CN118522396B - Clinical diagnosis and treatment data input method and system - Google Patents
Clinical diagnosis and treatment data input method and system Download PDFInfo
- Publication number
- CN118522396B CN118522396B CN202410985107.XA CN202410985107A CN118522396B CN 118522396 B CN118522396 B CN 118522396B CN 202410985107 A CN202410985107 A CN 202410985107A CN 118522396 B CN118522396 B CN 118522396B
- Authority
- CN
- China
- Prior art keywords
- treatment data
- diagnosis
- current patient
- treatment
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000011282 treatment Methods 0.000 title claims abstract description 399
- 238000003759 clinical diagnosis Methods 0.000 title claims abstract description 189
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000003745 diagnosis Methods 0.000 claims abstract description 168
- 239000003814 drug Substances 0.000 claims description 65
- 208000024891 symptom Diseases 0.000 claims description 58
- 230000011218 segmentation Effects 0.000 claims description 39
- 229940079593 drug Drugs 0.000 claims description 25
- 238000007781 pre-processing Methods 0.000 claims description 16
- 238000007621 cluster analysis Methods 0.000 claims description 10
- 238000013479 data entry Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 9
- 230000001225 therapeutic effect Effects 0.000 claims description 8
- 238000004458 analytical method Methods 0.000 claims description 6
- 238000012552 review Methods 0.000 claims description 2
- 238000011160 research Methods 0.000 abstract description 2
- 201000010099 disease Diseases 0.000 description 8
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 8
- 238000011269 treatment regimen Methods 0.000 description 8
- 238000012795 verification Methods 0.000 description 6
- 230000002159 abnormal effect Effects 0.000 description 4
- 230000005856 abnormality Effects 0.000 description 3
- 238000013524 data verification Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 229940126585 therapeutic drug Drugs 0.000 description 3
- 238000010606 normalization Methods 0.000 description 2
- 229940124597 therapeutic agent Drugs 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007334 copolymerization reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
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
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/04—Inference or reasoning models
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Health & Medical Sciences (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention relates to the technical field of clinical research, in particular to a method and a system for inputting clinical diagnosis and treatment data, which are characterized in that firstly, historical clinical diagnosis and treatment data are acquired and preprocessed; judging the logic consistency of the current patient diagnosis and treatment data and the preprocessed historical clinical diagnosis and treatment data; if the logic consistency is greater than a first preset threshold value, recording current patient diagnosis and treatment data; otherwise, judging the logic rationality of the current patient diagnosis and treatment data; if the logic rationality is greater than a second preset threshold, the current patient diagnosis and treatment data is input. According to the invention, by analyzing the current patient diagnosis and treatment data and the historical clinical diagnosis and treatment data, the diagnosis and treatment data with the current patient diagnosis and treatment data with the logic consistency and the logic rationality reaching certain requirements can be allowed to be recorded, so that the diagnosis and treatment data with logic errors is prevented from being recorded into a hospital information system.
Description
Technical Field
The invention relates to the technical field of clinical research, in particular to a method and a system for inputting clinical diagnosis and treatment data.
Background
Clinical diagnostic data refers to a series of information related to diagnosis, treatment, and management of patients generated in clinical practice. Such data includes, but is not limited to, personal information of the patient, medical history, physical examination, laboratory examination results, imaging examination results, treatment regimens, treatment effects, follow-up information, and the like. The clinical diagnosis and treatment data are various in sources and can be paper records, electronic medical record systems, medical equipment, laboratory information systems and the like. With the development of information technology, more and more clinical diagnosis and treatment data exist in an electronic form, and a so-called Electronic Health Record (EHR) or Electronic Medical Record (EMR) is formed.
Clinical diagnosis and treatment data input refers to that medical staff inputs medical information of patients into an electronic medical record system of a hospital in an electronic form. The electronic medical record system has the data verification function, and the accuracy and the integrity of the medical information of the patient are required to be checked in the recording process, so that errors are reduced, and the data quality is improved. The existing data verification strategies comprise format verification, field verification which is needed to be filled, logic verification and the like, and the aim is to ensure that the input data accords with the preset standard and format. However, inaccurate use of medical terms filled in by medical staff in electronic medical records can lead to erroneous judgment of the patient's condition and treatment regimen. When the existing method is used for logic verification, whether the medical terms of the electronic medical record are used accurately is generally only analyzed, but the logic relation between the medicine used by a doctor in the electronic medical record and the illness state is not analyzed, and if the medicine is used inaccurately, the illness state and the treatment scheme of a patient can be judged wrongly.
Disclosure of Invention
In order to solve the technical problems that when clinical diagnosis and treatment data are input into a hospital information system, due to inaccurate and irregular filling of the clinical diagnosis and treatment data and lack of logical relation verification between medicines and illness states, incorrect judgment is made on illness states and treatment schemes of patients, the invention aims to provide a clinical diagnosis and treatment data input method and a clinical diagnosis and treatment data input system, and the adopted technical scheme is as follows:
In a first aspect, the present invention is a clinical diagnostic data entry method, the entry method comprising: acquiring historical clinical diagnosis and treatment data, and preprocessing the historical clinical diagnosis and treatment data; judging the logic consistency of the current patient diagnosis and treatment data and the preprocessed historical clinical diagnosis and treatment data; if the logic consistency is greater than a first preset threshold, recording the current patient diagnosis and treatment data; otherwise, judging the logic rationality of the current patient diagnosis and treatment data; if the logic rationality is greater than a second preset threshold, the current patient diagnosis and treatment data is input.
