CN111696640A - Method, device and storage medium for automatically acquiring medical record template - Google Patents
Method, device and storage medium for automatically acquiring medical record template Download PDFInfo
- Publication number
- CN111696640A CN111696640A CN202010535511.9A CN202010535511A CN111696640A CN 111696640 A CN111696640 A CN 111696640A CN 202010535511 A CN202010535511 A CN 202010535511A CN 111696640 A CN111696640 A CN 111696640A
- Authority
- CN
- China
- Prior art keywords
- medical record
- template
- medical
- record template
- keywords
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 73
- 230000001575 pathological effect Effects 0.000 claims abstract description 72
- 230000011218 segmentation Effects 0.000 claims description 55
- 230000008569 process Effects 0.000 claims description 18
- 238000012545 processing Methods 0.000 claims description 13
- 238000000605 extraction Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 10
- 238000010276 construction Methods 0.000 claims description 8
- 238000007781 pre-processing Methods 0.000 claims description 8
- 230000007170 pathology Effects 0.000 claims description 5
- 210000004072 lung Anatomy 0.000 description 17
- 238000002059 diagnostic imaging Methods 0.000 description 14
- 238000010586 diagram Methods 0.000 description 12
- 230000006870 function Effects 0.000 description 12
- 230000003902 lesion Effects 0.000 description 12
- 238000013528 artificial neural network Methods 0.000 description 9
- 230000002159 abnormal effect Effects 0.000 description 8
- 238000004891 communication Methods 0.000 description 8
- 238000003384 imaging method Methods 0.000 description 8
- 230000002146 bilateral effect Effects 0.000 description 6
- 238000003672 processing method Methods 0.000 description 6
- 210000000115 thoracic cavity Anatomy 0.000 description 5
- 210000000621 bronchi Anatomy 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 210000001370 mediastinum Anatomy 0.000 description 4
- 210000004224 pleura Anatomy 0.000 description 4
- 230000002829 reductive effect Effects 0.000 description 4
- 239000013598 vector Substances 0.000 description 4
- 210000001165 lymph node Anatomy 0.000 description 3
- 230000002441 reversible effect Effects 0.000 description 3
- 208000031481 Pathologic Constriction Diseases 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 210000000038 chest Anatomy 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 239000012530 fluid Substances 0.000 description 2
- 230000000670 limiting effect Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000036961 partial effect Effects 0.000 description 2
- 210000003281 pleural cavity Anatomy 0.000 description 2
- 238000011176 pooling Methods 0.000 description 2
- 238000012552 review Methods 0.000 description 2
- 230000036262 stenosis Effects 0.000 description 2
- 208000037804 stenosis Diseases 0.000 description 2
- 230000008719 thickening Effects 0.000 description 2
- 210000001519 tissue Anatomy 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 206010061218 Inflammation Diseases 0.000 description 1
- 208000008771 Lymphadenopathy Diseases 0.000 description 1
- 206010028980 Neoplasm Diseases 0.000 description 1
- 206010035588 Pleural adhesion Diseases 0.000 description 1
- 206010035600 Pleural fibrosis Diseases 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000002457 bidirectional effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000003759 clinical diagnosis Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000011982 device technology Methods 0.000 description 1
- 230000008034 disappearance Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000004054 inflammatory process Effects 0.000 description 1
- 238000003331 infrared imaging Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 238000002595 magnetic resonance imaging Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 238000009206 nuclear medicine Methods 0.000 description 1
- 238000012634 optical imaging Methods 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000002601 radiography Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 238000002603 single-photon emission computed tomography Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000001931 thermography Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 210000003462 vein Anatomy 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/166—Editing, e.g. inserting or deleting
- G06F40/186—Templates
Landscapes
- Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Epidemiology (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The application relates to a method, a device and a storage medium for automatically acquiring a medical record template, wherein the automatically acquiring the medical record template comprises the following steps: constructing a medical record template database; acquiring medical information of a subject; obtaining pathological keywords of corresponding examinees according to the medical information; and automatically outputting a medical record template according to the pathological keywords and the medical record template database. The obtained medical information is automatically identified to obtain pathological keywords, corresponding medical record templates are searched in a database in which a large number of medical record templates are stored through the pathological keywords, and time and energy for doctors to record reports are saved by obtaining the medical record templates.
Description
Technical Field
The present application relates to the field of medical device technology, and in particular, to a method, an apparatus, and a storage medium for automatically acquiring a medical record template.
Background
Medical imaging refers to the technique and process of obtaining images of internal tissues of a human body or a part of the human body in a non-invasive manner for medical treatment or medical research. It contains the following two relatively independent directions: medical imaging systems (medical imaging systems) and medical image processing (medical image processing). The former refers to the process of image formation, including the problems of analysis of imaging mechanism, imaging equipment, imaging system, etc.; the latter means that the already acquired image is further processed in order to make the originally less sharp image more sharp. After the medical imaging device is examined, a doctor usually needs to present a clinical diagnosis report according to the image generated by the medical imaging device.
In the conventional technology at present, after the medical image is generated by the medical imaging device, the physician needs to review the medical image and manually print all the words in the report. And manually reporting by the physician consumes a great deal of time and effort by the physician.
Disclosure of Invention
The embodiment of the application provides a method, a device, a computer device and a storage medium for automatically acquiring a medical record template, so as to at least solve the problem that the manual report of a physician in the related art consumes a great deal of time and energy of the physician.
In a first aspect, an embodiment of the present application provides a method for automatically acquiring a medical record template, including: constructing a medical record template database; acquiring medical information of a subject; obtaining pathological keywords of corresponding examinees according to the medical information; and automatically outputting a medical record template according to the pathological keywords and the medical record template database.
In one embodiment, the obtaining the pathological keywords of the corresponding subject according to the medical information includes: the medical information comprises medical text and/or medical images; inputting the medical image into a recognition model to obtain focus information; and extracting the focus information and/or the keywords of the medical text to obtain the pathological keywords of the corresponding examinee.
