CN116383344A - Data processing method and system for medical clinical study based on middle stage technology - Google Patents

Data processing method and system for medical clinical study based on middle stage technology Download PDF

Info

Publication number
CN116383344A
CN116383344A CN202310593395.XA CN202310593395A CN116383344A CN 116383344 A CN116383344 A CN 116383344A CN 202310593395 A CN202310593395 A CN 202310593395A CN 116383344 A CN116383344 A CN 116383344A
Authority
CN
China
Prior art keywords
data
medical clinical
medical
value
sequence
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
Application number
CN202310593395.XA
Other languages
Chinese (zh)
Other versions
CN116383344B (en
Inventor
曹莉琼
谭鑫
陈建长
温伟军
李明书
胡曾山
付佳龙
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangdong Zhujiang Chilink Information Technology Co ltd
Original Assignee
Guangdong Zhujiang Chilink Information Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Guangdong Zhujiang Chilink Information Technology Co ltd filed Critical Guangdong Zhujiang Chilink Information Technology Co ltd
Priority to CN202310593395.XA priority Critical patent/CN116383344B/en
Publication of CN116383344A publication Critical patent/CN116383344A/en
Application granted granted Critical
Publication of CN116383344B publication Critical patent/CN116383344B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33—Querying
    • G06F16/3331—Query processing
    • G06F16/334—Query execution
    • G06F16/3344—Query execution using natural language analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/31—Indexing; Data structures therefor; Storage structures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/30—Semantic analysis
    • 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
    • G16H70/00—ICT specially adapted for the handling or processing of medical references
    • 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)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • Computational Linguistics (AREA)
  • Databases & Information Systems (AREA)
  • Artificial Intelligence (AREA)
  • Software Systems (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Epidemiology (AREA)
  • Medical Informatics (AREA)
  • Primary Health Care (AREA)
  • Public Health (AREA)
  • Medical Treatment And Welfare Office Work (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention relates to the technical field of data processing consoles, in particular to a data processing method and a system for medical clinical research based on a console technology, wherein the method comprises the following steps: medical clinical data in hospitals or big data are collected, standardized processing is carried out on the medical clinical data, the screened medical clinical data are stored into a database, the medical clinical data in the database are extracted, further data processing is carried out on the medical clinical data, a nerve convolution model is input for training, the medical clinical data are processed through the trained nerve convolution model, the medical clinical data are stored in a distributed mode, the medical clinical data corresponding to keywords are stored in a distributed mode through weights, the medical clinical data can be guaranteed to be acquired rapidly and accurately, the data are cleaned to remove redundant data, and the data size is greatly reduced.

Description

Data processing method and system for medical clinical study based on middle stage technology
Technical Field
The invention relates to the technical field of data processing consoles, in particular to a data processing method and system for medical clinical research based on a console technology.
Background
In a medical clinical experiment, a large amount of data is required, the data is continuously changed according to the deep of the experiment, and meanwhile, the data is generated due to error of the experiment, so that the experiment data in a medical clinical experiment is huge, the recorded amount is huge, a large amount of storage space is occupied, the data is redundant, the transmission speed is slow, the viewing is difficult, the data format is various, and in practical processing application, the problems of high efficiency such as secondary processing and conversion of large-scale data are required to be considered, so that a data processing method and a system for medical clinical research based on a middle-stage technology are needed to solve the problems.
Disclosure of Invention
In view of the limitations of the prior art methods described above, it is an object of the present invention to provide a smart data center technology and an application system for medical clinical research, which solve one or more technical problems existing in the prior art, and at least provide a beneficial choice or creation condition.
An intelligent data center technology oriented to medical clinical research, which is characterized by comprising the following steps:
s100: acquiring medical clinical data in medical clinical experiments and big data;
s200: carrying out standardized processing on the medical clinical data, and storing the screened medical clinical data into a database;
s300: extracting medical clinical data in a database, performing further data processing on the medical clinical data, and inputting a nerve convolution model for training;
s400: and carrying out data processing on the medical clinical data through the trained nerve convolution model, and carrying out distributed storage on the medical clinical data.
Further, in step S100, the big data acquiring medical clinical data is acquiring medical clinical data obtained in a clinical experiment through a medical college or a hospital database, and the method for acquiring medical clinical data in the medical clinical experiment is acquiring medical clinical data through a sensor and medical equipment, where the sensor includes: vision sensor, temperature sensor, pressure sensor, PH reagent, acquire medical clinical data through one or more sensors, medical device includes: an X-ray diagnostic apparatus, an ultrasonic diagnostic apparatus, a functional examination apparatus, an endoscopy apparatus, a nuclear medicine apparatus, an experimental diagnostic apparatus, and a pathological diagnosis apparatus, medical clinical data is acquired through one or more medical apparatuses.
Further, in step S200, the acquired medical clinical data is subjected to normalization processing, and the acquired medical clinical data acquired in the medical device is recorded with the time of acquisition as a time stamp, and the blank part in the medical clinical data record is screened and deleted by the time stamp, and redundant data and repeated data are deleted, and the medical clinical data left by the screening is stored in the database.
Further, in step S300, the acquired medical clinical data in the database is processed, the data after the normalization processing is further processed by the middle station, the data after the data processing is input into the neural convolution network for training, and the trained neural convolution model is transmitted back to the middle station of the system for perfecting, and the further data processing method comprises the following steps:
s301: distributing the data subjected to the standardization treatment according to the medical clinical experiment time and the medical clinical experiment time of the medical clinical experiment, wherein the medical clinical experiment time is calculated according to the day, the medical clinical experiment time is from the experiment starting time to the experiment ending time in the experiment plan to be one medical clinical experiment time, one medical clinical experiment time is taken as a root node, the medical clinical experiment time in one medical clinical experiment time is taken as a child node of the root node, the medical clinical data is stored into the corresponding node, the root node is defined as frist, and the child node is defined as srist;
s302: acquiring a plurality of keywords of medical clinical data according to semantic analysis and access records, acquiring retrieval quantity of the keywords in the medical clinical data in the root node frist, constructing a retrieval quantity sequence Re according to the sequence of the retrieval quantity from large to small, and calculating the weight coefficient of the retrieval quantity
Figure SMS_1
，/>
Figure SMS_2
Said->
Figure SMS_3
And->
Figure SMS_4
For retrieving the k-th and k+1-th elements of the sequence Re, the sequence is selected according to +.>
Figure SMS_5
Assigning the keywords to obtain the weight value E,/-of the search quantity to the keywords>
Figure SMS_6
D is the total element amount of the search amount sequence Re, d-1 is the weight coefficient +.>
Figure SMS_7
Is a total amount of (2);
( The method for acquiring the weight value E of the retrieval quantity on the keyword has the beneficial effects that: the weight value E obtained through calculation represents the retrieval quantity through the keywords, and the weight value corresponding to the keywords is determined, so that clinical experimenters do not need to call the same experimental data too much to cause the problem of network blocking, and the progress of the clinical experiments of medicine is ensured. )
S303: integrating medical clinical experiment data corresponding to the keywords into a data stream, defining the data stream as data, and arranging the data stream through time sequence to construct a data stream sequence Lidtc, lidtc= [
Figure SMS_8
]Storing the data streams into corresponding nodes, wherein n is the total number of the data streams output at the current moment, and the data streams are +.>
Figure SMS_9
The flow velocity Ve of the data stream in the data stream sequence lidatc is obtained and the flow velocity sequence Vidtc, vidtc= = -is constructed>
Figure SMS_10
The critical value S of the flow rate sequence Vidtc is obtained through calculation,
Figure SMS_11
，
Figure SMS_12
for the value of the element in position i in the flow sequence Vidtc, < >>
Figure SMS_13
For the maximum value in the flow rate sequence Vidtc,
Figure SMS_14
for the minimum value in the flow rate sequence, exp () is an exponential function, and the threshold value S is set as the lowest flow rate value when searching the keyword, if +.>
Figure SMS_15
If the flow speed value is equal to or greater than S, the flow speed value is normal, and the value of the flow speed value is assigned to be 1, if +.>
Figure SMS_16
< S, the flow rate value is slow, and the flow rate value is assigned 0The method comprises the steps of obtaining a corresponding keyword in a stored data stream sequence Lidtc, storing the corresponding keyword in a child node srist, obtaining the keyword in the data stream sequence Lidtc from the child node srist, and binding the keyword with the data stream sequence Lidtc;
s304: the flow rate of the flow rate sequence Vidtc
Figure SMS_17
Assigning a matrix M to the flow values, said matrix m= [ -or ]>
Figure SMS_18
]Said->
Figure SMS_19
The element values are expressed as the ith row and the jth column in a matrix M, the rows of the matrix M represent the flow velocity Ve of the data flow, the columns represent the judging flow velocity transmission values in the matrix M, the matrix M is input into a convolutional neural network model, the model is subjected to deep learning, the matrix M is finally output, the weight value D of the transmission influence of the flow velocity in keyword retrieval is obtained through calculation,
Figure SMS_20
，
( The beneficial effect of obtaining the weight value D of the flow velocity on the keyword retrieval medical clinical data is as follows: the flow velocity of the corresponding data stream of the corresponding medical clinical data is searched through the keywords, the weight value is obtained through calculation, the medical clinical data can be stored in a distributed mode according to the corresponding weight value, the searching time can be greatly saved, and the medical clinical data in the child nodes can be stored in a distributed mode through the weight value. )
Figure SMS_21
For the element values of the ith row and jth column of the matrix M, p is the total number of the matrix M, ln () is a logarithmic function, and finally the weight E and the weight D are calculated to obtain a comprehensive weight value,/-, and the weight E is the sum of the weight E and the weight D>
Figure SMS_22
，
The variance calculation is carried out on the weight value E and the weight value D to obtain a comprehensive weight value with corresponding proportion
Figure SMS_23
Min () is a minimum function, +.>
Figure SMS_24
For its comprehensive weight function, when ∈>
Figure SMS_25
When the minimum value is reached, the error of the weight value is minimized, and +.>
Figure SMS_26
Namely, the weight value of the medical clinical data is searched for the key word, and the weight value is +.>
Figure SMS_27
Constructing an integrated weight matrix Z to obtain an integrated weight matrix Z=>
Figure SMS_28
And finally, transmitting a result W of data influence on the keyword retrieval through the comprehensive weight matrix Z and the matrix M:
Figure SMS_29
。
further, in step S400, the weight of the medical clinical data is obtained by retrieving the keyword through the numerical value calculated by W, the medical clinical data is stored in a distributed manner through the keyword retrieval weight and the flow rate weight, the medical clinical data with higher stored weight value is stored into the corresponding sub-node with faster flow rate, and the medical clinical data with lower weight value is stored into the corresponding sub-node with slower flow rate.
A data system for medical clinical studies based on a mid-table technique, the system comprising: medical device, sensor, processor and memory, the data that medical device, sensor and processor obtained can be stored in memory, the medical device, sensor and memory can run computer program on the processor, the processor when executing the computer program realizes the steps in a data processing method based on medical clinical research of the middle stage technology of any one of the above methods.
The functions of each unit in the data system of the medical clinical study based on the middle stage technology are as follows:
medical equipment: comprises an X-ray diagnosis device, an ultrasonic diagnosis device, a functional examination device, an endoscopy device, a nuclear medicine device, an experimental diagnosis device, a pathological diagnosis device and the like, and is mainly used for acquiring various body data of an acting object in medical clinic;
a sensor: the system comprises a visual sensor, a temperature sensor, a pressure sensor, a PH reagent and the like, and mainly acquires some environmental factor influence data and some external influence data in medical clinic;
a processor: acquiring medical clinical data and performing data processing on the medical clinical data;
a memory: data acquired by the medical device, the sensor, and the processor is stored.
The beneficial effects of the invention are as follows: through carrying out corresponding storage to medical clinical data according to the keyword, carrying out distributed storage to the medical clinical data that the keyword corresponds through the weight, guarantee that medical clinical data can acquire fast and accurately to wash the data and get rid of unnecessary data, the data volume significantly reduces, orderly arrangement obtains the data volume, and the data and the work load of arrangement in the acquisition medical clinical research have significantly reduced, also because acquire data and real-time processing in real time, the medical clinical research of acquisition has more authenticity.
Drawings
The above and other features of the present invention will become more apparent from the detailed description of the embodiments thereof given in conjunction with the accompanying drawings, in which like reference characters designate like or similar elements, and it is apparent that the drawings in the following description are merely some examples of the present invention, and other drawings may be obtained from these drawings without inventive effort to those of ordinary skill in the art, in which:
fig. 1 is a flow chart of a method of data processing for medical clinical studies based on a middle stage technique.
Detailed Description
The conception, specific structure, and technical effects produced by the present invention will be clearly and completely described below with reference to the embodiments and the drawings to fully understand the objects, aspects, and effects of the present invention. It should be noted that, in the case of no conflict, the embodiments and features in the embodiments may be combined with each other.
A smart data center technology for medical clinical research according to an embodiment of the present invention is described below with reference to fig. 1, the method comprising the steps of:
an intelligent data center technology oriented to medical clinical research, which is characterized by comprising the following steps:
s100: acquiring medical clinical data in medical clinical experiments and big data;
s200: carrying out standardized processing on the medical clinical data, and storing the screened medical clinical data into a database;
s300: extracting medical clinical data in a database, performing further data processing on the medical clinical data, and inputting a nerve convolution model for training;
s400: and carrying out data processing on the medical clinical data through the trained nerve convolution model, and carrying out distributed storage on the medical clinical data.
Further, in step S100, the big data acquiring medical clinical data is acquiring medical clinical data obtained in a clinical experiment through a medical college or a hospital database, and the method for acquiring medical clinical data in the medical clinical experiment is acquiring medical clinical data through a sensor and medical equipment, where the sensor includes: vision sensor, temperature sensor, pressure sensor, PH reagent, acquire medical clinical data through one or more sensors, medical device includes: an X-ray diagnostic apparatus, an ultrasonic diagnostic apparatus, a functional examination apparatus, an endoscopy apparatus, a nuclear medicine apparatus, an experimental diagnostic apparatus, and a pathological diagnosis apparatus, medical clinical data is acquired through one or more medical apparatuses.
Further, in step S200, the acquired medical clinical data is subjected to normalization processing, and the acquired medical clinical data acquired in the medical device is recorded with the time of acquisition as a time stamp, and the blank part in the medical clinical data record is screened and deleted by the time stamp, and redundant data and repeated data are deleted, and the medical clinical data left by the screening is stored in the database.
Further, in step S300, medical clinical data in the acquired database is processed, the data after normalization processing is further processed by the middle station, the data after data processing is input into the neural convolution network for training, and the trained neural convolution model is transmitted back to the middle station of the system for perfecting;
the system center is a system which can search technical information through various ways to meet the information searching requirement of a user and timely feed back and respond to the data requirement of the user;
the further data processing method comprises the following steps:
s301: distributing the data subjected to the standardization treatment according to the medical clinical experiment time and the medical clinical experiment time of the medical clinical experiment, wherein the medical clinical experiment time is calculated according to the day, the medical clinical experiment time is from the experiment starting time to the experiment ending time in the experiment plan to be one medical clinical experiment time, one medical clinical experiment time is taken as a root node, the medical clinical experiment time in one medical clinical experiment time is taken as a child node of the root node, the medical clinical data is stored into the corresponding node, the root node is defined as frist, and the child node is defined as srist;
s302: acquiring medical from semantic analysis in combination with access recordsSeveral keywords of clinical data, obtaining the retrieval quantity of keywords in the medical clinical data in the root node frist, constructing a retrieval quantity sequence Re according to the order of the retrieval quantity from large to small, and calculating the weight coefficient of the retrieval quantity
Figure SMS_30
，/>
Figure SMS_31
Said->
Figure SMS_32
And->
Figure SMS_33
For retrieving the k-th and k+1-th elements of the sequence Re, the sequence is selected according to +.>
Figure SMS_34
Assigning the keywords to obtain the weight value E,/-of the search quantity to the keywords>
Figure SMS_35
D is the total element amount of the search amount sequence Re, d-1 is the weight coefficient +.>
Figure SMS_36
Is a total amount of (2);
( The method for acquiring the weight value E of the retrieval quantity on the keyword has the beneficial effects that: the weight value E obtained through calculation represents the retrieval quantity through the keywords, and the weight value corresponding to the keywords is determined, so that clinical experimenters do not need to call the same experimental data too much to cause the problem of network blocking, and the progress of the clinical experiments of medicine is ensured. )
S303: integrating medical clinical experiment data corresponding to the keywords into a data stream, defining the data stream as data, and arranging the data stream through time sequence to construct a data stream sequence Lidtc, lidtc= [
Figure SMS_37
]Storing the data streams into corresponding nodes, wherein n is the total number of the data streams output at the current moment, and the data streams are stored in the corresponding nodesData stream->
Figure SMS_38
The flow velocity Ve of the data stream in the data stream sequence lidatc is obtained and the flow velocity sequence Vidtc, vidtc= = -is constructed>
Figure SMS_39
The critical value S of the flow rate sequence Vidtc is obtained through calculation,
Figure SMS_40
，
Figure SMS_41
for the value of the element in position i in the flow sequence Vidtc, < >>
Figure SMS_42
For the maximum value in the flow rate sequence Vidtc,
Figure SMS_43
for the minimum value in the flow rate sequence, exp () is an exponential function, and the threshold value S is set as the lowest flow rate value when searching the keyword, if +.>
Figure SMS_44
If the flow speed value is equal to or greater than S, the flow speed value is normal, and the value of the flow speed value is assigned to be 1, if +.>
Figure SMS_45
If the flow velocity value is less than S, the flow velocity value is slow, the flow velocity value is assigned to 0, the corresponding keywords in the stored data stream sequence Lidtc are acquired and are correspondingly stored in the child node srist, the keywords in the data stream sequence Lidtc are acquired from the child node srist, and the keywords are bound with the data stream sequence Lidtc;
s304: the flow rate of the flow rate sequence Vidtc
Figure SMS_46
Assigning a matrix M to the flow values, said matrix m= [ -or ]>
Figure SMS_47
]Said->
Figure SMS_48
The element values are expressed as the ith row and the jth column in a matrix M, the rows of the matrix M represent the flow velocity Ve of the data flow, the columns represent the judging flow velocity transmission values in the matrix M, the matrix M is input into a convolutional neural network model, the model is subjected to deep learning, the matrix M is finally output, the weight value D of the transmission influence of the flow velocity in keyword retrieval is obtained through calculation,
Figure SMS_49
，
( The beneficial effect of obtaining the weight value D of the flow velocity on the keyword retrieval medical clinical data is as follows: the flow velocity of the corresponding data stream of the corresponding medical clinical data is searched through the keywords, the weight value is obtained through calculation, the medical clinical data can be stored in a distributed mode according to the corresponding weight value, the searching time can be greatly saved, and the medical clinical data in the child nodes can be stored in a distributed mode through the weight value. )
Figure SMS_50
For the element values of the ith row and jth column of the matrix M, p is the total number of the matrix M, ln () is a logarithmic function, and finally the weight E and the weight D are calculated to obtain a comprehensive weight value,/-, and the weight E is the sum of the weight E and the weight D>
Figure SMS_51
，
The variance calculation is carried out on the weight value E and the weight value D to obtain a comprehensive weight value with corresponding proportion
Figure SMS_52
Min () is a minimum function, +.>
Figure SMS_53
For its comprehensive weight function, when ∈>
Figure SMS_54
When the minimum value is reached, the error of the weight value is minimized, and +.>
Figure SMS_55
Namely, the weight value of the medical clinical data is searched for the key word, and the weight value is +.>
Figure SMS_56
Constructing an integrated weight matrix Z to obtain an integrated weight matrix Z=>
Figure SMS_57
And finally, transmitting a result W of data influence on the keyword retrieval through the comprehensive weight matrix Z and the matrix M:
Figure SMS_58
。
further, in step S400, the weight of the medical clinical data is obtained by retrieving the keyword through the numerical value calculated by W, the medical clinical data is stored in a distributed manner through the keyword retrieval weight and the flow rate weight, the medical clinical data with higher stored weight value is stored into the corresponding sub-node with faster flow rate, and the medical clinical data with lower weight value is stored into the corresponding sub-node with slower flow rate.
A data system for medical clinical studies based on a mid-table technique, the system comprising: medical device, sensor, processor and memory, the data that medical device, sensor and processor obtained can be stored in memory, the medical device, sensor and memory can run computer program on the processor, the processor when executing the computer program realizes the steps in a data processing method based on medical clinical research of the middle stage technology of any one of the above methods.
The functions of each unit in the data system of the medical clinical study based on the middle stage technology are as follows:
medical equipment: comprises an X-ray diagnosis device, an ultrasonic diagnosis device, a functional examination device, an endoscopy device, a nuclear medicine device, an experimental diagnosis device, a pathological diagnosis device and the like, and is mainly used for acquiring various body data of an acting object in medical clinic;
a sensor: the system comprises a visual sensor, a temperature sensor, a pressure sensor, a PH reagent and the like, and mainly acquires some environmental factor influence data and some external influence data in medical clinic;
a processor: acquiring medical clinical data and performing data processing on the medical clinical data;
a memory: data acquired by the medical device, the sensor, and the processor is stored.
Through carrying out corresponding storage to medical clinical data according to the keyword, carrying out distributed storage to the medical clinical data that the keyword corresponds through the weight, guarantee that medical clinical data can acquire fast and accurately to wash the data and get rid of unnecessary data, the data volume significantly reduces, orderly arrangement obtains the data volume, and the data and the work load of arrangement in the acquisition medical clinical research have significantly reduced, also because acquire data and real-time processing in real time, the medical clinical research of acquisition has more authenticity.
Although the present invention has been described in considerable detail and with particularity with respect to several described embodiments, it is not intended to be limited to any such detail or embodiment or any particular embodiment so as to effectively cover the intended scope of the invention. Furthermore, the foregoing description of the invention has been presented in its embodiments contemplated by the inventors for the purpose of providing a useful description, and for the purposes of providing a non-essential modification of the invention that may not be presently contemplated, may represent an equivalent modification of the invention.

Claims (6)

1. A method of data processing for medical clinical studies based on a mesotechnology, the method comprising the steps of:
s100: acquiring medical clinical data in medical clinical experiments and big data;
s200: carrying out standardized processing on the medical clinical data, and storing the screened medical clinical data into a database;
s300: extracting medical clinical data in a database, performing further data processing on the medical clinical data, and inputting a nerve convolution model for training;
s400: and carrying out data processing on the medical clinical data through the trained nerve convolution model, and carrying out distributed storage on the medical clinical data.
2. The data processing method of a medical clinical study based on the middle stage technology according to claim 1, wherein in step S100, the big data obtaining medical clinical data is obtaining medical clinical data obtained in a clinical experiment through a medical college or a hospital database, the method of obtaining medical clinical data in a medical clinical experiment is obtaining through a sensor and a medical device, and the sensor includes: vision sensor, temperature sensor, pressure sensor, PH reagent, acquire medical clinical data through one or more sensors, medical device includes: an X-ray diagnostic apparatus, an ultrasonic diagnostic apparatus, a functional examination apparatus, an endoscopy apparatus, a nuclear medicine apparatus, an experimental diagnostic apparatus, and a pathological diagnosis apparatus, medical clinical data is acquired through one or more medical apparatuses.
3. The data processing method of a medical clinical study based on the middle stage technology according to claim 1, wherein in step S200, the acquired medical clinical data is standardized, and the time of acquisition of the acquired medical clinical data record in the medical device is recorded as a time stamp, and the empty part in the medical clinical data record is screened and deleted by the time stamp, and redundant data and repeated data are deleted, and the medical clinical data remaining from the screening is stored in the database.
4. The method for processing data of medical clinical study based on the middle stage technology according to claim 1, wherein in step S300, medical clinical data in the acquired database is processed, the data after normalization is further processed by the middle stage, the data after the data processing is input into the neural convolutional network for training, and the trained neural convolutional model is transmitted back to the middle stage of the system for perfecting, the further data processing method comprises:
s301: distributing the data subjected to the standardization treatment according to the medical clinical experiment time and the medical clinical experiment time of the medical clinical experiment, wherein the medical clinical experiment time is calculated according to the day, the medical clinical experiment time is from the experiment starting time to the experiment ending time in the experiment plan to be one medical clinical experiment time, one medical clinical experiment time is taken as a root node, the medical clinical experiment time in one medical clinical experiment time is taken as a child node of the root node, the medical clinical data is stored into the corresponding node, the root node is defined as frist, and the child node is defined as srist;
s302: acquiring a plurality of keywords of medical clinical data according to semantic analysis and access records, acquiring retrieval quantity of the keywords in the medical clinical data in the root node frist, constructing a retrieval quantity sequence Re according to the sequence of the retrieval quantity from large to small, and calculating the weight coefficient of the retrieval quantity
Figure QLYQS_1
，/>
Figure QLYQS_2
Said->
Figure QLYQS_3
And->
Figure QLYQS_4
For retrieving the k-th and k+1-th elements of the sequence Re, the sequence is selected according to +.>
Figure QLYQS_5
The keyword is assigned with a value and,obtaining the weight value E of the search quantity on the keywords, < ->
Figure QLYQS_6
D is the total element amount of the search amount sequence Re, d-1 is the weight coefficient +.>
Figure QLYQS_7
Is a total amount of (2);
s303: integrating medical clinical experiment data corresponding to the keywords into a data stream, defining the data stream as data, and arranging the data stream through time sequence to construct a data stream sequence Lidtc, lidtc= [
Figure QLYQS_8
