CN114628043A - Privacy-protecting medicine clinical application frequency spectrum statistical method and device - Google Patents

Privacy-protecting medicine clinical application frequency spectrum statistical method and device Download PDF

Info

Publication number
CN114628043A
CN114628043A CN202210531839.2A CN202210531839A CN114628043A CN 114628043 A CN114628043 A CN 114628043A CN 202210531839 A CN202210531839 A CN 202210531839A CN 114628043 A CN114628043 A CN 114628043A
Authority
CN
China
Prior art keywords
sample
grouping
statistical
count value
party
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202210531839.2A
Other languages
Chinese (zh)
Inventor
陆林
何德峰
窦书明
张晓娟
余文峰
黄飞
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.)
CLP Cloud Digital Intelligence Technology Co Ltd
Original Assignee
CLP Cloud Digital Intelligence 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 CLP Cloud Digital Intelligence Technology Co Ltd filed Critical CLP Cloud Digital Intelligence Technology Co Ltd
Priority to CN202210531839.2A priority Critical patent/CN114628043A/en
Publication of CN114628043A publication Critical patent/CN114628043A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H70/00—ICT specially adapted for the handling or processing of medical references
    • G16H70/40—ICT specially adapted for the handling or processing of medical references relating to drugs, e.g. their side effects or intended usage
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
    • G06F21/60—Protecting data
    • G06F21/62—Protecting access to data via a platform, e.g. using keys or access control rules
    • G06F21/6218—Protecting access to data via a platform, e.g. using keys or access control rules to a system of files or objects, e.g. local or distributed file system or database
    • G06F21/6245—Protecting personal data, e.g. for financial or medical purposes
    • 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
    • G16H10/20—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for electronic clinical trials or questionnaires
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Epidemiology (AREA)
  • Primary Health Care (AREA)
  • Public Health (AREA)
  • Theoretical Computer Science (AREA)
  • Bioethics (AREA)
  • Pharmacology & Pharmacy (AREA)
  • Medicinal Chemistry (AREA)
  • Toxicology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Databases & Information Systems (AREA)
  • Computer Hardware Design (AREA)
  • Computer Security & Cryptography (AREA)
  • Software Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Chemical & Material Sciences (AREA)
  • Investigating Or Analysing Biological Materials (AREA)

Abstract

The invention provides a medicine clinical application frequency spectrum statistical method for protecting privacy, which comprises the following steps: the inquiring party obtains the target medicine components and the grouping items and issues local statistical tasks to the sample party; the sample side receives and executes the local statistical task issued by the inquiring side, and returns the result of the local statistical task to the inquiring side; and the inquiring party carries out aggregation processing on the results of the local statistical tasks to obtain a global statistical result. According to the method and the device for counting the frequency spectrum of the privacy-protecting drug clinical application, the analysis result is obtained in a mode of local statistics and global aggregation through a mode of federal learning, and the leakage of privacy information of original diagnosis and treatment records is avoided; the sample party adds the differential privacy noise to the local statistical result, so that the differential attack of the inquiry party on the sample party is avoided.

