terminal, and optimize the first algorithm model corresponding to the data cleaning module 30, the second algorithm model corresponding to the semantic analysis module 40, and the third algorithm model corresponding to the event analysis module 50 according to the processing result. The first algorithm model corresponding to the data cleaning module 30 may be used to clean data, and retain data meeting the adverse event risk value condition and data having a correlation with the data meeting the adverse event risk value condition, which is not limited in the embodiment of the present invention.
In this embodiment of the present invention, optionally, the management terminal may be a PC terminal or a mobile terminal, where the mobile terminal may specifically be a mobile phone, an intelligent tablet, and the like, and the embodiment of the present invention is not limited.
As can be seen, with the active monitoring and management system for hospital-wide adverse events described in fig. 1, the data acquisition module can acquire specific data in the data acquisition source, store the specific data in the data storage module, then the data cleaning module, the semantic analysis module and the event analysis module can perform step-by-step processing on the specific data in the data storage module, extract an analysis result with an adverse event hidden danger, and then the event intervention module and the event early warning module can display the analysis result to an adverse event manager, thereby implementing real-time monitoring and management of hospital-wide adverse events; in addition, the algorithm models of the data cleaning module, the semantic analysis module and the event analysis module are automatically optimized through the automatic learning module according to the processing result of an adverse event manager, so that the aim of intelligently monitoring adverse events of a whole hospital more accurately is achieved, and the effects of continuously improving the medical safety management level of the hospital and effectively guaranteeing the safety of patients are achieved.
Optionally, as shown in fig. 2, in the above-mentioned active monitoring and management system for hospital-wide adverse events, the data cleansing module 30 may include a screening sub-module 301, a searching sub-module 302, and a determining sub-module 303, where:
the screening submodule 301 is configured to screen specific data according to a preset adverse event risk value condition to obtain first data meeting the adverse event risk value condition, and provide the first data to the searching submodule 302 and the determining submodule 303.
The searching sub-module 302 is configured to search the specific data for second data with a correlation degree greater than a preset correlation degree threshold, and provide the second data to the determining sub-module 303.
The determining submodule 303 is configured to determine valid data according to the first data and the second data.
As can be seen, with the active monitoring and management system for hospital-wide adverse events described in fig. 2, the data acquisition module can acquire specific data in the data acquisition source, store the specific data in the data storage module, then the data cleaning module, the semantic analysis module and the event analysis module can process the specific data in the data storage module step by step, extract an analysis result with an adverse event hidden danger, and then the event intervention module and the event early warning module can display the analysis result to an adverse event manager, thereby realizing real-time monitoring and management of hospital-wide adverse events; in addition, the algorithm models of the data cleaning module, the semantic analysis module and the event analysis module are automatically optimized through the automatic learning module according to the processing result of an adverse event manager, so that the aim of intelligently monitoring adverse events of a whole hospital more accurately is achieved, and the effects of continuously improving the medical safety management level of the hospital and effectively guaranteeing the safety of patients are achieved.
The following are examples of the method of the present invention.
Fig. 3 is a flow diagram illustrating a method for proactive monitoring management of hospital wide adverse events according to an exemplary embodiment. As shown in fig. 3, the method is applied to a hospital-wide adverse event active monitoring management system, which may include a data cleansing module, a semantic analysis module, and an event analysis module, wherein:
As an alternative embodiment, the data collection source includes a HIS (Hospital Information System) database, an EMR (Electronic Medical Record) database, an LIS (Laboratory Information Management System) database, an HRP (Hospital Resource Planning) database, a CIS (Clinical Information System) database, and a Medical complaint dispute Management System database.
As an optional implementation, the cleaning processing of the specific data by the detection management system to obtain valid data may include:
screening specific data by using a preset adverse event risk value condition to obtain first data meeting the adverse event risk value condition; searching second data with the correlation degree larger than a preset correlation degree threshold value with the first data from the specific data; valid data is determined from the first data and the second data.
In this embodiment of the present invention, optionally, the identifying, by the monitoring management system, the event type of the target event may include:
extracting the event characteristics of the target event, and identifying the event type by using a pre-constructed third algorithm model; wherein the third algorithm model is a deep neural network model.
And step 206, the monitoring management system determines the event grade of the target event according to the analysis result of the adverse event hidden danger, compares the event grade of the target event with a preset grade threshold, and sends the analysis result of the adverse event hidden danger to the management terminal for the adverse event manager to check if the event grade of the target event is equal to or higher than the grade threshold.
In this embodiment of the present invention, optionally, if the event rank of the target event is lower than the preset rank threshold, the target event may be stored in the medical event database.
And step 207, respectively optimizing a first algorithm model corresponding to the data cleaning module, a second algorithm model corresponding to the semantic analysis module and a third algorithm model corresponding to the event analysis module by the monitoring management system according to the processing result fed back by the adverse event manager and aiming at the target event.
Therefore, by the active monitoring and management method for the hospital-wide adverse events described in fig. 3, real-time monitoring and management of the hospital-wide adverse events can be realized; in addition, the algorithm models of the data cleaning module, the semantic analysis module and the event analysis module can be automatically optimized according to the processing result of the adverse event manager, so that the purpose of intelligently monitoring the hospital-wide adverse events more accurately is achieved, the medical safety management level of the hospital is continuously improved, and the safety of patients is effectively guaranteed.
It will be understood that the invention is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the invention is limited only by the appended claims.
Claims (8)
1. The utility model provides a hospital-wide adverse event active monitoring management system which characterized in that, the system includes data acquisition module, data storage module, data washing module, semantic analysis module, event early warning module, event intervention module and automatic learning module, wherein:
the data acquisition module is used for acquiring specific data in a data acquisition source;
the data storage module is used for storing the specific data;
the data cleaning module is used for cleaning the specific data to obtain effective data;
the semantic analysis module is used for performing semantic analysis on the effective data to obtain a semantic analysis result and determining a target event according to the semantic analysis result;
the event analysis module is used for identifying the event type of the target event, analyzing the target event based on the event type, judging whether the target event has the potential hazard of an adverse event according to an analysis result, and if so, extracting the analysis result of the potential hazard of the adverse event from the analysis result;
the event early warning module is used for determining the event grade of the target event according to the analysis result of the adverse event hidden danger, comparing the event grade of the target event with a preset grade threshold value, and triggering the event intervention module if the event grade of the target event is equal to or higher than the grade threshold value;
the event intervention module is used for sending the analysis result of the adverse event hidden danger to a management terminal for an adverse event manager to check;
the automatic learning module is used for respectively optimizing a first algorithm model corresponding to the data cleaning module, a second algorithm model corresponding to the semantic analysis module and a third algorithm model corresponding to the event analysis module according to a processing result fed back by an adverse event manager and aiming at the target event.
2. The active hospital-wide adverse event monitoring and management system according to claim 1, wherein the data collection sources include a hospital information system database, an electronic medical record system database, a laboratory information management system database, a hospital operation management system database, a clinical information system database, and a medical complaint dispute management system database.
3. The active monitoring and management system for hospital adverse events according to claim 1 or 2, characterized in that the data cleansing module comprises:
the screening submodule is used for screening the specific data by utilizing a preset adverse event risk value condition to obtain first data which accords with the adverse event risk value condition;
the searching submodule is used for searching second data, the correlation degree of which with the first data is greater than a preset correlation degree threshold value, from the specific data;
and the determining submodule is used for determining valid data according to the first data and the second data.
4. The active monitoring and management system for all-hospital adverse events according to claim 1, wherein the event analysis module identifies the event type of the target event by:
extracting the event characteristics of the target event, and identifying the event type by using a pre-constructed third algorithm model; wherein the third algorithm model is a deep neural network model.
5. A hospital-wide adverse event active monitoring and management method is applied to a hospital-wide adverse event active monitoring and management system, the system comprises a data cleaning module, a semantic analysis module and an event analysis module, wherein:
collecting specific data in a data collection source and storing the specific data;
cleaning the specific data to obtain effective data;
performing semantic analysis on the effective data to obtain a semantic analysis result, and determining a target event according to the semantic analysis result;
identifying the event type of the target event, analyzing the target event based on the event type, judging whether the target event has the adverse event hidden danger according to an analysis result, and if so, extracting the analysis result of the adverse event hidden danger from the analysis result;
determining the event grade of the target event according to the analysis result of the adverse event hidden danger, comparing the event grade of the target event with a preset grade threshold, and if the event grade of the target event is equal to or higher than the grade threshold, sending the analysis result of the adverse event hidden danger to a management terminal for an adverse event manager to check;
and respectively optimizing a first algorithm model corresponding to the data cleaning module, a second algorithm model corresponding to the semantic analysis module and a third algorithm model corresponding to the event analysis module according to a processing result fed back by an adverse event manager and aiming at the target event.
6. The active hospital-wide adverse event monitoring and management method according to claim 5, wherein the data collection sources include a hospital information system database, an electronic medical record system database, a laboratory information management system database, a hospital operation management system database, a clinical information system database, and a medical complaint dispute management system database.
7. The active monitoring and management method for all-hospital adverse events according to claim 5 or 6, wherein the cleaning of the specific data to obtain valid data comprises:
screening the specific data by using a preset adverse event risk value condition to obtain first data meeting the adverse event risk value condition;
searching second data with the correlation degree larger than a preset correlation degree threshold value with the first data from the specific data;
and determining valid data according to the first data and the second data.
8. The active monitoring and management method for all-hospital adverse events according to claim 5, wherein the identifying the event type of the target event comprises:
extracting the event characteristics of the target event, and identifying the event type by using a pre-constructed third algorithm model; wherein the third algorithm model is a deep neural network model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010305217.9A CN111627533B (en) | 2020-04-17 | 2020-04-17 | Active monitoring and management system and method for hospital-wide adverse events |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010305217.9A CN111627533B (en) | 2020-04-17 | 2020-04-17 | Active monitoring and management system and method for hospital-wide adverse events |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111627533A CN111627533A (en) | 2020-09-04 |
| CN111627533B true CN111627533B (en) | 2022-02-25 |
Family
ID=72259724
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010305217.9A Active CN111627533B (en) | 2020-04-17 | 2020-04-17 | Active monitoring and management system and method for hospital-wide adverse events |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111627533B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113923239A (en) * | 2021-09-18 | 2022-01-11 | 苏州城之瞳安防智能科技有限公司 | System, method and medium applied to hospital security |
| CN116504367A (en) * | 2023-03-27 | 2023-07-28 | 华中科技大学同济医学院附属同济医院 | Hospital monitoring system processing method and device and hospital monitoring system |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7733224B2 (en) * | 2006-06-30 | 2010-06-08 | Bao Tran | Mesh network personal emergency response appliance |
| US20080082361A1 (en) * | 2006-10-02 | 2008-04-03 | Siemens Medical Solutions Usa, Inc. | Adverse Treatment Event Management System |
| WO2015009513A2 (en) * | 2013-07-18 | 2015-01-22 | Parkland Center For Clinical Innovation | Patient care surveillance system and method |
| CN105976291A (en) * | 2016-05-30 | 2016-09-28 | 镇江市第人民医院 | Hospital adverse event reporting processing system and hospital adverse event reporting processing method |
| CN108010576A (en) * | 2018-01-22 | 2018-05-08 | 山东省药品不良反应监测中心 | A key generation method and system for medical instrument failure classes adverse events report |
| EP3525213A1 (en) * | 2018-02-07 | 2019-08-14 | Koninklijke Philips N.V. | Identifying adverse events |
| CN110136843A (en) * | 2019-04-12 | 2019-08-16 | 佛山市第一人民医院（中山大学附属佛山医院） | Immediate reporting processing method and system for hospital transfusion adverse reaction event |
| CN110162522B (en) * | 2019-05-22 | 2023-04-07 | 武汉市公安局 | Distributed data search system and method |
-
2020
- 2020-04-17 CN CN202010305217.9A patent/CN111627533B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN111627533A (en) | 2020-09-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9990356B2 (en) | Device and method for analyzing reputation for objects by data mining | |
| US9531743B2 (en) | Data trend analysis | |
| CN104598367B (en) | Data center's event of failure management specialty and method | |
| US7451155B2 (en) | Statistical methods and apparatus for records management | |
| US9787838B1 (en) | System and method for analysis of interactions with a customer service center | |
| WO2013163114A1 (en) | Method and system for assessing risk | |
| CN111627533B (en) | Active monitoring and management system and method for hospital-wide adverse events | |
| KR20160060243A (en) | Apparatus and method for customer interaction service | |
| US20170300582A1 (en) | Event identification through analysis of social-media postings | |
| CN112751925B (en) | Pet dog management system and method based on big data and Internet of things and intelligent equipment | |
| CN105765612A (en) | System and method of determining missing interval change information in radiology reports | |
| CN110472057B (en) | Topic label generation method and device | |
| CN113077196A (en) | Dispute event processing method and device, readable storage medium and computer equipment | |
| CN114116872A (en) | Data processing method and device, electronic equipment and computer readable storage medium | |
| CN112016769B (en) | Method and device for managing relative person risk prediction and information recommendation | |
| WO2016203652A1 (en) | System related to data analysis, control method, control program, and recording medium therefor | |
| CN112631889A (en) | Portrayal method, device and equipment for application system and readable storage medium | |
| JP4838593B2 (en) | Trouble information analysis program, trouble information analysis apparatus, and trouble information analysis method | |
| CN111325422B (en) | Work order dispatching method and system | |
| CN110751092A (en) | Agricultural monitoring method and device based on Internet of things, storage medium and electronic equipment | |
| CN113657547A (en) | Public opinion monitoring method based on natural language processing model and related equipment thereof | |
| Farruggia et al. | Bayesian network based classification of mammography structured reports | |
| CN117094688B (en) | Digital control method and system for power supply station | |
| CN111324711B (en) | Post timeliness judging method and device and storage medium | |
| CN115222070B (en) | Data analysis method for intelligent fire-fighting quick positioning maintenance problem |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |