CN110739075A - COPD disease auxiliary diagnosis monitoring system based on big data - Google Patents
COPD disease auxiliary diagnosis monitoring system based on big data Download PDFInfo
- Publication number
- CN110739075A CN110739075A CN201911028122.0A CN201911028122A CN110739075A CN 110739075 A CN110739075 A CN 110739075A CN 201911028122 A CN201911028122 A CN 201911028122A CN 110739075 A CN110739075 A CN 110739075A
- Authority
- CN
- China
- Prior art keywords
- monitoring
- data
- copd
- monitoring block
- block
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 179
- 208000006545 Chronic Obstructive Pulmonary Disease Diseases 0.000 title claims abstract description 101
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 title claims abstract description 66
- 238000003745 diagnosis Methods 0.000 title claims abstract description 32
- 210000004072 lung Anatomy 0.000 claims abstract description 30
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 19
- 238000012806 monitoring device Methods 0.000 claims abstract description 17
- 201000010099 disease Diseases 0.000 claims abstract description 14
- 238000004364 calculation method Methods 0.000 claims abstract description 12
- 230000002159 abnormal effect Effects 0.000 claims description 12
- 230000005540 biological transmission Effects 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 7
- 238000000605 extraction Methods 0.000 claims description 6
- 238000004806 packaging method and process Methods 0.000 claims description 4
- 238000013154 diagnostic monitoring Methods 0.000 claims 5
- 230000036387 respiratory rate Effects 0.000 claims 4
- 230000017525 heat dissipation Effects 0.000 claims 1
- 238000000034 method Methods 0.000 description 11
- 208000037656 Respiratory Sounds Diseases 0.000 description 8
- 230000036391 respiratory frequency Effects 0.000 description 8
- 238000011161 development Methods 0.000 description 6
- 230000036541 health Effects 0.000 description 6
- 238000011160 research Methods 0.000 description 5
- 201000006306 Cor pulmonale Diseases 0.000 description 3
- 206010011224 Cough Diseases 0.000 description 3
- 206010036790 Productive cough Diseases 0.000 description 3
- 208000004186 Pulmonary Heart Disease Diseases 0.000 description 3
- 208000004756 Respiratory Insufficiency Diseases 0.000 description 3
- 238000004026 adhesive bonding Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 201000004193 respiratory failure Diseases 0.000 description 3
- 238000003759 clinical diagnosis Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000007418 data mining Methods 0.000 description 2
- 238000013499 data model Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000002405 diagnostic procedure Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000009798 acute exacerbation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000008280 blood Substances 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 238000004883 computer application Methods 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000009533 lab test Methods 0.000 description 1
- 238000010827 pathological analysis Methods 0.000 description 1
- 238000004393 prognosis Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000004202 respiratory function Effects 0.000 description 1
- 238000002922 simulated annealing Methods 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/0205—Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/024—Detecting, measuring or recording pulse rate or heart rate
- A61B5/02438—Detecting, measuring or recording pulse rate or heart rate with portable devices, e.g. worn by the patient
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/08—Detecting, measuring or recording devices for evaluating the respiratory organs
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/08—Detecting, measuring or recording devices for evaluating the respiratory organs
- A61B5/0816—Measuring devices for examining respiratory frequency
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/145—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue
- A61B5/14542—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue for measuring blood gases
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/145—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue
- A61B5/1455—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue using optical sensors, e.g. spectral photometrical oximeters
- A61B5/14551—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue using optical sensors, e.g. spectral photometrical oximeters for measuring blood gases
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
- A61B5/6801—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient specially adapted to be attached to or worn on the body surface
- A61B5/6802—Sensor mounted on worn items
-
- 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
- G16H30/00—ICT specially adapted for the handling or processing of medical images
- G16H30/20—ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS
-
- 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
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/60—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices
- G16H40/67—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices for remote operation
-
- 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
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Physics & Mathematics (AREA)
- Pathology (AREA)
- Veterinary Medicine (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Heart & Thoracic Surgery (AREA)
- Biophysics (AREA)
- Epidemiology (AREA)
- Physiology (AREA)
- Primary Health Care (AREA)
- Pulmonology (AREA)
- Cardiology (AREA)
- Data Mining & Analysis (AREA)
- Optics & Photonics (AREA)
- Databases & Information Systems (AREA)
- Business, Economics & Management (AREA)
- General Business, Economics & Management (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention provides a COPD disease auxiliary diagnosis monitoring system based on big data, which comprises an acquisition module, a subset generation module, a calculation module and a monitoring device, wherein the acquisition module is used for acquiring COPD disease data in a database, the COPD disease data comprises COPD patient information and COPD patient clinical information, the subset generation module is used for acquiring -th disease characteristics in the COPD disease data and acquiring the characteristic subsets through an MDF algorithm, the calculation module is used for classifying the characteristic subsets based on a algorithm and outputting a judgment result, the monitoring device is used for monitoring patient physical signs in real time, and the monitoring device comprises a lung monitoring unit and a nail monitoring unit.