Description

Privacy-protecting medicine clinical application frequency spectrum statistical method and device
Technical Field
The invention relates to the field of privacy calculation, in particular to a method and a device for counting frequency spectrums of clinical application of medicines for protecting privacy.
Background
The spectrum distribution analysis is carried out on the historical clinical application cases adopting a certain type of medicine, which is beneficial to the adjustment of research and development decisions of medicine research and development mechanisms and improves the market competitiveness of medicines. The distribution analysis of the target drug in clinical applications relies on a large number of real clinical cases, which are scattered in different hospitals on the one hand, resulting in a limited number of case samples for a single hospital not enough to support the effectiveness of the distribution analysis; on the other hand, clinical diagnosis cases involve the privacy of the patient, and hospitals forbid sharing of these cases for privacy protection purposes.
Currently, the medicine research and development organization cannot directly access the part of data and can only know the data in a side form. Therefore, the research and development mechanism has a limited understanding of the application of the developed medicine in clinical operation, which affects the research and development investment and market decision. How to carry out the compliant distribution analysis of the operation on the prescriptions and operation records of each hospital under the privacy protection is of great significance for confirming the target diseases of the follow-up research and researching which layers should be provided for the research.
Therefore, how to provide a spectrum analysis method for clinical application of drugs, which can effectively protect the privacy of cases, becomes a technical problem to be solved urgently.
Disclosure of Invention
In view of this, the invention mainly solves the problem of how to perform statistical analysis on the medication of related cases to obtain a distribution spectrum of the medication without acquiring the diagnostic data of medical institutions; the invention adopts a difference federal learning method to carry out distributed statistics, thereby carrying out local calculation and global summary on the operation medication records of a plurality of hospitals without revealing the original diagnosis and treatment records. The invention can assist research and development institutions to know what the medicine is in the real world, and confirm the target diseases of follow-up research.
In one aspect, the invention provides a drug clinical application spectrum statistical method for protecting privacy, which comprises the following steps:
s1: the inquiring party obtains the target medicine components and the grouping items and issues local statistical tasks to the sample party;
s2: the sample side receives and executes the local statistical task issued by the inquiring side, and returns the result of the local statistical task to the inquiring side;
s3: and the inquiring party carries out aggregation processing on the results of the local statistical tasks to obtain a global statistical result.
Further, in step S2, the receiving and executing of the local statistical task issued by the querying party by the sample party includes:
s21: inquiring case information containing target medicine components and grouping items to obtain an inquiry result;
s22: grouping the query results according to the grouping items to obtain a grouping item set, and counting the real count value of each grouping item to obtain a real count value set;
s23: carrying out differential privacy processing on the real count value to obtain a noise count value set after noise is added;
s24: and returning the grouping item set and the corresponding noise count value set to a query party as a result of the local statistical task.
Further, in step S22, the query results are grouped according to grouping items, so as to obtain a grouping item set, which is expressed in the following manner:
Figure 699764DEST_PATH_IMAGE001
in the formula (I), the compound is shown in the specification,
Figure 820167DEST_PATH_IMAGE002
a set of grouping items representing a sample t, t representing the number of sample orders, m representing a grouping ID,
Figure 68746DEST_PATH_IMAGE003
representing the mth grouping item in the sample t.
Further, in step S22, the set of true count values is expressed in the following manner:
Figure 729534DEST_PATH_IMAGE004
in the formula (I), the compound is shown in the specification,
Figure 747169DEST_PATH_IMAGE005
a set of true count values representing a sample t, t representing the number of sample bins, m representing the packet ID,
Figure 835211DEST_PATH_IMAGE006
representing the real count value corresponding to the ith grouping item in the sample t.
Further, in step S23, the differential privacy processing is performed on the true count value, and includes: and traversing the real counting values corresponding to all the grouping items, and adding a random noise value sampled from Laplace distribution L (0, 1/epsilon) to each real counting value.
Further, in step S23, the noise count value after adding noise is obtained as follows:
Figure 102244DEST_PATH_IMAGE007
in the formula (I), the compound is shown in the specification,
Figure 504406DEST_PATH_IMAGE008
to add the set of noise count values at the sample side t after the noise,
Figure 438864DEST_PATH_IMAGE009
is the random noise value sampled from the Laplace distribution L (0, 1/ε), and 1/ε is the scale parameter of the Laplace distribution.
Further, in step S3, the process of aggregating the results of the local statistics task by the querying party includes: and traversing results of all sample-side local statistical tasks.
Further, in step S3, the inquiring party performs aggregation processing on the results of the local statistics task according to the following method:
Figure 134026DEST_PATH_IMAGE010
where k is the grouping item ID, XkIs the global count value of the kth packet entry,
Figure 888355DEST_PATH_IMAGE011
adding noise to the kth real count value in the real count value set in the sample side t,
Figure 890946DEST_PATH_IMAGE002
a set of grouped items representing a sample t.
In another aspect, the present invention provides a device for analyzing clinical application distribution of drugs based on differential federal statistics, comprising:
the query module comprises a task scheduling unit and an aggregation statistical unit, wherein the task scheduling unit is used for acquiring target medicine components and grouping items and issuing local statistical tasks to a sample party; the aggregation statistical unit is used for;
the sample module comprises a sample library unit and a differential statistical unit, wherein the differential statistical unit is used for inquiring case information containing target medicine components and grouping items from the sample library unit to obtain an inquiry result; grouping the query results according to grouping items, and counting the number of cases in each group and a real count value corresponding to each group; carrying out differential privacy processing on the real count value to obtain a noise count value added with noise; and returning the grouping items and the corresponding noise count values to the inquiring party as local statistical results.
Finally, the invention also provides a computer device comprising a memory, a processor and a computer program stored on said memory and executable on said processor, said processor implementing the steps of said method when executing said program.
The method and the device for counting the frequency spectrum of the clinical application of the medicine for protecting privacy have the following beneficial effects:
1) obtaining an analysis result in a mode of local statistics and global aggregation through a mode of federal learning, and avoiding the leakage of original diagnosis and treatment record privacy information;
2) the local statistical result is added with the differential privacy noise by the sample party, so that the differential attack of the inquiring party on the sample party is avoided.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a flowchart of an exemplary first embodiment of a privacy preserving pharmaceutical clinical application spectrum statistics method according to the present invention.
Fig. 2 is a flowchart of a spectrum statistics method for privacy-preserving pharmaceutical clinical applications according to a second exemplary embodiment of the present invention.
FIG. 3 is a block diagram of an exemplary fourth embodiment of a differential federal statistics based drug clinical applications distribution analysis device in accordance with the present invention.
FIG. 4 is a block diagram of an exemplary fifth embodiment of the present invention in the application of differential federal statistics based drug clinical application profiling.
Detailed Description
Embodiments of the present invention will be described in detail below with reference to the accompanying drawings.
It should be noted that, in the case of no conflict, the features in the following embodiments and examples may be combined with each other; moreover, all other embodiments that can be derived by one of ordinary skill in the art from the embodiments disclosed herein without making any creative effort fall within the scope of the present disclosure.
It is noted that various aspects of the embodiments are described below within the scope of the appended claims. It should be apparent that the aspects described herein may be embodied in a wide variety of forms and that any specific structure and/or function described herein is merely illustrative. Based on the disclosure, one skilled in the art should appreciate that one aspect described herein may be implemented independently of any other aspects and that two or more of these aspects may be combined in various ways. For example, an apparatus may be implemented and/or a method practiced using any number of the aspects set forth herein. Additionally, such an apparatus may be implemented and/or such a method may be practiced using other structure and/or functionality in addition to one or more of the aspects set forth herein.
Fig. 1 is a flowchart of a method for spectrum statistics of a privacy-preserving pharmaceutical clinical application according to an exemplary first embodiment of the present invention, as shown in fig. 1, the method according to the present embodiment includes:
s1: the inquiring party obtains the target medicine components and the grouping items and issues local statistical tasks to the sample party;
s2: the sample side receives and executes the local statistical task issued by the inquiring side, and returns the result of the local statistical task to the inquiring side;
s3: and the inquiring party carries out aggregation processing on the results of the local statistical tasks to obtain a global statistical result.
An exemplary second embodiment of the present invention provides a method for spectrum statistics for clinical application of drugs, which is a preferred embodiment of the method shown in fig. 1, as shown in fig. 1 and fig. 2, in the method of this embodiment, in step S2, the sample party receives and executes a local statistics task issued by the querying party, and the method includes:
s21: inquiring case information containing target medicine components and grouping items to obtain an inquiry result;
s22: grouping the query results according to the grouping items to obtain a grouping item set, and counting the real count value of each grouping item to obtain a real count value set;
s23: carrying out differential privacy processing on the real count value to obtain a noise count value set after noise is added;
s24: and returning the grouping item set and the corresponding noise count value set to a query party as a result of the local statistical task.
Specifically, in step S22 of this embodiment, the query result is grouped according to the grouping items to obtain a grouping item set, which is expressed in the following manner:
Figure 617594DEST_PATH_IMAGE012
in the formula (I), the compound is shown in the specification,
Figure 47438DEST_PATH_IMAGE002
a set of grouping items representing a sample t, t representing the number of sample orders, m representing a grouping ID,
Figure 554643DEST_PATH_IMAGE013
representing the mth grouping item of the sample.
Specifically, in step S22 of this embodiment, the set of true count values is expressed as follows:
Figure 33029DEST_PATH_IMAGE014
in the formula (I), the compound is shown in the specification,
Figure 676500DEST_PATH_IMAGE015
a set of true count values representing a sample t, t representing the number of sample directions, m representing a grouping item ID,
Figure 277245DEST_PATH_IMAGE016
indicating the true count value corresponding to the ith grouping item in the sample t.
Specifically, in step S23 of this embodiment, the differential privacy processing is performed on the real count value, and includes: the corresponding real count values for all packets are traversed and a random noise value sampled from the laplacian distribution L (0, 1/epsilon) is added to each real count value.
Specifically, in step S23 of the present embodiment, the noise count value after adding noise is obtained as follows:
Figure 209429DEST_PATH_IMAGE007
in the formula (I), the compound is shown in the specification,
Figure 553823DEST_PATH_IMAGE008
to add the set of noise count values for the post-noise sample t,
Figure 51800DEST_PATH_IMAGE009
is the random noise value sampled from the Laplace distribution L (0, 1/ε), and 1/ε is the scale parameter of the Laplace distribution.
An exemplary third embodiment of the present invention provides a method for spectrum statistics of clinical application of drugs for privacy protection, where this embodiment is a preferred embodiment of the method shown in fig. 1 and fig. 2, and in step S3, the querying party performs aggregation processing on results of local statistics tasks, where the method includes: and traversing results of all sample-side local statistical tasks.
Specifically, in step S3, the inquiring party performs aggregation processing on the results of the local statistics task, and the method of this embodiment is performed as follows:
Figure 26709DEST_PATH_IMAGE010
where k is the grouping item ID, XkIs the global count value of the kth packet entry,
Figure 242927DEST_PATH_IMAGE017
adding noise to the kth real count value in the real count value set in the sample side t,
Figure 125432DEST_PATH_IMAGE002
a set of grouped items representing a sample t.
Fig. 3 is a block diagram of a differential federal statistics-based distribution analyzer for clinical applications of drugs according to an exemplary fourth embodiment of the present invention, as shown in fig. 3, the differential federal statistics-based distribution analyzer for clinical applications of drugs of this embodiment includes:
the query module comprises a task scheduling unit and an aggregation statistical unit, wherein the task scheduling unit is used for acquiring target medicine components and grouping items and issuing local statistical tasks to a sample party; the aggregation statistical unit is used for;
the sample module comprises a sample library unit and a differential statistical unit, wherein the differential statistical unit is used for inquiring case information containing target medicine components and grouping items from the sample library unit to obtain an inquiry result; grouping the query results according to grouping items, and counting the number of cases in each group and a real count value corresponding to each group; carrying out differential privacy processing on the real count value to obtain a noise count value added with noise; and returning the grouping items and the corresponding noise count values to the inquiring party as local statistical results.
The fifth exemplary embodiment of the present invention provides an application of the spectrum statistical method for the clinical application of the medicine for protecting the privacy in the fields of hospitals and medicine research and development institutions. FIG. 4 is a block diagram of the clinical application distribution analysis of drugs based on differential federal statistics in an embodiment of the present invention.
In this embodiment, a drug development organization, as an inquiring party, obtains a target drug component (selecting the target drug component to be analyzed as a blood coagulation enzyme) and a grouping item (operation name and operation time), and issues a local statistical task to a sample party;
the hospital side as a sample side receives and executes the local statistical task issued by the inquiring side, and returns the result of the local statistical task to the inquiring side, specifically:
the record of the prescription containing the target drug component (hemocoagulase) is inquired from the 'western medicine, Chinese patent medicine prescription detailed table' and 'operation record table' in the sample library unit (diagnosis case library), and the information of the code of the visit, the operation time, the operation name and the drug name (such as 'agkistrodon acutus thrombin, agkistrodon spearhead hemocoagulase, snake venom hemocoagulase, white eyebrow snake venom hemocoagulase') is obtained from the record, as shown in table 1:
TABLE 1
Figure 681179DEST_PATH_IMAGE019
Grouping the query results according to grouping items (operation names and operation times) to obtain m (grouping ID) groups which are expressed as
Figure 889306DEST_PATH_IMAGE020
And counts the number of cases in each group, expressed as
Figure 327241DEST_PATH_IMAGE021
Wherein
Figure 951120DEST_PATH_IMAGE022
Representing the true count value corresponding to the ith packet on the t-th sample side. Assuming the t-th hospital, the counting results are shown in table 2 by the specific grouping of the surgical name and the surgical time:
TABLE 2
Figure 423690DEST_PATH_IMAGE024
Count the true
Figure 802719DEST_PATH_IMAGE025
The difference privacy processing is performed to obtain a noise count value after adding noise, which is expressed as
Figure 931212DEST_PATH_IMAGE026
. The specific process of the differential privacy processing is as follows: traversing m real counting values, setting the scale parameter 1/epsilon of the Laplace distribution to be 10, and adding random noise sampled from the Laplace distribution L (0, 10) to each counting value, wherein the formula is as follows:
Figure 388475DEST_PATH_IMAGE027
wherein the content of the first and second substances,
Figure 449972DEST_PATH_IMAGE028
is the random noise sampled from the laplacian distribution L (0, 10). Assume that the specific statistics for the tth hospital are shown in table 3:
TABLE 3
Figure 937585DEST_PATH_IMAGE030
And returning the grouping items and the corresponding noise count values to the inquiring party as the results of the local statistical tasks.
Suppose n is 3, there are local statistics of three medicines. The inquirer aggregates the results of the local statistical tasks and traverses all the grouping items, and for the k =1 item (hemorrhoid excision, 2019), the local statistical results of the three hospitals are
Figure 615691DEST_PATH_IMAGE031
=3.5、
Figure 846953DEST_PATH_IMAGE032
=0 (i.e. not including the statistics of the grouping entry) =,
Figure 28535DEST_PATH_IMAGE033
And =10, the item 1 is aggregated according to the following aggregation statistical formula, and the global count value of the 1 st packet item is finally obtained to be 13.5.
Figure 483787DEST_PATH_IMAGE034
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are also within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims (10)

1. A privacy preserving spectrum statistical method for clinical application of drugs, the method comprising:
s1: the inquiring party obtains the target medicine components and the grouping items and issues local statistical tasks to the sample party;
s2: the sample side receives and executes the local statistical task issued by the inquiring side, and returns the result of the local statistical task to the inquiring side;
s3: and the inquiring party carries out aggregation processing on the results of the local statistical tasks to obtain a global statistical result.
2. The method for spectrum statistics of clinical applications of drugs with privacy protection as claimed in claim 1, wherein the step S2 is that the sample party receives and executes the local statistics task issued by the query party, which includes:
s21: inquiring case information containing target medicine components and grouping items to obtain an inquiry result;
s22: grouping the query results according to the grouping items to obtain a grouping item set, and counting the real count value of each grouping item to obtain a real count value set;
s23: carrying out differential privacy processing on the real count value to obtain a noise count value set after noise is added;
s24: and returning the grouping item set and the corresponding noise count value set to a query party as a result of the local statistical task.
3. The method for spectrum statistics of clinical applications of drugs with privacy protection as claimed in claim 2, wherein in step S22, the query results are grouped according to grouping items to obtain a grouping item set, which is expressed as follows:
Figure 286302DEST_PATH_IMAGE001
in the formula (I), the compound is shown in the specification,
Figure 475975DEST_PATH_IMAGE002
a set of grouping items representing a sample t, t representing the number of sample orders, m representing a grouping ID,
Figure 375798DEST_PATH_IMAGE003
representing the mth grouping item in the sample t.
4. The privacy-preserving pharmacogenical clinical application spectrum statistical method according to claim 3, wherein in step S22, the set of true count values is expressed as follows:
Figure 941908DEST_PATH_IMAGE004
in the formula (I), the compound is shown in the specification,
Figure 305894DEST_PATH_IMAGE005
a set of true count values representing a sample t, t representing the number of sample bins, m representing the packet ID,
Figure 666468DEST_PATH_IMAGE006
representing the real count value corresponding to the ith grouping item in the sample t.
5. The privacy-preserving pharmaceutical clinical application spectrum statistical method according to claim 4, wherein in step S23, the differential privacy processing is performed on the true count value, and the differential privacy processing includes: and traversing the real count values corresponding to all the grouping items, and adding a random noise value sampled from the Laplace distribution L (0, 1/epsilon) to each real count value, wherein 1/epsilon is a scale parameter of the Laplace distribution.
6. The method for spectrum statistics of clinical applications of drugs with privacy protection according to claim 5, wherein in step S23, the noise count value after adding noise is obtained as follows:
Figure 53587DEST_PATH_IMAGE007
in the formula (I), the compound is shown in the specification,
Figure 423388DEST_PATH_IMAGE008
to add the set of noise count values at the sample side t after the noise,
Figure 313984DEST_PATH_IMAGE009
is a random noise value sampled from the laplacian distribution L (0, 1/epsilon).
7. The method for spectrum statistics of clinical applications of drugs with privacy protection according to claim 1, wherein in step S3, the gathering process of the results of the local statistics task by the querying party includes: and traversing results of all sample-side local statistical tasks.
8. The method for spectrum statistics of clinical applications of drugs with privacy protection as claimed in claim 7, wherein in step S3, the inquiring party performs the aggregation process on the results of the local statistics task according to the following method:
Figure 111039DEST_PATH_IMAGE010
where k is the grouping item ID, XkIs the global count value of the kth packet entry,
Figure 280726DEST_PATH_IMAGE011
adding noise to the kth real count value in the real count value set in the sample side t,
Figure 454219DEST_PATH_IMAGE012
a set of grouped items representing a sample t.
9. A differential federal statistics based drug clinical application profile analysis device, the device comprising:
the query module comprises a task scheduling unit and an aggregation statistical unit, wherein the task scheduling unit is used for acquiring target medicine components and grouping items and issuing local statistical tasks to a sample party; the aggregation statistical unit is used for;
the sample module comprises a sample library unit and a differential statistical unit, wherein the differential statistical unit is used for inquiring case information containing target medicine components and grouping items from the sample library unit to obtain an inquiry result; grouping the query results according to grouping items, and counting the number of cases in each group and a real count value corresponding to each group; carrying out differential privacy processing on the real count value to obtain a noise count value added with noise; and returning the grouping items and the corresponding noise count values to the inquiring party as local statistical results.
10. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the method of any one of claims 4 to 8 when executing the program.
CN202210531839.2A 2022-05-17 2022-05-17 Privacy-protecting medicine clinical application frequency spectrum statistical method and device Pending CN114628043A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210531839.2A CN114628043A (en) 2022-05-17 2022-05-17 Privacy-protecting medicine clinical application frequency spectrum statistical method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210531839.2A CN114628043A (en) 2022-05-17 2022-05-17 Privacy-protecting medicine clinical application frequency spectrum statistical method and device