]Storing the data streams into corresponding nodes, wherein n is the total number of the data streams output at the current moment, and the data streams are +.>
Figure QLYQS_9
The flow velocity Ve of the data stream in the data stream sequence lidatc is obtained and the flow velocity sequence Vidtc, vidtc= = -is constructed>
Figure QLYQS_10
The critical value S of the flow rate sequence Vidtc is obtained through calculation,
Figure QLYQS_11
，
Figure QLYQS_12
for the value of the element in position i in the flow sequence Vidtc, < >>
Figure QLYQS_13
For the maximum value in the flow rate sequence Vidtc,
Figure QLYQS_14
for the minimum value in the flow rate sequence, exp () refers toA digital function, setting a threshold S as the lowest flow speed value during keyword search, if +.>
Figure QLYQS_15
If the flow speed value is equal to or greater than S, the flow speed value is normal, and the value of the flow speed value is assigned to be 1, if +.>
Figure QLYQS_16
If the flow velocity value is less than S, the flow velocity value is slow, the flow velocity value is assigned to 0, the corresponding keywords in the stored data stream sequence Lidtc are acquired and are correspondingly stored in the child node srist, the keywords in the data stream sequence Lidtc are acquired from the child node srist, and the keywords are bound with the data stream sequence Lidtc;
s304: the flow rate of the flow rate sequence Vidtc
Figure QLYQS_17
Assigning a matrix M to the flow values, said matrix m= [ -or ]>
Figure QLYQS_18
]Said->
Figure QLYQS_19
The element values are expressed as the ith row and the jth column in a matrix M, the rows of the matrix M represent the flow velocity Ve of the data flow, the columns represent the judging flow velocity transmission values in the matrix M, the matrix M is input into a convolutional neural network model, the model is subjected to deep learning, the matrix M is finally output, the weight value D of the transmission influence of the flow velocity in keyword retrieval is obtained through calculation,
Figure QLYQS_20
，
Figure QLYQS_21
for the element values of the ith row and jth column of the matrix M, p is the total number of the matrix M, ln () is a logarithmic function, and finally the weight value E and the weight are used for the matrix MThe value D is calculated to obtain a comprehensive weight value, < + >>
Figure QLYQS_22
，
The variance calculation is carried out on the weight value E and the weight value D to obtain a comprehensive weight value with corresponding proportion
Figure QLYQS_23
Min () is a minimum function, +.>
Figure QLYQS_24
For its comprehensive weight function, when ∈>
Figure QLYQS_25
When the minimum value is reached, the error of the weight value is minimized, and +.>
Figure QLYQS_26
Namely, the weight value of the medical clinical data is searched for the key word, and the weight value is +.>
Figure QLYQS_27
Constructing an integrated weight matrix Z to obtain an integrated weight matrix Z=>
Figure QLYQS_28
And finally, transmitting a result W of data influence on the keyword retrieval through the comprehensive weight matrix Z and the matrix M:
Figure QLYQS_29
。
5. the data processing method of medical clinical study based on the middle stage technology according to claim 4, wherein in step S400, the weight of the medical clinical data is obtained by retrieving a keyword through the numerical value obtained by calculating W, the medical clinical data is stored in a distributed manner through the keyword retrieval weight and the flow rate weight, the medical clinical data with higher storage weight value is stored into the corresponding sub-node with higher flow rate, and the medical clinical data with lower weight value is stored into the corresponding sub-node with lower flow rate.
6. A data system for medical clinical studies based on a mid-table technique, the system comprising: medical device, sensor, processor and memory, the data acquired by the medical device, sensor and processor being storable in memory, the medical device, sensor and memory being operable on the processor, the processor executing the computer program implementing the steps in a data processing method of any one of claims 1-5 based on a medical clinical study of a middle stage technique.
CN202310593395.XA 2023-05-25 2023-05-25 Data processing method and system for medical clinical study based on middle stage technology Active CN116383344B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310593395.XA CN116383344B (en) 2023-05-25 2023-05-25 Data processing method and system for medical clinical study based on middle stage technology