Description
Technical Field
The invention relates to the technical field of big data and medical treatment, in particular to COPD disease auxiliary diagnosis monitoring systems based on big data.
Background
At present, along with the economic development and scientific and technological progress of China, the construction requirements of various data centers are obviously increased, 2016, 10 months, Changzhou, Nanjing, Fuzhou and Xizao are determined as the first trial point units for the construction of big national health medical data centers and industrial gardens, and regional nationwide health information platforms of 'City and county integration' are built all over the country, so that interconnection and intercommunication and data sharing and exchange of all public medical institutions are realized.
, it is mainly used for PACS and ECG monitoring system to generate unstructured data such as video and audio stored in multimedia format, HIS and LIS to generate structured data such as patient file, medical order and prescription, and laboratory test report stored in standard form, and electronic medical record to generate semi-structured data.
In another aspect, from the information recording mode, entity may have records in multiple systems, but its specific attribute sets may be different, even if attribute, its name or data is more likely to be in conflict with each other in the interactive process due to system or manual recording errors.
The multi-source heterogeneous health big data can only be subjected to rough statistical analysis at present, and the clinical scientific research big data acquisition of specific disease species can not be carried out across medical institutions, so that the clinical diagnosis and treatment are assisted.
COPD is common diseases which can be prevented and treated and are characterized by continuous airflow limitation, can cause the gradual reduction of the respiratory function of patients, become the fourth approximately death disease in the world, and currently, about more than 1.7 hundred million COPD patients are in the world, the disease development of COPD is a progressive process, the early stage of COPD is not obvious, the symptoms of COPD are presented as cough and expectoration, the patients are not easy to detect and are the best treatment time, and the middle and later stage of COPD treatment can even cause complications such as pulmonary heart disease, respiratory failure and the like if the patients are not timely, so the early stage of COPD discovery is very important, the patients need to be stably managed for a long time, and if the disease is not prevented and managed, the patients are more harmed particularly if acute exacerbation occurs along with the development of steps.
With the development of computer data mining technology, the problems become research hotspots in the computer field, at present, the data mining technology has been widely applied to the research fields of pathological analysis, clinical diagnosis and the like of COPD, and the research is mainly carried out in two aspects, namely, a) the influence of a single characteristic on the disease is mined by analyzing the electronic case data by using the existing data analysis tool, b) the prognosis risk effect of the patient with COPD is verified by a simple model, but no method or system can effectively judge COPD assistant physicians.
Disclosure of Invention
The invention provides large data-based COPD disease auxiliary diagnosis monitoring systems, which can mine multidimensional data characteristics, design a COPD disease analysis algorithm, deeply learn, optimize a COPD diagnosis model, and be applied to clinical auxiliary diagnosis, are ways for applying medical large data to COPD clinical auxiliary diagnosis, and have practical significance for the perfection, development and practicability of information system data models in the medical field.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
COPD disease auxiliary diagnosis monitoring system based on big data, comprising an acquisition module, a subset generation module, a calculation module and a monitoring device;
the acquisition module: for obtaining COPD disease data in a database, the COPD disease data comprising COPD patient information and COPD patient clinical information;
the subset generation module is used for acquiring th quantity of disease state features in COPD disease data and obtaining feature subsets through an MDF algorithm;
and the calculation module classifies the feature subsets based on the th algorithm and outputs a judgment result.
The monitoring device is characterized in that: the monitoring device is used for monitoring the physical signs of a patient in real time and comprises a lung monitoring unit and a nail monitoring unit.
, the big data-based COPD disease aided diagnosis monitoring system further comprises the following modules:
a standard data acquisition module: acquiring HL7 standard data of each sub-database, wherein the HL7 standard data comprises at least two types of data;
an classification processing module, which is used for performing semantic packaging on each HL7 standard data through a heterogeneous data semantic extraction framework, performing classification processing on a plurality of HL7 standard data with the same semantics to generate COPD disease data and storing the COPD disease data in a database.
With the improvement and popularization of electronic medical record products, doctors have adapted to the standardized workflow and are willing to input patient data in a structured system, but in practice, although information collected to a central database by hospitals has a structured appearance according to the HL7 standard, most data per se is unstructured. For the analysis of these data, the data are first extracted according to a specific disease species and then structured.
Further , the HL7 standard data includes structured two-dimensional table data, semi-structured XML document data, unstructured images, documents, and data.
Further to , the computing module further comprises:
a function generation unit: and acquiring a data point generation speed and a data flow length of the COPD disease data included in the feature subset, and generating a preset function by using the data point generation speed and the data flow length.
Further to , the computing module further comprises:
acquiring COPD patient clinical information, wherein each COPD patient clinical information comprises a number of sub-clusters (i, j), the number of sub-clusters for each patient satisfying the following formula:
wherein a plurality of sub-clusters (i, j) respectively satisfy [0, 1%]The values of the interval, i, j are the class numbers i representing the ith sample, μijRepresenting the membership degree of the sample i belonging to the j class; a centroid c. "belongs to fuzzy C means clustering algorithm".
Initializing the clinical information of the COPD patient, and generating sample data, wherein the clinical information of the COPD patient comprises a classification number k, a fuzzy factor m, an iteration number num, a convergence threshold limit and a maximum iteration number max _ num;
calculating the distance between the sample data and the clustering center to calculate the membership degree;
and outputting the sample data with the membership degree larger than the second preset value, and covering the previous sample data.
The lung monitoring unit comprises an th monitoring block and a second monitoring block which are used for monitoring the left lung, and a third monitoring block and a fourth monitoring block which are used for monitoring the right lung, wherein the th monitoring block is tightly attached to the corresponding chest of the left lung, the second monitoring block is tightly attached to the corresponding back of the left lung, the third monitoring block is tightly attached to the corresponding chest of the right lung, the fourth monitoring block is tightly attached to the corresponding back of the right lung, the nail monitoring unit comprises a nail oximeter and a th wireless information transmission module arranged in the nail oximeter, the th wireless information transmission module transmits the collected data of the nail oximeter to the information receiving part of a hospital, and the data of the information receiving part is uploaded to a database.
The th and the second monitoring blocks monitor the left lung from the chest and the back respectively, which can improve the accuracy of the left lung monitoring, like when a doctor auscultates, the doctor should listen to of the chest and of the back, and can only listen to two parts to determine a better diagnosis, and the third and the fourth monitoring blocks have the same functions as the th and the second monitoring blocks.
monitoring block, second monitoring block, third monitoring block, fourth monitoring block all set up on ring belt and monitoring block, second monitoring block, third monitoring block, fourth monitoring block's position all is adjustable, the ring belt constraint just on the body that the lung corresponds the ring belt is equipped with the junction convenient to detach, and the junction is through the thread gluing area connection.
The monitoring block, the second monitoring block, the third monitoring block and the fourth monitoring block are fixed on the inner side surface of the annular belt through pins, and holes for the pin points to pass through are formed in the outer side surfaces of the monitoring block, the second monitoring block, the third monitoring block and the fourth monitoring block, so that the pins can conveniently pass through the monitoring block, the second monitoring block, the third monitoring block and the fourth monitoring block, and the monitoring block, the second monitoring block, the third monitoring block and the fourth monitoring block can be conveniently fixed.
The COPD disease auxiliary diagnosis monitoring system based on big data further comprises a mobile power supply and an information collection module, wherein the information collection module is electrically connected with the mobile power supply, the th monitoring block, the second monitoring block, the third monitoring block and the fourth monitoring block are respectively and electrically connected with the mobile power supply and the information collection module through electric wires, the information collection module is provided with a second wireless information transmission module, the second wireless information transmission module transmits the collected data of the information collection module to an information receiving place of a hospital, and the data of the information receiving place is uploaded to a database.
For the person with the heart on the left, a plurality of sensors for monitoring the respiratory frequency, the intensity, the heart rate and the abnormal breathing sound are arranged on the th monitoring block, a plurality of sensors for monitoring the respiratory frequency, the intensity and the abnormal breathing sound are arranged on the second monitoring block, the third monitoring block and the fourth monitoring block, a plurality of sensors for monitoring the respiratory frequency, the intensity, the heart rate and the abnormal breathing sound are arranged on the third monitoring block, a plurality of sensors for monitoring the respiratory frequency, the intensity and the abnormal breathing sound are arranged on the th monitoring block, the second monitoring block and the fourth monitoring block, radiating holes are arranged on the annular belt, radiating holes are convenient for radiating the annular belt, a pin can conveniently penetrate through the annular belt, and the th monitoring block, the second monitoring block, the third monitoring block and the fourth monitoring block can be quickly.