Publications (1)

Publication Number Publication Date
CN114628043A true CN114628043A (en) 2022-06-14

Family

ID=81906922

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210531839.2A Pending CN114628043A (en) 2022-05-17 2022-05-17 Privacy-protecting medicine clinical application frequency spectrum statistical method and device

Country Status (1)

Country Link
CN (1) CN114628043A (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112185395A (en) * 2020-09-04 2021-01-05 哈尔滨工业大学（深圳） Federal voiceprint recognition method based on differential privacy
CN112749407A (en) * 2020-12-18 2021-05-04 广东精点数据科技股份有限公司 Data desensitization device based on medical data
CN113169957A (en) * 2019-04-12 2021-07-23 杭州锘崴信息科技有限公司 Personal medical data security sharing and ownership decentralized ownership system
CN114283909A (en) * 2021-12-28 2022-04-05 高堃 Method, system, device and storage medium for inquiring clinical scientific research data

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113169957A (en) * 2019-04-12 2021-07-23 杭州锘崴信息科技有限公司 Personal medical data security sharing and ownership decentralized ownership system
CN112185395A (en) * 2020-09-04 2021-01-05 哈尔滨工业大学（深圳） Federal voiceprint recognition method based on differential privacy
CN112749407A (en) * 2020-12-18 2021-05-04 广东精点数据科技股份有限公司 Data desensitization device based on medical data
CN114283909A (en) * 2021-12-28 2022-04-05 高堃 Method, system, device and storage medium for inquiring clinical scientific research data

Similar Documents

Publication Publication Date Title
Pramanik et al. Healthcare big data: A comprehensive overview
US20120221589A1 (en) Method and system for selecting, retrieving, visualizing and exploring time-oriented data in multiple subject records
US20080114808A1 (en) Visual filtering to create logical associations in timeline based metaphors
Berends et al. AMR–an R package for working with antimicrobial resistance data
Murray et al. Design and validation of a data simulation model for longitudinal healthcare data
Gardner et al. SHARE: system design and case studies for statistical health information release
JP2013518317A (en) How to organize clinical trial data
US20230178189A1 (en) System and method for phenotype vector manipulation of medical data
Awrahman et al. A review of the role and challenges of big data in healthcare informatics and analytics
National Academies of Sciences, Engineering, and Medicine Examining the Impact of Real-World Evidence on Medical Product Development
Krasowski et al. Use of a data warehouse at an academic medical center for clinical pathology quality improvement, education, and research
US8744872B1 (en) System and method for pharmacovigilance
CN116469571A (en) Method and system for constructing specific disease map of real world data
Ma et al. Using the shapes of clinical data trajectories to predict mortality in ICUs
Moser et al. Application of data mining to intensive care unit microbiologic data.
Silva et al. Predicting hospital emergency department visits accurately: A systematic review
Son et al. Visualization of e-Health research topics and current trends using social network analysis
Ruppert et al. Predictive modeling for readmission to intensive care: a systematic review
CN114628043A (en) Privacy-protecting medicine clinical application frequency spectrum statistical method and device
Xiang et al. Efficiently mining Adverse Event Reporting System for multiple drug interactions
Chandrababu et al. Comparative analysis of graph and relational databases using herbmicrobeDB
Alexander et al. Big data and data-driven healthcare systems
Cimino Racial disparity in clinical alert overrides
Studnicki et al. Using information systems for public health administration
Finkelstein et al. A medical application to bridge the gap between clinicians and clinical data

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
WD01 Invention patent application deemed withdrawn after publication
WD01 Invention patent application deemed withdrawn after publication

Application publication date: 20220614