In one embodiment, the constructing a medical record template database includes: acquiring a case text with complete record, and preprocessing the case text to obtain a case history template; performing word segmentation processing on the medical record template to obtain all words corresponding to the medical record template; and extracting template keywords according to all the word segments, and establishing a medical record template database of the template keywords and corresponding medical record templates.
In one embodiment, the acquiring a medical record text with a complete record, and preprocessing the medical record text to obtain a medical record template includes: acquiring a case text with complete record; extracting sensitive words, interference words and stop words according to the case text with complete records; and hiding the sensitive words, the interference words and the stop words in the case text to obtain a medical record template.
In one embodiment, the word segmentation process comprises: a word segmentation process based on string matching, a word segmentation process based on understanding, and a word segmentation process based on statistics.
In one embodiment, the extracting a template keyword according to all the participles and establishing a medical record template database of the template keyword and a corresponding medical record template includes: inputting the word segmentation into a keyword extraction model to obtain the template keyword; and establishing a medical record template database of the template keyword and the corresponding medical record template.
In one embodiment, the inputting the word segmentation into a keyword extraction model to obtain the template keyword includes: acquiring the occurrence frequency of each word in the medical record template, the total word number of the medical record template, the total number of the medical record templates and the number of the medical record templates in which each word appears; obtaining the word frequency of the corresponding participle according to the times of the participle appearing in the medical record template and the total word number of the corresponding medical record template; obtaining the inverse document frequency of the corresponding word segmentation according to the number of medical record templates with the word segmentation and the total number of the medical record templates; and obtaining the template keyword according to the word frequency and the inverse document frequency.
In one embodiment, automatically outputting the medical record template according to the pathology keyword and the medical record template database includes: calculating the similarity between the corresponding pathological keyword and each medical record template according to the pathological keyword and the template keyword of each medical record template in the medical record template database; and selecting the medical record template corresponding to the highest similarity as the final medical record template.
In a second aspect, an embodiment of the present application provides an apparatus for automatically acquiring a medical record template, including: the database construction module is used for constructing a medical record template database; a medical information acquisition module for acquiring medical information of a subject; the keyword extraction module is used for obtaining pathological keywords of corresponding examinees according to the medical information; and the medical record template acquisition module is used for automatically outputting a medical record template according to the pathological keywords and the medical record template database.
In a third aspect, an embodiment of the present application provides a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor executes the computer program to implement the method for automatically acquiring a medical record template according to the first aspect.
In a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the method for automatically acquiring a medical record template as described in the first aspect.
Compared with the related technology, the method for automatically acquiring the medical record template provided by the embodiment of the application acquires the medical information of the examinee, generates the pathological keywords of the examinee according to the acquired medical information, and finally acquires the medical record template according to the pathological keywords and the medical record template database. The obtained medical information is automatically identified to obtain pathological keywords, corresponding medical record templates are searched in a database in which a large number of medical record templates are stored through the pathological keywords, and time and energy for doctors to record reports are saved by obtaining the medical record templates.
The details of one or more embodiments of the application are set forth in the accompanying drawings and the description below to provide a more thorough understanding of the application.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
FIG. 1 is a flow diagram illustrating a method for automatically obtaining medical record templates, according to one embodiment;
FIG. 2 is a schematic diagram of a lesion recognition neural network according to an embodiment;
FIG. 3 is a schematic flow chart diagram illustrating a method for constructing a medical record template database, according to one embodiment;
FIG. 4 is a flow diagram illustrating a method for automatically obtaining medical record templates, according to one embodiment;
FIG. 5 is a block diagram of an apparatus for automatically obtaining medical record templates, according to one embodiment;
fig. 6 is a schematic hardware configuration diagram of a computer device in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be described and illustrated below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments provided in the present application without any inventive step are within the scope of protection of the present application.
It is obvious that the drawings in the following description are only examples or embodiments of the present application, and that it is also possible for a person skilled in the art to apply the present application to other similar contexts on the basis of these drawings without inventive effort. Moreover, it should be appreciated that in the development of any such actual implementation, as in any engineering or design project, numerous implementation-specific decisions must be made to achieve the developers' specific goals, such as compliance with system-related and business-related constraints, which may vary from one implementation to another.
Reference in the specification to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the specification. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of ordinary skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments without conflict.
Unless defined otherwise, technical or scientific terms referred to herein shall have the ordinary meaning as understood by those of ordinary skill in the art to which this application belongs. Reference to "a," "an," "the," and similar words throughout this application are not to be construed as limiting in number, and may refer to the singular or the plural. The present application is directed to the use of the terms "including," "comprising," "having," and any variations thereof, which are intended to cover non-exclusive inclusions; for example, a process, method, system, article, or apparatus that comprises a list of steps or modules (elements) is not limited to the listed steps or elements, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus. Reference to "connected," "coupled," and the like in this application is not intended to be limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The term "plurality" as referred to herein means two or more. "and/or" describes an association relationship of associated objects, meaning that three relationships may exist, for example, "A and/or B" may mean: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship. Reference herein to the terms "first," "second," "third," and the like, are merely to distinguish similar objects and do not denote a particular ordering for the objects.
The medical imaging apparatus includes an X-ray imaging apparatus (digital radiography, CT, X-ray machine), a magnetic resonance imaging apparatus, an ultrasonic imaging apparatus (a-type, B-type, C-type, M-type, and the like), a thermal imaging apparatus (infrared imaging, optical scanning imaging, and the like), a nuclear medicine imaging apparatus (PET, SPECT, and the like), and an optical imaging apparatus (medical endoscopic imaging). The present application is applicable to any one of the above devices or a combination of devices.
The embodiment also provides a method for automatically acquiring the medical record template. Fig. 1 is a schematic flowchart of a method for automatically acquiring a medical record template in an embodiment, as shown in fig. 1, the flowchart includes the following steps:
and step S102, constructing a medical record template database.
