KR20250140795A - Medical Record System - Google Patents

Abstract

The present invention relates to a medical record system, and more particularly, to a medical record system including a medical image providing unit that provides a medical image visualizing medical data of a subject, a medical image recommendation unit that recommends a medical image to be provided next by the medical image providing unit, and a storage unit that stores order information regarding the order provided from the medical image providing unit.

Description

Medical Record System

The present invention relates to a medical record system capable of sequentially presenting the steps of a record so that a medical record can be created easily and quickly.

Recently, the digitization and standardization of medical data has been actively pursued. First, digitizing medical data involves converting text and images directly created by medical professionals, rather than using computer devices, into digital form. For example, descriptive text data directly entered into medical records by medical professionals or model data drawn directly on medical records by medical professionals are considerably more difficult to digitize.

Next, standardizing medical data involves establishing standards for quality, shape, dimensions, and composition, thereby enhancing the compatibility and reusability of digitized medical data. For example, surgery is a surgical procedure that involves incising the skin, mucosa, or other tissues for therapeutic purposes. Because the methods and sequences chosen by each surgeon vary, standardizing medical data and documenting the actual surgical procedure in real time is practically impossible.

To solve these problems, related document 1 relates to a device and method for generating multimedia surgical record content, which segments surgical image data and enables generation of a surgical record sheet using the segmented surgical image data and surgical content input through a user input unit.

However, Related Document 1 requires users to select a body tissue by selecting a screen, then individually select a view within that tissue to individually select each area. This process of selecting each area is considerably time-consuming and challenging for medical professionals. Furthermore, Related Document 1 requires processing surgical details (i.e., descriptive text data) entered through a user input interface, posing technical limitations in the digitization and standardization of medical data.

Therefore, there is an urgent need in this field for technologies that enable users to easily and intuitively check medical records and to facilitate the digitization and standardization of medical data for medical records.

Republic of Korea Patent Publication No. 10-2020-0050262

The present invention is intended to solve the above problems, and it is an object of the present invention to obtain a medical record system that provides a medical image visualizing the medical data of a subject so that the medical record can be easily and intuitively checked from the user's perspective and the process of performing a medical service, and at the same time enables the digitization and standardization of medical data for surgical records, recommends the next medical image to be provided, and stores the medical images in the order provided.

The technical problems to be solved by the present invention are not limited to the technical problems mentioned above, and other technical problems not mentioned can be clearly understood by a person having ordinary skill in the art from the description of the present invention.

In order to achieve the above object, the medical record system of the present invention provides a medical image providing unit that provides a medical image visualizing the medical data of a subject; a medical image recommendation unit that recommends a medical image to be provided next by the medical image providing unit; and a storage unit that stores order information regarding the order provided from the medical image providing unit.

As described above, according to the present invention, by recording using recommended medical images, it is considerably easier for the user to record medical processes and results than with the conventional descriptive text data writing method.

In addition, the present invention provides medical images and stores them in the order in which they were provided, so that medical staff other than the medical staff who directly recorded the images can visually and intuitively check the medical process and results provided to the examinee.

In addition, the present invention records the medical data of a subject using medical images, thereby enabling visualization and display of the areas or order of treatment, examination, and surgery, and enabling structuring, digitization, and standardization of medical data compared to medical data written in conventional descriptive text data.

In addition, the medical data structured, digitized, and standardized through the present invention can be utilized in various ways, such as for statistics, research, and patient treatment, compared to medical records created by conventional medical staff.

The effects of the present invention are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the detailed description and the description of the claims.

Figure 1 is a configuration diagram of the medical record system of the present invention.
FIG. 2 is a drawing showing medical image 1 according to one embodiment of the present invention and medical image 2 provided according to selection data.
FIG. 3 is a diagram showing medical images 2 to 5 automatically recommended using a pre-trained machine learning algorithm according to one embodiment of the present invention.
FIG. 4 is a diagram showing recommended medical images 2 to 5 according to a preset medical record procedure from a user terminal according to one embodiment of the present invention.
Figure 5 is an original image according to one embodiment of the present invention.
Figure 6 is a medical image with a designated region of interest according to one embodiment of the present invention.
Figure 7 is an edited image reflecting a region of interest according to one embodiment of the present invention.
FIG. 8 is an attribute value window showing attribute values for another recommended edited image and an area of interest following an edited image according to one embodiment of the present invention.
FIG. 9 is a medical image including a surgical tool object according to one embodiment of the present invention.
FIG. 10 is an edited image reflecting a surgical tool selected from a user terminal according to one embodiment of the present invention.
FIG. 11 is a plurality of medical images according to sequence information according to one embodiment of the present invention.
FIG. 12 is a drawing showing a medical image and a human model according to one embodiment of the present invention.

The terms used in this specification have been selected from widely used, current terms, taking into account the functions of the present invention. However, these terms may vary depending on the intentions of those skilled in the art, precedents, the emergence of new technologies, etc. Furthermore, in certain cases, terms may be arbitrarily selected by the applicant, and in such cases, their meanings will be described in detail in the relevant description of the invention. Therefore, the terms used in this invention should not be defined simply as names, but rather based on their inherent meanings and the overall content of the present invention.

Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by those of ordinary skill in the art to which this invention pertains. Terms defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning within the context of the relevant technology, and shall not be interpreted in an idealized or overly formal sense unless explicitly defined herein.

Hereinafter, embodiments of the present invention will be described in detail with reference to the attached drawings. Fig. 1 is a configuration diagram of a medical record system according to the present invention. Fig. 2 is a diagram showing medical image 1 and medical image 2 provided according to selection data according to an embodiment of the present invention. Fig. 3 is a diagram showing medical images 2 to 5 automatically recommended using a pre-trained machine learning algorithm according to an embodiment of the present invention. Fig. 4 is a diagram showing medical images 2 to 5 recommended according to a pre-set medical record procedure from a user terminal (10) according to an embodiment of the present invention.

FIG. 5 is an original image according to an embodiment of the present invention. FIG. 6 is a medical image with a designated region of interest according to an embodiment of the present invention. FIG. 7 is an edited image reflecting a region of interest according to an embodiment of the present invention. FIG. 8 is an attribute value window displaying attribute values for another edited image recommended after the edited image and the region of interest according to an embodiment of the present invention. FIG. 9 is a medical image including a surgical tool object according to an embodiment of the present invention. FIG. 10 is an edited image reflecting a surgical tool selected from a user terminal according to an embodiment of the present invention. FIG. 11 is a plurality of medical images according to order information according to an embodiment of the present invention. FIG. 12 is a diagram showing a medical image and a human model according to an embodiment of the present invention.

Referring to FIG. 1, the medical record system of the present invention includes a medical image providing unit (100) that provides a medical image visualizing the medical data of a subject, a medical image recommendation unit (200) that recommends a medical image to be provided next by the medical image providing unit (100), and a storage unit (300) that stores order information about the order provided from the medical image providing unit (100).

The subject of examination referred to in the present invention may include a person who was hospitalized at any medical institution and received surgery and inpatient treatment, or a person who was an outpatient at any medical institution and received outpatient treatment. The user may be the examiner who directly treated the subject of examination or a representative of the examiner. The user may include a person who has obtained qualifications, licenses, etc. or is permitted to engage in health care services in accordance with the provisions of health care-related laws and regulations, and may include medical technicians including doctors, chiropractors, podiatrists, nursing practitioners, nurses, clinical pathologists, radiologists, physical therapists, occupational therapists, dental technicians and dental hygienists, pharmacists, and oriental medicine doctors.

According to one embodiment of the present invention, the medical image providing unit (100) is characterized in that it searches for the medical data and stores the searched medical data by linking with a medical institution server (30) or an electronic medical record (EMR) server (20). At this time, the medical image providing unit (100) can search for and store the medical data of any subject from the medical institution server (30) or the electronic medical record server (20) in real time, at preset intervals, or at a time desired by the user.

The medical data referred to in the present invention may include text data written by an examiner during a treatment at a medical institution or online, and medical images taken by the examinee at a medical institution. First, the text data is data written in digital format using letters, numbers, spelling, mathematical symbols, units, and combinations thereof, such as the examinee's body part, the condition of the body part, suspected disease/disease name, diagnosis, diagnosis result, test result, surgery name, and procedure name. For example, the text data may include 'cervical disc disorder' recorded in a cervical MRI reading sheet, 'lumbar disc disorder' recorded in a CT reading sheet, and the like.

And among the above medical data, the medical images may include videos and images taken with X-rays, MRIs, CTs, and ultrasounds, nuclear medicine videos and images, and videos and images taken in a clinic. For example, the medical images may be MR angiography images of the subject's cerebral blood vessels.

The medical image referred to in the present invention may be an image including one or more body part objects. The body part objects are two-dimensional or three-dimensional representations of the internal or external shapes of body parts, such as bones, skin, blood vessels, and muscles, in a manner identical or similar to the original shape. In addition, the medical image may be an image including one or more medical tool objects. The medical tool objects are two-dimensional or three-dimensional representations of medical tools, including surgical tools, treatment tools, surgical tools, examination tools, and traction tools, in a manner identical or similar to the original shape. In addition, the medical image may be an image in which the medical tool objects are reflected in the body part objects.

Meanwhile, the body part object and the medical tool object are characterized in that they each include one or more attribute values written in XML (eXtensible Markup Language) or JSON (JavaScript Object Notation) format. The one or more attribute values may include a name or unique number indicating the object, coordinates of the object on the medical image, pixel or numerical spatial information.

For example, a bone object exposed at a surgical site may include a ‘standard medical term’ called ‘SNOMED SCTID:23416004’ as an attribute value, and a ‘body part name’ called ‘Bone structure of ulna’ as an attribute value. Referring to an example of FIG. 9, surgical tool object 1 may include the surgical tool name ‘surgical knife’ and the unique number ‘SCTID(102307003)’ as attribute values, and surgical tool object 2 may include the surgical tool name ‘Metzenbaum Scissor’ and the unique number ‘SCTID(385590002)’ as attribute values.

Traditionally, medical professionals have simply used descriptive text data (free text) to record treatment results, diagnosis results, test results, procedure results, and surgical results in analog and digital formats. This text-based descriptive text data (free text) is unstructured, making it difficult to standardize medical data. Furthermore, the medical professionals themselves have to re-write previous treatments, tests, and surgeries in text format, which is cumbersome. This text-based descriptive text data (free text) makes it difficult for others to intuitively understand the treatment process and results, diagnosis process and results, test process and results, procedure process and results, and surgical process and results. The present invention provides and recommends the medical images to address these issues and enable the structuring, digitization, and standardization of medical records. Therefore, the medical images may be images used to record the treatment, diagnosis, test, procedure, and surgical processes of a subject, and are not limited to the types of images described above.

According to one embodiment of the present invention, in using text data among the medical data, the medical image providing unit (100) includes a text data analysis unit (110) that analyzes the text data among the medical data and extracts at least one of a body part name, a diagnosis name, a procedure name, and a surgery name from the text data, and is characterized in that it provides one or more medical images related to at least one of a body part name, a diagnosis name, a procedure name, and a surgery name as an original image.

The diagnosis referred to in the present invention may include the name of a disease or abnormal condition determined by a medical professional. The procedure referred to in the present invention refers to a non-invasive treatment method performed by a medical professional for the purpose of improving the affected area of a subject, and may include endoscopic procedures, catheter procedures, etc. The surgical procedure referred to in the present invention refers to a treatment method performed by cutting, incising, or manipulating tissue using a medical tool, and may include gastrectomy, spinal fusion, lung resection, etc.

The above text data analysis unit (110) may include a preset text analysis algorithm for recognizing text data written in analog or digital format. The preset text analysis algorithm may be implemented as a pre-trained machine learning algorithm, a pre-trained neural network model, an algorithm composed of mathematical formulas and preset rules, and is not limited to a specific method.

For example, the text data may include ‘stomachache’ and ‘heartburn’ written in the chief complaint. At this time, the text data analysis unit (110) may extract the body part name ‘stomach/stomach organ’ from the text data of ‘stomachache’ and ‘heartburn. Then, as in the embodiment of FIG. 2, the medical image provision unit (100) may first provide a two-dimensional or three-dimensional medical image of the ‘stomach/stomach organ’ extracted from the text data analysis unit (110), which may be referred to as the original image.

Alternatively, if the text data includes at least one of a body part name, a surgery name, a diagnosis name, and a procedure name, the text data analysis unit (110) can extract at least one of the body part name, the surgery name, the diagnosis name, and the procedure name. Then, the medical image providing unit (100) can initially provide a two-dimensional or three-dimensional medical image stored in connection with the body part name, the surgery name, the diagnosis name, and the procedure name, and this can be called an original image.

At this time, the original image may be a single image or a set of two or more images. If the original image is a set of two or more images, the medical image providing unit (100) may provide all of the two or more image sets as original images. Alternatively, the medical image providing unit (100) may provide one or more medical images selected through the user terminal (10) from among the two or more image sets as original images.