Before the current patient diagnosis and treatment data is input, firstly judging the logic consistency of the current patient diagnosis and treatment data, and if the logic consistency is larger than a first preset threshold value, inputting is permitted. If the logic consistency does not reach the standard, judging the logic rationality of the current patient diagnosis and treatment data, and if the logic consistency is larger than a second preset threshold, recording is permitted. According to the invention, the logic consistency and the logic rationality are judged before the diagnosis and treatment data is input into the hospital information system, so that the diagnosis and treatment data conforming to the logic is allowed to be input into the hospital information system, the accuracy of inputting the data is improved, the erroneous judgment on the illness state and the treatment scheme of a patient caused by the inaccuracy of inputting the diagnosis and treatment data is reduced, and the diagnosis and treatment data with logic errors is prevented from being input into the hospital information system.
Further, preprocessing the historical clinical diagnosis and treatment data includes: based on M diagnosis and treatment department categories of a hospital, carrying out cluster analysis on the historical clinical diagnosis and treatment data to obtain M large clusters, wherein M is a positive integer.
Further, judging the logical consistency of the current patient diagnosis and treatment data and the preprocessed historical clinical diagnosis and treatment data specifically comprises the following steps: based on symptom similarity among the historical clinical diagnosis and treatment data in the m-th big cluster, carrying out cluster analysis on the historical clinical diagnosis and treatment data in the m-th cluster to obtain N small clusters; n is a positive integer; ; traversing M large clusters to obtain M multiplied by N small clusters; determining a big cluster corresponding to the current patient diagnosis and treatment data according to a diagnosis and treatment department in which the current patient diagnosis and treatment data is located; according to the symptom similarity of the current patient diagnosis and treatment data and the historical clinical diagnosis and treatment data of all small clusters in the large cluster, obtaining the logic consistency of the current patient diagnosis and treatment data and the preprocessed historical clinical diagnosis and treatment data.
Further, according to the symptom similarity of the current patient diagnosis and treatment data and the historical clinical diagnosis and treatment data of all small clusters in the large cluster, obtaining the logic consistency of the current patient diagnosis and treatment data and the preprocessed historical clinical diagnosis and treatment data, wherein the logic consistency comprises the following steps: according to the symptom similarity of the current patient diagnosis and treatment data and the historical clinical diagnosis and treatment data of all the small clusters in the large cluster, determining the nth small cluster most similar to the symptom of the current patient diagnosis and treatment data, and according to the medicine similarity between the treatment medicine of the current patient diagnosis and treatment data and the treatment medicine of all the historical clinical diagnosis and treatment data in the nth small cluster, obtaining the logic consistency of the current patient diagnosis and treatment data and the preprocessed historical clinical diagnosis and treatment data; wherein, 。
Further, judging the logic rationality of the current patient diagnosis and treatment data specifically includes: acquiring all the historical clinical diagnosis and treatment data of doctors to which the current patient belongs from the preprocessed historical clinical diagnosis and treatment data; analyzing the symptom similarity of the current patient diagnosis and treatment data and all the historical clinical diagnosis and treatment data of doctors to which the current patient belongs, and taking the historical clinical diagnosis and treatment data with the symptom similarity larger than a third threshold value as comparison clinical diagnosis and treatment data; and analyzing the medicine similarity between the therapeutic medicine of the current patient diagnosis and treatment data and the therapeutic medicine of the comparison clinical diagnosis and treatment data to obtain the logic rationality of the current patient diagnosis and treatment data.
Wherein the drug similarity comprises: drug composition, number of drugs, and number of drug occurrences.
Further, the preprocessing of the historical clinical diagnosis and treatment data further comprises: performing word segmentation processing on all the historical clinical diagnosis and treatment data to obtain word segmentation sequences of each piece of historical clinical diagnosis and treatment data; performing word segmentation processing on the current patient diagnosis and treatment data to obtain word segmentation sequences of the current patient diagnosis and treatment data; based on the word segmentation sequence of each piece of historical clinical diagnosis and treatment data and the text similarity between the word segmentation sequences of the current patient diagnosis and treatment data, judging the symptom similarity or the medicine similarity.
Further, before cluster analysis is performed on the historical clinical diagnosis and treatment data, rationality test is performed on the historical clinical diagnosis and treatment data.
Further, if the logic rationality is not greater than a second preset threshold, the doctor to which the current patient belongs rechecks the diagnosis and treatment data of the current patient; and (5) carrying out judgment on logic consistency or logic rationality again based on the current patient diagnosis and treatment data after the recheck.
In a second aspect, the invention is a clinical diagnostic data entry system comprising: the data acquisition module is used for acquiring historical clinical diagnosis and treatment data; the data preprocessing module is used for preprocessing the historical clinical diagnosis and treatment data; the analysis judging module is used for judging the logic consistency of the current patient diagnosis and treatment data and the preprocessed historical clinical diagnosis and treatment data; if the logic consistency is greater than a first preset threshold, recording the current patient diagnosis and treatment data; otherwise, judging the logic rationality of the current patient diagnosis and treatment data; if the logic rationality is greater than a second preset threshold, recording the current patient diagnosis and treatment data; the return module is used for rechecking the diagnosis and treatment data of the current patient by a doctor to which the current patient belongs if the logic rationality is not greater than a second preset threshold value; and (5) carrying out judgment on logic consistency or logic rationality again based on the current patient diagnosis and treatment data after the recheck.
The invention has the following beneficial effects:
According to the invention, by analyzing the current patient diagnosis and treatment data and the historical clinical diagnosis and treatment data, the diagnosis and treatment data with the current patient diagnosis and treatment data with the logic consistency and the logic rationality reaching certain requirements can be allowed to be input into the hospital information system, so that the clinical diagnosis and treatment data with abnormal logic can be effectively prevented from being input into the hospital information system. The recorded data is reasonable and accurate, so that incorrect judgment of patient conditions and treatment schemes caused by the recording reasons of the diagnosis and treatment data is avoided, and the diagnosis and treatment data with logic errors is prevented from being recorded into a hospital information system.
The invention aims at the problems that when the traditional method is used for carrying out logic verification on clinical diagnosis and treatment data, whether the medical terms of the electronic medical record are used accurately is generally only analyzed, and the logic relation between the medicine used by a doctor in the electronic medical record and the illness state is not analyzed, and if the medicine is used inaccurately, the illness state of a patient and the treatment scheme are wrongly judged. And preliminarily judging the logical consistency of the current patient diagnosis and treatment data by calculating the logical consistency of the current patient diagnosis and treatment data and the historical clinical diagnosis and treatment data of the historical similar symptoms. And finally judging by combining the historical clinical diagnosis and treatment data of the doctor of the current patient under similar symptoms with the logical rationality of the treatment style deviation degree of the diagnosis and treatment data of the current patient. And furthermore, the clinical patient diagnosis and treatment data with abnormal logic can be effectively prevented from being input into the hospital information system.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for entering clinical treatment data according to an embodiment of the present invention;
Fig. 2 is a schematic diagram of a clinical diagnosis and treatment data input system according to an embodiment of the present invention.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following detailed description refers to specific implementation, structure, characteristics and effects of a clinical diagnosis and treatment data input method and system according to the invention by combining the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The invention provides a clinical diagnosis and treatment data input method and a specific scheme of a system by combining drawings.
Clinical diagnosis and treatment data input refers to that medical staff inputs medical information of patients into an electronic medical record system of a hospital in an electronic form. The electronic medical record system has the data verification function, and the accuracy and the integrity of the medical information of the patient are required to be checked in the recording process, so that errors are reduced, and the data quality is improved. According to the embodiment of the invention, the logic reasonable condition of the clinical diagnosis and treatment data in the clinical diagnosis and treatment data input process is analyzed, and the clinical diagnosis and treatment data with logic errors is prevented from being input into a hospital information system.
Referring to fig. 1, a flowchart of a clinical diagnosis and treatment data input method according to an embodiment of the present invention is shown, which specifically includes: acquiring historical clinical diagnosis and treatment data, and preprocessing the historical clinical diagnosis and treatment data; judging the logic consistency of the current patient diagnosis and treatment data and the preprocessed historical clinical diagnosis and treatment data; if the logic consistency is greater than a first preset threshold value, recording current patient diagnosis and treatment data; otherwise, judging the logic rationality of the current patient diagnosis and treatment data; if the logic rationality is greater than a second preset threshold, the current patient diagnosis and treatment data is input.
Before the diagnosis and treatment data of a current patient are input, firstly judging the logic consistency of the diagnosis and treatment data of the current patient, and if the logic consistency is larger than a first preset threshold value, inputting is permitted. If the logic consistency does not reach the standard, judging the logic rationality of the current patient diagnosis and treatment data, and if the logic consistency is larger than a second preset threshold, recording is permitted. According to the invention, the logic consistency and the logic rationality are judged before the diagnosis and treatment data is input into the hospital information system, so that the diagnosis and treatment data conforming to the logic is allowed to be input into the hospital information system, the accuracy of inputting the data is improved, the erroneous judgment on the illness state and the treatment scheme of a patient caused by the inaccuracy of inputting the diagnosis and treatment data is reduced, and the diagnosis and treatment data with logic errors is prevented from being input into the hospital information system. In an actual application scene, the first preset threshold and the second preset threshold can be set correspondingly according to the requirement of data entry or some unspecified specificities of the disease data, and the first preset threshold and the second preset threshold can be the same or different.
In one possible embodiment, if the logic rationality is not greater than the second preset threshold, the hospital information system is refused to be entered, which indicates that the current patient diagnosis and treatment data has logic errors, such as errors in the logic relationship between the medicine and the illness state for the doctor. Returning to the doctor of the current patient, and rechecking the diagnosis and treatment data of the current patient again. And (3) carrying out judgment on logical consistency or logical rationality again based on the current patient diagnosis and treatment data after the recheck until the requirement of the logical consistency or the logical rationality is met, and then allowing the patient to enter a hospital information system so as to ensure that the logic between the medicine used by a doctor and the illness state is correct and avoid making wrong judgment on the illness state and the treatment scheme of the patient.
The historical clinical diagnosis and treatment data of doctors on patients are acquired through a hospital information system, and the data mainly exist in the form of electronic medical records. Wherein historical clinical diagnostic data has been subjected to a rationality test (here, a rationality test, which can be understood to be determined by the methods of embodiments of the invention, in summary, the historical clinical diagnostic data herein is uniformly considered to be all reasonable), and therefore, the historical clinical diagnostic data is all reasonable. For the current patient diagnosis and treatment data uploaded by the doctor at present, the qualification of the clinical diagnosis and treatment data is primarily checked by using the traditional prior mode check such as format check, character field check and the like. And (5) after the doctor is qualified, carrying out subsequent operation, and if the doctor is unqualified, returning the doctor to the corresponding doctor for refilling.
Before judging logical consistency or logical rationality, the embodiment of the invention firstly carries out preprocessing on the historical clinical diagnosis and treatment data, and the specific method is as follows: based on M diagnosis and treatment department categories of a hospital, carrying out cluster analysis on historical clinical diagnosis and treatment data to obtain M large clusters, wherein M is a positive integer. Namely, according to the diagnosis and treatment department category of the hospital, the historical clinical diagnosis and treatment data are subjected to clustering analysis. Clustering historical clinical diagnosis and treatment data according to diagnosis and treatment departments of hospitals, placing the diagnosis and treatment data of the same diagnosis and treatment departments in one cluster, and analyzing the logical consistency of the diagnosis and treatment data of each patient according to the cluster in the subsequent analysis. There are M clinical departments, and M clusters.
In one possible embodiment, the preprocessing of the historical clinical diagnosis and treatment data further comprises: performing word segmentation processing on all the historical clinical diagnosis and treatment data to obtain word segmentation sequences of each piece of historical clinical diagnosis and treatment data; performing word segmentation processing on the current patient diagnosis and treatment data to obtain word segmentation sequences of the current patient diagnosis and treatment data; based on the word segmentation sequence of each piece of historical clinical diagnosis and treatment data and the text similarity between the word segmentation sequences of the current patient diagnosis and treatment data, judging the symptom similarity or the medicine similarity.
Calculating the logic consistency of clinical diagnosis and treatment data and historical diagnosis and treatment data of a current patient, wherein the clinical diagnosis and treatment data of the current patient and the current patient diagnosis and treatment data are different expression modes with the same meaning in the embodiment of the invention.
In one possible embodiment, determining the logical consistency of the current patient diagnosis and treatment data and the preprocessed historical clinical diagnosis and treatment data specifically includes: based on symptom similarity among the historical clinical diagnosis and treatment data in the m-th big cluster, carrying out cluster analysis on the historical clinical diagnosis and treatment data in the m-th cluster to obtain N small clusters; n is a positive integer; ; and traversing M large clusters of all medical departments to obtain M multiplied by N small clusters. Determining a big cluster corresponding to the current patient diagnosis and treatment data according to a diagnosis and treatment department in which the current patient diagnosis and treatment data is located; determining a cluster small cluster which is the most similar to the symptoms of the current patient diagnosis and treatment data according to the symptom similarity of the current patient diagnosis and treatment data and the historical clinical diagnosis and treatment data of all small clusters in the large cluster, namely, the nth small cluster, and obtaining the logic consistency of the current patient diagnosis and treatment data and the preprocessed historical clinical diagnosis and treatment data according to the medicine similarity between the treatment medicine of the current patient diagnosis and treatment data and the treatment medicine of all the historical clinical diagnosis and treatment data in the nth small cluster; wherein, 。
Wherein, the medicine similarity can be judged according to factors such as medicine components, medicine quantity, medicine occurrence frequency and the like.
More specifically, for each large cluster, clinical diagnosis and treat data with similar symptoms in each large cluster is clustered according to text data of disease columns in the historical clinical diagnosis and treat data. The diagnosis and treatment data with similar symptoms are put together. For the m-th big cluster, firstly, word segmentation processing is carried out on text data of symptom columns of all diagnosis and treatment data in the big cluster by using JieBa word segmentation tools so as to obtain word segmentation sequences of symptom columns in each diagnosis and treatment data, wherein JieBa word segmentation is in the prior art and is not repeated here. Symptom similarity between each diagnosis and treatment data is then determined through text similarity between word segmentation sequences. Specific:
the formula is constructed: ；
wherein, The symptom similarity of the p-th clinical diagnosis and treatment data and the q-th clinical diagnosis and treatment data in the m-th cluster is represented.Representing Jaccard correlation coefficients.An exponential function based on a natural constant is represented.And the symptom column word segmentation sequence of the p-th clinical diagnosis and treatment data in the m-th cluster is represented.And the symptom column word segmentation sequence of the q-th clinical diagnosis and treatment data in the m-th cluster is represented.The number of the words in the symptom column word segmentation sequence of the p-th clinical diagnosis and treatment data in the m-th cluster is represented.The number of the words in the word segmentation sequence of the symptom column of the q clinical diagnosis and treatment data in the m-th cluster is represented.
The larger the value of (c) is, the more the same word segmentation number of the disease column in the p-th clinical diagnosis and treatment data and the q-th clinical diagnosis and treatment data in the m-th big cluster is.The smaller the value of (c) is, the more similar the number of segmentation words of the disease columns representing the p-th clinical diagnosis and treatment data and the q-th clinical diagnosis and treatment data in the m-th cluster is.
Thus (2)The larger the value of (c) is,The smaller the value of (c) is, the more similar the number of word segmentation sequences of the disease columns in the p-th clinical diagnosis and treatment data and the q-th clinical diagnosis and treatment data in the m-th big cluster is, and the more the number of identical words is. The more similar the symptoms of the p-th clinical diagnosis and treatment data and the q-th clinical diagnosis and treatment data in the corresponding m-th cluster are.
Thus, the symptom similarity between every two clinical diagnosis and treatment data in the mth cluster can be quantified. Clinical diagnostic data in the mth cluster were then reclustered using the K-means method based on symptom similarity between the clinical diagnostic data in pairs. The copolymerization is set to N small clusters. Wherein the clinical data in each cluster are relatively similar in terms of condition. And similarly, the diagnosis and treatment data in each other large cluster can be clustered again to obtain a plurality of small clusters, and M multiplied by N small clusters are formed.
For clinical diagnosis and treatment data of a current patient, firstly acquiring a medical department where the current patient is located and locating the current patient in a corresponding cluster. And then calculating the symptom similarity of the clinical diagnosis and treatment data of the current patient and the symptom columns in the corresponding clustered large clusters to position the clustered small clusters where the clinical diagnosis and treatment data of the current patient are located. Specific:
the formula is constructed: ；
wherein, The symptom similarity of clinical diagnosis and treatment data of the current patient and clinical diagnosis and treatment data in the nth cluster is represented.Symptom similarity between current patient clinical treatment data and the ith clinical treatment data in the nth cluster.Representing the number of clinical treatment data in the nth cluster. According to the operation, the symptom similarity of the diagnosis and treatment data of the current patient and the clinical diagnosis and treatment data of each cluster can be calculated. And marking the cluster corresponding to the condition with the maximum symptom similarity as the diagnosis and treatment data matching cluster of the current patient.
Since the current patient's clinical data and the conditions in the matched cluster are relatively similar, their corresponding treatment regimens should also be relatively similar. The consistency of the current patient's diagnosis and treatment data and the treatment plan of each diagnosis and treatment data in the matched cluster is used for determining the logical consistency of the current patient's diagnosis and treatment data and the historical diagnosis and treatment data. And similarly, using JieBa word segmentation tools to perform word segmentation processing on the diagnosis and treatment data of the current patient and text data of treatment scheme columns in each diagnosis and treatment data in the matched cluster to obtain a treatment scheme word segmentation sequence of each diagnosis and treatment data. Since the therapeutic drugs are included in the treatment plan, the therapeutic drugs in the treatment plan of each diagnosis and treatment data are first identified by the drug library of the hospital.
The formula is constructed:；
wherein, Representing the logical consistency of clinical diagnosis and treatment data and historical diagnosis and treatment data of the current patient.Representing Jaccard correlation coefficients.Representing the normalization function.A sequence of treatment plan words in clinical treatment data representing a current patient.And representing the treatment scheme word segmentation sequence in the j-th clinical diagnosis and treatment data in the matched cluster.And (5) representing the number of clinical diagnosis and treatment data in the matched cluster.Representing the number of drugs used in the current patient's clinical diagnostic data.A component word segmentation sequence representing the kth drug in the current patient treatment regimen.And (5) representing the component word segmentation sequence of all medicines in the j-th clinical diagnosis and treatment data.
The larger the value of (c) is, the more identical segmentation words are in the treatment scheme segmentation word sequence in the clinical diagnosis and treatment data of the current patient and the j-th clinical diagnosis and treatment data in the matched cluster are.The maximum similarity value of the word segmentation sequences of the k-th therapeutic drug in the clinical diagnosis and treatment data of the current patient and all drugs in the j-th clinical diagnosis and treatment data is represented.The larger the value of (c) is, the more similar the composition of the components of the kth therapeutic agent in the clinical diagnosis and treatment data and the jth therapeutic agent in the clinical diagnosis and treatment data of the current patient is.
Thus (2)Is toIs used for avoiding the situation that the names of medicines are different and the components of the medicines are the same.
Thus (2)The larger the value of (c) indicates the greater the logical agreement between the clinical diagnosis and treatment data and the historical diagnosis and treatment data of the current patient. In the present embodiment, the time is setIf the value of (2) is greater than 0.5, the logic of the clinical diagnosis and treatment data of the current patient is reasonable, and the doctor is not required to review. Logic representing clinical diagnostic data of the current patient may be abnormal if less than or equal to 0.5. There is therefore a need to make a further decision as to the logical rationality of the clinical diagnostic data itself for the current patient.
In one possible embodiment, determining the logic rationality of the current patient diagnosis and treatment data specifically includes: and acquiring all the historical clinical diagnosis and treatment data of doctors to which the current patient belongs from the preprocessed historical clinical diagnosis and treatment data. The doctor is responsible for clinical diagnosis and treatment data of the current patient, and in most cases, the doctor is the attending doctor of the current patient. Then, analyzing the symptom similarity of the current patient diagnosis and treatment data and all the historical clinical diagnosis and treatment data of doctors to which the current patient belongs, and taking the historical clinical diagnosis and treatment data with the symptom similarity larger than a third threshold value as comparison clinical diagnosis and treatment data; and analyzing the medicine similarity between the therapeutic medicine of the current patient diagnosis and treatment data and the therapeutic medicine of the comparison clinical diagnosis and treatment data to obtain the logic rationality of the current patient diagnosis and treatment data. Wherein, the drug similarity refers to the drug similarity represented by factors such as drug components, drug quantity, and drug occurrence number.
In this embodiment, the logical consistency, logical rationality, and symptom similarity are normalized values, and the range of values is. In this embodiment, the logic consistency, the logic rationality, and the symptom similarity all use 0.5 as the demarcation point, that is, the first preset threshold, the second preset threshold, and the third preset threshold are all set to 0.5. But depending on the actual scene requirements, one possible scenario is as follows: when the data to be diagnosed needs to be loosely recorded, a numerical value smaller than 0.5 can be used as a demarcation point of logic consistency and logic rationality, for example, the numerical values of a first preset threshold value and a second preset threshold value are set to be 0.3. In another possible case, the logical consistency of the diagnosis and treatment data of the current patient and the historical diagnosis and treatment data is not required, and when the logical rationality requirement of the diagnosis and treatment data of the current patient is strict, the value of the first preset threshold may be set to be less than 0.5, and the value of the second preset threshold may be set to be greater than 0.5. In another possible case, when the requirements of the clinical diagnosis and treatment data recorded by the attending doctor are more standard and uniform, the demarcation point of the symptom similarity can be set higher, for example, the value of the third preset threshold is set to be 0.8, and the historical clinical diagnosis and treatment data with the symptom similarity greater than 0.8 is recorded as the historical clinical diagnosis and treatment data matched by the corresponding attending doctor.
Therefore, in the practical application scene, the third preset threshold value can be correspondingly set according to the requirement of data entry or some unspecified particularities of the disease data, and the third preset threshold value can be completely the same as the first preset threshold value or the second preset threshold value or can be respectively different from the first preset threshold value or the second preset threshold value.
Because each doctor has different treatment experiences and has own style, under the condition of similar symptoms, the treatment scheme of a certain doctor and the treatment schemes of other doctors and the used medicines are different. In this case, the clinical diagnosis and treatment data of the current patient determined by using the above logical consistency may have a logical abnormality. But no abnormalities may occur if compared to the physician's own historical treatment regimen. Therefore, when the clinical diagnosis and treatment data of the current patient are calculated to have logic abnormality according to the logic consistency judging method, the logic rationality of the clinical diagnosis and treatment data of the current patient is determined by calculating the historical treatment scheme of the main doctor of the current patient and the style deviation degree of the treatment scheme of the current patient under the condition that symptoms are known. Specific:
Firstly, all historical clinical diagnosis and treatment data of an attending doctor corresponding to the clinical diagnosis and treatment data of a current patient are acquired. Symptom similarity (same method of symptom similarity in the same logical consistency analysis) of the disease columns in the clinical diagnosis and treatment data of the current patient and all the historical clinical diagnosis and treatment data of the attending doctor is then calculated. And recording the historical clinical diagnosis and treatment data with the disease similarity greater than 0.5 as the historical clinical diagnosis and treatment data matched with the corresponding attending doctor, namely, as the comparison clinical diagnosis and treatment data.
A degree of style shift in the treatment plan between the current patient's clinical diagnosis and treatment data and the historical clinical diagnosis and treatment data matched to the corresponding attending physician is then calculated. Specific:
the formula is constructed: ；
wherein, Treatment style deviation indicative of a treatment regimen of clinical treatment data of a current patient.An exponential function based on a natural constant is represented.Representing the normalization function.Representing the number of drugs used in the current patient's clinical diagnostic data.Representing the number of historical clinical diagnostic data corresponding to the physician match.The kth drug in the treatment regimen representing clinical treatment data of the current patient is in allThe number of occurrences in the secondary clinical diagnostic data.
The larger the value of (c) indicates that the kth drug is in all of the treatment regimens for the clinical data of the current patientThe more times that occur in the secondary clinical diagnostic data.
Thus (2)The larger the value of (c) is, the smaller the treatment style deviation of the treatment plan of the clinical diagnosis and treatment data of the current patient is. When (when)If the value of (2) is less than or equal to 0.5, the logic rationality of the clinical diagnosis and treatment data of the current patient is abnormal.
In the embodiment of the invention, the style deviation degree of the treatment scheme is taken as the logic degree of the embodiment of the invention to judge, namely, the logic degree of the clinical diagnosis and treatment data of the current patient is equally understood as the style deviation degree of the treatment scheme, namely, when the logic degree of the clinical diagnosis and treatment data of the current patient is more than 0.5, the logic degree of the clinical diagnosis and treatment data of the current patient is normal, and the clinical information system can be input. If the logic rationality is less than or equal to 0.5, refusing to enter the hospital information system, and indicating that the clinical diagnosis and treatment data of the current patient has logic errors. Returning to the main doctor corresponding to the current patient, and manually rechecking the diagnosis and treatment data of the current patient again. And then, based on the clinical diagnosis and treatment data of the current patient after the recheck, carrying out judgment on the logic consistency or the logic rationality again, and allowing the patient to enter a hospital information system until the requirement of the logic consistency or the logic rationality is met, so as to ensure that the logic correctness between the medicine used by a doctor and the illness state is ensured, and avoiding making wrong judgment on the illness state and the treatment scheme of the patient.
In the method of the embodiment, the logic consistency or logic rationality is greater than a certain threshold, or less than a certain threshold, or equal to a certain threshold in judgment, and different threshold boundary points can be set according to the requirements of actual specific application scenes.
Based on the same inventive concept as the method embodiment, the embodiment of the invention also provides a clinical diagnosis and treatment data input system, as shown in fig. 2, which specifically comprises:
the data acquisition module is used for acquiring historical clinical diagnosis and treatment data;
The data preprocessing module is used for preprocessing the historical clinical diagnosis and treatment data;
The analysis judging module is used for judging the logic consistency of the current patient diagnosis and treatment data and the preprocessed historical clinical diagnosis and treatment data; if the logic consistency is greater than a first preset threshold value, recording current patient diagnosis and treatment data; otherwise, judging the logic rationality of the current patient diagnosis and treatment data; if the logic rationality is greater than a second preset threshold, recording current patient diagnosis and treatment data;
the return module is used for rechecking the diagnosis and treatment data of the current patient by the doctor to which the current patient belongs if the logic rationality is not greater than a second preset threshold value; and (5) carrying out judgment on logic consistency or logic rationality again based on the current patient diagnosis and treatment data after the recheck.
It should be noted that: the sequence of the embodiments of the present invention is only for description, and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments.
Claims (6)
1. A method of clinical diagnostic data entry, the method comprising:
acquiring historical clinical diagnosis and treatment data, and preprocessing the historical clinical diagnosis and treatment data;
Judging the logic consistency of the current patient diagnosis and treatment data and the preprocessed historical clinical diagnosis and treatment data; if the logic consistency is greater than a first preset threshold, recording the current patient diagnosis and treatment data;
Otherwise, judging the logic rationality of the current patient diagnosis and treatment data; if the logic rationality is greater than a second preset threshold, recording the current patient diagnosis and treatment data;
Wherein preprocessing the historical clinical diagnosis and treatment data comprises: based on M diagnosis and treatment department categories of a hospital, carrying out cluster analysis on the historical clinical diagnosis and treatment data to obtain M large clusters, wherein M is a positive integer;
the method for acquiring the logic consistency comprises the following steps: based on symptom similarity among the historical clinical diagnosis and treatment data in the m-th big cluster, carrying out cluster analysis on the historical clinical diagnosis and treatment data in the m-th cluster to obtain N small clusters; n is a positive integer; ; traversing M large clusters to obtain M multiplied by N small clusters; determining a big cluster corresponding to the current patient diagnosis and treatment data according to a diagnosis and treatment department in which the current patient diagnosis and treatment data is located; according to the symptom similarity of the current patient diagnosis and treatment data and the historical clinical diagnosis and treatment data of all small clusters in the large cluster, obtaining the logic consistency of the current patient diagnosis and treatment data and the preprocessed historical clinical diagnosis and treatment data;
According to the symptom similarity of the current patient diagnosis and treatment data and the historical clinical diagnosis and treatment data of all small clusters in the large cluster, obtaining the logic consistency of the current patient diagnosis and treatment data and the preprocessed historical clinical diagnosis and treatment data, wherein the logic consistency comprises the following steps: according to the symptom similarity of the current patient diagnosis and treatment data and the historical clinical diagnosis and treatment data of all the small clusters in the large cluster, determining the nth small cluster most similar to the symptom of the current patient diagnosis and treatment data, and according to the medicine similarity between the treatment medicine of the current patient diagnosis and treatment data and the treatment medicine of all the historical clinical diagnosis and treatment data in the nth small cluster, obtaining the logic consistency of the current patient diagnosis and treatment data and the preprocessed historical clinical diagnosis and treatment data; wherein, ；
The method for judging the logic rationality of the diagnosis and treatment data of the current patient specifically comprises the following steps: acquiring all the historical clinical diagnosis and treatment data of doctors to which the current patient belongs from the preprocessed historical clinical diagnosis and treatment data; analyzing the symptom similarity of the current patient diagnosis and treatment data and all the historical clinical diagnosis and treatment data of doctors to which the current patient belongs, and taking the historical clinical diagnosis and treatment data with the symptom similarity larger than a third threshold value as comparison clinical diagnosis and treatment data; and analyzing the medicine similarity between the therapeutic medicine of the current patient diagnosis and treatment data and the therapeutic medicine of the comparison clinical diagnosis and treatment data to obtain the logic rationality of the current patient diagnosis and treatment data.
2. A method of clinical trial data entry according to any one of claim 1, wherein the drug similarity comprises: drug composition, number of drugs, and number of drug occurrences.
3. A method of clinical trial data entry according to claim 2, further comprising, after preprocessing the historical clinical trial data:
Performing word segmentation processing on all the historical clinical diagnosis and treatment data to obtain word segmentation sequences of each piece of historical clinical diagnosis and treatment data;
performing word segmentation processing on the current patient diagnosis and treatment data to obtain word segmentation sequences of the current patient diagnosis and treatment data;
Based on the word segmentation sequence of each piece of historical clinical diagnosis and treatment data and the text similarity between the word segmentation sequences of the current patient diagnosis and treatment data, judging the symptom similarity or the medicine similarity.
4. A method of clinical trial data entry according to any one of claims 1 or 3, wherein the historical clinical trial data is plausible prior to the cluster analysis of the historical clinical trial data.
5. The method of claim 1, wherein if the logic rationality is not greater than a second preset threshold, review the current patient diagnostic data by a doctor to which the current patient belongs; and (5) carrying out judgment on logic consistency or logic rationality again based on the current patient diagnosis and treatment data after the recheck.
6. A clinical diagnostic data entry system, the entry system comprising:
the data acquisition module is used for acquiring historical clinical diagnosis and treatment data;
The data preprocessing module is used for preprocessing the historical clinical diagnosis and treatment data; wherein preprocessing the historical clinical diagnosis and treatment data comprises: based on M diagnosis and treatment department categories of a hospital, carrying out cluster analysis on the historical clinical diagnosis and treatment data to obtain M large clusters, wherein M is a positive integer;
The analysis judging module is used for judging the logic consistency of the current patient diagnosis and treatment data and the preprocessed historical clinical diagnosis and treatment data; if the logic consistency is greater than a first preset threshold, recording the current patient diagnosis and treatment data; otherwise, judging the logic rationality of the current patient diagnosis and treatment data; if the logic rationality is greater than a second preset threshold, recording the current patient diagnosis and treatment data;
the method for acquiring the logic consistency comprises the following steps: based on symptom similarity among the historical clinical diagnosis and treatment data in the m-th big cluster, carrying out cluster analysis on the historical clinical diagnosis and treatment data in the m-th cluster to obtain N small clusters; n is a positive integer; ; traversing M large clusters to obtain M multiplied by N small clusters; determining a big cluster corresponding to the current patient diagnosis and treatment data according to a diagnosis and treatment department in which the current patient diagnosis and treatment data is located; according to the symptom similarity of the current patient diagnosis and treatment data and the historical clinical diagnosis and treatment data of all small clusters in the large cluster, obtaining the logic consistency of the current patient diagnosis and treatment data and the preprocessed historical clinical diagnosis and treatment data;
According to the symptom similarity of the current patient diagnosis and treatment data and the historical clinical diagnosis and treatment data of all small clusters in the large cluster, obtaining the logic consistency of the current patient diagnosis and treatment data and the preprocessed historical clinical diagnosis and treatment data, wherein the logic consistency comprises the following steps: according to the symptom similarity of the current patient diagnosis and treatment data and the historical clinical diagnosis and treatment data of all the small clusters in the large cluster, determining the nth small cluster most similar to the symptom of the current patient diagnosis and treatment data, and according to the medicine similarity between the treatment medicine of the current patient diagnosis and treatment data and the treatment medicine of all the historical clinical diagnosis and treatment data in the nth small cluster, obtaining the logic consistency of the current patient diagnosis and treatment data and the preprocessed historical clinical diagnosis and treatment data; wherein, ；
The method for judging the logic rationality of the diagnosis and treatment data of the current patient specifically comprises the following steps: acquiring all the historical clinical diagnosis and treatment data of doctors to which the current patient belongs from the preprocessed historical clinical diagnosis and treatment data; analyzing the symptom similarity of the current patient diagnosis and treatment data and all the historical clinical diagnosis and treatment data of doctors to which the current patient belongs, and taking the historical clinical diagnosis and treatment data with the symptom similarity larger than a third threshold value as comparison clinical diagnosis and treatment data; analyzing the medicine similarity between the therapeutic medicine of the current patient diagnosis and treatment data and the therapeutic medicine of the comparison clinical diagnosis and treatment data to obtain the logic rationality of the current patient diagnosis and treatment data;
The return module is used for rechecking the diagnosis and treatment data of the current patient by a doctor to which the current patient belongs if the logic rationality is not greater than a second preset threshold value; and (5) carrying out judgment on logic consistency or logic rationality again based on the current patient diagnosis and treatment data after the recheck.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410985107.XA CN118522396B (en) | 2024-07-23 | 2024-07-23 | Clinical diagnosis and treatment data input method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410985107.XA CN118522396B (en) | 2024-07-23 | 2024-07-23 | Clinical diagnosis and treatment data input method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118522396A CN118522396A (en) | 2024-08-20 |
| CN118522396B true CN118522396B (en) | 2024-10-01 |
Family
ID=92282233
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410985107.XA Active CN118522396B (en) | 2024-07-23 | 2024-07-23 | Clinical diagnosis and treatment data input method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118522396B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108172302A (en) * | 2017-12-15 | 2018-06-15 | 广州市康软信息科技有限公司 | Rational use of medicines information monitoring method and system |
| CN109637615A (en) * | 2018-11-30 | 2019-04-16 | 平安医疗健康管理股份有限公司 | Judgment method, device, equipment and the readable storage medium storing program for executing of abnormal medicine prescription |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110249392A (en) * | 2018-08-20 | 2019-09-17 | 深圳市全息医疗科技有限公司 | Intelligent assisting in diagnosis and treatment system and method |
| CN110875093A (en) * | 2019-11-19 | 2020-03-10 | 泰康保险集团股份有限公司 | Treatment scheme processing method, device, equipment and storage medium |
| US20220328156A1 (en) * | 2021-04-10 | 2022-10-13 | Zhejiang University | Method, apparatus, device and medium for medication decision support based on graphics state machine |
| CN112992370B (en) * | 2021-05-06 | 2021-07-30 | 四川大学华西医院 | An unsupervised electronic medical record-based medical behavior compliance assessment method |
| CN113674858B (en) * | 2021-08-30 | 2023-12-01 | 康键信息技术（深圳）有限公司 | Intelligent inspection method, device, equipment and storage medium for on-line medical prescription medication |
| CN114334070A (en) * | 2022-01-05 | 2022-04-12 | 上海良方健康科技有限公司 | Auxiliary prescription system based on medical big data |
| CN118072904B (en) * | 2024-04-24 | 2024-09-06 | 万链指数(青岛)信息科技有限公司 | Intelligent inspection method and system for on-line medical prescription medication |
-
2024
- 2024-07-23 CN CN202410985107.XA patent/CN118522396B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108172302A (en) * | 2017-12-15 | 2018-06-15 | 广州市康软信息科技有限公司 | Rational use of medicines information monitoring method and system |
| CN109637615A (en) * | 2018-11-30 | 2019-04-16 | 平安医疗健康管理股份有限公司 | Judgment method, device, equipment and the readable storage medium storing program for executing of abnormal medicine prescription |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118522396A (en) | 2024-08-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11669791B2 (en) | Accession number correction system and methods for use therewith | |
| US11763933B2 (en) | Medical report labeling system and method for use therewith | |
| CN110136788B (en) | A medical record quality inspection method, device, equipment and storage medium based on automatic detection | |
| US11037070B2 (en) | Diagnostic test planning using machine learning techniques | |
| KR102237449B1 (en) | Method, server and program of learning a patient diagnosis | |
| EP3654343A1 (en) | Application of deep learning for medical imaging evaluation | |
| CN110689939A (en) | Recommendation method and device for medication sequence, readable medium and electronic equipment | |
| CN112447270A (en) | Medication recommendation method, device, equipment and storage medium | |
| WO2017017554A1 (en) | Reliability measurement in data analysis of altered data sets | |
| WO2021151302A1 (en) | Drug quality-control analysis method, apparatus, device, and medium based on machine learning | |
| CN110491519A (en) | A kind of method of inspection of medical data | |
| CN118522396B (en) | Clinical diagnosis and treatment data input method and system | |
| Nair et al. | Automated clinical concept-value pair extraction from discharge summary of pituitary adenoma patients | |
| CN113517044A (en) | Clinical data processing method and system for evaluating citicoline based on pharmacokinetics | |
| CN118760973A (en) | A method for predicting intensive care needs of patients with cerebral hemorrhage based on multimodal fusion | |
| CN114649071A (en) | Real world data-based peptic ulcer treatment scheme prediction system | |
| CN112071431A (en) | Clinical path automatic generation method and system based on deep learning and knowledge graph | |
| CN111667922A (en) | Clinical diagnosis and treatment data entry system and method | |
| Berdaly et al. | Comparative machine-learning approach: study for heart diseases | |
| CN112820368A (en) | Method, system, device and storage medium for constructing critical patient data set | |
| Röhr et al. | Revisiting Clinical Outcome Prediction for MIMIC-IV | |
| CN113450919A (en) | Construction method and construction system of heart failure early warning model and heart failure early warning device | |
| Heryawan et al. | Deep learning and machine learning model comparison for diagnosis detection from medical records | |
| RU2818874C1 (en) | Medical decision support system | |
| CN118445419B (en) | Method, device, equipment and medium for constructing prompt automatic labeling medical text based on large model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |