CN110851503A - Medical mode conversion identification method and device, electronic equipment and storage medium - Google Patents
Medical mode conversion identification method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN110851503A CN110851503A CN201911135520.2A CN201911135520A CN110851503A CN 110851503 A CN110851503 A CN 110851503A CN 201911135520 A CN201911135520 A CN 201911135520A CN 110851503 A CN110851503 A CN 110851503A
- Authority
- CN
- China
- Prior art keywords
- subsequence
- breakpoint
- medical
- medical data
- patient
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2474—Sequence data queries, e.g. querying versioned data
-
- 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
Abstract
The disclosure provides a medical mode conversion identification method, a medical mode conversion identification device, electronic equipment and a computer readable storage medium, and belongs to the technical field of intelligent medical treatment. The method comprises the following steps: acquiring medical data of a plurality of time nodes in a full life cycle of a patient; determining one or more breakpoints in the full lifecycle, the breakpoints being located between two adjacent time nodes; determining the difference degree between the medical data before the breakpoint and the medical data after the breakpoint; and determining a target breakpoint for the medical mode of the patient to be converted from the breakpoints according to the difference degree. The method and the device can effectively identify the conversion point of the medical treatment mode in the whole life cycle of the patient, and have higher identification accuracy.
Description
Technical Field
The present disclosure relates to the field of intelligent medical technologies, and in particular, to a medical mode conversion method, a medical mode conversion apparatus, an electronic device, and a computer-readable storage medium.
Background
In a medical procedure, in order to determine the state change of a patient and to effectively adjust medical decision, it is usually necessary to find out the time point when the patient changes the medical mode in the whole life cycle.
Existing medical mode transition recognition methods typically analyze the patient's medical data as a whole or default that the same medical mode may occur over a period of time. In practical application, due to the irreversibility of the state development of the patient, the medical mode of the patient cannot be repeated in a long time range on the same individual, and the method is difficult to accurately and effectively identify the medical mode of the patient in the whole life cycle.
Therefore, how to realize effective and accurate medical mode conversion and identification is a problem to be solved in the prior art.
It is to be noted that the information disclosed in the above background section is only for enhancement of understanding of the background of the present disclosure, and thus may include information that does not constitute prior art known to those of ordinary skill in the art.
Disclosure of Invention
The present disclosure provides a medical mode conversion identification method, a medical mode conversion identification apparatus, an electronic device, and a computer-readable storage medium, thereby overcoming, at least to some extent, the problems of low accuracy and effectiveness of the existing medical mode conversion method.
Additional features and advantages of the disclosure will be set forth in the detailed description which follows, or in part will be obvious from the description, or may be learned by practice of the disclosure.
According to an aspect of the present disclosure, there is provided a medical mode transition recognition method including: acquiring medical data of a plurality of time nodes in a full life cycle of a patient; determining one or more breakpoints in the full lifecycle, the breakpoints being located between two adjacent time nodes; determining the difference degree between the medical data before the breakpoint and the medical data after the breakpoint; and determining a target breakpoint for the medical mode of the patient to be converted from the breakpoints according to the difference degree.
In an exemplary embodiment of the present disclosure, after acquiring the medical data, the method further comprises: converting the medical data of each time node into vectors, and arranging the vectors into a sequence according to the sequence of the time nodes; the determining the difference between the medical data before the breakpoint and the medical data after the breakpoint comprises: extracting a first subsequence from vectors in the sequence that are located before the breakpoint and a second subsequence from vectors in the sequence that are located after the breakpoint; and calculating the difference degree of the first subsequence and the second subsequence.
In an exemplary embodiment of the present disclosure, the first subsequence and the second subsequence are the same length; the calculating the difference degree of the first subsequence and the second subsequence comprises: based on the first subsequence and the second subsequence, establishing a scoring matrix, wherein the scoring matrix comprises a difference degree between a vector of any time node in the first subsequence and a vector of any time node in the second subsequence; determining a target matching path in the scoring matrix; and taking the average value of the difference degrees in the target matching paths as the difference degree of the first subsequence and the second subsequence.
In an exemplary embodiment of the present disclosure, when extracting a first subsequence and a second subsequence, extracting a plurality of sets of the first subsequence and the second subsequence, respectively, wherein the length of each set of the first subsequence and the second subsequence is the same; the calculating the difference degree of the first subsequence and the second subsequence comprises: and respectively calculating the difference degree of each group of the first subsequence and the second subsequence, and taking the difference degree with the minimum value as the difference degree of the medical data before the breakpoint and the medical data after the breakpoint.
In an exemplary embodiment of the disclosure, the first sub-sequences each use the time node before the breakpoint as an end point, and the second sub-sequences each use the time node after the breakpoint as a start point.
In an exemplary embodiment of the present disclosure, the acquiring medical data of a plurality of time nodes in a full life cycle of a patient includes: acquiring original data of a plurality of time nodes in the whole life cycle of a patient, and carrying out structured processing on the original data according to a preset field; and carrying out normalization processing on the raw data after the structuralization processing to obtain the medical data of the multiple time nodes.
In an exemplary embodiment of the present disclosure, determining one or more breakpoints in the full lifecycle includes: a breakpoint is determined between any two adjacent said time nodes.
In an exemplary embodiment of the present disclosure, the determining a target breakpoint from the breakpoints for which the medical mode of the patient is converted according to the difference degree includes: and determining the breakpoint corresponding to the difference degree exceeding the preset threshold value as a target breakpoint for the medical mode conversion of the patient.
In an exemplary embodiment of the disclosure, the degree of difference includes any one or more of: euclidean distance, Mandarin distance, and the inverse of cosine similarity.
According to an aspect of the present disclosure, there is provided a medical mode transition recognition apparatus including: the data acquisition module is used for acquiring medical data of a plurality of time nodes in the whole life cycle of a patient; a breakpoint determination module configured to determine one or more breakpoints in the full lifecycle, where the breakpoints are located between two adjacent time nodes; the data calculation module is used for determining the difference degree between the medical data before the breakpoint and the medical data after the breakpoint; and the breakpoint identification module is used for determining a target breakpoint for switching the medical mode of the patient from the breakpoints according to the difference degree.
In an exemplary embodiment of the present disclosure, after acquiring the medical data, the medical mode transition recognition apparatus further includes: the vector conversion module is used for converting the medical data of each time node into vectors and arranging the vectors into a sequence according to the sequence of the time nodes; the data calculation module comprises: a sequence extraction unit, configured to extract a first subsequence from a vector in the sequence that is located before the breakpoint and extract a second subsequence from a vector in the sequence that is located after the breakpoint; and the sequence calculating unit is used for calculating the difference degree of the first subsequence and the second subsequence.
In an exemplary embodiment of the present disclosure, the first subsequence and the second subsequence are the same length; the sequence calculation unit includes: a scoring matrix establishing subunit, configured to establish a scoring matrix based on the first subsequence and the second subsequence, where the scoring matrix includes a difference between a vector of any time node in the first subsequence and a vector of any time node in the second subsequence; a path determining subunit, configured to determine a target matching path in the scoring matrix; and the difference degree calculation unit is used for taking the average value of the difference degrees in the target matching paths as the difference degree of the first subsequence and the second subsequence.
In an exemplary embodiment of the present disclosure, when extracting a first subsequence and a second subsequence, extracting a plurality of sets of the first subsequence and the second subsequence, respectively, wherein the length of each set of the first subsequence and the second subsequence is the same; the sequence calculation unit is used for calculating the difference degree of each group of the first subsequence and the second subsequence, and taking the difference degree with the minimum value as the difference degree of the medical data before the breakpoint and the medical data after the breakpoint.
In an exemplary embodiment of the disclosure, the first sub-sequences each use the time node before the breakpoint as an end point, and the second sub-sequences each use the time node after the breakpoint as a start point.
In an exemplary embodiment of the present disclosure, the data acquisition module includes: the system comprises a structural processing unit, a data processing unit and a data processing unit, wherein the structural processing unit is used for acquiring original data of a plurality of time nodes in the whole life cycle of a patient and carrying out structural processing on the original data according to preset fields; and the normalization processing unit is used for performing normalization processing on the raw data after the structuralization processing to obtain the medical data of the multiple time nodes.
In an exemplary embodiment of the disclosure, the breakpoint determination module is configured to determine a breakpoint between any two adjacent time nodes.
In an exemplary embodiment of the disclosure, the breakpoint identification module is configured to determine a breakpoint corresponding to the difference degree exceeding a preset threshold as a target breakpoint for switching the medical mode of the patient.
In an exemplary embodiment of the disclosure, the degree of difference includes any one or more of: euclidean distance, Mandarin distance, and the inverse of cosine similarity.
According to an aspect of the present disclosure, there is provided an electronic device including: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to perform the method of any one of the above via execution of the executable instructions.
According to an aspect of the present disclosure, there is provided a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the method of any one of the above.
Exemplary embodiments of the present disclosure have the following advantageous effects:
according to the medical mode conversion and identification method, the medical mode conversion and identification device, the electronic equipment and the storage medium, medical data of a plurality of time nodes in the whole life cycle of a patient are obtained, one or more break points between two adjacent time nodes are determined, and a target break point for conversion of the medical mode of the patient is determined from the break points by calculating the difference degree of the medical data before and after the break points. On one hand, the target breakpoint of medical mode conversion is identified by comparing the difference degree of the medical data before and after the breakpoint, and the difference degree can represent the difference of the two parts of medical data in the change trend, so that the accuracy of the identified target breakpoint is improved. On the other hand, the whole identification process is realized based on the processing of the medical data of the patient, the characteristic information can be mined from the medical data with time sequence distribution, the data in other aspects does not need to be acquired, and the method has high practicability.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and together with the description, serve to explain the principles of the disclosure. It is to be understood that the drawings in the following description are merely exemplary of the disclosure, and that other drawings may be derived from those drawings by one of ordinary skill in the art without the exercise of inventive faculty.
Fig. 1 schematically illustrates a flow chart of a medical mode transition recognition method in the present exemplary embodiment;
FIG. 2 schematically illustrates a sub-flow diagram of a medical mode transition recognition method in the present exemplary embodiment;
FIG. 3 schematically illustrates a sub-flow diagram of another medical mode transition recognition method in the present exemplary embodiment;
fig. 4 is a block diagram schematically showing the structure of a medical mode transition recognition apparatus in the present exemplary embodiment;
fig. 5 schematically illustrates an electronic device for implementing the above method in the present exemplary embodiment;
fig. 6 schematically illustrates a computer-readable storage medium for implementing the above-described method in the present exemplary embodiment.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many different forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
An exemplary embodiment of the present disclosure first provides a medical mode transition recognition method. Generally, when a patient is hospitalized, taking into consideration the type of disease, pathological manifestations of the disease, and difference of severity of the disease, the patient may perform a medical action in different medical modes, where a medical mode may refer to a medical method adopted when the patient is hospitalized, for example, according to the disease severity of the patient, a medical mode in which the patient may adopt expert diagnosis, a medical mode in general diagnosis, an online cloud intelligent medical mode, or a medical mode in multidisciplinary cooperation is determined; or according to different pathological manifestations of a patient, it may be determined whether the patient adopts a medical mode of drug therapy or a medical mode of surgical therapy, and the like, and the medical mode may have various categories according to different division criteria, which is not specifically limited by the present disclosure.
The application scenario of the method of the embodiment may be as follows: when the medical data of the whole life cycle of a certain patient is subjected to macroscopic analysis, determining a node for medical mode conversion of the patient, and adjusting the current medical mode according to the condition of the patient; or accurately distinguishing the medical modes of the patients at different stages so as to realize the medical data analysis of the patients at the same stage; or analysis of patterns of changes in the medical pattern that occur as pathology progresses through the patient's life cycle.
The exemplary embodiment is further described with reference to fig. 1, and as shown in fig. 1, the medical mode conversion identification method may include the following steps S110 to S140:
step S110, medical data of a plurality of time nodes in the whole life cycle of the patient are obtained.