The beneficial effects are as follows:
, the invention provides COPD disease auxiliary diagnosis monitoring systems based on big data, which can mine multidimensional data characteristics, design COPD disease analysis algorithm, deeply learn, optimize COPD diagnosis model, and be applied to clinical auxiliary diagnosis, is ways of applying medical big data to COPD clinical auxiliary diagnosis, and has very practical significance to the perfection, development and practicability of information system data model in medical field.
The monitoring device can monitor the physical signs of the patient in real time, provides more favorable real data support for the treatment of the patient, is convenient for doctors to know the condition of the patient in time, is convenient for adjusting a treatment scheme, and also provides more real and direct data support for a COPD database.
Thirdly, the monitoring device of the invention comprises an th monitoring block, a second monitoring block, a third monitoring block and a fourth monitoring block, and can monitor the physical signs of patients more accurately.
And fourthly, the annular belts of the monitoring device are connected at the connection positions through the thread gluing belts, so that the monitoring device is convenient to disassemble.
The technical solution of the present invention is further described in steps by the accompanying drawings and examples.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and constitute a part of this specification, and are included to explain the invention and not to limit the invention by way of example .
FIG. 1 is a flow chart of embodiment of the present invention;
FIG. 2 is a flow chart of a second embodiment of the present invention;
FIG. 3 is a schematic view of a monitoring device according to the present invention;
FIG. 4 is a block diagram of an th embodiment of the diagnostic method of the present invention;
fig. 5 is a structural diagram of a diagnostic method according to a second embodiment of the present invention.
Detailed Description
The preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, and it will be understood that they are described herein for the purpose of illustration and explanation and not limitation.
Embodiment , as shown in fig. 1, big data based COPD disease assisted diagnosis monitoring system, includes an acquisition module, a subset generation module, a calculation module and a monitoring device.
An acquisition module: acquiring COPD disease data in a database, wherein the COPD disease data comprises COPD patient information and COPD patient clinical information;
the subset generation module is used for acquiring th disease characteristics of COPD disease data and acquiring a characteristic subset through an MDF algorithm;
and the calculation module is used for classifying the feature subsets based on the th algorithm and outputting judgment results.
The monitoring device is characterized in that: the monitoring device is used for monitoring the physical signs of a patient in real time and comprises a lung monitoring unit and a nail monitoring unit.
In a second embodiment, as shown in fig. 2, big data-based COPD auxiliary diagnosis and monitoring systems further include the following modules:
a standard data acquisition module: acquiring HL7 standard data of each sub-database, wherein the HL7 standard data comprises at least two types of data;
an classification processing module, which is used for performing semantic packaging on each HL7 standard data through a heterogeneous data semantic extraction framework, performing classification processing on a plurality of HL7 standard data with the same semantics to generate COPD disease data and storing the COPD disease data in a database.
The HL7 standard data includes structured two-dimensional table data, semi-structured XML file data, unstructured images, documents, and data.
The calculation module further comprises:
a function generation unit: and acquiring a data point generation speed and a data flow length of the COPD disease data included in the feature subset, and generating a preset function by using the data point generation speed and the data flow length.
The calculation module further comprises:
acquiring COPD patient clinical information, wherein each COPD patient clinical information comprises a number of sub-clusters (i, j), the number of sub-clusters for each patient satisfying the following formula:
wherein a plurality of sub-clusters (i, j) respectively satisfy [0, 1%]The number of intervals; i, j are class labels i denoting the ith sample, μijRepresenting the membership degree of the sample i belonging to the j class; a centroid c. "belongs to fuzzy C means clustering algorithm".
Initializing the clinical information of the COPD patient, and generating sample data, wherein the clinical information of the COPD patient comprises a classification number k, a fuzzy factor m, an iteration number num, a convergence threshold limit and a maximum iteration number max _ num;
calculating the distance between the sample data and the clustering center to calculate the membership degree;
and outputting the output sample data with the membership degree larger than a second preset value and covering the previous sample data.
As shown in fig. 3, the lung monitoring unit of the big data-based COPD auxiliary diagnosis monitoring system of the present invention includes th monitoring block 1 and 2 for monitoring the left lung, and third monitoring block 3 and fourth monitoring block 4 for monitoring the right lung, the th monitoring block 1 is attached to the chest corresponding to the left lung, the second monitoring block 2 is attached to the back corresponding to the left lung, the third monitoring block 3 is attached to the chest corresponding to the right lung, the fourth monitoring block 4 is attached to the back corresponding to the right lung, the nail monitoring unit includes a nail oximeter 10 and a th wireless information transmission module 11 disposed in the nail oximeter 10, the th wireless information transmission module 11 transmits the data collected by the nail oximeter 10 to the information receiver of the hospital, and the data at the information receiver is uploaded to the database.
monitoring block 1, second monitoring block 2, third monitoring block 3, fourth monitoring block 4 all set up on zonular ring belt 5 and monitoring block 1, second monitoring block 2, third monitoring block 3, fourth monitoring block 4's position all is adjustable, the zonular ring belt 5 constraint just on the body that the lung corresponds the zonular ring belt 5 is equipped with convenient to detach's junction, and the junction passes through the thread gluing area 6 and connects.
monitoring block 1, second monitoring block 2, third monitoring block 3, fourth monitoring block 4 pass through the safety pin to be fixed the medial surface of ring belt 5, the lateral surface of monitoring block 1, second monitoring block 2, third monitoring block 3, fourth monitoring block 4 is equipped with the hole that supplies the safety pin needle point to pass through.
The COPD disease auxiliary diagnosis monitoring system based on big data further comprises a mobile power supply 7 and an information collection module 8, wherein the information collection module 8 is electrically connected with the mobile power supply 7, the th monitoring block 1, the second monitoring block 2, the third monitoring block 3 and the fourth monitoring block 4 are respectively and electrically connected with the mobile power supply 7 and the information collection module 8 through electric wires, the information collection module 8 is provided with a second wireless information transmission module 9, the second wireless information transmission module 9 transmits the collected data of the information collection module 8 to an information receiving place of a hospital, and the data of the information receiving place is uploaded to a database.
For the person with the heart on the left, a plurality of sensors for monitoring the respiratory frequency, the intensity, the heart rate and the abnormal respiratory sound are arranged on the th monitoring block 1, a plurality of sensors for monitoring the respiratory frequency, the intensity and the abnormal respiratory sound are arranged on the second monitoring block 2, the third monitoring block 3 and the fourth monitoring block 4, a plurality of sensors for monitoring the respiratory frequency, the intensity, the heart rate and the abnormal respiratory sound are arranged on the third monitoring block 3, a plurality of sensors for monitoring the respiratory frequency, the intensity and the abnormal respiratory sound are arranged on the monitoring block 1, the second monitoring block 2 and the fourth monitoring block 4, and heat radiation holes are formed in the annular belt 5.
The diagnosis method of the big data-based COPD disease auxiliary diagnosis monitoring system is a flow chart of embodiment shown in figure 4, and comprises the following steps:
s1, acquiring COPD disease data in a database, wherein the COPD disease data comprises COPD patient information and COPD patient clinical information, the COPD patient information comprises any or more of the name, age, sex, work unit, blood type, height and weight of a patient, and the patient clinical information comprises any or more of cough, expectoration, pulmonary heart disease and respiratory failure.
And S2, a subset generation step, wherein the COPD disease data is obtained, the disease characteristics of the th number are acquired, the characteristic subset is obtained through an MDF algorithm, the th number can be ten, namely, original more than 10 characteristics are extracted from the database, the characteristics comprise any or more of cough, expectoration, pulmonary heart disease and respiratory failure, and then the characteristic subset is obtained through an optimized MDF algorithm.
The MDF algorithm is disclosed in the literature 'COPD multidimensional feature extraction and integrated diagnosis method', and is published in 'computer application research' 2019, stage 10, and the author: the houses are beautiful, royal red, Dirichong, Wanglong Tong and Song Yong.
S3, calculating, namely classifying the feature subsets based on the algorithm, outputting judgment results, judging the illness state, the etiology, the treatment method and the like of a COPD patient by a doctor according to different judgment results to achieve the aim and the effect of auxiliary treatment, optimizing the combination of SVM parameters C and gamma by utilizing a direct search simulated annealing algorithm, establishing a virtual window in a local parameter, setting a parameter range threshold until the parameter is stable as an accepted range, and finally finding the optimal combination of the parameters C and gamma by utilizing a cross validation method in order to improve various indexes such as the accuracy of a model.
As shown in fig. 5, a flow chart of a second embodiment of the diagnosis method for the big data-based COPD disease auxiliary diagnosis monitoring system, before the step of acquiring COPD disease data in the database, the COPD disease data including COPD patient information and COPD patient clinical information, further includes the following steps:
a1, a step of obtaining standard data, namely obtaining HL7 standard data of each sub-database, wherein the HL7 standard data comprises at least two types of data, in embodiments, the HL7 standard data comprises structured two-dimensional table data, semi-structured XML file data, unstructured images, documents and data.
A2 and grouping , namely performing semantic packaging on each HL7 standard data through a heterogeneous data semantic extraction framework, and grouping processing a plurality of HL7 standard data with the same semantics to generate COPD disease data and store the COPD disease data in a database.
As electronic medical records are improved and popularized, doctors are adapted to the standardized work flow and are willing to input the data of patients in a structured system, but in practice, although the information collected to a central database by hospitals has a structured appearance according to an HL7 standard, most of the data are unstructured, and the data analysis needs to be carried out according to specific disease types firstly.
Generally, the field heterogeneous data mainly comprises 3 types, namely structured two-dimensional table data, semi-structured XML file data, unstructured image data, unstructured document data and the like, different semantic conversion and extraction rules can be formulated for the different types of data, complex and diverse data systems are converted into an element form of OWL, and the data contents expressing the same meaning are combined, mapped and the like on the basis, so that the field ontology is constructed and formed preliminarily.
In embodiments, the step of classifying the feature subset based on the algorithm and outputting the determination result further includes the steps of:
and acquiring a data point generation speed and a data flow length of the COPD disease data included in the feature subset, and generating a preset function by using the data point generation speed and the data flow length.
Different detection items of different health service organizations and different accuracy and granularity of the detection items not only affect the diagnosis of doctors, but also greatly affect the qualitative and treatment schemes of disease types, so that medical data of different levels need to be screened and cleaned. Considering that health medical information has the characteristics of time series data streams, we will mainly study the time-varying fractal dimension of the time series data streams, and the box counting method cannot divide the data space of the whole time series data streams and is insensitive to the time sequence of data, so that it is not suitable for calculating the fractal dimension of the time series data streams. This study will attempt to calculate the multi-granularity time-varying fractal dimension using a small spectrum method.
The medical health data has a degree of subjectivity of , such as the implementation of the COPD diagnostic criteria by physicians and the certainly incomplete by another physicians, if two physicians are asked to have the criteria of system for the definitive diagnosis of diabetics, three different answers may be obtained, so there is no absolute diagnosis scheme.
The main task of the cluster analysis is to identify important data information from a large amount of unknown data of the class, divide a sample data set into a plurality of clusters, so that the sample data set is similar to the inside of each cluster to the maximum extent, the sample data sets are different from each other to the maximum extent, and the cluster to which each sample belongs is determined, and valuable and understandable patterns hidden in the data set are found out from the sample data sets.
In the step of classifying the feature subset based on the th algorithm and outputting the judgment result, the method further comprises the following steps:
acquiring COPD patient clinical information, wherein each COPD patient clinical information comprises a number of sub-clusters (i, j), the number of sub-clusters for each patient satisfying the following formula:
wherein the sub-clusters (i, j) are numerical values respectively satisfying the interval of [0,1 ];
initializing the clinical information of the COPD patient, including the classification number k, the iteration number num of the fuzzy factor m and the maximum iteration number max _ num of the convergence threshold limit, and generating sample data;
calculating the distance between the sample data and the clustering center to calculate the membership degree;
and outputting the output sample data with the membership degree larger than a second preset value and covering the previous sample data.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (10)
- The system is characterized by comprising an acquisition module, a subset generation module, a calculation module and a monitoring device;the acquisition module: for obtaining COPD disease data in a database, the COPD disease data comprising COPD patient information and COPD patient clinical information;the subset generation module is used for acquiring th quantity of disease state features in COPD disease data and obtaining feature subsets through an MDF algorithm;and the calculation module classifies the feature subsets based on the th algorithm and outputs a judgment result.The monitoring device is characterized in that: the monitoring device is used for monitoring the physical signs of a patient in real time and comprises a lung monitoring unit and a nail monitoring unit.
- 2. Big data based COPD disease assisted diagnostic monitoring system according to claim 1,the system also comprises the following modules:a standard data acquisition module: acquiring HL7 standard data of each sub-database, wherein the HL7 standard data comprises at least two types of data;an classification processing module, which is used for performing semantic packaging on each HL7 standard data through a heterogeneous data semantic extraction framework, performing classification processing on a plurality of HL7 standard data with the same semantics to generate COPD disease data and storing the COPD disease data in a database.
- 3. Big data based COPD disease assisted diagnostic monitoring system according to claim 2,the HL7 standard data includes structured two-dimensional table data, semi-structured XML file data, unstructured images, documents, and data.
- 4. Big data based COPD disease assisted diagnostic monitoring system according to claim 3,the calculation module further comprises:a function generation unit: and acquiring a data point generation speed and a data flow length of the COPD disease data included in the feature subset, and generating a preset function by using the data point generation speed and the data flow length.
- 5. Big data based COPD disease assisted diagnostic monitoring system according to claim 4,the calculation module further comprises:acquiring COPD patient clinical information, wherein each COPD patient clinical information comprises a number of sub-clusters (i, j), the number of sub-clusters for each patient satisfying the following formula:
wherein, a plurality of sub-clusters (i, j) respectively satisfy [0, 1%]The number of intervals; i, j are class labels, i denotes the ith sample, μijRepresenting the membership degree of the sample i belonging to the j class; c represents a centroid;initializing the clinical information of the COPD patient, and generating sample data, wherein the clinical information of the COPD patient comprises a classification number k, a fuzzy factor m, an iteration number num, a convergence threshold limit and a maximum iteration number max _ num;calculating the distance between the sample data and the clustering center to calculate the membership degree;and outputting the sample data with the membership degree larger than the second preset value, and covering the previous sample data. - 6. The COPD auxiliary diagnosis monitoring system according to claim 1, wherein the lung monitoring unit comprises th monitoring block and a second monitoring block for monitoring the left lung, and a third monitoring block and a fourth monitoring block for monitoring the right lung, the th monitoring block is tightly attached to the chest corresponding to the left lung, the second monitoring block is tightly attached to the back corresponding to the left lung, the third monitoring block is tightly attached to the chest corresponding to the right lung, the fourth monitoring block is tightly attached to the back corresponding to the right lung, the nail monitoring unit comprises a nail oximeter and a th wireless information transmission module arranged in the nail oximeter, the th wireless information transmission module transmits the collected data of the nail oximeter to a hospital information receiver, and the data of the information receiver is uploaded to a database.
- 7. The COPD disease auxiliary diagnosis monitoring system based on big data according to claim 6, characterized in that the monitoring block, the second monitoring block, the third monitoring block and the fourth monitoring block are all arranged on the same annular belt, and the monitoring block, the second monitoring block, the third monitoring block and the fourth monitoring block are all adjustable in position, the annular belt is bound on the corresponding body of the lung and is provided with a detachable connection, and the connection is connected through a sticky buckle belt.
- 8. The big data-based COPD disease auxiliary diagnostic monitoring system according to claim 7, wherein the monitoring block, the second monitoring block, the third monitoring block and the fourth monitoring block are fixed on the inner side surface of the annular belt through pins, and the outer side surfaces of the monitoring block, the second monitoring block, the third monitoring block and the fourth monitoring block are provided with holes for the pins to pass through.
- 9. The system for auxiliary diagnosis and monitoring of COPD diseases based on big data according to claim 8, further comprising a mobile power source and an information collection module, wherein the information collection module is electrically connected with the mobile power source, the th monitoring block, the second monitoring block, the third monitoring block and the fourth monitoring block are electrically connected with the mobile power source and the information collection module respectively through wires, the information collection module is provided with a second wireless information transmission module, the second wireless information transmission module transmits the collected data of the information collection module to an information receiving place of a hospital, and the data of the information receiving place is uploaded to a database.
- 10. The big data-based COPD disease auxiliary diagnosis monitoring system according to claim 9, wherein for the person whose heart is located at the left, said monitoring block is provided with a plurality of sensors for monitoring respiratory rate, intensity, heart rate, abnormal breath sound, said second, third and fourth monitoring blocks are provided with a plurality of sensors for monitoring respiratory rate, intensity, abnormal breath sound, for the person whose heart is located at the right, said third monitoring block is provided with a plurality of sensors for monitoring respiratory rate, intensity, heart rate, abnormal breath sound, said , second and fourth monitoring blocks are provided with a plurality of sensors for monitoring respiratory rate, intensity, abnormal breath sound, and said ring belt is provided with heat dissipation holes.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911028122.0A CN110739075A (en) | 2019-10-28 | 2019-10-28 | COPD disease auxiliary diagnosis monitoring system based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911028122.0A CN110739075A (en) | 2019-10-28 | 2019-10-28 | COPD disease auxiliary diagnosis monitoring system based on big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110739075A true CN110739075A (en) | 2020-01-31 |
Family
ID=69271651
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911028122.0A Pending CN110739075A (en) | 2019-10-28 | 2019-10-28 | COPD disease auxiliary diagnosis monitoring system based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110739075A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111767332A (en) * | 2020-06-12 | 2020-10-13 | 上海森亿医疗科技有限公司 | Data integration method, system and terminal for heterogeneous data sources |
| CN113488126A (en) * | 2021-07-27 | 2021-10-08 | 心医国际数字医疗系统(大连)有限公司 | Information processing method, information processing device, electronic equipment and storage medium |
| CN113892909A (en) * | 2021-09-13 | 2022-01-07 | 吾征智能技术(北京)有限公司 | Intelligent chronic disease screening system based on cognitive state |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108597601A (en) * | 2018-04-20 | 2018-09-28 | 山东师范大学 | Diagnosis of chronic obstructive pulmonary disease auxiliary system based on support vector machines and method |
-
2019
- 2019-10-28 CN CN201911028122.0A patent/CN110739075A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108597601A (en) * | 2018-04-20 | 2018-09-28 | 山东师范大学 | Diagnosis of chronic obstructive pulmonary disease auxiliary system based on support vector machines and method |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111767332A (en) * | 2020-06-12 | 2020-10-13 | 上海森亿医疗科技有限公司 | Data integration method, system and terminal for heterogeneous data sources |
| CN111767332B (en) * | 2020-06-12 | 2021-07-30 | 上海森亿医疗科技有限公司 | Data integration method, system and terminal for heterogeneous data sources |
| CN113488126A (en) * | 2021-07-27 | 2021-10-08 | 心医国际数字医疗系统(大连)有限公司 | Information processing method, information processing device, electronic equipment and storage medium |
| CN113892909A (en) * | 2021-09-13 | 2022-01-07 | 吾征智能技术(北京)有限公司 | Intelligent chronic disease screening system based on cognitive state |
| CN113892909B (en) * | 2021-09-13 | 2023-06-06 | 吾征智能技术(北京)有限公司 | Intelligent chronic disease screening system based on cognitive state |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| LaFreniere et al. | Using machine learning to predict hypertension from a clinical dataset | |
| CN110459328B (en) | Clinical monitoring equipment | |
| US20200303072A1 (en) | Method and system for supporting medical decision making | |
| Bozkurt et al. | Using automatically extracted information from mammography reports for decision-support | |
| CN110739075A (en) | COPD disease auxiliary diagnosis monitoring system based on big data | |
| CN109785927A (en) | Clinical document structuring processing method based on internet integration medical platform | |
| CN108511056A (en) | Therapeutic scheme based on patients with cerebral apoplexy similarity analysis recommends method and system | |
| Chowriappa et al. | Introduction to machine learning in healthcare informatics | |
| CN110085314A (en) | Intelligent analysis method, system and the equipment of medical test data | |
| Krasteva et al. | Application of dense neural networks for detection of atrial fibrillation and ranking of augmented ECG feature set | |
| CN107767960A (en) | Data processing method, device and the electronic equipment of clinical detection project | |
| Al-Mualemi et al. | A deep learning-based sepsis estimation scheme | |
| Kokol et al. | Artificial intelligence and pediatrics: A synthetic mini review | |
| Refaee et al. | A computing system that integrates deep learning and the internet of things for effective disease diagnosis in smart health care systems | |
| Zalewski et al. | Estimating patient's health state using latent structure inferred from clinical time series and text | |
| CN110010250B (en) | Cardiovascular disease patient weakness grading method based on data mining technology | |
| Tong et al. | Locating abnormal heartbeats in ECG segments based on deep weakly supervised learning | |
| Ashu et al. | A novel approach of telemedicine for managing fetal condition based on machine learning technology from IoT-based wearable medical device | |
| Chen et al. | Classification and Progression Based on CFS‐GA and C5. 0 Boost Decision Tree of TCM Zheng in Chronic Hepatitis B | |
| Kokkinaki et al. | Searching biosignal databases by content and context: Research Oriented Integration System for ECG Signals (ROISES) | |
| Basha et al. | Deep learning neural network (DLNN)-based classification and optimization algorithm for organ inflammation disease diagnosis | |
| CN116030965A (en) | Processing method for whole-course diagnosis and treatment data covering hospital-outside special diseases | |
| Tasdelen et al. | Artificial Intelligence Research on COVID-19 Pandemic: A Bibliometric Analysis | |
| Chaithra et al. | A Review of Machine Learning Techniques Used in the Prediction of Heart Disease. | |
| Hooda et al. | An Ontology driven model for detection and classification of cardiac arrhythmias using ECG 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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200131 |