According to another embodiment of the present invention, when using a medical image among the medical data, the medical image providing unit (100) further includes a medical image analysis unit (120) that outputs at least one of a body part name, a diagnosis name, a procedure name, and a surgery name by inputting the medical image among the medical data into a preset image analysis algorithm, and is characterized in that it provides a medical image related to at least one of the body part name, the diagnosis name, the procedure name, and the surgery name as an original image.

Here, the preset image analysis algorithm can be implemented as a pre-learned machine learning algorithm, a pre-learned neural network model, an algorithm composed of mathematical formulas and preset rules, and is not limited to a specific method.

For example, the medical image analysis unit (120) may include a pre-trained neural network model. In addition, the medical image analysis unit (120) may input an MR angiography image of the subject's cerebral blood vessels into the pre-trained neural network model, and output 'cerebral aneurysm' as a diagnosis from the pre-trained neural network model. Here, a cerebral aneurysm refers to a case where the internal elastic layer and the media forming the inner side of a cerebral blood vessel are damaged and missing, causing the blood vessel wall to swell and form a new intravascular space. Therefore, the medical image analysis unit (120) may output the body part name 'brain' or, more specifically, 'cerebral blood vessel' along with the diagnosis 'cerebral aneurysm'. Then, the medical image providing unit (100) can first provide a medical image representing a body part object for the ‘brain’ or, more specifically, a body part object for the ‘cerebral blood vessel’ in two dimensions or three dimensions, and this can be called an original image.

As described above, the medical image providing unit (100) can provide original images based on the medical data of the subject. However, there are technical limitations in recording the diagnosis process and results, treatment process and results, examination process and results, procedure process and results, and surgical process and results using only the original images. Therefore, the present invention provides the medical image recommendation unit (200) so that it can recommend medical images to be provided after the original images in various ways. Therefore, it has a remarkable effect of enabling medical staff to quickly and accurately create standardized medical records in real time during treatment, diagnosis, examination, treatment, and surgery.

At this time, the medical image recommendation unit (200) of the present invention can recommend one or more medical images. If the images recommended by the medical image recommendation unit (200) are two or more image sets, the medical image provision unit (100) can provide all of the two or more image sets. Alternatively, the medical image provision unit (100) can provide only some medical images selected through the user terminal (10) from among the two or more image sets.

For example, the medical image recommendation unit (200) may recommend item texts such as ‘gastrointestinal endoscopy’, ‘heartburn medication’, and ‘blood test’ and medical images related to each item text based on the diagnosis names ‘abdominal pain’ and ‘heartburn’ derived from the medical image provision unit (100) and the body part name ‘stomach/stomach’.

Meanwhile, the medical image recommendation unit (200) is characterized by providing a user interface so that the user terminal (10) can select an item text and a medical image related to each item text. As in the embodiment of Fig. 2, if ‘gastroenteroscope’ is selected from the user terminal (10), the medical image provision unit (100) can provide a medical image (medical image 2) for the ‘inner surface of the stomach’ related to the ‘gastroenteroscope’ next to the original image (medical image 1) so that the user can make a record related to the gastroenteroscope.

Alternatively, the medical image providing unit (100) is characterized in that it accumulates selection data selected from the same user terminal (10) and provides one or more medical images having a high selection probability among a plurality of medical images recommended from the medical image recommendation unit (200) based on the selection data selected from the same user terminal (10).

For example, the medical image recommendation unit (200) may recommend item texts such as ‘gastrointestinal endoscopy’, ‘heartburn medication’, and ‘blood test’, and medical images related to each item text. At this time, the medical image provision unit (100) may provide a medical image for ‘gastrointestinal endoscopy’ if the selection probability for ‘gastrointestinal endoscopy’ was the highest from the same user terminal (10) in the past, based on selection data selected from the same user terminal (10). Therefore, the medical image provision unit (100) of the present invention can automatically provide medical images frequently used by the same user without having to repeatedly request selection from the same user, thereby having a remarkable effect of minimizing inconvenience to the user.

In another medical image recommendation method, the medical image recommendation unit (200) is characterized by recommending medical images using a preset recommendation algorithm. Here, the preset recommendation algorithm may be implemented using a pre-learned machine learning algorithm, a pre-learned neural network model, an algorithm composed of mathematical formulas and preset rules, and is not limited to a specific method.

Referring to an embodiment of FIG. 3, the medical image recommendation unit (200) may utilize a recurrent neural network (RNN) as a pre-trained machine learning algorithm. A recurrent neural network is a neural network for learning time-series data that changes over time, and has a structure in which input values are sent from the input layer to the output layer, while information from the hidden layer is passed on to the next hidden layer. As described above, the present invention is intended to record medical treatment processes, diagnosis processes, examination processes, treatment processes, and surgical processes, and thus, a recurrent neural network can be used to automatically recommend medical record procedures.

That is, the medical image recommendation unit (200) can automatically recommend medical images 2 to 5 that can be sequentially provided after the original image (medical image 1) by inputting the original image (medical image 1) into the recurrent neural network. Alternatively, the medical image recommendation unit (200) can automatically recommend medical images according to the procedure, surgical procedure, and examination procedure by inputting one of the procedure name, surgical procedure, and examination name into the recurrent neural network. This can be implemented by having the recurrent neural network learn the detailed surgical procedures of the gastrectomy, such as ‘abdominal skin incision’, ‘abdominal muscle dissection’, ‘stomach removal’, ‘esophageal-small intestine connection’, ‘fluid tube insertion’, and ‘incision site suturing’, and medical images related to each procedure.

In another medical image recommendation method, the medical image recommendation unit (200) is characterized by recommending medical images according to a preset medical record procedure from a user terminal (10).

Referring to an embodiment of FIG. 4, the user terminal (10) can set a medical record procedure and step-by-step medical images to be recorded in the order of skin incision, muscle incision, periosteum removal, and bone fracture site confirmation. When the medical image providing unit (100) provides an original image (medical image 1), the medical image recommendation unit (200) can recommend medical image 2 for ‘skin incision’ as the next, medical image 3 for ‘muscle incision’ as the next, medical image 4 for ‘periosteum removal’ as the next, and lastly, medical image 5 for ‘bone fracture site confirmation’ as the next according to the medical record procedure set by the user definition.

Next, the present invention can support the user terminal (10) to record in various ways the medical image provided from the medical image providing unit (100).

First, the present invention provides a user interface so that a region of interest can be designated in the medical image by at least one of a click, touch, and drag method from a user terminal (10), and further includes a region of interest acquisition unit (400) that acquires a region of interest composed of a point, a line, a plane, a three-dimensional space, or a combination thereof from the user terminal (10), and the medical image providing unit (100) is characterized in that it further provides an edited image reflecting the region of interest in the medical image.

Alternatively, the present invention provides a user interface that allows at least one of voice and text to be input from a user terminal (10), and further includes a user input processing unit (500) that processes at least one of voice data and text data input from the user terminal (10), and the medical image providing unit (100) is characterized in that it provides an edited image that further reflects at least one of the voice data and the text data.

In processing voice data, the user input processing unit (500) may analyze voice data input from the user terminal (10) and extract at least one of a body part name, a diagnosis name, a procedure name, and a surgery name as an attribute value from the voice data. Alternatively, the user input processing unit (500) may convert voice data input from the user terminal (10) into text data and extract at least one of a body part name, a diagnosis name, a procedure name, and a surgery name as an attribute value from the converted text data.

Referring to an example embodiment of FIG. 5, the medical image providing unit (100) may provide a medical image for the body part name "arm" as an original image. The original image may include a skin object and its attribute values.

Referring to an embodiment of FIG. 6, the user terminal (10) can designate a region of interest in the skin object within the original image by dragging. Then, the medical image providing unit (100) can obtain a region of interest comprised of a point, line, plane, three-dimensional space, or a combination thereof from the original image.

And, the user terminal (10) can input ‘incision’, which is one of the surgical methods, as voice data or text data. If ‘incision’ or ‘incision’ is input as text data, the user input processing unit (500) can extract an attribute value for the surgical method called ‘incision’ from the text data. Alternatively, if ‘incision’ or ‘incision’ is input as voice data, the user input processing unit (500) can directly extract an attribute value for the surgical method called ‘incision’ from the voice data. If ‘incision’ or ‘incision’ is input as voice data, the user input processing unit (500) can convert it into text data and then extract an attribute value for the surgical method called ‘incision’ from the converted text data. At this time, the attribute value may be a ‘standard medical terminology’.

Then, as in the example of FIG. 7, the medical image providing unit (100) can provide an edited image that reflects the region of interest acquired from the user terminal (10) and the attribute value for the surgical method called ‘incision’ following the original image or the previous edited image.

Next, when voice data of ‘add traction device’ is input, the user input processing unit (500) can directly extract a traction device object or attribute values for the traction device object from the voice data, or convert the voice data into text data and then extract the traction device object or attribute values for the traction device object. And, as in the embodiment of FIG. 8, the medical image providing unit (100) can provide an edited image that reflects both the region of interest and the traction device object or attribute values for the traction device object acquired from the user terminal (10) next to the original image or the previous edited image.

Next, the medical image recommendation unit (200) may recommend medical images to be provided after the surgical method called "incision" using a preset recommendation algorithm. Alternatively, the medical image recommendation unit (200) may recommend medical images to be provided after the surgical method called "incision" according to a user-defined medical record procedure preset from the user terminal (10).

In the case of a surgical procedure for a fractured arm, as in the example of Fig. 9, the medical image recommendation unit (200) may recommend multiple medical images including multiple retractor objects for “confirming the fracture site” so that the broken arm bone can be confirmed after the surgical procedure called “incision.” Each medical image may include “retractor name” as an attribute value.

At this time, the user terminal (10) can select one or more medical images from a plurality of medical images. Alternatively, the user terminal (10) can select one or more traction device objects from a plurality of traction device objects within a single medical image. Then, as in the embodiment of FIG. 8, the medical image providing unit (100) can provide an edited image reflecting a "traction device" object that secures a field of view by spreading the muscles of the incised region of interest.

Next, the medical image recommendation unit (200) may recommend a number of medical images including a "joint device" object for "joining" so that the broken arm bone can be reattached after the surgical method of "confirming the bone fracture site." Each medical image may include "joint device name" as an attribute value.

At this time, the user terminal (10) can select a ‘prosthetic plate’ object or a medical image including a ‘prosthetic plate’ object from among a plurality of medical images. Alternatively, the user terminal (10) can select a ‘prosthetic plate’ object from among a plurality of joint device objects within a single medical image. Then, as in the embodiment of FIG. 10, the medical image providing unit (100) can provide an edited image reflecting a ‘prosthetic plate’ object for joining a broken bone.

Meanwhile, the medical record system of the present invention is characterized by further including an attribute value providing unit (800) that extracts and stores attribute values for objects in a medical image or attribute values for the region of interest, and displays the extracted attribute values in an attribute value window. As described above, the medical image including the edited image and the original image may include various objects and may include attribute values for each object.

Referring to an embodiment of FIG. 8, when the user terminal (10) clicks on a part of a body part object for a ‘bone’ on a medical image, an area of interest may be designated for a part of the bone object. Then, the attribute value providing unit (800) may provide an attribute value of ‘SNOMED SCTID:23416004’ for the body part object to be displayed in an attribute value window arranged on one side of the medical image. Alternatively, when the user terminal (10) clicks on ‘Bone of Ulna’, which is a body part name for the body part object, in the attribute value window, the attribute value providing unit (800) may provide an attribute value of ‘SNOMED SCTID:23416004’ for the bone object to be displayed in the attribute value window. Alternatively, when the user terminal (10) clicks on an area of interest that overlaps with a part of a body part object on a medical image, the attribute value providing unit (800) can extract and store an attribute value called ‘SNOMED SCTID:23416004’ for the area of interest in an attribute value window, and display the attribute value in the attribute value window.

Next, in recording, referring to an embodiment of FIG. 11, the storage unit (300) can group and store some or all of the medical images provided from the medical image providing unit (100). At this time, the storage unit (300) can store the medical images in the order provided from the medical image providing unit (100) along with the order information.

In addition, the medical record system of the present invention is characterized by further including a medical record image generation unit (600) that generates a medical record image by listing a plurality of medical images according to the order information stored in the storage unit (300) so that the medical record can be intuitively confirmed.

In general, an image includes multiple frames, or images, and can be visualized as an object moving within the image as multiple frames pass over time. In this way, the record image generation unit (600) can generate a medical record image for the corresponding medical record by using the sequence information stored in the storage unit (300) and multiple medical images provided from the medical image provision unit (100). Therefore, while in the past, users checked medical records written in simple text format using difficult medical terms, the present invention enables medical record confirmation by recording diagnosis processes, treatment processes, examination processes, treatment processes, and surgical processes in images that are easy for both users and examinees to intuitively understand.

In addition, the medical record system of the present invention is characterized by further including a human body model providing unit (700) that provides a human body model that visualizes the human body and displays the positions of body part objects and the positions of the regions of interest in the medical image on the human body model. Referring to an embodiment of FIG. 12, the human body model providing unit (700) can set a view from 0 degrees to 360 degrees based on the x-axis, y-axis, and z-axis. Therefore, by moving the human body model, the user can visually confirm the positions of body part objects and the positions of the regions of interest on the human body model at a desired point in time. In addition, there is a remarkable effect that the examinee can increase his or her understanding of his or her own treatment process and results, diagnosis process and results, surgical process and results, and surgical process and results.

Meanwhile, the medical record system of the present invention is characterized by further including a record writing unit (900) that records and provides a plurality of medical images and attribute values included therein provided from the medical image providing unit (100) according to a record form including a surgical record, a progress record, and a medical record, according to the order information stored in the storage unit (300).

Specifically, the record writing unit (900) of the present invention can further record at least one of text data extracted from the text data analysis unit (110), voice data and text data input from the user input processing unit (500), attribute values extracted therefrom, attribute values of an object selected from the user terminal (10), and attribute values of an area of interest designated from the user terminal (10) according to a record form including a surgical record, a progress record, and a medical record, according to the order information. The record writing unit (900) can provide the record in JSON or XML format.

For example, the record writing unit (900) may provide a record in which the surgical method (Action) and the body part name (Target) are recorded together with the ‘incision image’ of the embodiment of FIG. 7, and the attribute value ‘{action:incision, target:skin}’ is recorded.

Alternatively, the user input processing unit (500) may receive at least one of voice data and text data such as ‘Fracture site was not identified, so additional soft tissue dissection was performed. Fracture site confirmed.’ from the user terminal (10) to enable a detailed description of the surgical procedure. In addition, the storage unit (300) may store the data so that it can be displayed together with the corresponding edited image in the future. Accordingly, the record writing unit (900) may provide a record that further includes the surgical content such as ‘Fracture site was not identified, so additional soft tissue dissection was performed. Fracture site confirmed’ along with the attribute values of ‘incision image’ and ‘{action:incision, target:skin}’.

Alternatively, the user input processing unit (500) may receive at least one of voice data or text data such as ‘add traction device’ from the user terminal (10). In addition, the storage unit (300) may store the data so that it can be displayed together with the corresponding edited image in the future. Accordingly, the record writing unit (900) may provide a record that further includes an attribute value for the fracture site name and an attribute value for the traction device object, along with an ‘incision image’, an attribute value of ‘{action:incision, target:skin}’, and a surgical content such as ‘fracture site not confirmed, so additional soft tissue dissection was performed. Fracture site confirmed’.

Alternatively, the record writing unit (900) may provide a record written with only attribute values included in a plurality of medical images provided from the medical image providing unit. For example, the attribute values may include the body part name ‘Forearm’, the surgical instrument name ‘Surgical knife’, and the operation name ‘Incision’. The record writing unit (900) may provide a record in the form of a simple surgical note by simply listing the attribute values.

Alternatively, the record writing unit (900) is characterized in that it writes the record in sentence format by inputting attribute values included in a plurality of medical images provided from the medical image providing unit (100) into the generative AI model. Here, like the generative AI model ChatGPT, it is an artificial intelligence model that creates new creations through comparative learning with existing data.

For example, a generative AI model can be input with attribute values including the body part name ‘Forearm’ and the surgery name ‘Incision’. Then, the generative AI model can output multiple sentences such as ‘Surgery was performed on the patient’s forearm. This involved a small incision to access the forearm muscles and blood vessels. The surgery was performed according to normal medical procedures, and the medical staff did their best to provide quick and safe patient care.’ Then, the record writing unit (900) can write multiple sentences output from the generative AI model on the record. At this time, the generative AI model can output multiple sentences without being limited to a specific language such as English/Korean.

Alternatively, the generative AI model may be input with attribute values including the body part name ‘Forearm’, the surgical tool name ‘surgical knife (SNOMED SCTID: 102307003)’, and the surgery name ‘Incision’. Then, the generative AI model may output multiple sentences such as ‘Surgery was performed on the patient’s forearm. This surgery used a surgical knife (SNOMED SCTID: 102307003), and an incision was made on the forearm.’ Then, the record writing unit (900) may write multiple sentences output from the generative AI model on the record.

Therefore, the record writing unit (900) of the present invention has a remarkable effect of being able to write records including surgical records, progress records, and medical records in text format or a combination of text format and image format, and provide the records to a user terminal (10).

Embodiments may be implemented in hardware, software, firmware, middleware, microcode, hardware description language, or any combination thereof. When implemented in software, firmware, middleware, or microcode, program code or code segments that perform the necessary tasks may be stored on a computer-readable storage medium and executed by one or more processors.

Aspects of the subject matter described herein may be described in the general context of computer-executable instructions, such as program modules or components, being executed by a computer. Typically, program modules or components include routines, programs, objects, and data structures that perform particular tasks or implement particular data formats. Aspects of the subject matter described herein may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media, including memory storage devices.

Although the embodiments described above have been described by way of limited examples and drawings, those skilled in the art will appreciate that various modifications and variations can be made based on the above description. For example, appropriate results can be achieved even if the described techniques are performed in a different order than described, and/or components of the described systems, structures, devices, circuits, etc. are combined or combined in a different manner than described, or are replaced or substituted with other components or equivalents.

Therefore, other implementations, other embodiments, and equivalents to the claims also fall within the scope of the claims described below.

100.. Medical Image Provider
110.. Text Data Analysis Department
120.. Medical Image Analysis Department
200.. Medical Image Recommendation Department
300.. storage
400.. Area of interest acquisition section
500.. User input processing unit
600.. Medical Record Image Generation Department
700.. Human body model provider
800.. Attribute value provider
900. Record preparation department
10.. User terminal
20.. Electronic Medical Record (EMR) Server
30.. Medical institution server

Claims (14)

Medical image provision department that provides medical images visualizing the medical data of the subject;
A medical image recommendation unit that recommends the medical images to be provided next by the above medical image provision unit; and
A medical record system comprising a storage unit that stores sequence information about the sequence provided from the medical image providing unit. In the first paragraph,
The above medical image provider,
A text data analysis unit that analyzes text data among the above medical data and extracts at least one of a body part name, a diagnosis name, a procedure name, and a surgery name from the text data;
A medical record system characterized in that it provides one or more medical images related to at least one of a body part name, a diagnosis name, a procedure name, and a surgical name as an original image. In the first paragraph,
The above medical image provider,
Further comprising a medical image analysis unit that outputs at least one of a body part name, a diagnosis name, a procedure name, and a surgical name by inputting a medical image among the above medical data into a preset image analysis algorithm;
A medical record system characterized in that it provides one or more medical images related to at least one of a body part name, a diagnosis name, a procedure name, and a surgical name as an original image. In the first paragraph,
The above medical image recommendation section is,
A medical record system characterized by recommending medical images according to a preset medical record procedure from a user terminal. In the first paragraph,
The above medical image recommendation section is,
A medical record system characterized by recommending medical images using a preset recommendation algorithm. In the first paragraph,
The above medical image provider,
Accumulate and store selected selection data from the same user terminal,
A medical record system characterized in that it provides one or more medical images having a high selection probability among a plurality of medical images recommended by the medical image recommendation unit based on selection data selected from the same user terminal. In the first paragraph,
Provides a user interface so that a region of interest can be designated in the medical image by at least one of a click, touch, and drag method from a user terminal, and further includes a region of interest acquisition unit that acquires a region of interest composed of a point, a line, a plane, a three-dimensional space, or a combination thereof from the user terminal;
The above medical image provider,
A medical record system characterized in that it further provides an edited image reflecting the area of interest in the medical image. In paragraph 7,
A medical record system further comprising an attribute value providing unit that extracts and stores attribute values for an object in a medical image or an area of interest, and displays the extracted attribute values in an attribute value window. In the first paragraph,
Provides a user interface so that at least one of voice and text can be input from a user terminal, and further includes a user input processing unit that processes at least one of voice data and text data input from the user terminal;
The above medical image provider,
A medical record system characterized in that it provides an edited image that further reflects at least one of the above voice data and the above text data. In the first paragraph,
The above medical image provider,
A medical record system characterized by linking with a medical institution server or an electronic medical record (EMR) server to retrieve the medical data and store the retrieved medical data. In the first paragraph,
A medical record system further comprising a medical record image generation unit that generates a medical record image by listing a plurality of medical images according to the order information stored in the storage unit so that the medical record can be intuitively checked. In paragraph 7,
A medical record system, characterized in that it further includes a human body model providing unit that provides a human body model visualizing the human body and displays the location of a body part object and the location of the region of interest in the medical image on the human body model. In the first paragraph,
A medical record system further comprising a record writing unit that records and provides a plurality of medical images and attribute values included therein provided from the medical image providing unit according to a record form including a surgical record, a progress record, and a medical record, according to the order information stored in the storage unit. In Article 13,
The above record-making department,
A medical record system characterized in that a record is created in sentence format by inputting attribute values included in a plurality of medical images provided from the medical image provider into a generative AI model.