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310593395.XA CN116383344B (en) 2023-05-25 2023-05-25 Data processing method and system for medical clinical study based on middle stage technology

Publications (2)

Publication Number Publication Date
CN116383344A true CN116383344A (en) 2023-07-04
CN116383344B CN116383344B (en) 2023-08-04

Family

ID=86965944

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310593395.XA Active CN116383344B (en) 2023-05-25 2023-05-25 Data processing method and system for medical clinical study based on middle stage technology

Country Status (1)

Country Link
CN (1) CN116383344B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116682519A (en) * 2023-08-03 2023-09-01 广东杰纳医药科技有限公司 Clinical experiment data unit analysis method

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107220506A (en) * 2017-06-05 2017-09-29 东华大学 Breast cancer risk assessment analysis system based on deep convolutional neural network
US20210225463A1 (en) * 2020-01-22 2021-07-22 doc.ai, Inc. System and Method with Federated Learning Model for Medical Research Applications
CN114464328A (en) * 2022-02-11 2022-05-10 阿里巴巴（中国）有限公司 Test information retrieval method and device, clinical test recommendation method and terminal

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107220506A (en) * 2017-06-05 2017-09-29 东华大学 Breast cancer risk assessment analysis system based on deep convolutional neural network
US20210225463A1 (en) * 2020-01-22 2021-07-22 doc.ai, Inc. System and Method with Federated Learning Model for Medical Research Applications
CN114464328A (en) * 2022-02-11 2022-05-10 阿里巴巴（中国）有限公司 Test information retrieval method and device, clinical test recommendation method and terminal

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
俞益洲;马杰超;石德君;周振;: "深度学习在医学影像分析中的应用综述", 数据与计算发展前沿, no. 06, pages 41 - 56 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116682519A (en) * 2023-08-03 2023-09-01 广东杰纳医药科技有限公司 Clinical experiment data unit analysis method
CN116682519B (en) * 2023-08-03 2024-03-19 广东杰纳医药科技有限公司 Clinical experiment data unit analysis method

Also Published As

Publication number Publication date
CN116383344B (en) 2023-08-04

Similar Documents

Publication Publication Date Title
CN112183747B (en) Neural network training method, neural network compression method and related equipment
CN109993227B (en) Method, system, apparatus and medium for automatically adding international disease classification code
CN116383344B (en) Data processing method and system for medical clinical study based on middle stage technology
CN117235630B (en) Intelligent disease area visual management system and method thereof
CN115937644B (en) Point cloud feature extraction method and device based on global and local fusion
CN108962394A (en) A kind of medical data decision support method and system
Buldakova et al. Multi-agent architecture for medical diagnostic systems
CN115658886A (en) Intelligent liver cancer staging method, system and medium based on semantic text
CN115424691A (en) Case matching method, system, device and medium
CN110083842B (en) Translation quality detection method, device, machine translation system and storage medium
CN117612693B (en) Patient real-time monitoring and early warning method, device, computer and storage medium
CN117542467A (en) Automatic construction method of disease-specific standard database based on patient data
Portela et al. Real-time Intelligent decision support in intensive medicine
CN115346084B (en) Sample processing method, device, electronic equipment, storage medium and program product
CN111696674A (en) Deep learning method and system for electronic medical record
Apeldoorn et al. Automated creation of expert systems with the intekrator toolbox
CN115862844A (en) M-N + model-based chronic pain feature recognition system
Rakhmetulayeva et al. Building Disease Prediction Model Using Machine Learning Algorithms on Electronic Health Records' Logs.
CN113822439A (en) Task prediction method, device, equipment and storage medium
CN111415750B (en) Rule-based user information structuring and quick retrieval method and system
CN114496231A (en) Constitution identification method, apparatus, equipment and storage medium based on knowledge graph
CN116802646A (en) Data processing method and device
CN114974554A (en) Method, device and storage medium for fusing atlas knowledge to strengthen medical record features
Permanasari et al. A web-based decision support system of patient time prediction using iterative dichotomiser 3 algorithm
CN111062477B (en) Data processing method, device and storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant