CN113689923B - Medical data processing device, system and method - Google Patents
Medical data processing device, system and method Download PDFInfo
- Publication number
- CN113689923B CN113689923B CN202010422606.XA CN202010422606A CN113689923B CN 113689923 B CN113689923 B CN 113689923B CN 202010422606 A CN202010422606 A CN 202010422606A CN 113689923 B CN113689923 B CN 113689923B
- Authority
- CN
- China
- Prior art keywords
- order
- name
- medical
- weights
- medical data
- 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
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
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention provides a medical data processing device, a medical data processing system and a medical data processing method. The apparatus includes an acquisition module configured to acquire a reference medical dataset and an order interface image, the reference medical dataset including a reference identification set including a plurality of reference patient identifications and a reference order name set including a plurality of reference order names; a processing module configured to determine a weight configuration for each of the plurality of reference order names; identifying a patient identification and an order name from the order interface image; calculating a sum of weights for each word of the identified order name based on the weight configuration of the closest reference order name when it is determined that the identified patient identification matches one of the plurality of reference patient identifications; and determining whether the identification result of the order name is valid based on the sum of the weights; and an output module configured to output the valid identification of the order name and the corresponding patient identification.
Description
Technical Field
The present invention relates to a medical data processing device, system and method.
Background
As various medical information systems are increasingly used, there is a need to interact medical data between these medical information systems. For this reason, it is necessary to obtain true and accurate medical data.
One existing solution is to manually enter medical data in one medical information system (e.g., HIS) into another medical information system, which has the problem of manual entry errors and high workload.
Another existing solution is to use electronic devices to analyze and identify documents containing medical data to obtain the medical data. Such a scheme, although not requiring manual entry, has a problem of lower accuracy because such a recognition scheme has a higher recognition rate for a general language of a printed body, but has a lower recognition rate for medical data containing such as medical terms as "text+punctuation".
Yet another existing solution is to perform model training or migration learning on medical data such as medical terms, "text+punctuation", but such a solution requires high computational effort on the computing device, long training and debugging cycles, and may still not achieve satisfactory results.
It is therefore desirable to propose a solution to the above-mentioned problems of the prior art.
Disclosure of Invention
In view of the above-mentioned problems in the prior art, the present invention aims to provide an improved medical data processing solution, which can automatically obtain medical data with higher accuracy.
To this end, according to one aspect of the present invention, there is provided a medical data processing apparatus comprising: an acquisition module configured to acquire a reference medical data set and an order interface image of a medical terminal, the reference medical data set including a reference identification set including a plurality of reference patient identifications and a reference order name set including a plurality of reference order names; a processing module configured to determine a weight configuration for each of the plurality of reference order names, the weight configuration including weights for individual words in a reference order name; identifying a patient identification and an order name from the order interface image; upon determining that the identified patient identification matches one of the plurality of reference patient identifications, calculating a sum of weights of the words of the identified order name based on a weight configuration of a reference order name of the plurality of reference order names that is closest to the identified order name; and determining whether the identification result of the order name is valid based on the sum of the weights; and an output module configured to output the valid identification of the order name and the corresponding patient identification.
According to a possible embodiment, the weight configuration contains a weight representing the weight of the information amount in the reference order name of each word in the reference order name, and the sum of the weights of all words of the reference order is 1.
According to a possible implementation, the processing module is further configured to determine the closest reference order name by: calculating a plurality of edit distances between the identified order name and each of the plurality of reference order names; and determining a reference order name corresponding to the minimum editing distance among the plurality of editing distances as the closest reference order name.
According to a possible implementation, the processing module calculates the sum of the weights of the individual words of the identified order name by: determining an edit type of each word of the identified order name relative to a corresponding word of the closest reference order name, the edit type including equal and unequal; setting the weights of words with the same editing type as positive values of the weights of the corresponding words, and setting the weights of words with unequal editing type as negative values of the weights of the corresponding words; and adding the values of the weights of the words set according to the editing type to obtain the sum of the weights.
According to a possible embodiment, the processing module is configured to: determining that the identification result of the doctor's advice name is valid when the sum of the weights is greater than zero, and determining that the identification result of the doctor's advice name is invalid when the sum of the weights is less than or equal to zero; or when the sum of the weights is greater than or equal to zero, determining that the identification result of the doctor's advice name is valid, and when the sum of the weights is less than zero, determining that the identification result of the doctor's advice name is invalid.
According to one possible implementation, the processing module is configured to identify the order name by: extracting a unit table in the doctor's advice interface image; determining the most listed unit table in the unit tables as an order table containing an order name; and performing OCR recognition on the order form to obtain the order name therein.
According to a possible embodiment, the processing module is configured to identify the patient identification by: extracting a region of interest containing a patient identifier from the order interface image; and performing OCR (optical character recognition) on the region of interest to obtain a patient identification.
According to a possible embodiment the processing module is further configured to: calculating a plurality of edit distances of the identified patient identification from each of the plurality of reference patient identifications; comparing the calculated minimum edit distance of the plurality of edit distances with a predetermined edit distance threshold; determining that the identified patient identification matches one of the plurality of reference patient identifications when the minimum edit distance is not greater than the predetermined edit distance threshold; and when the minimum edit distance is greater than the predetermined edit distance threshold, determining that the identified patient identifier does not match any of the plurality of reference patient identifiers, and ending the medical data processing.
According to a possible embodiment, the patient identification comprises the patient name, optionally also the patient visit number and/or the outpatient number; and the order name comprises at least one of: drug name, injection name, inspection/examination item name, surgery name.
According to another aspect of the present invention, there is provided a medical data processing system comprising: the medical information system comprises one or more capturing modules, a medical information system and a medical information system, wherein each capturing module is arranged on a medical terminal and used for capturing medical advice interface images of the medical information system in the medical terminal; the database is arranged in a medical terminal server in communication connection with the medical terminal and is used for storing a reference medical data set; and the medical data processing device as described above, for identifying the order name from the order interface image based on the reference medical data set and outputting a valid identification result of the order name.
According to a further aspect of the present invention, a method of medical data processing is presented, optionally performed by a medical data processing device as described above and/or a medical data processing system as described above, the method comprising: acquiring a reference medical data set and a medical order interface image of a medical terminal, wherein the reference medical data set comprises a reference identification set containing a plurality of reference patient identifications and a reference order name set containing a plurality of reference order names; determining a weight configuration for each of the plurality of reference order names, the weight configuration including weights for individual words in a reference order name; identifying a patient identification and an order name from the order interface image; upon determining that the identified patient identification matches one of the plurality of reference patient identifications, calculating a sum of weights of the words of the identified order name based on a weight configuration of a reference order name of the plurality of reference order names that is closest to the identified order name; determining whether the identification result of the doctor's advice name is valid based on the sum of the weights; and outputting the effective identification result of the doctor's advice name and the corresponding patient identification.
According to yet another aspect of the invention, a machine-readable storage medium having stored thereon executable instructions, wherein the executable instructions when executed cause a machine to perform a method as described above is presented.
According to the technical scheme of the invention, under the condition of no special training and migration learning, the high-efficiency processing of the medical data is realized by simple operation, so that the medical data with high accuracy is obtained from the interface image of the medical information system, and the operation cost and the time cost are saved. Moreover, according to the technical scheme of the invention, the original data for medical data processing comes from the real medical behavior data directly captured at the medical terminal, so that the medical data processing result of the invention has objectivity.
Drawings
FIG. 1 is a schematic block diagram of a medical data processing system according to an embodiment of the present invention.
Fig. 2 is a schematic block diagram of a medical data processing device according to an embodiment of the present invention.
Fig. 3 is a schematic diagram of a medical data processing technique according to the present invention.
FIG. 4 is a schematic illustration of an order interface image from which medical data is extracted.
Fig. 5 is a schematic diagram of a patient identification recognition process according to one embodiment of the present invention.
FIG. 6 is a schematic diagram of a physician order identification and weight calculation process according to one embodiment of the invention.
Fig. 7 is a flowchart of a medical data processing method according to an embodiment of the present invention.
Detailed Description
The present invention relates to medical data processing schemes under computer application conditions.
In the present invention, "medical data" refers to medical data based on a computer application, i.e., medical data that can be captured by operation of a medical information system. The medical data may include information for uniquely identifying the patient identification and the order name.
In the present invention, a "reference order name set" refers to a set of those accurate (standard) order names. The set of reference order names may be stored in a database of the medical terminal server. The reference order names in the reference order name set may be regarded as reference data for identification and judgment of the order names.
In the present invention, a "reference patient identification set" refers to a set of those accurate (standard) patient identifications. The reference patient identification set may be stored in a database of the medical terminal server. The reference patient identities in the set of reference patient identities may be regarded as baseline data for the identification and judgment of patient identities.
Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.
FIG. 1 schematically illustrates a medical data processing system 100 according to an embodiment of the present invention, which mainly comprises one or more capture modules 10, 20, 30; a database 40; and a medical data processing device 50.
