CN116013480A

CN116013480A - Intelligent medical information generation prompting method and system

Info

Publication number: CN116013480A
Application number: CN202211573803.7A
Authority: CN
Inventors: 匡明; 杨文林; 李刚; 张阁; 刘晓华
Original assignee: Hangzhou Kangsheng Health Consulting Co Ltd
Current assignee: Hangzhou Kangsheng Health Consulting Co Ltd
Priority date: 2022-12-08
Filing date: 2022-12-08
Publication date: 2023-04-25

Abstract

The invention discloses an intelligent medical information generation prompting method and system, wherein the method comprises the following steps: saving the target individual medical archive file into an archive data file by OCR; identifying the type of the archive data file, and sorting the archive data file into a structured data file according to the type, wherein the structured data file comprises a state data file and a process data file; and carrying out time sequence arrangement on the structured data file, selecting key medical indexes, modeling the key medical indexes, obtaining a key medical index model, generating process abnormal parameters, and determining process abnormal grades for prompting. The method of the invention can realize intelligent management and risk monitoring on the medical archive data, and prompt various abnormal conditions in time, so that a user can quickly find the medical archive data with risk.

Description

Intelligent medical information generation prompting method and system

Technical Field

The invention belongs to the technical field of computers, and particularly relates to an intelligent medical information generation prompting method and system.

Background

Along with the continuous popularization of private cloud and public cloud, the cloud management can be realized by the electronic medical record medical data. The electronic medical record medical data not only comprises medical record outpatient data, but also comprises medical archive files, which are usually the summary of a large number of medical measures, diagnosis results and detection results generated by a single body in a short time such as a hospitalization process, and have complete information content, but also have complicated information content, and play an important role in identifying whether medical accidents and medical information are forged or not.

How to intelligently manage massive medical archive data, realize risk monitoring, and timely prompt possible abnormal conditions for risks is a problem to be solved.

Disclosure of Invention

Aiming at the defects in the prior art, the invention provides an intelligent medical information generation prompting method, which comprises the following steps:

step S1, scanning all medical archive files of a target individual in an optical character recognition OCR mode, and storing each archive file into an archive data file;

step S2, identifying the types of the archive data files, wherein the types comprise a state data type and a process data type;

s3, arranging the archive data files into structured data files according to types, wherein the structured data files comprise state data files and process data files;

s4, carrying out time sequence arrangement on the structured data files, marking the state data files as first state data files or last state data files, and sequencing the process data files according to time information;

s5, selecting key medical indexes according to the head state data and the tail state data;

step S6, modeling the key medical indexes based on the process data file to obtain at least one key medical index model;

step S7, generating process abnormality parameters according to the key medical index model, and determining process abnormality levels according to the process abnormality parameters;

and S8, carrying out process abnormality prompt according to the process abnormality grade.

The step S4 of sorting the process data files according to time information specifically includes:

dividing the process data file into a nursing record data file and an inspection data file, acquiring time information of the nursing record data file and time information of the inspection data file, and taking the inspection data file which is closest to the time after the nursing record data file as a matched inspection data file of the nursing data file according to the time association degree;

and sorting the matching pairs of the nursing record data file and the checking data file according to the time sequence.

In the step S5, a key medical index is selected according to the first status data and the tail status data, specifically:

acquiring various medical indexes and corresponding detection values in the head state data file, acquiring various medical indexes and corresponding detection values in the tail state data file, comparing the change rates of the matched medical indexes in the head state data file and the tail head state data file, and taking the medical indexes with the change rates exceeding a preset threshold as key medical indexes;

when no medical index with the change rate exceeding the preset threshold value exists, the change rate of the medical indexes is ordered, and the medical indexes with the earlier ordering are selected as key medical indexes.

Step S6, modeling the key medical indexes according to the process data file, to obtain at least one key medical index model, which specifically includes:

and acquiring matched pairs of all nursing record data files and inspection data files which are sequenced according to time sequence, wherein the number of the matched pairs is n, extracting detection values corresponding to key medical indexes in the inspection data files in all matched pairs, extracting medical modes and corresponding dosage values related to the detection values in the nursing record data in all matched pairs, and generating a target individual sign feature model by utilizing the quantitative relation between the dosage values of the medical modes related to the detection values in the matched pairs and the detection values corresponding to the key medical indexes in the (n-1) pairs with the n pairs of matched pairs being ranked at the front in time.

Wherein the dose value V of the medical mode is related to the detected value _i As an independent variable, a detection value index corresponding to the key medical index is obtained _k As a dependent variable, a linear fitting model is built, specifically,

time-ordering the n pairs of matching pairs to the first (n-1) pair of matching pairs to the detected value-dependent medical dose value V _i Detection value index corresponding to key medical index _k As training data, m and V in a linear fitting model are determined _i Correlated index pair _k Influence factor a of (2) _i Generating the target individual sign feature model, wherein the target individual sign feature model specifically comprises the following steps:

wherein index _k For the detection value of the kth determined key medical index, V _i A is the dose value of the ith medical modality associated with the test value, a _i Is equal to V _i Correlated index pair _k Is the influence factor of m is the detection value index _k The number of medical modes, m<n-1。

In step S7, generating abnormal parameters of the process according to the key medical index model, specifically:

step s7_1, obtaining a dose value corresponding to the medical mode associated with the detected value in the last matching pair ordered by time

Wherein the method comprises the steps of/>

Indicating the detection value corresponding to the kth medical mode in the last matching pair;

step S7_2, inputting the target individual sign feature model to generate a predicted key medical index detection value

Wherein->

Indicating a predicted value for the detection value corresponding to the kth medical modality,

step S7-3, obtaining the detection value corresponding to the key medical index in the last matching pair according to time sequence

Wherein->

step S7_4, comparing the detection value of the predicted key medical index with the detection value corresponding to the key medical index in the matching pair, determining a process abnormality parameter Y,

/>

wherein determining a process anomaly level based on the process anomaly level parameter comprises:

and presetting process anomaly intervals of a process anomaly parameter Y, wherein each process anomaly interval corresponds to a process anomaly grade, and determining the corresponding process anomaly grade according to the process anomaly interval of the process anomaly parameter Y.

Comparing the first state data file with the first state change percentage of the detection values corresponding to the key medical indexes in the first matching pair according to time sequence;

comparing the tail state data file with the tail state change percentage of the detection value corresponding to the key medical index in the last matching pair according to time sequence;

and when the first state change percentage or the tail state change percentage exceeds a preset threshold value, carrying out state abnormality prompt.

Wherein, the process abnormality prompt and the state abnormality prompt are carried out in the medical information generation result.

The invention also provides an intelligent medical information generation prompt system which is characterized by comprising a processor and a memory, wherein the processor realizes the method by executing computer instructions in the memory.

Compared with the prior art, the method provided by the invention can be used for intelligently managing the medical archive data and realizing risk monitoring, and prompting various abnormal conditions in time, so that a user can quickly find the medical archive data with risk.

Drawings

The above, as well as additional purposes, features, and advantages of exemplary embodiments of the present disclosure will become readily apparent from the following detailed description when read in conjunction with the accompanying drawings. Several embodiments of the present disclosure are illustrated by way of example, and not by way of limitation, in the figures of the accompanying drawings and in which like reference numerals refer to similar or corresponding parts and in which:

fig. 1 is a flowchart illustrating an intelligent medical information generation prompting method according to an embodiment of the present invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail below with reference to the accompanying drawings, and it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.

The terminology used in the embodiments of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in this application and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise, the "plurality" generally includes at least two.

It should be understood that although the terms first, second, third, etc. may be used to describe … … in embodiments of the present invention, these … … should not be limited to these terms. These terms are only used to distinguish … …. For example, the first … … may also be referred to as the second … …, and similarly the second … … may also be referred to as the first … …, without departing from the scope of embodiments of the present invention.

It should be understood that the term "and/or" as used herein is merely one relationship describing the association of the associated objects, meaning that there may be three relationships, e.g., a and/or B, may represent: a exists alone, A and B exist together, and B exists alone. In addition, the character "/" herein generally indicates that the front and rear associated objects are an "or" relationship.

The words "if", as used herein, may be interpreted as "at … …" or "at … …" or "in response to a determination" or "in response to a detection", depending on the context. Similarly, the phrase "if determined" or "if detected (stated condition or event)" may be interpreted as "when determined" or "in response to determination" or "when detected (stated condition or event)" or "in response to detection (stated condition or event), depending on the context.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a product or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such product or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a commodity or device comprising such element.

Alternative embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

Embodiment 1,

As shown in fig. 1, the invention discloses an intelligent medical information generation prompting method, which comprises the following steps:

The OCR is an identification technology, and can realize scanning or photographing of the paper document through a scanning device or a camera which is in matched connection with the data processing equipment, and convert scanning and photographing results into character information readable by a computer for storage.

In one embodiment, the sorting the process data files in step S4 according to the time information specifically includes:

In this step, the character information file converted by OCR recognition is converted into a standard medical document, for example, a standardized xml document, which is stored in a standardized manner, and then sorted and classified according to the corresponding attribute information. The identification can be performed by means of regular analysis or by means of semantic identification in the prior art, and the semantic identification algorithm comprises conventional algorithms such as Bi-LSTLM, CRF and the like.

In an embodiment, in the step S5, a key medical index is selected according to the first status data and the tail status data, specifically:

The medical indexes corresponding to the detection values are established in a bottom medical knowledge base, any detection value can be searched for the medical index matched with the detection value, and reverse search can be realized. If the test value is a blood glucose related medical index, then the corresponding medical procedure may include metformin, gliclazide, insulin injection, etc., and the corresponding medical index may be found, matched by looking up the test value.

In one embodiment, step S6 is performed to model the key medical indicators according to the process data file, so as to obtain at least one key medical indicator model, which specifically is:

In one embodiment, the medical mode dose value V will be related to the sensed value _i As an independent variable, a detection value index corresponding to the key medical index is obtained _k As a dependent variable, a linear fitting model is built, specifically,

In one embodiment, in step S7, a process anomaly parameter is generated according to the key medical index model, specifically:

Wherein->

Wherein->

Wherein->

Indicating the detection value corresponding to the kth medical mode in the last matching pair; />

in one embodiment, determining a process anomaly level from the process anomaly level parameter comprises:

For a unit individual, the physical sign data of the individual is kept in a continuous state, for example, the response degree and the sensitivity degree of the individual to a certain medicine are basically kept stable, and by establishing the model, whether the archival data of the individual has a risk in a process or not can be judged by predicting whether the last process data has an excessive error or not, including the problems of abnormal modification, filling errors and the like.

In one embodiment, the first state data file is compared with the first state change percentage of the detection value corresponding to the key medical index in the first matching pair according to time sequence;

The actual reliability of the head-to-tail data can be determined to effectively measure by comparing the difference between the head-to-tail data and the process data.

In one embodiment, the process abnormality notification and the status abnormality notification are performed in the medical information generation result.

Example two

The invention also provides a device for sharing the memory by the safety container for executing the method, which comprises the following steps:

a template acquisition module for acquiring container templates of all client operating systems;

a set generation module for generating a set of container templates;

the template comparison module is used for comparing the container templates in the container template set in pairs to form a container template mapping table;

the importing module is used for importing the container template mapping table into the secure container shared memory when the first client operating system is started, wherein the secure container shared memory is a physical page cached by one or more secure container pages pointed by all the client operating systems;

and the mapping starting module is used for acquiring a corresponding starting file from the secure container by the second client operating system through the container template mapping table in the secure container shared memory and starting the second client operating system.

In one embodiment, the secure container is implemented in hardware.

Embodiment II,

The embodiment of the disclosure provides an intelligent medical information generation prompting system, which is characterized by comprising a processor and a memory, wherein the processor realizes the method by executing computer instructions in the memory.

It should be noted that the computer readable medium described in the present disclosure may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this disclosure, a computer-readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present disclosure, however, the computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with the computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, fiber optic cables, RF (radio frequency), and the like, or any suitable combination of the foregoing.

The computer readable medium may be contained in the electronic device; or may exist alone without being incorporated into the electronic device.

Computer program code for carrying out operations of the present disclosure may be written in one or more programming languages, including an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).

The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units involved in the embodiments of the present disclosure may be implemented by means of software, or may be implemented by means of hardware. Wherein the names of the units do not constitute a limitation of the units themselves in some cases.

The foregoing description of the preferred embodiments of the present invention has been presented for purposes of clarity and understanding, and is not intended to limit the invention to the particular embodiments disclosed, but is intended to cover all modifications, alternatives, and improvements within the spirit and scope of the invention as outlined by the appended claims.

Claims

1. An intelligent medical information generation prompting method comprises the following steps:

2. The method according to claim 1, wherein the process data files are ordered according to time information in step S4, specifically:

3. The method of claim 1, wherein the selecting key medical indicators according to the first status data and the tail status data in the step S5 is specifically:

4. The method according to any one of claims 1 or 2, wherein step S6 is performed to model the key medical indicators from the process data file to obtain at least one key medical indicator model, in particular:

and acquiring matched pairs of all nursing record data files and inspection data files which are sequenced according to time sequence, wherein the number of the matched pairs is n, extracting detection values corresponding to key medical indexes in the inspection data files in all matched pairs, extracting medical modes and corresponding dosage values related to the detection values in all the nursing record data in the matched pairs, and generating a target individual sign feature model by utilizing the quantitative relation between the dosage values of the medical modes related to the detection values in the matched pairs and the detection values corresponding to the key medical indexes in the (n-1) pairs with the n pairs of matched pairs being sequenced at the front time.

5. The method of claim 4, wherein the medical dosage value V is correlated with the sensed value _i As an independent variable, a detection value index corresponding to the key medical index is obtained _k As a dependent variable, a linear fitting model is built, specifically,

wherein index _k For the detection value of the kth determined key medical index, V _i A is the dose value of the ith medical modality associated with the test value, a _i Is equal to V _i Correlated index pair _k Is the influence factor of m is the detection value index _k The number of medical modes is related, and m is less than n-1.

6. The method according to claim 1 or 5, wherein generating process anomaly parameters according to the key medical indicator model in step S7 is specifically:

step s7_1, obtaining a dose value V corresponding to the medical mode associated with the detected value in the last matching pair ordered in time _i ^last I=1, 2..m, wherein

Wherein->

step S73, obtaining the detection values corresponding to the key medical indexes in the last matching pair according to the time sequence

Wherein->

7. the method of claim 6 wherein determining a process anomaly level based on the process anomaly level parameter comprises:

8. The method of claim 1, wherein,

comparing the first state data file with the first state change percentage of the detection value corresponding to the key medical index in the first matching pair according to time sequence;

9. The method as claimed in claim 1 or 8, wherein the process abnormality presentation and the status abnormality presentation are performed in the medical information generation result.

10. An intelligent medical information generation prompting system, comprising a processor, a memory, the processor implementing the method of claims 1-9 by executing computer instructions in the memory.