CN116013453A - Medical record writing improvement system based on artificial intelligence technology - Google Patents
Medical record writing improvement system based on artificial intelligence technology Download PDFInfo
- Publication number
- CN116013453A CN116013453A CN202310308665.8A CN202310308665A CN116013453A CN 116013453 A CN116013453 A CN 116013453A CN 202310308665 A CN202310308665 A CN 202310308665A CN 116013453 A CN116013453 A CN 116013453A
- Authority
- CN
- China
- Prior art keywords
- medical record
- record information
- standard
- central control
- control module
- 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.)
- Granted
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention relates to the technical field of data processing, in particular to a medical record writing improvement system based on an artificial intelligence technology, which comprises the following steps: the input module is used for receiving medical record information, wherein the medical record information comprises unstructured medical record information and pre-structured medical record information; the conversion module is connected with the input module and used for extracting characteristic parameters in unstructured medical record information and pre-structured medical record information; the storage module is used for storing the post-structured historical medical record information, the unstructured medical record information, the pre-structured medical record information and the hierarchy of the post-structured historical medical record information; the central control module is used for calculating the average identification duration of the historical medical record information according to the identification durations of the plurality of pieces of historical medical record information of the single department, and judging whether to update the hierarchical standard of the single department according to the average identification duration of the historical medical record information.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a medical record writing improvement system based on an artificial intelligence technology.
Background
The traditional medical record writing also has the problems of incomplete medical record writing, unclear medical record writing, more missing items and the like, and the medical record management is inconvenient, and the medical record writing system in the prior art also has the problem of lower writing efficiency.
Chinese patent publication No.: CN115458113a. The invention discloses a medical record generating method, a system, a storage medium and electronic equipment, wherein the medical record generating method comprises the following steps: constructing a medical knowledge graph and a text analysis model according to the existing clinical medical data; collecting doctor-patient dialogue text information, and carrying out structural processing on the doctor-patient dialogue text information by combining the medical knowledge graph to obtain structural medical record information; inputting the structured medical record information into a text analysis model to obtain an analysis result; when the analysis result comprises abnormal content, marking the abnormal content; and checking the analysis result and forming an electronic medical record. It can be seen that the medical record generating method, system, storage medium and electronic device have the following problems: and the problem of low medical record writing efficiency caused by the fact that the hierarchical standard of the post-structured medical record information of different departments is not updated timely.
Disclosure of Invention
Therefore, the invention provides an artificial intelligence technology-based medical record writing improvement system, which is used for solving the problem of low medical record writing efficiency caused by untimely updating of the hierarchical standards of post-structured medical record information of different departments in the prior art.
To achieve the above object, the present invention provides an improved medical record writing system based on artificial intelligence technology, comprising: the input module is used for receiving medical record information, wherein the medical record information comprises unstructured medical record information and pre-structured medical record information; the conversion module is connected with the input module and used for extracting characteristic parameters in unstructured medical record information and pre-structured medical record information and converting the characteristic parameters into corresponding positions in post-structured medical record information; the characteristic parameters comprise word characteristics and additional description characteristics with the distance from the word characteristics being lower than a preset standard; the storage module is respectively connected with the input module and the conversion module and used for storing the post-structured historical medical record information, the unstructured medical record information, the pre-structured medical record information and the hierarchy of the post-structured historical medical record information; the central control module is respectively connected with the input module, the conversion module and the storage module and is used for calculating the average identification duration of the historical medical record information according to the identification duration of a plurality of pieces of historical medical record information of a single department, judging whether to update the hierarchy standard of the single department according to the average identification duration of the historical medical record information, increasing the character distance standard of the additional description feature and the word feature to the corresponding value or adjusting the hierarchy standard of the disorder to the corresponding value according to the average identification duration of the disorder type and the average identification duration of the disorder detail, and respectively detecting the identification duration of the post-structured historical medical record information of each disorder in the department so as to adjust the hierarchy standard of the department to the corresponding value.
Further, for a single department, the central control module periodically counts the average layer number of post-structured medical record information of the single department in the storage module, and preliminarily determines the hierarchical standard of the single department according to the average layer number, and the central control module marks the department with the average layer number of post-structured medical record information of n as n-level departments, wherein n=1, 2,3,4 and 5.
Further, the central control module judges whether to update the hierarchy standard of the department by calculating the average identification time length T of a plurality of periods aiming at the post-structured historical medical record information in the single department, a first preset average identification time length T1 and a second preset average identification time length T2 are arranged in the central control module,
if T is less than or equal to T1, the central control module judges that the average identification duration of the post-structured historical medical record information of the single department meets the preset standard, and the hierarchy standard of the department is not updated;
if T1 is more than or equal to T2, the central control module preliminarily judges that the average identification duration of the post-structured historical medical record information of the single department does not meet the preset standard, and calculates the ratio of the average identification duration of the post-structured historical medical record information of the single department to the average identification duration of the disease type to the disease details so as to determine the specific reason that the average identification duration does not meet the preset standard;
if T is more than T2, the central control module preliminarily judges that the average identification duration of the post-structured historical medical record information of the single department does not meet the preset standard, and preliminarily marks the post-structured historical medical record information of each disease of the department as abnormal post-structured medical record information.
Further, the central control module calculates a condition type average identification time length duty ratio Ba and a condition detail average identification time length duty ratio Bb under a first preset condition, and sets Ba=Ta/T and Bb=Tb/T, wherein Ta is condition type average identification time length, and Tb is condition detail average identification time length;
the first preset condition is that T satisfies T1 < T2.
Further, the central control module judges whether to increase the character distance standard of the additional description feature and the word feature to the corresponding value according to the comparison result of the average identification time length duty ratio Ba of the disease type and the preset average time length duty ratio Ba0,
if Ba is less than or equal to Ba0, the central control module judges that the average identification duration of the disease types meets the preset standard;
if Ba > Ba0, the central control module determines that the average recognition duration ratio of the disease types does not meet the preset standard, calculates the difference Δba between Ba and Ba0, and increases the character distance standard of the additional description feature and the word feature to the corresponding value, and sets Δba=ba-Ba 0.
Further, the central control module increases the character distance standard L of the additional description feature and the word feature to corresponding values according to DeltaBa under a second preset condition, wherein the central control module is provided with a first preset disease type average identification time length accounting for a difference DeltaBa 1, a second preset disease type average identification time length accounting for a difference DeltaBa 2, a first preset distance standard adjustment coefficient alpha 1, a second preset distance standard adjustment coefficient alpha 2 and a third preset distance standard adjustment coefficient alpha 3, deltaBa 1 < DeltaBa2, 1 < alpha 2 < alpha 3 < 1.3,
if Δba is less than or equal to Δba1, the central control module uses α1 to increase the character distance standard of the additional description feature and the word feature to L ', and sets L' =l×α1;
if Δba1 < Δba2is less than or equal to Δba2, the central control module uses α2 to increase the character distance standard of the additional description feature and the word feature to L ', and sets L' =l×α2;
if Δba > - Δba2, the central control module uses α3 to increase the character distance standard of the additional description feature and the word feature to L ', and sets L' =l×α3;
the central control module re-counts the average identification duration of single disease types after finishing the adjustment of the character distance standard, and calculates the average identification duration ratio of the single disease types until the average identification duration ratio of the disease types of the structured historical medical record information after the department meets the preset standard;
the second preset condition is Ba > Ba0.
Further, the central control module adjusts the level standard for the symptoms to a corresponding value according to the average symptom detail identification time length proportion Bb, the central control module is provided with a first preset symptom detail average identification time length proportion Bb1 and a second preset symptom detail average identification time length proportion Bb2, wherein Bb1 is less than Bb2,
if Bb is less than or equal to Bb1, the central control module increases the level standard aiming at the symptoms by one level;
if Bb1 is more than Bb and less than Bb2, the central control module judges that the level standard for the symptoms accords with a preset standard;
if Bb is more than or equal to Bb2, the central control module reduces the level standard aiming at the symptoms by one step.
Further, for a single department, the central control module recalculates the number of post-structured case information for different levels in the single department upon completion of adjustment of the hierarchical criteria for the disorder to update the hierarchical criteria for the single department to corresponding values.
Further, the central control module respectively detects the identification time period ti of the post-structured medical record information of each disease in the single department under a third preset condition, i=1, 2,3, …, n is set, wherein n is the total number of the disease symptoms of the post-structured medical record information of the department stored in the central control module, for the ith disease, the central control module calculates the ratio Ci of the identification time period ti of the post-structured medical record information of the ith disease to the identification time period ti0 of the preset post-structured medical record information, judges whether the identification time period Ci of the post-structured medical record information of the ith disease accords with the preset standard according to Ci, sets Ci=ti/ti 0,
if Ci is less than or equal to 1, the central control module judges that the identification duration of the structured historical medical record information accords with a preset standard;
if Ci is more than 1, the central control module marks the post-structured medical record information of the ith disease as post-abnormal structured medical record information, and adjusts the hierarchical standard of the department to a corresponding value by counting the total number M of the post-abnormal structured medical record information in the department;
the third preset condition is that T is more than T2.
Further, the central control module adjusts the hierarchical standard of the department to a corresponding value according to the total number M of the abnormal structured medical record information under a fourth preset condition, the central control module is provided with the total number M1 of the first preset abnormal structured medical record information and the total number M2 of the second preset abnormal structured medical record information, wherein M1 is smaller than M2,
if M is less than or equal to M1, the central control module increases the hierarchy standard of the department by one level;
if M1 is more than M and less than or equal to M2, the central control module increases the hierarchy standard of the department by two stages;
if M is more than M2, the central control module increases the hierarchy standard of the department by three levels;
the fourth preset condition is Ci > 1.
Compared with the prior art, the system has the beneficial effects that by arranging the input module, the conversion module, the storage module and the central control module and judging whether to update the hierarchical standard of a single department according to the average identification duration of the historical medical record information, the influence of inaccuracy of updating the hierarchical standard of the single department on the writing efficiency of the medical record is reduced; by increasing the character distance standard of the additional description feature and the word feature to the corresponding value or adjusting the hierarchy standard of the disorder to the corresponding value according to the average recognition duration ratio of the disorder type and the average recognition duration ratio of the disorder detail, the influence on the writing efficiency of the medical record writing system due to inaccurate adjustment of the character distance standard of the additional description feature and the word feature and inaccurate adjustment of the disorder hierarchy standard is reduced; the identification duration of the post-structured historical medical record information for each disease in the department is detected respectively so as to adjust the hierarchical standard of the department to the corresponding value, the influence on the medical record writing efficiency due to inaccurate adjustment of the hierarchical standard of the department is reduced, and the improvement of the medical record writing efficiency is realized.
Furthermore, the system further realizes the improvement of the writing efficiency of the medical records by determining the hierarchy standard of the single department according to the average hierarchy level of the post-structured medical record information.
Further, the system judges whether to update the hierarchy standard of the department or not by calculating the average identification time length of the post-structured historical medical record information in the single department for a plurality of periods through the set first preset average identification time length and the second preset average identification time length, so that the influence of unreasonable setting of the department hierarchy standard reflected by the average identification time length of the post-structured historical medical record information on the medical record writing efficiency is reduced, and the improvement of the medical record writing efficiency is further realized.
Further, the system judges whether the character distance standard of the additional description feature and the word feature is increased to the corresponding value according to the comparison result of the average identification duration duty ratio Ba of the disease type and the preset average duration duty ratio Ba0, so that the influence on the medical record writing efficiency caused by inaccurate adjustment of the character distance standard is reduced, and the improvement of the medical record writing efficiency is further realized.
Further, the system of the invention sets the average recognition duration of the first preset disease type to the corresponding value, sets the average recognition duration of the second preset disease type to the corresponding value, sets the first preset distance standard adjustment coefficient, sets the second preset distance standard adjustment coefficient and sets the third preset distance standard adjustment coefficient, and increases the character distance standard of the additional description feature and the word feature to the corresponding value according to delta Ba, thereby reducing the influence on the writing efficiency due to inaccurate adjustment of the character distance standard and further realizing the improvement of the writing efficiency of medical records.
Furthermore, the system of the invention reduces the influence on the medical record writing efficiency due to inaccurate regulation of the hierarchical standard of the disease by regulating the hierarchical standard of the disease to the corresponding value according to the average disease detail identification time length proportion by setting the average first preset disease detail identification time length proportion and the average second preset disease detail identification time length proportion, and further realizes the improvement of the medical record writing efficiency.
Further, the system of the invention reduces the influence on the medical record writing efficiency due to inaccurate judgment on whether the identification of the rear structured medical record information accords with the preset standard by calculating the ratio Ci of the identification time ti of the rear structured medical record information of the ith disease to the identification time ti0 of the preset rear structured medical record information and judging whether the identification time ti of the rear structured medical record information of the ith disease accords with the preset standard according to Ci, thereby further realizing the improvement of the medical record writing efficiency.
Further, the system compares the total number of the abnormal structured medical record information with the preset value in the central control module under the fourth preset condition through the preset total number of the abnormal structured medical record information and the second preset total number of the abnormal structured medical record information so as to adjust the hierarchical standard of the department to the corresponding value, thereby reducing the influence on the medical record writing efficiency caused by inaccurate adjustment of the hierarchical standard of the department and further realizing the improvement of the medical record writing efficiency.
Drawings
FIG. 1 is a block diagram of the overall architecture of an improved system for medical record writing based on artificial intelligence technology in accordance with an embodiment of the present invention;
FIG. 2 is a block diagram of a transformation module of an improved system for medical record writing based on artificial intelligence technology according to an embodiment of the invention;
FIG. 3 is a block diagram of a connection between a conversion module and a central control module of the medical record writing improvement system based on the artificial intelligence technology according to the embodiment of the invention;
fig. 4 is a block diagram of a connection structure of a conversion module, a storage module, an input module and a central control module of the medical record writing improvement system based on the artificial intelligence technology according to the embodiment of the invention.
Detailed Description
In order that the objects and advantages of the invention will become more apparent, the invention will be further described with reference to the following examples; it should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are merely for explaining the technical principles of the present invention, and are not intended to limit the scope of the present invention.
It should be noted that, in the description of the present invention, terms such as "upper," "lower," "left," "right," "inner," "outer," and the like indicate directions or positional relationships based on the directions or positional relationships shown in the drawings, which are merely for convenience of description, and do not indicate or imply that the apparatus or elements must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as limiting the present invention.
Furthermore, it should be noted that, in the description of the present invention, unless explicitly specified and limited otherwise, the terms "mounted," "connected," and "connected" are to be construed broadly, and may be either fixedly connected, detachably connected, or integrally connected, for example; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the above terms in the present invention can be understood by those skilled in the art according to the specific circumstances.
Referring to fig. 1, fig. 2, fig. 3, and fig. 4, the overall structure block diagram, the structure block diagram of the conversion module, the structure block diagram of the connection between the conversion module and the central control module, and the connection structure block diagram of the connection between the conversion module, the storage module, the input module and the central control module of the medical record writing improvement system based on the artificial intelligence technology according to the embodiment of the invention are shown respectively; the invention relates to an artificial intelligence technology-based medical record writing improvement system, which comprises:
the input module is used for receiving medical record information, wherein the medical record information comprises unstructured medical record information and pre-structured medical record information;
the conversion module is connected with the input module and used for extracting characteristic parameters in unstructured medical record information and pre-structured medical record information and converting the characteristic parameters into corresponding positions in post-structured medical record information; the characteristic parameters comprise word characteristics and additional description characteristics with the distance from the word characteristics being lower than a preset standard;
the storage module is respectively connected with the input module and the conversion module and used for storing the post-structured historical medical record information, the unstructured medical record information, the pre-structured medical record information and the hierarchy of the post-structured historical medical record information;
the central control module is respectively connected with the input module, the conversion module and the storage module and is used for calculating the average identification duration of the historical medical record information according to the identification duration of a plurality of pieces of historical medical record information of a single department, judging whether to update the hierarchy standard of the single department according to the average identification duration of the historical medical record information, increasing the character distance standard of the additional description feature and the word feature to the corresponding value or adjusting the hierarchy standard of the disorder to the corresponding value according to the average identification duration of the disorder type and the average identification duration of the disorder detail, and respectively detecting the identification duration of the post-structured historical medical record information of each disorder in the department so as to adjust the hierarchy standard of the department to the corresponding value.
As a preferred embodiment of the present invention, the transformation module is operative to retrieve from the storage module an academic feature that most closely matches the word feature; and selecting a right temporal part to replace the right side of the head in the medical record, and determining the content of the corresponding position in the structured medical record information by combining with the additional description characteristic.
In a preferred embodiment of the present invention, the hierarchy corresponding to the post-structured medical record information stored in the storage module is, for example, that a rash exists in a certain portion of the post-structured medical record information, if the range and the color of the rash are recorded, the hierarchy of the post-structured medical record information corresponding to the rash is recorded as three levels, the post-structured medical record information itself is counted as one level, and the subsequent supplementary description is used as the newly added hierarchy.
According to the system, the input module, the conversion module, the storage module and the central control module are arranged, whether the hierarchy standard of a single department is updated is judged according to the average identification duration of the historical medical record information, and the influence of inaccuracy in updating of the hierarchy standard of the single department on the medical record writing efficiency is reduced; by increasing the character distance standard of the additional description feature and the word feature to the corresponding value or adjusting the hierarchy standard of the disorder to the corresponding value according to the average recognition duration ratio of the disorder type and the average recognition duration ratio of the disorder detail, the influence on the writing efficiency of the medical record writing system due to inaccurate adjustment of the character distance standard of the additional description feature and the word feature and inaccurate adjustment of the disorder hierarchy standard is reduced; the identification duration of the post-structured historical medical record information for each disease in the department is detected respectively so as to adjust the hierarchical standard of the department to the corresponding value, the influence on the medical record writing efficiency due to inaccurate adjustment of the hierarchical standard of the department is reduced, and the improvement of the medical record writing efficiency is realized.
Specifically, for a single department, the central control module periodically counts the average layer number of post-structured medical record information of the single department in the storage module, and performs preliminary determination on the hierarchical standard of the single department according to the average layer number, and the central control module marks the department with the average layer number of post-structured medical record information of n as n-level departments, wherein n=1, 2,3,4,5.
Furthermore, the system further realizes the improvement of the writing efficiency of the medical records by determining the hierarchy standard of the single department according to the average hierarchy level of the post-structured medical record information.
Referring to fig. 2, the central control module determines whether to update the hierarchical standard of the department by calculating the average identification time length T of a plurality of periods for the post-structured historical medical record information in a single department, wherein a first preset average identification time length T1 and a second preset average identification time length T2 are set in the central control module,
if T is less than or equal to T1, the central control module judges that the average identification duration of the post-structured historical medical record information of the single department meets the preset standard, and the hierarchy standard of the department is not updated;
if T1 is more than or equal to T2, the central control module preliminarily judges that the average identification duration of the post-structured historical medical record information of the single department does not meet the preset standard, and calculates the ratio of the average identification duration of the post-structured historical medical record information of the single department to the average identification duration of the disease type to the disease details so as to determine the specific reason that the average identification duration does not meet the preset standard;
if T is more than T2, the central control module preliminarily judges that the average identification duration of the post-structured historical medical record information of the single department does not meet the preset standard, and preliminarily marks the post-structured historical medical record information of each disease of the department as abnormal post-structured medical record information.
Further, the system judges whether to update the hierarchy standard of the department or not by calculating the average identification time length of the post-structured historical medical record information in the single department for a plurality of periods through the set first preset average identification time length and the second preset average identification time length, so that the influence of unreasonable setting of the department hierarchy standard reflected by the average identification time length of the post-structured historical medical record information on the medical record writing efficiency is reduced, and the improvement of the medical record writing efficiency is further realized.
Specifically, the central control module calculates a condition type average identification time length duty ratio Ba and a condition detail average identification time length duty ratio Bb under a first preset condition, and sets ba=ta/T, bb=tb/T, where Ta is the condition type average identification time length and Tb is the condition detail average identification time length;
the first preset condition is that T satisfies T1 < T2.
Referring to fig. 3, the central control module determines whether to increase the character distance standard of the additional description feature and the word feature to the corresponding values according to the comparison result of the average identification duration ratio Ba of the disease type and the preset average duration ratio Ba0,
if Ba is less than or equal to Ba0, the central control module judges that the average identification duration of the disease types meets the preset standard;
if Ba > Ba0, the central control module determines that the average recognition duration ratio of the disease types does not meet the preset standard, calculates the difference Δba between Ba and Ba0, and increases the character distance standard of the additional description feature and the word feature to the corresponding value, and sets Δba=ba-Ba 0.
Further, the system judges whether the character distance standard of the additional description feature and the word feature is increased to the corresponding value according to the comparison result of the average identification duration duty ratio Ba of the disease type and the preset average duration duty ratio Ba0, so that the influence on the medical record writing efficiency caused by inaccurate adjustment of the character distance standard is reduced, and the improvement of the medical record writing efficiency is further realized.
Specifically, the central control module increases the character distance standard L of the additional description feature and the word feature to corresponding values according to DeltaBa under a second preset condition, wherein the central control module is provided with a first preset disease type average identification time length accounting for a difference DeltaBa 1, a second preset disease type average identification time length accounting for a difference DeltaBa 2, a first preset distance standard adjustment coefficient alpha 1, a second preset distance standard adjustment coefficient alpha 2 and a third preset distance standard adjustment coefficient alpha 3, deltaBa 1 < DeltaBa2, 1 < alpha 2 < alpha 3 < 1.3,
if Δba is less than or equal to Δba1, the central control module uses α1 to increase the character distance standard of the additional description feature and the word feature to L ', and sets L' =l×α1;
if Δba1 < Δba2is less than or equal to Δba2, the central control module uses α2 to increase the character distance standard of the additional description feature and the word feature to L ', and sets L' =l×α2;
if Δba > - Δba2, the central control module uses α3 to increase the character distance standard of the additional description feature and the word feature to L ', and sets L' =l×α3;
the central control module re-counts the average identification duration of single disease types after finishing the adjustment of the character distance standard, and calculates the average identification duration ratio of the single disease types until the average identification duration ratio of the disease types of the structured historical medical record information after the department meets the preset standard;
the second preset condition is Ba > Ba0.
Further, the system of the invention sets the average recognition duration of the first preset disease type to the corresponding value, sets the average recognition duration of the second preset disease type to the corresponding value, sets the first preset distance standard adjustment coefficient, sets the second preset distance standard adjustment coefficient and sets the third preset distance standard adjustment coefficient, and increases the character distance standard of the additional description feature and the word feature to the corresponding value according to delta Ba, thereby reducing the influence on the writing efficiency due to inaccurate adjustment of the character distance standard and further realizing the improvement of the writing efficiency of medical records.
Referring to fig. 4, the central control module adjusts the level standard for the symptoms to a corresponding value according to the average symptom detail recognition duration ratio Bb, the central control module is provided with a first preset symptom detail average recognition duration ratio Bb1 and a second preset symptom detail average recognition duration ratio Bb2, wherein Bb1 is smaller than Bb2,
if Bb is less than or equal to Bb1, the central control module increases the level standard aiming at the symptoms by one level;
if Bb1 is more than Bb and less than Bb2, the central control module judges that the level standard for the symptoms accords with a preset standard;
if Bb is more than or equal to Bb2, the central control module reduces the level standard aiming at the symptoms by one step.
Furthermore, the system of the invention reduces the influence on the medical record writing efficiency due to inaccurate regulation of the hierarchical standard of the disease by regulating the hierarchical standard of the disease to the corresponding value according to the average disease detail identification time length proportion by setting the average first preset disease detail identification time length proportion and the average second preset disease detail identification time length proportion, and further realizes the improvement of the medical record writing efficiency.
In particular, for a single department, the central control module recalculates the number of post-structured case information for different levels in the single department upon completion of adjustment of the hierarchical criteria for the disorder to update the hierarchical criteria for the single department to corresponding values.
Specifically, the central control module respectively detects the identification time period ti of the post-structured medical record information of each disease in the single department under a third preset condition, i=1, 2,3, …, n is set, wherein n is the total number of the disease symptoms of the post-structured medical record information of the department stored in the central control module, for the ith disease, the central control module calculates the ratio Ci of the identification time period ti of the post-structured medical record information of the ith disease to the identification time period ti0 of the preset post-structured medical record information, determines whether the identification time period Ci of the post-structured medical record information of the ith disease accords with the preset standard according to Ci, sets Ci=ti/ti 0,
if Ci is less than or equal to 1, the central control module judges that the identification duration of the structured historical medical record information accords with a preset standard;
if Ci is more than 1, the central control module marks the post-structured medical record information of the ith disease as post-abnormal structured medical record information, and adjusts the hierarchical standard of the department to a corresponding value by counting the total number M of the post-abnormal structured medical record information in the department;
the third preset condition is that T is more than T2.
Further, the system of the invention reduces the influence on the medical record writing efficiency due to inaccurate judgment on whether the identification of the rear structured medical record information accords with the preset standard by calculating the ratio Ci of the identification time ti of the rear structured medical record information of the ith disease to the identification time ti0 of the preset rear structured medical record information and judging whether the identification time ti of the rear structured medical record information of the ith disease accords with the preset standard according to Ci, thereby further realizing the improvement of the medical record writing efficiency.
Specifically, the central control module adjusts the hierarchy standard of the department to a corresponding value according to the total number M of the structured medical record information after abnormality under a fourth preset condition, the central control module is provided with the total number M1 of the structured medical record information after abnormality and the total number M2 of the structured medical record information after abnormality, wherein M1 is less than M2,
if M is less than or equal to M1, the central control module increases the hierarchy standard of the department by one level;
if M1 is more than M and less than or equal to M2, the central control module increases the hierarchy standard of the department by two stages;
if M is more than M2, the central control module increases the hierarchy standard of the department by three levels;
the fourth preset condition is Ci > 1.
Further, the system compares the total number of the abnormal structured medical record information with the preset value in the central control module under the fourth preset condition through the preset total number of the abnormal structured medical record information and the second preset total number of the abnormal structured medical record information so as to adjust the hierarchical standard of the department to the corresponding value, thereby reducing the influence on the medical record writing efficiency caused by inaccurate adjustment of the hierarchical standard of the department and further realizing the improvement of the medical record writing efficiency.
Thus far, the technical solution of the present invention has been described in connection with the preferred embodiments shown in the drawings, but it is easily understood by those skilled in the art that the scope of protection of the present invention is not limited to these specific embodiments. Equivalent modifications and substitutions for related technical features may be made by those skilled in the art without departing from the principles of the present invention, and such modifications and substitutions will be within the scope of the present invention.
Claims (10)
1. An artificial intelligence technology-based medical record writing improvement system, comprising:
the input module is used for receiving medical record information, wherein the medical record information comprises unstructured medical record information and pre-structured medical record information;
the conversion module is connected with the input module and used for extracting characteristic parameters in unstructured medical record information and pre-structured medical record information and converting the characteristic parameters into corresponding positions in post-structured medical record information; the characteristic parameters comprise word characteristics and additional description characteristics with the distance from the word characteristics being lower than a preset standard;
the storage module is respectively connected with the input module and the conversion module and used for storing the post-structured historical medical record information, the unstructured medical record information, the pre-structured medical record information and the hierarchy of the post-structured historical medical record information;
the central control module is respectively connected with the input module, the conversion module and the storage module and is used for calculating the average identification duration of the historical medical record information according to the identification duration of a plurality of pieces of historical medical record information of a single department, judging whether to update the hierarchy standard of the single department according to the average identification duration of the historical medical record information, increasing the character distance standard of the additional description feature and the word feature to the corresponding value or adjusting the hierarchy standard of the disorder to the corresponding value according to the average identification duration of the disorder type and the average identification duration of the disorder detail, and respectively detecting the identification duration of the post-structured historical medical record information of each disorder in the department so as to adjust the hierarchy standard of the department to the corresponding value.
2. The system of claim 1, wherein for a single department, the central control module periodically counts the average number of layers of post-structured medical record information for the single department in the storage module, and performs preliminary determination on the hierarchical standard of the single department according to the average number of layers, and the central control module marks the department with the average number of layers of post-structured medical record information as n-level departments, where n=1, 2,3,4,5.
3. The medical record writing improvement system based on the artificial intelligence technology according to claim 2, wherein the central control module determines whether to update the hierarchy standard of the department by calculating the average identification time length T of a plurality of periods for the post-structured historical medical record information in the single department, the central control module is provided with a first preset average identification time length T1 and a second preset average identification time length T2,
if T is less than or equal to T1, the central control module judges that the average identification duration of the post-structured historical medical record information of the single department meets the preset standard, and the hierarchy standard of the department is not updated;
if T1 is more than or equal to T2, the central control module preliminarily judges that the average identification duration of the post-structured historical medical record information of the single department does not meet the preset standard, and calculates the ratio of the average identification duration of the post-structured historical medical record information of the single department to the average identification duration of the disease type to the disease details so as to determine the specific reason that the average identification duration does not meet the preset standard;
if T is more than T2, the central control module preliminarily judges that the average identification duration of the post-structured historical medical record information of the single department does not meet the preset standard, and preliminarily marks the post-structured historical medical record information of each disease of the department as abnormal post-structured medical record information.
4. The medical record writing improvement system based on artificial intelligence technology according to claim 3, wherein the central control module calculates a condition type average identification duration duty ratio Ba and a condition detail average identification duration duty ratio Bb under a first preset condition, and sets ba=ta/T, bb=tb/T, where Ta is a condition type average identification duration and Tb is a condition detail average identification duration;
the first preset condition is that T satisfies T1 < T2.
5. The medical record writing improvement system based on the artificial intelligence technology according to claim 4, wherein the central control module determines whether to increase the character distance standard of the additional description feature and the word feature to the corresponding values according to the comparison result of the average identification time period duty ratio Ba of the disease type and the preset average time period duty ratio Ba0,
if Ba is less than or equal to Ba0, the central control module judges that the average identification duration of the disease types meets the preset standard;
if Ba > Ba0, the central control module determines that the average recognition duration ratio of the disease types does not meet the preset standard, calculates the difference Δba between Ba and Ba0, and increases the character distance standard of the additional description feature and the word feature to the corresponding value, and sets Δba=ba-Ba 0.
6. The medical record writing improvement system based on artificial intelligence technology according to claim 5, wherein the central control module increases the character distance standard L of the additional description feature and the word feature to the corresponding value according to DeltaBa under the second preset condition, wherein the central control module is provided with a first preset disease type average recognition duration occupying ratio difference DeltaBa 1, a second preset disease type average recognition duration occupying ratio difference DeltaBa 2, a first preset distance standard adjustment coefficient alpha 1, a second preset distance standard adjustment coefficient alpha 2 and a third preset distance standard adjustment coefficient alpha 3, wherein DeltaBa 1 < DeltaBa2, 1 < alpha 2 < alpha 3 < 1.3,
if Δba is less than or equal to Δba1, the central control module uses α1 to increase the character distance standard of the additional description feature and the word feature to L ', and sets L' =l×α1;
if Δba1 < Δba2is less than or equal to Δba2, the central control module uses α2 to increase the character distance standard of the additional description feature and the word feature to L ', and sets L' =l×α2;
if Δba > - Δba2, the central control module uses α3 to increase the character distance standard of the additional description feature and the word feature to L ', and sets L' =l×α3;
the central control module re-counts the average identification duration of single disease types after finishing the adjustment of the character distance standard, and calculates the average identification duration ratio of the single disease types until the average identification duration ratio of the disease types of the structured historical medical record information after the department meets the preset standard;
the second preset condition is Ba > Ba0.
7. The medical record writing improvement system based on the artificial intelligence technology according to claim 6, wherein the central control module adjusts the level standard for the symptoms to the corresponding value according to the average symptom detail identification time period Bb, the central control module is provided with a first preset symptom detail average identification time period Bb1 and a second preset symptom detail average identification time period Bb2, wherein Bb1 is less than Bb2,
if Bb is less than or equal to Bb1, the central control module increases the level standard aiming at the symptoms by one level;
if Bb1 is more than Bb and less than Bb2, the central control module judges that the level standard for the symptoms accords with a preset standard;
if Bb is more than or equal to Bb2, the central control module reduces the level standard aiming at the symptoms by one step.
8. The artificial intelligence technology based medical record writing improvement system according to claim 7, wherein for a single department, the central control module recalculates the number of post-structured case information at different levels in the single department to update the level criteria for the single department to the corresponding values when the adjustment of the level criteria for the condition is completed.
9. The medical record writing improvement system based on artificial intelligence technology according to claim 3, wherein the central control module detects the recognition duration ti of the post-structured medical record information of each disorder in the single department under the third preset condition, respectively, and sets i=1, 2,3, …, n, wherein n is the total number of disorders of the post-structured medical record information of the departments stored in the central control module, and for the ith disorder, the central control module calculates the ratio Ci of the recognition duration ti of the post-structured medical record information of the ith disorder to the recognition duration ti0 of the preset post-structured medical record information, and determines whether the recognition duration ti of the post-structured medical record information for the ith disorder meets the preset standard according to Ci, sets ci=ti/ti 0,
if Ci is less than or equal to 1, the central control module judges that the identification duration of the structured historical medical record information accords with a preset standard;
if Ci is more than 1, the central control module marks the post-structured medical record information of the ith disease as post-abnormal structured medical record information, and adjusts the hierarchical standard of the department to a corresponding value by counting the total number M of the post-abnormal structured medical record information in the department;
the third preset condition is that T is more than T2.
10. The medical record writing improvement system based on the artificial intelligence technology according to claim 9, wherein the central control module adjusts the hierarchy standard of the department to a corresponding value according to the total number M of the structured medical record information after the abnormality under a fourth preset condition, the central control module is provided with a first total number M1 of the structured medical record information after the abnormality and a second total number M2 of the structured medical record information after the abnormality, wherein M1 is less than M2,
if M is less than or equal to M1, the central control module increases the hierarchy standard of the department by one level;
if M1 is more than M and less than or equal to M2, the central control module increases the hierarchy standard of the department by two stages;
if M is more than M2, the central control module increases the hierarchy standard of the department by three levels;
the fourth preset condition is Ci > 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310308665.8A CN116013453B (en) | 2023-03-28 | 2023-03-28 | Medical record writing improvement system based on artificial intelligence technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310308665.8A CN116013453B (en) | 2023-03-28 | 2023-03-28 | Medical record writing improvement system based on artificial intelligence technology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116013453A true CN116013453A (en) | 2023-04-25 |
| CN116013453B CN116013453B (en) | 2023-08-15 |
Family
ID=86030234
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310308665.8A Active CN116013453B (en) | 2023-03-28 | 2023-03-28 | Medical record writing improvement system based on artificial intelligence technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116013453B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107527073A (en) * | 2017-09-05 | 2017-12-29 | 中南大学 | The recognition methods of entity is named in electronic health record |
| CN110610751A (en) * | 2019-09-09 | 2019-12-24 | 北京左医科技有限公司 | Electronic medical record inputting system and method |
| CN111951913A (en) * | 2020-07-13 | 2020-11-17 | 上海森亿医疗科技有限公司 | Medical record document quality control method and system based on electronic medical record management system |
| CN112201350A (en) * | 2020-11-11 | 2021-01-08 | 北京嘉和海森健康科技有限公司 | Intelligent triage method and device and electronic equipment |
| CN112309519A (en) * | 2020-10-26 | 2021-02-02 | 浙江大学 | Electronic medical record medication structured processing system based on multiple models |
| CN114255840A (en) * | 2022-02-25 | 2022-03-29 | 广州科犁医学研究有限公司 | Intelligent data processing system based on clinical research data |
| CN115080862A (en) * | 2022-07-20 | 2022-09-20 | 广州市保伦电子有限公司 | Conference recommendation system based on recommendation algorithm |
| CN115458113A (en) * | 2022-09-22 | 2022-12-09 | 云知声智能科技股份有限公司 | Medical record generation method, system, storage medium and electronic equipment |
| CN115661907A (en) * | 2022-11-15 | 2023-01-31 | 浙江远图技术股份有限公司 | Biological feature recognition method and system |
| US20230059693A1 (en) * | 2021-08-23 | 2023-02-23 | Wistron Corp. | Data analysis system and data analysis method |
-
2023
- 2023-03-28 CN CN202310308665.8A patent/CN116013453B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107527073A (en) * | 2017-09-05 | 2017-12-29 | 中南大学 | The recognition methods of entity is named in electronic health record |
| CN110610751A (en) * | 2019-09-09 | 2019-12-24 | 北京左医科技有限公司 | Electronic medical record inputting system and method |
| CN111951913A (en) * | 2020-07-13 | 2020-11-17 | 上海森亿医疗科技有限公司 | Medical record document quality control method and system based on electronic medical record management system |
| CN112309519A (en) * | 2020-10-26 | 2021-02-02 | 浙江大学 | Electronic medical record medication structured processing system based on multiple models |
| CN112201350A (en) * | 2020-11-11 | 2021-01-08 | 北京嘉和海森健康科技有限公司 | Intelligent triage method and device and electronic equipment |
| US20230059693A1 (en) * | 2021-08-23 | 2023-02-23 | Wistron Corp. | Data analysis system and data analysis method |
| CN114255840A (en) * | 2022-02-25 | 2022-03-29 | 广州科犁医学研究有限公司 | Intelligent data processing system based on clinical research data |
| CN115080862A (en) * | 2022-07-20 | 2022-09-20 | 广州市保伦电子有限公司 | Conference recommendation system based on recommendation algorithm |
| CN115458113A (en) * | 2022-09-22 | 2022-12-09 | 云知声智能科技股份有限公司 | Medical record generation method, system, storage medium and electronic equipment |
| CN115661907A (en) * | 2022-11-15 | 2023-01-31 | 浙江远图技术股份有限公司 | Biological feature recognition method and system |
Non-Patent Citations (1)
| Title |
|---|
| 孔志君;杨科春;陈强;黄武;汤黎明;秦锡虎;: "基于人工智能打造全结构化智慧病历系统", 中国医疗器械信息, no. 19 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116013453B (en) | 2023-08-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104600747B (en) | The Operation of Electric Systems optimization method that coordinated operation risk and wind energy are dissolved | |
| CN206209852U (en) | A kind of control system for Power Material field management | |
| CN109596929B (en) | Voltage curve similarity judgment method considering clock asynchronous influence | |
| US7877634B2 (en) | Data collecting apparatus and gateway apparatus | |
| CN111176953B (en) | Abnormality detection and model training method, computer equipment and storage medium | |
| CN116013453B (en) | Medical record writing improvement system based on artificial intelligence technology | |
| CN115510302A (en) | Intelligent factory data classification method based on big data statistics | |
| CN109544707B (en) | Intelligent control system and method for access of parking lot | |
| CN115758156A (en) | Business process anomaly detection method based on concept drift discovery | |
| CN110867077A (en) | Road optimization method based on traffic video structured data quality control | |
| CN108446202A (en) | A kind of judgment method of the safe condition of calculator room equipment | |
| CN115829646A (en) | Order data processing method and device, electronic equipment and storage medium | |
| CN115277607A (en) | Two-stage mimicry judgment method under heterogeneous system complex flow condition | |
| CN107784578A (en) | Bank's foreign exchange data monitoring and managing method and device | |
| CN113673829A (en) | Quality cost measuring, calculating and controlling method and system for research and development organization | |
| CN113128979A (en) | Scientific research aid decision-making system based on big data | |
| CN114596667B (en) | Data sharing method, system and computer storage medium | |
| CN111242673A (en) | Intelligent commission calculation method based on building element matching | |
| CN110264613A (en) | A kind of CRS clear adds paper money system and method | |
| CN116882896A (en) | Power supply station tool warehouse entry management system based on identity recognition | |
| CN116071931B (en) | Expressway traffic vehicle information prediction method and system | |
| CN211427402U (en) | Automatic sensing and identifying system for warehousing and ex-warehouse of safety tools | |
| CN112541562A (en) | Bus people counting system and control method thereof | |
| CN117077698A (en) | Control system and method based on intelligent mobile fusion bin | |
| CN117787772A (en) | Computerized hardness determination method for hub casting heat treatment |
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 |