Each of the capture modules 10, 20, 30 is disposed in a medical terminal. For example, each of the capture modules 10, 20, 30 is provided in one of the medical terminals 1,2, 3, respectively. Although 3 capture modules 10, 20, 30 are illustrated in fig. 1, the present invention is not limited in the number of capture modules. The medical data processing system 100 may include one capture module or may include other numbers of capture modules. The capture module is used for capturing an order interface image on the medical terminal, namely, the order interface image is an image of an order interface of a medical information system comprising the medical terminal. The manner in which the interface image is captured is not limited by the present invention.
The medical terminals 1,2, 3 can be understood as client computers, for example, computers used by doctors in hospitals, physical examination institutions, health offices, medical examination or diagnosis centers when they take care of patients. One or more medical information systems are provided in the medical terminal, such as a Hospital Information System (HIS), a computerized doctor order entry system (CPOE), a Clinical Decision Support System (CDSS), and the like. The capturing module can be suitable for various medical information systems in the medical terminal and captures the doctor's advice interface images of the medical information systems arranged by the capturing module.
The database 40 is provided in the medical terminal server 4. Stored in the database 40 are reference medical data sets, such as a reference patient identification set and a reference order name set, for use as references. The medical terminal server is, for example, a server of a hospital. The server (i.e., medical terminal server) is connected to one or more doctor computers (i.e., medical terminals) and can communicate with each doctor computer.
The medical data processing device 50 is provided in the server computer 5. The medical data processing device 50 is configured to execute a policy of processing medical data, i.e., calculate a weight sum of the identified medical order names by means of a reference medical data set and based on a weight configuration to the reference medical order names, and determine whether the identification result of the medical order names is valid based on the weight sum, and output only the valid identification result.
A "valid recognition result of the order name" may be understood as that the recognition accuracy rate reaches a predetermined criterion, i.e. that the recognized order name is available, for example, for a subsequent operation of the medical information system or for a medical evaluation system by means of the medical information system.
The medical data processing device 50 may be implemented in software or hardware or a combination of software and hardware. As shown in fig. 2, the medical data processing device 50 mainly includes an acquisition module 51, a processing module 52, and an output module 53. Such as software modules, the principles of each of which will be described in more detail below.
It is understood that the naming of the modules 51-53 of the medical data processing device 50 should be understood as a logical description rather than a limitation of physical form or arrangement. In other words, whenever a medical data processing device has the function of a module, it is understood that the medical data processing device contains the module.
It will be appreciated that each of the modules 51-53 of the medical data processing device 50 may be implemented in a variety of ways. These modules may be implemented as hardware, software, or a combination thereof. Furthermore, any of these modules may be functionally further divided into sub-modules or combined together.
It follows that the medical data processing system 100 according to the present invention captures an order interface image at a client (i.e., medical terminal), extracts medical data in the order interface image at a computer server, and outputs medical data with high accuracy. The high accuracy medical data can be used by a medical information system (e.g., a clinical information analysis system). The medical data processing system provided by the invention realizes capturing of the medical advice interface image and medical data extraction in independent equipment respectively, and has extremely high flexibility.
The operation and principles of the medical data processing device 50 and its various modules are described below with reference to fig. 2 and 3.
The acquisition module 51 may acquire a reference medical dataset. The acquisition module 51 may acquire the reference medical data set stored in the database 40 of the medical terminal server 4 on a periodic basis (e.g., daily). The acquisition module 51 may acquire the updated reference medical data set after the reference medical data set in the database 40 is updated.
The reference medical data set may include a reference patient identification set and a reference order name set.
The reference patient identification set contains a plurality of reference patient identifications for uniquely identifying the patient. A reference patient identification may include the patient's name and further may include the patient's number and/or clinic number.
The reference order name set contains a plurality of reference order names for representing the order names in the medical instructions issued by the physician in the medical campaign. These reference order names may be stored periodically by the administrator of the medical terminal into the medical terminal server. One reference order name may include names such as medication names, injectate names, and the like in the various items of the order, see the order name under the "item name" icon in fig. 4.
The acquisition module 51 also acquires an order interface image. After the capturing module 10 captures an order interface image (i.e., an image containing an order interface) in the medical information system of the medical terminal 1, the order interface image is transmitted to the medical data processing apparatus 50, for example, the acquisition module 51 of the medical data processing apparatus 50.
It can be seen that the raw data of the medical data processing according to the present invention comes from the real medical behavior data directly captured by the capturing module provided at the medical terminal. Therefore, such raw data is data which has not undergone processing such as transmission and derivation, and has objectivity and timeliness.
The processing module 52 performs the following processing on the order interface image based on the reference medical dataset: weight configuration, patient identification, physician order identification and weight calculation, and determination of valid identification results. Hereinafter, these processes will be specifically described.
The processing module 52 performs weight configuration on each of the acquired reference order names in the set of reference order names. In a weight configuration referring to a doctor's advice name, weights indicating the specific gravity of the information amount in the doctor's advice name are set for the respective words in the doctor's advice name, and the sum of the weights of the respective words in the doctor's advice name is 1. Here, the word in the order name should be understood to include chinese characters, letters, numbers, symbols.
The "information amount" of a word in a physician order name may be understood as a measure of the information conveyed by the word. For example, in the order name "cinobufagin capsule", the information amount of the "capsule" is lower than that of "cinobufagin", and accordingly, the weight of each word in "cinobufagin" is higher than that of each word in "capsule".
In one embodiment, the processing module 52 may calculate the weight matrix for each word in an order name in the form of a Term Frequency-inverse text Frequency index (TF-IDF), thereby obtaining the weight configuration described above.
Referring to fig. 4, the order interface image 400 may include an area 410 presenting patient identification information and an area 420 presenting order information. The information in both regions 410 and 420 may be presented in tabular form. It is to be appreciated that interface elements (not shown) representing other information can also be included on the order interface.
The processing module 52 identifies the order interface image 400 to extract patient identifications therein, i.e., identified patient identifications, and determines whether the identified patient identifications can match one of a plurality of reference patient identifications in the set of reference patient identifications. In other words, it may be determined by the process whether the patient represented by the identified patient identification is a patient that is being treated at the medical terminal.
Fig. 5 illustrates an exemplary process 500 for performing patient identification recognition.
Referring to fig. 5, in block 502, the processing module 52 extracts a region of interest (ROI region) in the order interface image 400. The region of interest may be understood as a region for displaying patient identification according to the specifications (habits) of the medical information system at the medical terminal, e.g., a region located in the upper left quadrant of the entire physician order interface.
In block 504, the processing module 52 identifies an image of the ROI area to obtain an identified patient identification.
In one embodiment, processing module 52 may convert the image of the ROI area into a gray scale map and extract edge information of the gray scale map (e.g., using a canny operator). Then, the edge information is subjected to an opening/closing manipulation, for example, expansion (for example, expansion with a nucleus of 9*9), corrosion (for example, corrosion with a nucleus of 12×12), re-expansion (for example, re-expansion with a nucleus of 4*4) is sequentially performed to remove "lines" in the image, and only "letters" and "icons" are left. Next, rectangular approximation is performed on the image after the opening and closing operation to obtain a text region set containing "noise". Then, the set of text regions is subjected to optical character recognition (Optical Character Recognition, OCR) to obtain an OCR recognition result, thereby obtaining the identified patient identification.
In block 506, the processing module 52 determines a reference patient identification from the set of reference patient identifications that is closest to the identified patient identification.
In one embodiment, the processing module 52 calculates an edit distance for each of the identified patient identifications and the reference patient identifications in the set of reference patient identifications, determines a minimum edit distance of the edit distances, and treats the reference patient identification corresponding to the minimum edit distance as the closest reference patient identification.
In block 508, the processing module 52 determines whether the identified patient identification can match one of the plurality of reference patient identifications in the set of reference patient identifications by determining whether the minimum edit distance meets a predetermined edit distance threshold.
In one embodiment, the edit distance threshold may be preset, for example to 2, i.e., the identified patient identification may be converted to a reference patient identification by 2 transformations. If the minimum edit distance is less than or equal to 2, it is determined that the identified patient identification matches a reference patient identification in the set of reference patient identifications. If the minimum edit distance is greater than 2, it is determined that the identified patient identifier does not match any of the reference patient identifiers in the set of reference patient identifiers, i.e., the patient identifier may be considered to be incorrect, and the medical data processing is ended.
In this way, by setting a reasonable edit distance threshold, it can be ensured that there is only a limited difference between the identified patient identification (e.g., name, etc.) and the exact patient identification, e.g., only one word or two words are different. Thereby, the accuracy of medical data processing can be improved.
The processing module 52 identifies the order interface image 400 to extract the order name therein, i.e., to obtain the identified order name, and calculates the sum of the weights of the words of the order name. The order name may be understood as an order name in medical instructions issued by a physician in a medical activity, such as a medication name, an injection name, a check/check name, a surgical name, and the like. The order names illustrated in fig. 4 include the drug names and the injection names under the "item names".
FIG. 6 illustrates an exemplary process 600 for performing order name identification and weight calculation.
Referring to FIG. 6, in block 602, the processing module 52 obtains a cell form in the order interface image 400.
In one embodiment, the processing module 52 converts the order interface image 400 into a gray scale map and extracts edge information in the gray scale map (e.g., using a canny operator). Then, the edge information is subjected to an opening/closing manipulation, for example, expansion (for example, expansion with a nucleus of 3*3), etching (for example, etching with a nucleus of 2×2) is sequentially performed to merge and close the edges of the form to form a closed rectangle. Next, a closed rectangular data structure is generated, fitted with a quadrilateral, and the area of the quadrilateral is filtered, for example, by setting an area threshold to filter, so as to remove the quadrilateral below the area threshold (for example, a part with a too small area and possibly "noise" can be filtered out), so as to obtain a quadrilateral set. Next, in the quadrangle set, the center points of the quadrangles are clustered into one or more clusters, each cluster representing a table, with the points representing the centers of the cells, based on whether they are adjacent and in rows and columns, thereby obtaining the cell table.
In block 604, an order form is determined from the unit forms.
In one embodiment, the processing module 52 counts the row-column relationships in the unit tables, determining the most-listed table as the order table (in the order interface, the table for entering the order information is the most-listed table), i.e., the table containing information for displaying the order. Other tables may be tables for other purposes, and the invention is not limited.
In block 606, the processing module 52 identifies the order name in the order form.
In one embodiment, the processing module 52 segments the order form and OCR identifies the segmented cells to obtain the identified order name. The identified order name may be one order name or may include a plurality of order names, for example, three order names below the "item names" column in fig. 4. In the case where a plurality of order names are identified, weights and judgments may be calculated separately for each order name.
In block 608, for the identified one of the order names, the processing module 52 determines a reference order name in the set of reference order names that is closest to the identified order name.
In one embodiment, the processing module 52 calculates an edit distance for each of the identified order names and the reference order names in the set of reference order names, determines a minimum edit distance of the edit distances and an edit type corresponding to the minimum edit distance, and uses the reference order name corresponding to the minimum edit distance as the closest reference order name.
Edit types may include equal and unequal (e.g., move, delete, add).
The edit type "equal" may be understood as the two words compared (i.e., the word in the closest reference order name and the word in the identified order name) are identical, including the two words being identical and the location in an order name being identical.
The edit type "unequal" may be understood as that the two words compared (i.e., the word in the closest reference order name and the word in the identified order name) are not exactly identical, e.g., the words are not identical and/or the locations in the order names are not identical. Where "move" is understood to mean that the two words compared are not in the same position in the order name, a movement transformation is required to transform into a coincidence. "delete" may be understood as an additional word of the identified order name relative to the nearest reference order name, requiring a delete transformation to change to be consistent. "adding" may be understood as the lack of words of the identified order name relative to the closest reference order name, requiring an added transformation to transform to be exactly consistent.
In block 610, the processing module 52 calculates a sum of weights for each of the words of the identified order name.
In one embodiment, the processing module 52 calculates the sum of weights based on the weight configuration and edit type in the closest reference order name. For example, for one word of the identified order name, if the edit types are equal, the weight thereof is set to the weight value (+weight) of the corresponding word in the closest reference order name, e.g., it is determined that the edit type of one word in the order name is "equal", and the weight of the corresponding word in the closest reference order name is 0.3, the weight value of the word in the identified order name is set to 0.3. If the edit type is not equal, the weight is set to the negative (-weight) of the weight value of the corresponding word in the closest reference order name, e.g., it is determined that the edit type of one word in the order name is "not equal" and the weight of the corresponding word in the closest reference order name is 0.3, the weight value of the word in the identified order name is set to-0.3. Then, the weight values of the respective words based on such settings are added to obtain the above-described sum of weights.
The processing module 52 may determine whether the identification of the order name is valid by determining whether the sum of the calculated weights meets a predetermined weight threshold.
For example, assuming that the validity probability of the recognition result of the order name is P and the number of words of the order name is n, P can be obtained by the following formula:
It may be determined whether the identification of the order name is valid by comparing the P value with zero.
In one embodiment, if P is greater than zero, the identification of the order name may be considered valid. If P is less than or equal to zero, then the identification of the order name may be considered invalid, i.e., insufficient to derive the correct order name.
In another embodiment, if P is greater than or equal to zero, the identification of the order name may be considered valid. If P is less than zero, the identification of the order name may be deemed invalid, i.e., the identification is insufficient to derive the correct order name.
The output module 53 outputs the identification result of the order name determined to be valid together with the corresponding patient identification. For example, to a clinical information system for further medical procedures or medical performance assessment.
In one test employing the medical data processing scheme according to the present invention, the accuracy of the test data reached 98.5%. The recognition rate for words with high information in the order name, such as "(", ")" of full and half angles, is extremely high. For example, the identification of the doctor's advice names such as "cinobufagin tablet", "cinobufagin capsule" and "cinobufagin injection", and the erroneous data may be the erroneous identification of the dosage forms such as "tablet", "capsule" and "injection", and the identification success rate for the "cinobufagin" with high information content is extremely high.
The invention also relates to a medical data processing method 700. The method 700 may be performed by the medical data processing device described above or by the medical data processing system described above, and thus the description above applies equally thereto. Next, referring to fig. 7, the main steps of the medical data processing method 700 are described.
In step 702, a medical order interface image of a reference medical dataset including a reference identification set including a plurality of reference patient identifications and a reference order name set including a plurality of reference order names and a medical terminal is acquired.
In step 704, a weight configuration for each of the plurality of reference order names is determined, the weight configuration including weights for individual words in a reference order name.
In step 706, a patient identification and a physician order name are identified from the physician order interface image.
In step 708, upon determining that the identified patient identification matches one of the plurality of reference patient identifications, a sum of weights for each word of the identified order name is calculated based on a weight configuration of a reference order name of the plurality of reference order names that is closest to the identified order name.
In step 710, it is determined whether the identification of the order name is valid based on the sum of the weights.
In step 712, the output valid identification of the order name and corresponding patient identification.
The present invention also provides a machine-readable storage medium storing executable instructions that, when executed, cause a machine to perform the method 700 described above.
It should be appreciated that examples of machine-readable storage media may include volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information (e.g., computer readable instructions, data structures, program modules, or other data). The storage medium may include, but is not limited to: random Access Memory (RAM), read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact Disks (CDs), digital Versatile Disks (DVDs) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store information.
In some embodiments, a machine-readable storage medium may store executable computer program instructions that, when executed by one or more processing units, cause the processing units to perform the above-described methods. The executable computer program instructions may comprise any suitable type of code, such as source code, compiled code, interpreted code, executable code, static code, dynamic code, and the like. The executable computer program instructions may be implemented using any suitable high-level, low-level, object-oriented, visual, compiled and/or interpreted programming language.
It should be appreciated that references throughout this specification to "one implementation," "an example implementation," "some implementations," "various implementations," etc., indicate that the implementations of the disclosure described may include particular features, structures, or characteristics, but every implementation may not necessarily include the particular features, structures, or characteristics. Furthermore, some implementations may have some, all, or none of the features described for other implementations.
It is to be understood that the various operations may be described as multiple discrete acts or operations in a sequential order, in a manner that is most helpful in understanding the claimed subject matter. However, the order of description should not be construed as to imply that these operations are necessarily order dependent. In particular, the operations may be performed out of the order presented. In other implementations, various additional operations may also be performed, and/or various operations already described may be omitted.
What has been described above includes examples of the disclosed architecture. It is, of course, not possible to describe every conceivable combination of components and/or methodologies, but one of ordinary skill in the art may recognize that many further combinations and permutations are possible. Accordingly, the novel architecture is intended to embrace all such alternatives, modifications and variations that fall within the spirit and scope of the appended claims.
Claims (10)
1. A medical data processing apparatus comprising:
An acquisition module configured to acquire a reference medical data set and an order interface image of a medical terminal, the reference medical data set including a reference identification set including a plurality of reference patient identifications and a reference order name set including a plurality of reference order names;
A processing module configured to determine a weight configuration for each of the plurality of reference order names, the weight configuration including weights for individual words in a reference order name; identifying a patient identification and an order name from the order interface image; upon determining that the identified patient identification matches one of the plurality of reference patient identifications, calculating a sum of weights of the words of the identified order name based on a weight configuration of a reference order name of the plurality of reference order names that is closest to the identified order name; and determining whether the identification result of the order name is valid based on the sum of the weights; and
An output module configured to output a valid identification of the order name and a corresponding patient identification,
Wherein the processing module is further configured to determine the closest reference order name by:
calculating a plurality of edit distances between the identified order name and each of the plurality of reference order names; and
Determining a reference order name corresponding to a minimum edit distance of the plurality of edit distances as the closest reference order name,
And wherein the processing module calculates a sum of weights for each word of the identified order name by:
Determining an edit type of each word of the identified order name relative to a corresponding word of the closest reference order name, the edit type including equal and unequal;
Setting the weights of words with the same editing type as positive values of the weights of the corresponding words, and setting the weights of words with unequal editing type as negative values of the weights of the corresponding words; and
And adding the weight values of the words set according to the editing type to obtain the weight sum.
2. The medical data processing apparatus of claim 1, wherein the weight configuration includes a weight representing the weight of the information amount thereof in the reference order name for each word in the reference order name, and the sum of the weights of all words of the reference order is 1.
3. The medical data processing device of claim 1, wherein the processing module is configured to:
Determining that the identification result of the doctor's advice name is valid when the sum of the weights is greater than zero, and determining that the identification result of the doctor's advice name is invalid when the sum of the weights is less than or equal to zero; or alternatively
When the sum of the weights is greater than or equal to zero, the identification result of the doctor's advice name is determined to be valid, and when the sum of the weights is less than zero, the identification result of the doctor's advice name is determined to be invalid.
4. The medical data processing device of claim 1, wherein the processing module is configured to identify the order name by:
Extracting a unit table in the doctor's advice interface image;
determining the most listed unit table in the unit tables as an order table containing an order name; and
Performing OCR recognition on the order form to obtain the order name therein.
5. The medical data processing device of claim 1, wherein the processing module is configured to identify the patient identification by:
extracting a region of interest containing a patient identifier from the order interface image; and
OCR is conducted on the region of interest to obtain patient identification.
6. The medical data processing device of claim 5, wherein the processing module is further configured to:
calculating a plurality of edit distances of the identified patient identification from each of the plurality of reference patient identifications;
comparing the calculated minimum edit distance of the plurality of edit distances with a predetermined edit distance threshold;
Determining that the identified patient identification matches one of the plurality of reference patient identifications when the minimum edit distance is not greater than the predetermined edit distance threshold; and
And when the minimum editing distance is larger than the preset editing distance threshold value, determining that the identified patient identification is not matched with any one of the plurality of reference patient identifications, and ending the medical data processing.
7. The medical data processing device of claim 1, wherein the patient identification includes a patient name, and a patient visit number and/or an outpatient number; and
The order name includes at least one of: drug name, injection name, inspection/examination item name, surgery name.
8. A medical data processing system, comprising:
The medical information system comprises one or more capturing modules, a medical information system and a medical information system, wherein each capturing module is arranged on a medical terminal and used for capturing medical advice interface images of the medical information system in the medical terminal;
the database is arranged in a medical terminal server in communication connection with the medical terminal and is used for storing a reference medical data set; and
The medical data processing apparatus of any one of claims 1-7, for identifying a medical order name from a medical order interface image based on a reference medical data set and outputting a valid identification result of the medical order name.
9. A method of medical data processing, the method being performed by the medical data processing device of any one of claims 1-7 and/or the medical data processing system of claim 8, the method comprising:
Acquiring a reference medical data set and a medical order interface image of a medical terminal, wherein the reference medical data set comprises a reference identification set containing a plurality of reference patient identifications and a reference order name set containing a plurality of reference order names;
Determining a weight configuration for each of the plurality of reference order names, the weight configuration including weights for individual words in a reference order name;
Identifying a patient identification and an order name from the order interface image;
Upon determining that the identified patient identification matches one of the plurality of reference patient identifications, calculating a sum of weights of the words of the identified order name based on a weight configuration of a reference order name of the plurality of reference order names that is closest to the identified order name;
Determining whether the identification result of the doctor's advice name is valid based on the sum of the weights; and
The output valid identification result of the doctor's advice name and the corresponding patient identification,
Wherein determining the closest reference order name comprises:
calculating a plurality of edit distances between the identified order name and each of the plurality of reference order names; and
Determining a reference order name corresponding to a minimum edit distance of the plurality of edit distances as the closest reference order name,
And wherein calculating the sum of weights of the individual words of the identified order name comprises:
Determining an edit type of each word of the identified order name relative to a corresponding word of the closest reference order name, the edit type including equal and unequal;
Setting the weights of words with the same editing type as positive values of the weights of the corresponding words, and setting the weights of words with unequal editing type as negative values of the weights of the corresponding words; and
And adding the weight values of the words set according to the editing type to obtain the weight sum.
10. A machine-readable storage medium having stored thereon executable instructions, wherein the executable instructions when executed cause a machine to perform the method of claim 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010422606.XA CN113689923B (en) | 2020-05-19 | 2020-05-19 | Medical data processing device, system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010422606.XA CN113689923B (en) | 2020-05-19 | 2020-05-19 | Medical data processing device, system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113689923A CN113689923A (en) | 2021-11-23 |
| CN113689923B true CN113689923B (en) | 2024-06-18 |
Family
ID=78575709
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010422606.XA Active CN113689923B (en) | 2020-05-19 | 2020-05-19 | Medical data processing device, system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113689923B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106126494A (en) * | 2016-06-16 | 2016-11-16 | 上海智臻智能网络科技股份有限公司 | Synonym finds method and device, data processing method and device |
| CN109256216A (en) * | 2018-08-14 | 2019-01-22 | 平安医疗健康管理股份有限公司 | Medical data processing method, device, computer equipment and storage medium |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7047493B1 (en) * | 2000-03-31 | 2006-05-16 | Brill Eric D | Spell checker with arbitrary length string-to-string transformations to improve noisy channel spelling correction |
| CN103399907A (en) * | 2013-07-31 | 2013-11-20 | 深圳市华傲数据技术有限公司 | Method and device for calculating similarity of Chinese character strings on the basis of edit distance |
| CN113724884A (en) * | 2016-09-21 | 2021-11-30 | 北京大学 | Disease symptom and weight knowledge acquisition and processing method based on disease case base |
| CN108804423B (en) * | 2018-05-30 | 2023-09-08 | 深圳平安医疗健康科技服务有限公司 | Medical text feature extraction and automatic matching method and system |
| CN110929499B (en) * | 2019-10-15 | 2022-02-11 | 平安科技（深圳）有限公司 | Text similarity obtaining method, device, medium and electronic equipment |
-
2020
- 2020-05-19 CN CN202010422606.XA patent/CN113689923B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106126494A (en) * | 2016-06-16 | 2016-11-16 | 上海智臻智能网络科技股份有限公司 | Synonym finds method and device, data processing method and device |
| CN109256216A (en) * | 2018-08-14 | 2019-01-22 | 平安医疗健康管理股份有限公司 | Medical data processing method, device, computer equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113689923A (en) | 2021-11-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110880361B (en) | Personalized accurate medication recommendation method and device | |
| CN113934895A (en) | Method for assisting in establishing patient main index | |
| US20140006044A1 (en) | System and method for preparing healthcare service bundles | |
| CN107239722B (en) | Method and device for extracting diagnosis object from medical document | |
| US20130208952A1 (en) | Method and Apparatus for Improving Accuracy of Biometric Identification in Specimen Collection Applications | |
| EP3467770B1 (en) | Method for analysing a medical imaging data set, system for analysing a medical imaging data set, computer program product and a computer-readable medium | |
| CN111180027B (en) | Patient portrait correlation rule screening method and device based on medical big data | |
| CN110580942A (en) | novel physical examination report generation method, device, medium and terminal equipment | |
| CN111402070A (en) | Medical information identification method and device, computer equipment and storage medium | |
| WO2021151302A1 (en) | Drug quality-control analysis method, apparatus, device, and medium based on machine learning | |
| CN118471420B (en) | A health examination report data analysis and management system based on the Internet | |
| CN111785383A (en) | Data processing method and related equipment | |
| CN110718276A (en) | Clinical path management information system | |
| CN111710402B (en) | Face recognition-based ward round processing method and device and computer equipment | |
| CN206907026U (en) | A kind of remote patient identification, retrieval, CT, MR compatible controller of matching sweeping scheme | |
| CN111667922A (en) | Clinical diagnosis and treatment data entry system and method | |
| CN113689923B (en) | Medical data processing device, system and method | |
| CN113990514A (en) | Abnormality detection device for doctor diagnosis and treatment behavior, computer device and storage medium | |
| CN109509550B (en) | Treatment information processing method, device, equipment and medium based on data analysis | |
| CN107610783A (en) | A kind of brain tumor information platform | |
| CN112509688B (en) | Automatic analysis system, method, equipment and medium for pressure sore picture | |
| CN118824561A (en) | A recognition system for abnormal medical treatment behavior based on combined algorithms | |
| CN113658653B (en) | Diagnosis and treatment information processing method, device and equipment | |
| US20230377697A1 (en) | System and a way to automatically monitor clinical trials - virtual monitor (vm) and a way to record medical history | |
| CN110689441B (en) | Case auditing method, device, equipment and storage medium based on commonality extraction |
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 |