The full life cycle refers to the overall process of diagnosis and treatment or observation of a patient, for example, the overall time from the beginning to the end of a disease of a certain patient can be regarded as the full life cycle of the patient; or the total time between the patient going to the hospital for the first examination and going to the hospital for the last examination may be considered the patient's full life cycle, etc. The time node refers to a time point when a patient makes a diagnosis and treatment each time in a medical process of a full life cycle, for example, a time point when the patient goes to a hospital each time in the full life cycle of the patient, such as a time point of a first examination, or a time point of a last review. The medical data refers to data generated by diagnosis and treatment of a patient at each time node, and can reflect a medical mode of the patient at a current stage or node, the medical data may include multiple types, such as medication data (for example, data on what kind of medicine and dosage the patient has), inspection data (for example, blood routine data obtained by performing an assay on blood of the patient), or inspection data (for example, data on basic inspection of heart rate, blood pressure, and the like of the patient), and each type of medical data may further include more specific data, for example, the medication data includes what kind of medicine the patient currently uses, and a specific medicine name or a medicine function (for example, the medication data includes medicine 1, medicine 2, medicine 3, and the like); or the test data includes what test items the patient has performed and what results are determined (e.g., the test data includes that the patient has performed a blood glucose test, a blood lipid test, a liver function test, etc.).
In the exemplary embodiment, medical personnel may obtain medical data from a particular database for a plurality of time nodes throughout a patient's life cycle. In addition, partial information of the patient can also be input into the system, so that the medical data of the patient can be searched in other databases to obtain the complete full-life-cycle medical data.
In an exemplary embodiment, step S110 may include the steps of:
acquiring original data of a plurality of time nodes in the whole life cycle of a patient, and carrying out structured processing on the original data according to a preset field;
and carrying out normalization processing on the structured original data to obtain medical data of a plurality of time nodes.
In consideration of the fact that the medical data of the patient, which is usually obtained from the database, may be a large amount of text data, in order to facilitate analysis processing, the raw data may be structured by preset fields, and the required data is extracted, for example, the medical data required in the present exemplary embodiment may be extracted from the large amount of text data according to keywords such as "medicine", "symptom", "examination", and the like. In addition, due to the abundant and inconsistent sources of data, it may happen that the same concept or similar data has different expressions, for example, the obtained medical data is white blood cell data, WBC data, or symptom data of the patient is cough, dry cough, etc., while white blood cell data is WBC data, and cough and dry cough are the same concept in some diseases. Therefore, the present exemplary embodiment can perform the structuring process and the normalization process on the acquired raw data, so that the acquired medical data of a plurality of time nodes maintain the same format and form. In addition, a word list can be established according to the medical data after the structuring and normalization processing, so that vectorization processing or other calculation and analysis can be performed on the medical data according to the word list.
Step S120, determining one or more breakpoints in the full lifecycle, the breakpoints being located between two adjacent time nodes.
The breakpoint refers to a point used for monitoring a medical mode change in a full life cycle of a patient, and may be located between two adjacent time nodes, for example, 10 examinations are performed in the full life cycle of a certain patient, that is, medical data of 10 time nodes is included, and the breakpoint may be located in the 10 time nodes, between two adjacent time nodes, for example, between the 1 st time node and the 2 nd time node, or between the 9 th time node and the 10 th time node, and so on. The number of the breakpoints can be set in a customized manner as needed, for example, one breakpoint between the 5 th time node and the 6 th time node can be selected, all breakpoints between every two time nodes (for example, 9 breakpoints can be determined for 10 time nodes), and the like, which is not specifically limited in this disclosure. In addition, the breakpoint can be represented according to the number of time nodes, for example, between the 1 st time node and the 2 nd time node, the breakpoint can be represented as 1.5; the breakpoint may also be represented according to a specific time, for example, any time between the 1 st time node and the 2 nd time node may also represent a current breakpoint, which is not specifically limited in this disclosure.
In an exemplary embodiment, the determining one or more breakpoints in the full lifecycle includes:
a breakpoint is determined between any two adjacent time nodes.
In particular, the present exemplary embodiment may select to determine the breakpoint between any two adjacent time nodes, for example, in the above-mentioned full life cycle of 10 time nodes, according to any two adjacent time nodes, that is, 9 breakpoints may be determined as the points analyzed by the present exemplary embodiment. The most accurate breakpoint can be determined from all breakpoints which are possible to be converted in the medical mode by comprehensively calculating and analyzing the breakpoints in the whole life cycle and comparing the breakpoints.
Step S130, determining the difference between the medical data before the breakpoint and the medical data after the breakpoint.
In the present exemplary embodiment, a key breakpoint of the medical mode conversion can be determined by calculating a difference degree, i.e., a dissimilarity degree, between the medical data before the breakpoint and the medical data after the breakpoint, and determining whether the medical mode before the breakpoint and the medical mode after the breakpoint have a large difference. Specifically, the time series of the medical data before the breakpoint and the time series of the medical data after the breakpoint can be determined, and the difference between the medical data before the breakpoint and the medical data after the breakpoint can be determined by comparing the time series before the breakpoint and the time series after the breakpoint.
In an exemplary embodiment, after the medical data is acquired, the medical mode transition recognition method may further include the steps of:
step S210, converting the medical data of each time node into vectors, and arranging the vectors into a sequence according to the sequence of the time nodes;
further, the step S130 may include the following steps:
step S220, extracting a first subsequence from a vector in the sequence before the breakpoint and extracting a second subsequence from a vector in the sequence after the breakpoint;
step S230, calculating a difference between the first subsequence and the second subsequence.
In order to facilitate calculation and analysis of the medical data, in the present exemplary embodiment, vectorization processing may be performed on the acquired medical data, for example, when a certain patient performs a1 st examination, the determined medical data includes "medication record: drug 1, drug 2, drug 3; checking data: blood sugar test, blood fat test, liver function test, etc., the vector of the 1 st time node of the patient about the medical data can be obtained by vectorization processing, and is represented as [ a1, a2, a3, b1, b2, b3], wherein a1, a2, a3 are respectively medicine 1, medicine 2, medicine 3, b1, b2, b3 are respectively blood sugar test, blood fat test, liver function test. The vectors of each time node of the patient full life cycle relative to the medical data are arranged according to the sequence of the time nodes, so that the time sequence of the patient full life cycle can be obtained. Since the time series is the medical data collected at different time nodes, each time node comprises the vector of the patient about the medical data under the time node, the information such as the change condition, state or degree of the medical mode of the patient under each time node in the whole life cycle along with the time can be reflected by the time series.
The first subsequence refers to a sequence extracted before a certain breakpoint in the time sequence, and the second subsequence is a sequence extracted after the breakpoint in the time sequence. The first subsequence may be a partial or complete time sequence before the breakpoint, for example, in a time sequence formed by vectors of 10 time nodes, a breakpoint between the 5 th time node and the 6 th time node is a partition point, the sequence before the breakpoint may be a sequence formed by vectors of 1 st time node to 5 th time node, a sequence formed by vectors of 3 rd time node to 5 th time node, a sequence formed by vectors of 2 nd time node to 4 th time node, and the like, and the extraction manner of the second subsequence is similar to the rule of the first subsequence, and is not described herein.
Furthermore, the difference degree of the medical modes reflected by the medical data before the breakpoint and the medical data after the breakpoint can be obtained by calculating the difference degree of the first subsequence and the second subsequence. Since the time series are collected according to the time sequence and arranged according to a certain rule, the exemplary embodiment can accurately judge whether the medical mode reflected by the two time series is greatly converted by determining the similarity and homology between the two time series, thereby determining the conversion point.
In an exemplary embodiment, the above-mentioned difference degree may include any one or more of the following: euclidean distance, Mandarin distance, and the inverse of cosine similarity.
And calculating the difference degree of the two subsequences, namely calculating the dissimilarity degree between vectors of every two time nodes in the two subsequences. In the present exemplary embodiment, the dissimilarity may be determined in various ways, such as a euclidean distance, a mannhain distance, and an inverse number of cosine similarities. Taking the euclidean distance as an example, the euclidean distance is a metric, and is usually defined by using the distance. The vector of each time node determined in the present exemplary embodiment may be mapped onto a multidimensional space, and by calculating the true distance between points in the multidimensional space where two vectors are located, the dissimilarity between the two vectors may be determined. For example, set V1，V2The space distance of the two medical data of the two vectorized time nodes is recorded as d (V)1，V2) Vector V1The data of the traditional Chinese medicine is recorded as V1AThe specific medication data may include "a1，a2，a3…an"data of multiple dimensions, inspection data is denoted as V1BThe detailed inspection data may include "b1，b2，b3…bn"data of multiple dimensions; vector V2The data of the traditional Chinese medicine is recorded as V2AAnd the inspection data is recorded as V2BWherein the representation of the particular data is associated with a vector V1Similarly. In addition, vector V1，V2May also include other N types of medical data than the A, B type of medical data, and may specifically include in the N type of medical data "n1，n2，n3…nn"data of multiple dimensions, etc., further, the dissimilarity between vectors of two time nodes can be calculated by the following formula:
wherein d (V)1A,V2A) Can be calculated by the following formula:
the difference degree of the two sequences can be determined by calculating the Euclidean distance between the vectors of every two time nodes in the two sequences. The present exemplary embodiment can also calculate the difference between two sequences by the inverse of the mansion distance and the cosine similarity, and so on.
And step S140, determining a target breakpoint for the medical mode conversion of the patient from the breakpoints according to the difference degree.
In the present exemplary embodiment, if the difference between the medical data before and after a certain breakpoint is higher than a preset condition, the breakpoint can be regarded as a key turning point of the medical mode conversion of the patient, that is, the target breakpoint. In the exemplary embodiment, only one breakpoint can be determined as a target breakpoint, or a plurality of target breakpoints can be determined, for example, time sequences before and after all breakpoints are calculated, and a corresponding breakpoint when the difference degree is the highest is determined as a target breakpoint; or all breakpoints with a degree of variance higher than a certain degree are taken as target breakpoints, and so on.
In addition, in order to facilitate the visualized analysis of the medical mode conversion state, the exemplary embodiment may further convert the time series of the patient's entire life cycle into a curve image in which a plurality of break points are abscissa and the difference between the time series before and after each break point is ordinate, and analyze the curve in the image by setting a threshold of the slope of the difference curve, and take the break point in the curve whose slope exceeds the threshold as a target break point. The threshold of the slope of the difference curve is an adjustable parameter, so that the threshold can be adjusted according to the intensity of the change of the medical mode, or can be set by self-definition according to the needs of an observer, which is not specifically limited in the present disclosure.
In an exemplary embodiment, the breakpoint corresponding to the difference degree exceeding the preset threshold is determined as a target breakpoint for the transition of the medical mode of the patient.
That is, a preset threshold value related to the degree of difference may be set in the present exemplary embodiment, and the target breakpoint is determined by determining whether the degree of difference exceeds the preset threshold value, where the preset threshold value may be set manually in a user-defined manner, for example, if a medical mode conversion recognition effect with higher sensitivity is required, the preset threshold value may be set lower, and if the medical mode conversion degree requirement is required to be higher, that is, if the medical mode has a larger difference, analysis is required, the preset threshold value may be set higher, which is not specifically limited by the present disclosure.
Based on the above description, in the present exemplary embodiment, medical data of a plurality of time nodes in the full life cycle of a patient is acquired, one or more break points located between two adjacent time nodes are determined, and a target break point at which the medical mode of the patient is converted is determined from the break points by calculating the difference degree of the medical data before and after the break point. On one hand, the target breakpoint of medical mode conversion is identified by comparing the difference degree of the medical data before and after the breakpoint, and the difference degree can represent the difference of the two parts of medical data in the change trend, so that the accuracy of the identified target breakpoint is improved. On the other hand, the whole identification process is realized based on the processing of the medical data of the patient, the characteristic information can be mined from the medical data with time sequence distribution, the data in other aspects does not need to be acquired, and the method has high practicability.
In an exemplary embodiment, the lengths of the first sub-sequence and the second sub-sequence are the same, and the step S230 may include the following steps:
step S310, establishing a scoring matrix based on the first subsequence and the second subsequence, wherein the scoring matrix comprises the difference degree between the vector of any time node in the first subsequence and the vector of any time node in the second subsequence;
step S320, determining a target matching path in the scoring matrix;
in step S330, the average value of the difference degrees in the target matching path is used as the difference degree between the first subsequence and the second subsequence.
In the present exemplary embodiment, a first subsequence C, denoted as C ═ C, may be extracted from the sequence preceding the break point1，C2，C3，…，CnExtracting a second subsequence D from the sequence following the breakpoint, denoted D ═ D1，D2，D3，…，DnWherein, CnVector representing the nth time node before the breakpoint, DnThe vector representing the nth time node after the breakpoint, the first subsequence and the second subsequence have the same length, the subscripts are merely illustrative, and the order of the time nodes is not limited, for example, taking a sequence of a full life cycle of 10 time nodes as an example, when the breakpoint is determined to be between the 5 th time node and the 6 th time node, the sequence of the 1 st time node to the 5 th time node is determined to be the first subsequence, and C is equal to C1，C2，C3，C4，C5Wherein, C1Vector representing the 1 st time node, C5Representing the vector of the 5 th time node, determining the sequence from the 6 th time node to the 10 th time node as a second subsequence, and then D ═ D1，D2，D3，D4，D5Wherein D is1Vector representing the 6 th time node, D5A vector representing the 10 th time node.
The scoring matrix is a matrix for determining the difference between the first subsequence and the second subsequence, and the exemplary embodiment may determine the difference between the first subsequence and the second subsequence by establishing the scoring matrix of the first subsequence and the second subsequence and determining a target matching path in the scoring matrix. In general, in the scoring matrix, a plurality of matching paths may be determined from the starting point to the end point, and the present exemplary embodiment may determine a best matching path, i.e., a target matching path, from the plurality of matching paths, and determine the difference between the first subsequence and the second subsequence according to the target matching path. For example, a first subsequence C is extracted before a breakpoint in a time sequence of a full life cycle of a patient, and a second subsequence D is extracted after the breakpoint, wherein the first subsequence C and the second subsequence D have the same length, and a scoring matrix is established according to the first subsequence C and the second subsequence D, as shown in the following table:
TABLE 1
| D | D1 | D2 | D3 | D4 | … | Dn | |
| C | 0 | d(C1,0) | d(0,D2) | d(0,D3) | d(0,D4) | … | d(0,Dn) |
| C1 | d(C1,0) | d(C1,D1) | d(C1,D2) | d(D1,D3) | d(C1,D4) | … | d(C1,Dn) |
| C2 | d(C2,0) | d(C2,D1) | d(C2,D2) | d(D2,C3) | d(C2,D4) | … | d(C2,Dn) |
| C3 | d(C3,0) | d(C3,D1) | d(C3,D2) | d(D3,C3) | d(C3,D4) | … | d(C3,Dn) |
| C4 | d(C4,0) | d(C4,D1) | d(C4,D2) | d(D4,C3) | d(C4,D4) | … | d(C4,Dn) |
| … | … | … | … | … | … | … | … |
| Cn | d(Cn,0) | d(Cn,D1) | d(Cn,D2) | d(Cn,D3) | d(Cn,D4) | … | d(Cn,Dn) |
Wherein d (C)n,Dn) Representing the Euclidean distance between the vector of the nth time node in the first subsequence C and the vector of the nth time node in the second subsequence D, the scoring matrix may beIncluding the euclidean distance between the vector of any time node in the first subsequence and the vector of any time node in the second subsequence, e.g., D (C1, D2) is the euclidean distance between the vector of the 1 st time node in the first subsequence C and the vector of the 2 nd time node in the second subsequence D, etc.
Considering that in the scoring matrix, the score between a pair of matched vectors is expressed by using the euclidean distance, therefore, the larger the value of the euclidean distance, the larger the vector difference between two time nodes representing the match, and thus the degree of difference can be characterized. In the present exemplary embodiment, the degree of difference between the first subsequence and the second subsequence may be scored using a Blast algorithm or the like.
Further, by using the scoring matrix, an optimal matching path may be constructed by using a dynamic programming algorithm, specifically, for the m-th row and the n-th column of cells (denoted as distance (m, n)), the value of the cell may be:
the above formula indicates that the path from each cell to the next cell in the process from the start point to the end point of the scoring matrix may have three directions, where δ represents the unit distance traveled by the lateral path or the longitudinal path, and d (Cm, Dn) represents the unit distance traveled by the diagonal path. In the present exemplary embodiment, the starting point of the target matching path is 0 point, the end point is the maximum time node n of the first subsequence and the second subsequence, if the starting point is 0, the end point is d (C)n,Dn). Starting from 0 point in the above-mentioned scoring matrix, d (C)n,Dn) For example, the best matching path of the two sequences for performing the path search may be a cell with the shortest euclidean distance in the above three directions, and each cell with the smallest euclidean distance passing through the scoring matrix may be determined according to this manner, so as to obtain the best matching path in the present exemplary embodiment, that is, the target matching path. For example, the target matching path may be "0-d (C)1,D1)—d(C2,D2)—d(C3,D2)—d(D3,C3)—d(C3,D4)—……—d(Cn,Dn)”。
Considering that the comparison of the degree of difference of the pairs of sub-sequences of different lengths may be involved in the present exemplary embodiment, the influence of the sequence length on the degree of difference may be corrected in order to make the calculation result universal. Specifically, the difference between the first subsequence and the second subsequence can be calculated by the following formula:
wherein d (Ci, Dj) is the euclidean distance of each cell in the target matching path, n represents the path length of the target matching path, that is, the sequence length of the first subsequence or the second subsequence, and dissimilarity represents the difference between the first subsequence and the second subsequence, that is, the difference between the first subsequence and the second subsequence can be obtained by calculating the average value of the differences in the target matching path. The exemplary embodiment integrates the matched sub-sequence length factor into the calculation formula of the sequence difference, so that the influence of the sequence length on the evaluation of the difference can be eliminated, and the comparability of the difference measurement between sequence matching with different lengths can be realized.
In an exemplary embodiment, when extracting the first subsequence and the second subsequence, extracting a plurality of groups of first subsequences and second subsequences respectively, wherein the length of each group of first subsequences and second subsequences is the same;
further, step S230 may include:
and respectively calculating the difference degree of each group of the first subsequence and the second subsequence, and taking the difference degree with the minimum value as the difference degree of the medical data before the breakpoint and the medical data after the breakpoint.
For a comprehensive analysis of the medical pattern before and after the breakpoint, the present exemplary embodiment may extract a plurality of sets of the first subsequence and the second subsequence. Wherein, the first subsequences all use the previous time node of the breakpoint as the end point, and the second subsequences all useThe node at the later time of the breakpoint is the starting point. For example, a sequence E ═ E composed of vectors of 10 time nodes of a patient1，E2，E3，…，EnWhen the breakpoint is determined to be located between the 5 th time node and the 6 th time node, the first subsequence before the breakpoint is extracted, which may be the vector "E" of the 5 th time node5", or may be a vector" E "from the 4 th time node to the 5 th time node4，E5", or a vector" E "from the 3 rd time node to the 5 th time node3，E4，E5", correspondingly, the second subsequence after the breakpoint is extracted is the vector 'E' of the 6 th and time nodes6", or may be a vector" E "from the 6 th time node to the 7 th time node6，E7", or a vector" E "from the 6 th time node to the 8 th time node6，E7，E8"etc. then" E5"and" E6"i.e., can be considered a set of subsequences," E4，E5"and" E6，E7"is a set of subsequences, and" E3，E4，E5"and" E6，E7，E8"is a set of subsequences, and so on.
By calculating each pair of first and second subsequences, a plurality of degrees of difference results can be obtained, e.g., L for the full life cycle time series of a patient and k for the length. L (x, y) (x < y) represents a sequence consisting of a vector of the x-th time node to a vector of the y-th time node. When the breakpoint is determined to be located between the vector of the mth time node and the vector of the m +1(m < k-1) th time node, the difference degree of the medical patterns on both sides of the breakpoint is marked as diversity, and then the difference degree can be calculated by the following formula:
wherein m > z and m + z < k-1, wherein V (m, m), V (m-1, m), …, V (m-z, m) all represent a first subsequence extracted from before the breakpoint, V (m +1), V (m +1, m +2), …, V (m +1, m +1+ z) all represent sets of second subsequences extracted from after the breakpoint, V (m, m) and V (m +1), V (m-1, m) and V (m +1, m +2), V (m-z, m) and V (m +1, m +1+ z) all represent a set of subsequences, and the like. It is considered that if the minimum difference degree satisfies the judgment condition for medical mode transition, the other difference degrees will tend to satisfy the judgment condition for medical mode transition. Therefore, the present exemplary embodiment can accurately identify the turning point at which the medical mode of the patient is switched by calculating the difference between the plurality of sets of sub-sequence pairs, and taking the difference with the smallest value as the difference between the medical data before the breakpoint and the medical data after the breakpoint to determine the target breakpoint at which the medical mode is switched according to the difference.
Exemplary embodiments of the present disclosure also provide a medical mode transition recognition apparatus. Referring to fig. 4, the apparatus 400 may include a data acquisition module 410 for acquiring medical data at a plurality of time nodes throughout a patient's life cycle; a breakpoint determination module 420, configured to determine one or more breakpoints in a full lifecycle, where a breakpoint is located between two adjacent time nodes; the data calculation module 430 is configured to determine a difference between the medical data before the breakpoint and the medical data after the breakpoint; and the breakpoint identification module 440 is configured to determine a target breakpoint for switching the medical mode of the patient from the breakpoints according to the difference.
In an exemplary embodiment, after acquiring the medical data, the medical mode transition recognition apparatus may further include: the vector conversion module is used for converting the medical data of each time node into vectors and arranging the vectors into a sequence according to the sequence of the time nodes; the data calculation module comprises: a sequence extraction unit, configured to extract a first subsequence from a vector in the sequence that is located before the breakpoint, and extract a second subsequence from a vector in the sequence that is located after the breakpoint; and the sequence calculating unit is used for calculating the difference degree of the first subsequence and the second subsequence.
In an exemplary embodiment, the first subsequence and the second subsequence are the same length; the sequence calculation unit may include: a scoring matrix establishing subunit, configured to establish a scoring matrix based on the first subsequence and the second subsequence, where the scoring matrix includes a difference between a vector of any time node in the first subsequence and a vector of any time node in the second subsequence; the path determining subunit is used for determining a target matching path in the scoring matrix; and the difference degree calculation unit is used for taking the average value of the difference degrees in the target matching path as the difference degree of the first subsequence and the second subsequence.
In an exemplary embodiment, when extracting the first subsequence and the second subsequence, extracting a plurality of groups of first subsequences and second subsequences respectively, wherein the length of each group of first subsequences and second subsequences is the same; the sequence calculation unit is used for calculating the difference degree of each group of the first subsequence and the second subsequence respectively, and taking the difference degree with the minimum numerical value as the difference degree of the medical data before the breakpoint and the medical data after the breakpoint.
In an exemplary embodiment, the first sub-sequences all use a previous time node of the breakpoint as an end point, and the second sub-sequences all use a later time node of the breakpoint as a start point.
In an exemplary embodiment, the data acquisition module may include: the structured processing unit is used for acquiring the original data of a plurality of time nodes in the whole life cycle of the patient and carrying out structured processing on the original data according to preset fields; and the normalization processing unit is used for performing normalization processing on the raw data after the structuralization processing to obtain the medical data of a plurality of time nodes.
In an exemplary embodiment, the breakpoint determination module can be configured to determine a breakpoint between any two adjacent time nodes.
In an exemplary embodiment, the breakpoint identification module may be configured to determine a breakpoint corresponding to the difference degree exceeding the preset threshold as a target breakpoint at which the medical mode of the patient is switched.
In an exemplary embodiment, the degree of difference may include any one or more of: euclidean distance, Mandarin distance, and the inverse of cosine similarity.
The specific details of each module/unit in the above-mentioned apparatus have been described in detail in the embodiment of the method section, and the details that are not disclosed may refer to the contents of the embodiment of the method section, and therefore are not described herein again.
Exemplary embodiments of the present disclosure also provide an electronic device capable of implementing the above method.
As will be appreciated by one skilled in the art, aspects of the present disclosure may be embodied as a system, method or program product. Accordingly, various aspects of the present disclosure may be embodied in the form of: an entirely hardware embodiment, an entirely software embodiment (including firmware, microcode, etc.) or an embodiment combining hardware and software aspects that may all generally be referred to herein as a "circuit," module "or" system.
An electronic device 500 according to such an exemplary embodiment of the present disclosure is described below with reference to fig. 5. The electronic device 500 shown in fig. 5 is only an example and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.
As shown in fig. 5, the electronic device 500 is embodied in the form of a general purpose computing device. The components of the electronic device 500 may include, but are not limited to: the at least one processing unit 510, the at least one memory unit 520, a bus 530 connecting various system components (including the memory unit 520 and the processing unit 510), and a display unit 540.
Where the storage unit stores program code, the program code may be executed by the processing unit 510 such that the processing unit 510 performs the steps according to various exemplary embodiments of the present disclosure as described in the above-mentioned "exemplary methods" section of this specification. For example, the processing unit 510 may execute steps S110 to S140 shown in fig. 1, or may execute steps S210 to S230 shown in fig. 3, or the like.
The storage unit 520 may include readable media in the form of volatile storage units, such as a random access memory unit (RAM)521 and/or a cache memory unit 522, and may further include a read only memory unit (ROM) 523.
The storage unit 520 may also include a program/utility 524 having a set (at least one) of program modules 525, such program modules 525 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may comprise an implementation of a network environment.
The electronic device 500 may also communicate with one or more external devices 700 (e.g., keyboard, pointing device, bluetooth device, etc.), with one or more devices that enable a user to interact with the electronic device 500, and/or with any devices (e.g., router, modem, etc.) that enable the electronic device 500 to communicate with one or more other computing devices. Such communication may occur via input/output (I/O) interfaces 550. Also, the electronic device 500 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, such as the internet) via the network adapter 560. As shown, the network adapter 560 communicates with the other modules of the electronic device 500 over the bus 530. It should be appreciated that although not shown in the figures, other hardware and/or software modules may be used in conjunction with the electronic device 500, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.
Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein may be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (which may be a CD-ROM, a usb disk, a removable hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which may be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the exemplary embodiments of the present disclosure.
Exemplary embodiments of the present disclosure also provide a computer-readable storage medium having stored thereon a program product capable of implementing the above-described method of the present specification. In some possible embodiments, various aspects of the disclosure may also be implemented in the form of a program product comprising program code for causing a terminal device to perform the steps according to various exemplary embodiments of the disclosure described in the above-mentioned "exemplary methods" section of this specification, when the program product is run on the terminal device.
Referring to fig. 6, a program product 600 for implementing the above method according to an exemplary embodiment of the present disclosure is described, which may employ a portable compact disc read only memory (CD-ROM) and include program code, and may be run on a terminal device, such as a personal computer. However, the program product of the present disclosure is not limited thereto, and in this document, a readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
A computer readable signal medium may include a propagated data signal with readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A readable signal medium may also be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Program code for carrying out operations for the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., through the internet using an internet service provider).
Furthermore, the above-described figures are merely schematic illustrations of processes included in methods according to exemplary embodiments of the present disclosure, and are not intended to be limiting. It will be readily understood that the processes shown in the above figures are not intended to indicate or limit the chronological order of the processes. In addition, it is also readily understood that these processes may be performed synchronously or asynchronously, e.g., in multiple modules.
It should be noted that although in the above detailed description several modules or units of the device for action execution are mentioned, such a division is not mandatory. Indeed, the features and functions of two or more modules or units described above may be embodied in one module or unit according to an exemplary embodiment of the present disclosure. Conversely, the features and functions of one module or unit described above may be further divided into embodiments by a plurality of modules or units.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is to be limited only by the terms of the appended claims.
Claims (10)
1. A medical treatment mode conversion recognition method is characterized by comprising the following steps:
acquiring medical data of a plurality of time nodes in a full life cycle of a patient;
determining one or more breakpoints in the full lifecycle, the breakpoints being located between two adjacent time nodes;
determining the difference degree between the medical data before the breakpoint and the medical data after the breakpoint;
and determining a target breakpoint for the medical mode of the patient to be converted from the breakpoints according to the difference degree.
2. The method of claim 1, wherein after acquiring the medical data, the method further comprises:
converting the medical data of each time node into vectors, and arranging the vectors into a sequence according to the sequence of the time nodes;
the determining the difference between the medical data before the breakpoint and the medical data after the breakpoint comprises:
extracting a first subsequence from vectors in the sequence that are located before the breakpoint and a second subsequence from vectors in the sequence that are located after the breakpoint;
and calculating the difference degree of the first subsequence and the second subsequence.
3. The method of claim 2, wherein the first subsequence and the second subsequence are the same length;
the calculating the difference degree of the first subsequence and the second subsequence comprises:
based on the first subsequence and the second subsequence, establishing a scoring matrix, wherein the scoring matrix comprises a difference degree between a vector of any time node in the first subsequence and a vector of any time node in the second subsequence;
determining a target matching path in the scoring matrix;
and taking the average value of the difference degrees in the target matching paths as the difference degree of the first subsequence and the second subsequence.
4. The method according to claim 2, wherein when extracting the first subsequence and the second subsequence, extracting a plurality of groups of the first subsequence and the second subsequence respectively, wherein the length of each group of the first subsequence and the second subsequence is the same;
the calculating the difference degree of the first subsequence and the second subsequence comprises:
and respectively calculating the difference degree of each group of the first subsequence and the second subsequence, and taking the difference degree with the minimum value as the difference degree of the medical data before the breakpoint and the medical data after the breakpoint.
5. The method according to any of claims 2-4, wherein the first sub-sequences each end at the time node preceding the breakpoint and the second sub-sequences each start at the time node succeeding the breakpoint.
6. The method of claim 1, wherein the obtaining medical data for a plurality of time nodes in a full life cycle of a patient comprises:
acquiring original data of a plurality of time nodes in the whole life cycle of a patient, and carrying out structured processing on the original data according to a preset field;
and carrying out normalization processing on the raw data after the structuralization processing to obtain the medical data of the multiple time nodes.
7. The method of claim 1, wherein determining one or more breakpoints in the full lifecycle comprises:
a breakpoint is determined between any two adjacent said time nodes.
8. A medical mode transition recognition apparatus, comprising:
the data acquisition module is used for acquiring medical data of a plurality of time nodes in the whole life cycle of a patient;
a breakpoint determination module configured to determine one or more breakpoints in the full lifecycle, where the breakpoints are located between two adjacent time nodes;
the data calculation module is used for determining the difference degree between the medical data before the breakpoint and the medical data after the breakpoint;
and the breakpoint identification module is used for determining a target breakpoint for switching the medical mode of the patient from the breakpoints according to the difference degree.
9. An electronic device, comprising:
a processor; and
a memory for storing executable instructions of the processor;
wherein the processor is configured to perform the method of any of claims 1-7 via execution of the executable instructions.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911135520.2A CN110851503B (en) | 2019-11-19 | 2019-11-19 | Medical mode conversion identification method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911135520.2A CN110851503B (en) | 2019-11-19 | 2019-11-19 | Medical mode conversion identification method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110851503A true CN110851503A (en) | 2020-02-28 |
| CN110851503B CN110851503B (en) | 2022-07-05 |
Family
ID=69602272
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911135520.2A Active CN110851503B (en) | 2019-11-19 | 2019-11-19 | Medical mode conversion identification method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110851503B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104750951A (en) * | 2013-11-21 | 2015-07-01 | 上海联影医疗科技有限公司 | Analytical processing method and device of medical image data |
| CN107015949A (en) * | 2016-12-31 | 2017-08-04 | 苏州市环亚数据技术有限公司 | Medical data standard handovers method |
| WO2018082261A1 (en) * | 2016-11-05 | 2018-05-11 | 深圳市前海安测信息技术有限公司 | Medical informatized medical data query and audit system and method based on electronic medical record |
| CN108320810A (en) * | 2018-04-11 | 2018-07-24 | 平安科技（深圳）有限公司 | Disease abnormal deviation data examination method and device, computer installation and storage medium |
| CN110060087A (en) * | 2019-03-07 | 2019-07-26 | 阿里巴巴集团控股有限公司 | Detection method, device and the server of abnormal data |
| CN110136794A (en) * | 2019-05-22 | 2019-08-16 | 湖北可汗广电文化有限公司 | A kind of mother and baby's Life cycle health medical treatment service system based on artificial intelligence |
| CN110442797A (en) * | 2019-08-19 | 2019-11-12 | 重庆华医康道科技有限公司 | A kind of internet hospital products configuration optimization method |
| CN110459285A (en) * | 2019-08-16 | 2019-11-15 | 济南大学 | Preprocess method, system, equipment and the medium of the medical data of disease |
-
2019
- 2019-11-19 CN CN201911135520.2A patent/CN110851503B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104750951A (en) * | 2013-11-21 | 2015-07-01 | 上海联影医疗科技有限公司 | Analytical processing method and device of medical image data |
| WO2018082261A1 (en) * | 2016-11-05 | 2018-05-11 | 深圳市前海安测信息技术有限公司 | Medical informatized medical data query and audit system and method based on electronic medical record |
| CN107015949A (en) * | 2016-12-31 | 2017-08-04 | 苏州市环亚数据技术有限公司 | Medical data standard handovers method |
| CN108320810A (en) * | 2018-04-11 | 2018-07-24 | 平安科技（深圳）有限公司 | Disease abnormal deviation data examination method and device, computer installation and storage medium |
| CN110060087A (en) * | 2019-03-07 | 2019-07-26 | 阿里巴巴集团控股有限公司 | Detection method, device and the server of abnormal data |
| CN110136794A (en) * | 2019-05-22 | 2019-08-16 | 湖北可汗广电文化有限公司 | A kind of mother and baby's Life cycle health medical treatment service system based on artificial intelligence |
| CN110459285A (en) * | 2019-08-16 | 2019-11-15 | 济南大学 | Preprocess method, system, equipment and the medium of the medical data of disease |
| CN110442797A (en) * | 2019-08-19 | 2019-11-12 | 重庆华医康道科技有限公司 | A kind of internet hospital products configuration optimization method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110851503B (en) | 2022-07-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109670054B (en) | Knowledge graph construction method and device, storage medium and electronic equipment | |
| CN110442840B (en) | Sequence labeling network updating method, electronic medical record processing method and related device | |
| CN111564223B (en) | Infectious disease survival probability prediction method, and prediction model training method and device | |
| US20170147753A1 (en) | Method for searching for similar case of multi-dimensional health data and apparatus for the same | |
| CN108231146B (en) | Deep learning-based medical record model construction method, system and device | |
| CN112541066B (en) | Text-structured-based medical and technical report detection method and related equipment | |
| US20190237200A1 (en) | Recording medium recording similar case retrieval program, information processing apparatus, and similar case retrieval method | |
| CN111259664B (en) | Method, device and equipment for determining medical text information and storage medium | |
| WO2021151302A1 (en) | Drug quality-control analysis method, apparatus, device, and medium based on machine learning | |
| CN116580849A (en) | Medical data acquisition and analysis system and method thereof | |
| CN110471941B (en) | Method and device for automatically positioning judgment basis and electronic equipment | |
| Gao et al. | Using case-level context to classify cancer pathology reports | |
| Shrestha et al. | Supervised machine learning for early predicting the sepsis patient: modified mean imputation and modified chi-square feature selection | |
| Yin et al. | Adaptive feature selection with shapley and hypothetical testing: Case study of EEG feature engineering | |
| CN111243753A (en) | Medical data-oriented multi-factor correlation interactive analysis method | |
| US20130138592A1 (en) | Data processing | |
| CN111177356B (en) | Acid-base index medical big data analysis method and system | |
| CN110851503B (en) | Medical mode conversion identification method and device, electronic equipment and storage medium | |
| Xie et al. | Continuous-valued annotations aggregation for heart rate detection | |
| Yuan et al. | Numerical Feature Transformation-Based Sequence Generation Model for Multi-Disease Diagnosis | |
| CN111640517B (en) | Medical record coding method and device, storage medium and electronic equipment | |
| Shruthi et al. | A Method for Predicting and Classifying Fetus Health Using Machine Learning | |
| Ghias et al. | Using Machine Learning Algorithms to predict sepsis and its stages in ICU patients | |
| Zhang et al. | Clinical utility of the automatic phenotype annotation in unstructured clinical notes: ICU use cases | |
| Seely | Prediction is difficult, especially about future unexpected deterioration |
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 |