Specifically, a large number of case texts that the physician has recorded are acquired. And preprocessing the case text to hide partial words. And performing word segmentation processing on the case text after the words are hidden to obtain a plurality of word segments. And finally, selecting template keywords for the corresponding case text according to the occurrence frequency of each participle. And corresponding the selected template keywords with the corresponding case texts to construct a medical record template database.
Step S104, acquiring medical information of the examinee.
Specifically, the subject may be a human body. The medical information includes: medical text and/or medical images. The examinee is scanned by the medical imaging equipment, and a corresponding medical image is generated. The medical image acquisition may be a medical image generated by directly acquiring a subject after scanning the subject by a medical imaging device; the medical image acquisition may also be to scan the subject through a medical imaging device to obtain a medical image, store the medical image in a memory, and acquire the medical image from the memory when needed. The medical imaging device may be any one of the above devices or a combination of multiple devices. The medical text is a pathological vocabulary selected by a physician or a pathological description written by the physician.
And step S106, obtaining pathological keywords of corresponding examinees according to the medical information.
Specifically, if the medical information is a medical text, extracting keywords of the medical text to obtain pathological keywords of the corresponding examinee. If the medical information is a medical image, inputting the medical image into an identification model to obtain focus information; and extracting the keywords of the focus information to obtain the pathological keywords of the corresponding examined person. The recognition model can be a recognition model established based on a neural network or a recognition model established based on machine learning, and the embodiment is not particularly limited, and only the condition that the pathological keywords can be recognized according to the images is satisfied. Taking a recognition model established based on a neural network as an example, before a medical image is input to a completely trained focus recognition neural network, a physician needs to label a key region, wherein the label can be one or more of a point label, a line label, a face label and a volume label, and the form of the label can be represented by coordinates. Wherein the emphasized region may be a region in the image having an abnormality. The labeled medical image is input into a completely trained focus recognition neural network to obtain focus information, wherein the focus information includes tumors, inflammations, masses, abnormal organ morphological signals and the like. Extracting keywords or other pathological feature expression modes according to the output pathological information, preferably extracting pathological keywords based on the pathological information.
In one embodiment, as shown in fig. 2, fig. 2 is a schematic structural diagram of a lesion recognition neural network in one embodiment. The focus recognition neural network comprises: input layer, convolution layer, batch normalization layer, pooling layer, full-link layer, loss layer, and output layer. The input layer is used for inputting data. The input data during the training process is a doctor labeled medical image training sample. And the convolutional layer is used for carrying out feature extraction and feature mapping. The low convolution layer may only extract some low-level features such as edges, lines, corners and other levels, and the network of more layers can iteratively extract more complex features from the low-level features. And the batch normalization layer is used for forcibly pulling the input distribution which is gradually mapped to the nonlinear function and then is close to the extreme saturation region of the value-taking interval back to the standard normal distribution with the mean value of 0 and the variance of 1 so that the input value of the nonlinear transformation function falls into a region which is sensitive to input, thereby avoiding the problem of gradient disappearance. The pooling layer is used for down-sampling data, learning and classifying multi-scale data features, improving the classification identification degree of model classification, providing nonlinearity, reducing the number of model parameters and reducing the over-fitting problem. And the full connection layer is used for performing refitting at the tail part of the model, so that the loss of characteristic information is reduced. And a loss layer, which accepts two inputs, one of which is a prediction value of the neural network and the other of which is a real label. The loss layer carries out a series of operations on the two inputs to obtain a loss function of the current network. The purpose of deep ferry learning is to find the weight that minimizes the loss function in the weight space. The loss function is obtained in the forward propagation calculation and is also the starting point of the backward propagation, the loss function basically consists of a real value and a predicted value, the correct loss function can achieve the effect of enabling the predicted value to approach the real value all the time, and when the predicted value and the real value are equal, the loss value is the minimum. The loss function employed in the present embodiment is preferably a normalized exponential function, a cross-entropy loss function, or a squared error loss function. And the output layer is used for outputting the result pathological classification result, wherein the result pathological classification result is pathological information in the example. The focus information is obtained by identifying the medical image through the focus identification neural network, so that the problem of error or deviation in obtaining the focus information caused by insufficient experience of a doctor can be avoided, the accuracy of the focus information is greatly improved, the workload of the doctor is reduced, and a large amount of time resources are saved for the doctor.
In one embodiment, the keyword of the lesion information is extracted to obtain a pathological keyword of the corresponding subject, which may specifically be: the lesion information includes bilateral thoracic symmetry and central tracheal mediastinum. The right thorax is seen in a flaky transparent area without lung texture, a small amount of effusion is seen in the thorax, the adjacent lung tissues are compressed by about X%, the textures of the two rest lungs are clear, no obvious space occupying lesion is seen in the two lungs, and the bronchus of each lung segment is clear in opening and no obvious stenosis is seen. No obvious enlarged lymph nodes are found in the mediastinum and bilateral pulmonis. No significant thickening of the bilateral pleura was seen. The pathological keywords extracted based on the focus information are lung, flaky non-lung-texture lucent areas and effusion.
In one embodiment, the keyword of the lesion information is extracted to obtain a pathological keyword of the corresponding subject, which may specifically be: the lesion information includes bilateral thoracic symmetry and central tracheal mediastinum. The veins of the two lungs are clear, the posterior basal segment of the right lung inferior lobe shows an irregular large compact image, the boundary is not clear, the center of the focus shows a liquid low-density area and a small cavity image, the adjacent pleura is thickened and adhered, the rest two lungs do not have obvious space occupying lesion, and the opening of the bronchus of each lung segment is clear and does not have obvious stenosis. No obvious enlarged lymph nodes are found in the mediastinum and bilateral pulmonis. No obvious fluid accumulation was observed in the bilateral thoracic cavities. The pathological keywords extracted based on the focus information include lung, dense shadow, unclear boundary, cavity shadow, pleural thickening and adhesion.
And step S108, automatically outputting a medical record template according to the pathological keywords and the medical record template database.
Specifically, the medical record template database comprises medical record templates and template keywords of corresponding pathology templates. Calculating the similarity between the corresponding pathological keyword and each medical record template according to the pathological keyword and the template keyword of each medical record template in the medical record template database; and selecting the medical record template corresponding to the highest similarity as the final medical record template. More specifically, the method may include searching a template keyword including the pathological keyword in a medical record template database according to the pathological keyword, and then finding a medical record template corresponding to the template keyword, for example, the pathological keyword includes lung and effusion, searching a template keyword including lung and effusion in the database, and then correspondingly finding a corresponding medical record template. Or converting the pathological keywords and the template keywords into word vectors through word2vec, calculating cosine similarity between the word vectors of the pathological keywords and the word vectors of all the template keywords, and taking the medical record template corresponding to the template keyword with the highest cosine similarity as the final medical record template. Where word2vec is a group of correlation models used to generate word vectors.
In the conventional technology, after a medical image is generated by a medical imaging device, a physician may review the medical image, mark a focus area, and analyze pathological information of the corresponding area according to the focus area image. For example, "the pleural cavity has a flaky and bright area without lung texture, and a small amount of fluid is present in the pleural cavity," thickening and adhesion of adjacent pleura, "" enlarged lymph nodes, "and opening of bronchus of each lung segment is narrow. In order to facilitate the physician to continuously monitor the pathology of the patient, after obtaining the pathology information, the physician usually writes a case report of the corresponding patient in combination with the identity information of the patient. Generally, case reports need to be written by doctors, and some case templates are acquired during the writing process to assist the doctors to quickly complete the writing of the case reports. However, the types of medical record templates are few at present, only a part of medical record templates in common lesion areas exist, and for uncommon pathological information, a doctor needs to write the whole case text by himself, which consumes a lot of time and energy of the doctor. The embodiment provides a method for automatically acquiring medical record templates, which comprises the steps of constructing a medical record template database, storing a large number of medical record templates in the medical record template database, extracting pathological keywords according to medical information of an examinee, searching medical record templates corresponding to the corresponding pathological keywords in the medical record template database through the pathological keywords, finding corresponding templates aiming at all the pathological keywords due to the fact that a large number of templates are stored in the medical record template database, completing writing of case texts only by filling pathological information to corresponding positions in the templates after the templates are acquired, and greatly reducing the time for a doctor to write the case texts.
According to the method for automatically acquiring the medical record template, the medical information of the examinee is acquired, the pathological keywords of the examinee are generated according to the acquired medical information, and finally the medical record template is acquired according to the pathological keywords and the medical record template database. The obtained medical information is automatically identified to obtain pathological keywords, corresponding medical record templates are searched in a database in which a large number of medical record templates are stored through the pathological keywords, and time and energy for doctors to write reports are saved by obtaining the medical record templates.
In some embodiments, a method for constructing a medical record template database is further provided, and fig. 3 is a schematic flowchart of the method for constructing a medical record template database in an embodiment, as shown in fig. 3, the flowchart includes the following steps:
step S302, a case text with complete records is obtained, and the case text is preprocessed to obtain a case history template.
Specifically, based on different medical imaging devices and different hospitals, a large number of cases of which the doctors have recorded complete cases are obtained. And preprocessing a large amount of acquired case texts to obtain a pathological template, wherein the preprocessing is to hide sensitive words, interference words and stop words in the case texts or replace the sensitive words, the interference words and the stop words by blank placeholders. More specifically, a case text with complete records is obtained; extracting sensitive words, interference words and stop words according to the case text with complete records; and hiding the sensitive words, the interference words and the stop words in the case text to obtain a medical record template. Wherein the sensitive words include the name, age, and variable data of the lesion of the subject. The variable data of the lesion include: size and length of the lesion. Removing noise includes removing a noise symbol, for example, [ "\", "" ═ "", "\ \/" ":" "-" (") can be removed. Symbol "\ n" ] and the like. Removing stop words includes removing the co-words "what" is "," on ", etc. Some irrelevant words, such as "has", "is", etc., may also be removed. It is also possible to extract stems and convert similar words into a standard form, for example, converting "above" to "over" and the like. Through the pretreatment of the case text, a large number of interfering vocabularies are removed, and the subsequent word segmentation treatment can be more accurate.
Step S304, performing word segmentation processing on the medical record template to obtain all word segments corresponding to the medical record template.
Specifically, word segmentation is a process of recombining continuous word sequences into word sequences according to a certain specification. The word segmentation processing comprises the following steps: a word segmentation process based on string matching, a word segmentation process based on understanding, and a word segmentation process based on statistics. The word segmentation processing method is not specifically limited in this embodiment, and the word segmentation is completed only according to the word segmentation processing method.
In one embodiment, the word segmentation processing method based on character string matching comprises the following steps: this requires a sufficiently large matchable dictionary that stores many entries, and the computer then matches these existing entries to complete a segmentation. Many medical professional vocabularies are encountered in clinical use, so that medical experts need to be found to establish a corresponding medical professional vocabulary database, and word segmentation is performed on the basis of the database. The word segmentation method for character string matching can be divided into forward matching and reverse matching according to different searching directions; according to the condition of preferential matching with different lengths, the method can be divided into longest matching and shortest matching. The currently common string matching method includes: a forward maximum matching method, a reverse maximum matching method, a least-squares method, and a two-way maximum matching method. The positive maximum matching method is to match the character strings from left to right; the reverse maximum matching method is to match the character strings from right to left; the least segmentation method is to minimize the number of words cut out from each sentence; the bidirectional maximum matching method is to match twice from left to right and from right to left of the character string. The string matching method may also be a combination of the above matching methods. Preferably, some words with obvious characteristics can be preferentially identified and segmented in the character string to be analyzed, the words are used as breakpoints, the original character string can be segmented into smaller strings, and then the character string is segmented, so that the matching error rate is reduced.
In one embodiment, the comprehension-based word segmentation processing method is that a computer simulates the comprehension of a sentence of a human being as much as possible, the computer analyzes syntax and semantics during word segmentation, and ambiguity is processed by using syntax information and semantic information. Understanding-based word segmentation methods typically include three components: word segmentation subsystem, syntax semantic subsystem, and master control part. Under the coordination of the master control part, the word segmentation subsystem can obtain syntactic and semantic information of related words, sentences and the like to judge word segmentation ambiguity, namely the word segmentation subsystem simulates the process of understanding sentences by people. This word segmentation method requires the use of a large amount of linguistic knowledge and information.
In one embodiment, the statistical-based word segmentation processing method is used in a context in which the more times adjacent words appear simultaneously, the more likely it is that a word is formed. Therefore, the frequency or probability of the co-occurrence of the characters and the adjacent characters can better reflect the credibility of the words. The frequency of the combination of adjacent co-occurring words in the material can be counted to calculate their co-occurrence information. The co-occurrence information is the adjacent co-occurrence probability of two Chinese characters X, Y. The mutual-occurrence information embodies the closeness of the combination relationship between the Chinese characters. When the degree of closeness is above a certain threshold, i.e. the mutual information is above a threshold, it is considered that the word group may constitute a word. Preferably, the statistical word segmentation processing method can provide a large amount of texts with segmented words, and then train corresponding word segmentation models by using a word segmentation mode and a word segmentation method of a machine learning text, so as to achieve word segmentation of unknown texts.
And step S306, extracting template keywords according to all the participles, and establishing a medical record template database of the template keywords and corresponding medical record templates.
Specifically, the word segmentation is input into a keyword extraction model to obtain the template keyword, wherein an algorithm for extracting the keyword comprises: TF-IDF, TextRank, word2vec, and the like. TF-IDF is a statistical method to evaluate the importance of a word to one of a set of documents or a corpus. The TextRank is to construct a network through adjacent relations between words, then calculate the importance degree of each word by using ranking iteration, and obtain the keywords by sequencing the importance degrees. And finally, establishing a medical record template database of the template keyword and the corresponding medical record template.
In one embodiment, the template keyword is obtained through a TF-IDF algorithm. Firstly, the occurrence frequency of each word in the medical record template, the total word number of the medical record template, the total number of the medical record templates and the number of the medical record templates in which each word appears are obtained. Wherein, the occurrence frequency of each word in the medical record template is the total occurrence frequency of the same word in the current text; the total number of the medical record templates is the total number of the acquired case texts with complete records; the number of the medical record templates of each participle is the total number of the medical record templates of the same participle. And obtaining the word frequency of the corresponding participle according to the times of the participle appearing in the medical record template and the total word number of the corresponding medical record template. Considering that the medical record templates have a short word number, in order to compare different medical record templates, the word frequency and the word frequency need to be calculated
According to the number of medical record templates with word segmentationAnd the total number of the medical record templates to obtain the inverse document frequency of the corresponding word segmentation. In particular, inverse document frequency
The more common a word is, the larger the inverse document frequency is, the closer to 0 the inverse document frequency is, the denominator is increased by 1 in order to avoid the denominator being 0, finally, the template keyword is obtained from the word frequency and the inverse document frequency, TF-IDF (TF) × Inverse Document Frequency (IDF), the larger the TF-IDF value is, the more important this word is, which can also be said to be a template keyword.
By the method for constructing the medical record template database, medical record templates containing all conditions can be obtained based on a large amount of completely recorded case texts, and the diversified medical record templates can better provide services for doctors, so that the time for the doctors to write a single report is further reduced, and the quality of the report is improved.
In one embodiment, as shown in fig. 4, fig. 4 is a flowchart illustrating a method for automatically obtaining a medical record template in one embodiment. Firstly, a human body is scanned through medical imaging equipment to obtain a medical image, a doctor technician can label an abnormal region in the medical image, the labeled medical image is input into a deep learning network, and the medical image can be divided into a picture region without abnormal marks and a picture region with abnormal marks after labeling. The abnormal mark can mark the abnormal area through a circular wire frame or a rectangular wire frame, and the wire frame can be in more obvious colors such as red, green and the like so as to be convenient for subsequent viewing. According to the medical image, an image with an abnormal mark is extracted, and the image of the abnormal area is input into a deep learning network to obtain identified pathological information, for example, a chest cavity is seen in a flaky transparent area without lung textures, a small amount of effusion is seen in the chest cavity, adjacent pleura is thickened and adhered, swollen lymph nodes, opening of bronchus of each lung segment leaf is narrowed, and the like. And extracting keywords according to the pathological information, preprocessing the pathological information, hiding sensitive words, interference words and stop words in the pathological information or replacing the sensitive words, the interference words and the stop words by using blank placeholders, performing word segmentation processing on the pathological information, and taking partial segmented words as the keywords. And comparing the similarity of the identified pathological keywords with template keywords of medical record templates in a medical record template database, and outputting the most similar medical record template.
It should be noted that the steps illustrated in the above-described flow diagrams or in the flow diagrams of the figures may be performed in a computer system, such as a set of computer-executable instructions, and that, although a logical order is illustrated in the flow diagrams, in some cases, the steps illustrated or described may be performed in an order different than here.
The embodiment also provides a medical record template acquisition device, which is used for implementing the above embodiments and preferred embodiments, and the description of the device is omitted. As used hereinafter, the terms "module," "unit," "subunit," and the like may implement a combination of software and/or hardware for a predetermined function. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware, or a combination of software and hardware is also possible and contemplated.
Fig. 5 is a block diagram illustrating an apparatus for automatically acquiring a medical record template according to an embodiment, as shown in fig. 5, the apparatus includes: the system comprises a database construction module 100, a medical information acquisition module 200, a keyword extraction module 300 and a medical record template acquisition module 400.
The database construction module 100 is used for constructing a medical record template database;
a medical information acquisition module 200 for acquiring medical information of a subject;
a keyword extraction module 400, configured to obtain a pathological keyword of a corresponding subject according to the medical information;
and a medical record template obtaining module 400, configured to automatically output a medical record template according to the pathological keyword and the medical record template database.
The keyword extraction module 300 is further configured to input the medical image into an identification model to obtain focus information; and extracting the focus information and/or the keywords of the medical text to obtain the pathological keywords of the corresponding examinee.
The database construction module 100 is configured to acquire a case text with a complete record, and preprocess the case text to obtain a medical record template; performing word segmentation processing on the medical record template to obtain all words corresponding to the medical record template; and extracting template keywords according to all the word segments, and establishing a medical record template database of the template keywords and corresponding medical record templates.
The database construction module 100 is further configured to acquire a case text with complete records; extracting sensitive words, interference words and stop words according to the case text with complete records; and hiding the sensitive words, the interference words and the stop words in the case text to obtain a medical record template.
The database construction module 100 is further configured to input the word segmentation into a keyword extraction model to obtain the template keyword; and establishing a medical record template database of the template keyword and the corresponding medical record template.
The database construction module 100 is further configured to obtain the number of times each type of participle appears in the medical record template, the total number of terms in the medical record template, the total number of medical record templates, and the number of medical record templates in which each type of participle appears; obtaining the word frequency of the corresponding participle according to the times of the participle appearing in the medical record template and the total word number of the corresponding medical record template; obtaining the inverse document frequency of the corresponding word segmentation according to the number of medical record templates with the word segmentation and the total number of the medical record templates; and obtaining the template keyword according to the word frequency and the inverse document frequency.
The medical record template acquisition module 400 is further configured to calculate similarity between the corresponding pathological keyword and each medical record template according to the pathological keyword and the template keyword of each medical record template in the medical record template database; and selecting the medical record template corresponding to the highest similarity as the final medical record template.
The above modules may be functional modules or program modules, and may be implemented by software or hardware. For a module implemented by hardware, the modules may be located in the same processor; or the modules can be respectively positioned in different processors in any combination.
In addition, the method for automatically acquiring a medical record template according to the embodiment of the present application described in conjunction with fig. 1 may be implemented by a computer device. Fig. 6 is a schematic hardware configuration diagram of a computer device in one embodiment.
The computer device may comprise a processor 61 and a memory 62 in which computer program instructions are stored.
Specifically, the processor 61 may include a Central Processing Unit (CPU), or A Specific Integrated Circuit (ASIC), or may be configured to implement one or more Integrated circuits of the embodiments of the present Application.
The memory 62 may be used to store or cache various data files that need to be processed and/or used for communication, as well as possible computer program instructions executed by the processor 61.
The processor 61 can implement any one of the above embodiments of the method for automatically obtaining a medical record template by reading and executing computer program instructions stored in the memory 62.
In some of these embodiments, the computer device may also include a communication interface 63 and a bus 60. As shown in fig. 6, the processor 61, the memory 62, and the communication interface 63 are connected via a bus 60 to complete mutual communication.
The communication interface 63 is used for implementing communication between modules, devices, units and/or apparatuses in the embodiments of the present application. The communication port 63 may also be implemented with other components such as: the data communication is carried out among external equipment, image/data acquisition equipment, a database, external storage, an image/data processing workstation and the like.
The computer device can execute the method for automatically acquiring the medical record template in the embodiment of the application based on the acquired computer instruction, so as to implement the method for automatically acquiring the medical record template described in conjunction with fig. 1.
In addition, in combination with the method for automatically acquiring a medical record template in the foregoing embodiment, an embodiment of the present application may provide a computer-readable storage medium to implement. The computer readable storage medium having stored thereon computer program instructions; the computer program instructions, when executed by a processor, implement any of the above-described embodiments of a method for automatically obtaining a medical record template.
The technical features of the embodiments described above may be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the embodiments described above are not described, but should be considered as being within the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A method for automatically acquiring a medical record template is characterized by comprising the following steps:
constructing a medical record template database;
acquiring medical information of a subject;
obtaining pathological keywords of corresponding examinees according to the medical information;
and automatically outputting a medical record template according to the pathological keywords and the medical record template database.
2. The method for automatically acquiring medical record templates as claimed in claim 1, wherein the obtaining pathological keywords of the corresponding subject according to the medical information comprises: the medical information comprises medical text and/or medical images;
inputting the medical image into a recognition model to obtain focus information;
and extracting the focus information and/or the keywords of the medical text to obtain the pathological keywords of the corresponding examinee.
3. The method for automatically acquiring medical record templates according to claim 1, wherein the constructing a medical record template database comprises:
acquiring a case text with complete record, and preprocessing the case text to obtain a case history template;
performing word segmentation processing on the medical record template to obtain all words corresponding to the medical record template;
and extracting template keywords according to all the word segments, and establishing a medical record template database of the template keywords and corresponding medical record templates.
4. The method for automatically acquiring medical record templates as claimed in claim 3, wherein the acquiring the case text with complete records and preprocessing the case text to obtain the medical record template comprises:
acquiring a case text with complete record;
extracting sensitive words, interference words and stop words according to the case text with complete records;
and hiding the sensitive words, the interference words and the stop words in the case text to obtain a medical record template.
5. The method for automatically acquiring medical record templates of claim 3,
the word segmentation processing comprises the following steps: at least one of a character string matching based word segmentation process, an understanding based word segmentation process, and a statistics based word segmentation process.
6. The method of automatically obtaining medical record templates according to claim 3, wherein the extracting template keywords according to all the participles and establishing a medical record template database of the template keywords and corresponding medical record templates comprises:
inputting the word segmentation into a keyword extraction model to obtain the template keyword;
and establishing a medical record template database of the template keyword and the corresponding medical record template.
7. The method for automatically obtaining a medical record template according to claim 6, wherein the step of inputting the segmentation into a keyword extraction model to obtain the template keyword comprises:
acquiring the occurrence frequency of each word in the medical record template, the total word number of the medical record template, the total number of the medical record templates and the number of the medical record templates in which each word appears;
obtaining the word frequency of the corresponding participle according to the times of the participle appearing in the medical record template and the total word number of the corresponding medical record template;
obtaining the inverse document frequency of the corresponding word segmentation according to the number of medical record templates with the word segmentation and the total number of the medical record templates;
and obtaining the template keyword according to the word frequency and the inverse document frequency.
8. The method of claim 3, wherein automatically outputting a medical record template according to the pathology keyword and the medical record template database comprises:
calculating the similarity between the corresponding pathological keyword and each medical record template according to the pathological keyword and the template keyword of each medical record template in the medical record template database;
and selecting the medical record template corresponding to the highest similarity as the final medical record template.
9. An apparatus for automatically obtaining a medical record template, comprising:
the database construction module is used for constructing a medical record template database;
a medical information acquisition module for acquiring medical information of a subject;
the keyword extraction module is used for obtaining pathological keywords of corresponding examinees according to the medical information;
and the medical record template acquisition module is used for automatically outputting a medical record template according to the pathological keywords and the medical record template database.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out a method for automatically acquiring a medical record template according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010535511.9A CN111696640A (en) | 2020-06-12 | 2020-06-12 | Method, device and storage medium for automatically acquiring medical record template |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010535511.9A CN111696640A (en) | 2020-06-12 | 2020-06-12 | Method, device and storage medium for automatically acquiring medical record template |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111696640A true CN111696640A (en) | 2020-09-22 |
Family
ID=72480550
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010535511.9A Pending CN111696640A (en) | 2020-06-12 | 2020-06-12 | Method, device and storage medium for automatically acquiring medical record template |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111696640A (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112349367A (en) * | 2020-11-11 | 2021-02-09 | 北京嘉和海森健康科技有限公司 | Method and device for generating simulation medical record, electronic equipment and storage medium |
| CN112786169A (en) * | 2020-12-29 | 2021-05-11 | 桂林医学院附属医院 | Outpatient medical history information acquisition system, outpatient medical history information acquisition method, storage medium, and computer program |
| CN112992370A (en) * | 2021-05-06 | 2021-06-18 | 四川大学华西医院 | Unsupervised electronic medical record-based medical behavior compliance assessment method |
| CN113361254A (en) * | 2021-06-03 | 2021-09-07 | 重庆南鹏人工智能科技研究院有限公司 | Automatic electronic medical record analysis method and device |
| CN113793677A (en) * | 2021-08-24 | 2021-12-14 | 挂号网（杭州）科技有限公司 | Electronic medical record management method and device, storage medium and electronic equipment |
| CN114242196A (en) * | 2021-12-13 | 2022-03-25 | 中南大学湘雅医院 | Automatic generation method and device for clinical medical record |
| CN114841136A (en) * | 2022-05-12 | 2022-08-02 | 青岛海信医疗设备股份有限公司 | Method, device and equipment for editing inspection report |
| CN115019320A (en) * | 2022-06-30 | 2022-09-06 | 京东方科技集团股份有限公司 | Data extraction method, device, equipment and storage medium |
| CN115034204A (en) * | 2022-05-12 | 2022-09-09 | 浙江大学 | Method for generating structured medical text, computer device, storage medium and program product |
| CN115983228A (en) * | 2022-12-28 | 2023-04-18 | 北京欧应科技有限公司 | Method, system, computing device and storage medium for generating medical record templates |
| TWI811598B (en) * | 2020-12-18 | 2023-08-11 | 正修學校財團法人正修科技大學 | Smart image diagnosis report translation method |
| CN117912624A (en) * | 2024-03-15 | 2024-04-19 | 江西曼荼罗软件有限公司 | Electronic medical record sharing method and system |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104835098A (en) * | 2015-05-15 | 2015-08-12 | 上海翼依信息技术有限公司 | Medical record electronic data identification method and system thereof |
| CN107644419A (en) * | 2017-09-30 | 2018-01-30 | 百度在线网络技术（北京）有限公司 | Method and apparatus for analyzing medical image |
| CN109215754A (en) * | 2018-09-10 | 2019-01-15 | 平安科技（深圳）有限公司 | Medical record data processing method, device, computer equipment and storage medium |
| CN109346188A (en) * | 2018-10-19 | 2019-02-15 | 刘瑞红 | A kind of medical statistics data processing method |
| CN109616195A (en) * | 2018-11-28 | 2019-04-12 | 武汉大学人民医院（湖北省人民医院） | The real-time assistant diagnosis system of mediastinum endoscopic ultrasonography image and method based on deep learning |
| CN110534170A (en) * | 2019-08-30 | 2019-12-03 | 志诺维思（北京）基因科技有限公司 | Data processing method, device, electronic equipment and computer readable storage medium |
| CN111048170A (en) * | 2019-12-23 | 2020-04-21 | 山东大学齐鲁医院 | Digestive endoscopy structured diagnosis report generation method and system based on image recognition |
-
2020
- 2020-06-12 CN CN202010535511.9A patent/CN111696640A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104835098A (en) * | 2015-05-15 | 2015-08-12 | 上海翼依信息技术有限公司 | Medical record electronic data identification method and system thereof |
| CN107644419A (en) * | 2017-09-30 | 2018-01-30 | 百度在线网络技术（北京）有限公司 | Method and apparatus for analyzing medical image |
| CN109215754A (en) * | 2018-09-10 | 2019-01-15 | 平安科技（深圳）有限公司 | Medical record data processing method, device, computer equipment and storage medium |
| CN109346188A (en) * | 2018-10-19 | 2019-02-15 | 刘瑞红 | A kind of medical statistics data processing method |
| CN109616195A (en) * | 2018-11-28 | 2019-04-12 | 武汉大学人民医院（湖北省人民医院） | The real-time assistant diagnosis system of mediastinum endoscopic ultrasonography image and method based on deep learning |
| CN110534170A (en) * | 2019-08-30 | 2019-12-03 | 志诺维思（北京）基因科技有限公司 | Data processing method, device, electronic equipment and computer readable storage medium |
| CN111048170A (en) * | 2019-12-23 | 2020-04-21 | 山东大学齐鲁医院 | Digestive endoscopy structured diagnosis report generation method and system based on image recognition |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112349367B (en) * | 2020-11-11 | 2023-08-08 | 北京嘉和海森健康科技有限公司 | Method, device, electronic equipment and storage medium for generating simulated medical record |
| CN112349367A (en) * | 2020-11-11 | 2021-02-09 | 北京嘉和海森健康科技有限公司 | Method and device for generating simulation medical record, electronic equipment and storage medium |
| TWI811598B (en) * | 2020-12-18 | 2023-08-11 | 正修學校財團法人正修科技大學 | Smart image diagnosis report translation method |
| CN112786169A (en) * | 2020-12-29 | 2021-05-11 | 桂林医学院附属医院 | Outpatient medical history information acquisition system, outpatient medical history information acquisition method, storage medium, and computer program |
| CN112992370A (en) * | 2021-05-06 | 2021-06-18 | 四川大学华西医院 | Unsupervised electronic medical record-based medical behavior compliance assessment method |
| CN112992370B (en) * | 2021-05-06 | 2021-07-30 | 四川大学华西医院 | Unsupervised electronic medical record-based medical behavior compliance assessment method |
| CN113361254A (en) * | 2021-06-03 | 2021-09-07 | 重庆南鹏人工智能科技研究院有限公司 | Automatic electronic medical record analysis method and device |
| CN113793677A (en) * | 2021-08-24 | 2021-12-14 | 挂号网（杭州）科技有限公司 | Electronic medical record management method and device, storage medium and electronic equipment |
| CN114242196A (en) * | 2021-12-13 | 2022-03-25 | 中南大学湘雅医院 | Automatic generation method and device for clinical medical record |
| CN114841136A (en) * | 2022-05-12 | 2022-08-02 | 青岛海信医疗设备股份有限公司 | Method, device and equipment for editing inspection report |
| CN115034204A (en) * | 2022-05-12 | 2022-09-09 | 浙江大学 | Method for generating structured medical text, computer device, storage medium and program product |
| CN114841136B (en) * | 2022-05-12 | 2024-11-01 | 青岛海信医疗设备股份有限公司 | Inspection report editing method, device and equipment |
| CN115019320A (en) * | 2022-06-30 | 2022-09-06 | 京东方科技集团股份有限公司 | Data extraction method, device, equipment and storage medium |
| CN115983228A (en) * | 2022-12-28 | 2023-04-18 | 北京欧应科技有限公司 | Method, system, computing device and storage medium for generating medical record templates |
| CN115983228B (en) * | 2022-12-28 | 2023-10-13 | 北京欧应科技有限公司 | Method, system, computing device and storage medium for generating medical record templates |
| CN117912624A (en) * | 2024-03-15 | 2024-04-19 | 江西曼荼罗软件有限公司 | Electronic medical record sharing method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111696640A (en) | Method, device and storage medium for automatically acquiring medical record template | |
| US20190347269A1 (en) | Structured report data from a medical text report | |
| CN111316281B (en) | Semantic classification method and system for numerical data in natural language context based on machine learning | |
| US11244755B1 (en) | Automatic generation of medical imaging reports based on fine grained finding labels | |
| US11989518B2 (en) | Normalized processing method and apparatus of named entity, and electronic device | |
| CN110069779B (en) | Symptom entity identification method of medical text and related device | |
| Carchiolo et al. | Medical prescription classification: a NLP-based approach | |
| CN111651991B (en) | Medical named entity identification method utilizing multi-model fusion strategy | |
| CN117524402A (en) | Method for analyzing endoscope image and automatically generating diagnostic report | |
| US11763081B2 (en) | Extracting fine grain labels from medical imaging reports | |
| EP4170670A1 (en) | Medical data processing method and system | |
| US20220375576A1 (en) | Apparatus and method for diagnosing a medical condition from a medical image | |
| CN115205880A (en) | Medical image report generation method and device | |
| Kisilev et al. | Semantic description of medical image findings: structured learning approach. | |
| CN112530550A (en) | Image report generation method and device, computer equipment and storage medium | |
| CN115206478A (en) | Medical report generation method and device, electronic equipment and readable storage medium | |
| CN111091914A (en) | Cancer typing staging method and device based on medical record | |
| Gu et al. | Automatic generation of pulmonary radiology reports with semantic tags | |
| CN117594183A (en) | Radiological report generation method based on inverse fact data enhancement | |
| CN117422074A (en) | Method, device, equipment and medium for standardizing clinical information text | |
| CN116631584A (en) | General medical image report generation method and system, electronic equipment and readable storage medium | |
| CN115985506A (en) | Information extraction method and device, storage medium and computer equipment | |
| CN112101034B (en) | Method and device for judging attribute of medical entity and related product | |
| US10910098B2 (en) | Automatic summarization of medical imaging studies | |
| CN113836926A (en) | Electronic medical record named entity identification method, electronic equipment and storage medium |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 201807 2258 Chengbei Road, Jiading District, Shanghai Applicant after: Shanghai Lianying Medical Technology Co., Ltd Address before: 201807 2258 Chengbei Road, Jiading District, Shanghai Applicant before: SHANGHAI UNITED IMAGING HEALTHCARE Co.,Ltd. |