CN113270196B - Cerebral apoplexy recurrence risk perception and behavior decision model construction system and method - Google Patents

Cerebral apoplexy recurrence risk perception and behavior decision model construction system and method Download PDF

Info

Publication number
CN113270196B
CN113270196B CN202110573782.8A CN202110573782A CN113270196B CN 113270196 B CN113270196 B CN 113270196B CN 202110573782 A CN202110573782 A CN 202110573782A CN 113270196 B CN113270196 B CN 113270196B
Authority
CN
China
Prior art keywords
layer
cerebral apoplexy
cloud
patient
edge
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202110573782.8A
Other languages
Chinese (zh)
Other versions
CN113270196A (en
Inventor
张振香
林蓓蕾
刘雪婷
郭娟娟
禹瑞
李冰华
王玲玲
郭二锋
张娜
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.)
Zhengzhou University
Original Assignee
Zhengzhou University
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 Zhengzhou University filed Critical Zhengzhou University
Priority to CN202110573782.8A priority Critical patent/CN113270196B/en
Publication of CN113270196A publication Critical patent/CN113270196A/en
Application granted granted Critical
Publication of CN113270196B publication Critical patent/CN113270196B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • 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
    • G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B3/00—Apparatus for testing the eyes; Instruments for examining the eyes
    • A61B3/10—Objective types, i.e. instruments for examining the eyes independent of the patients' perceptions or reactions
    • A61B3/12—Objective types, i.e. instruments for examining the eyes independent of the patients' perceptions or reactions for looking at the eye fundus, e.g. ophthalmoscopes
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B3/00—Apparatus for testing the eyes; Instruments for examining the eyes
    • A61B3/10—Objective types, i.e. instruments for examining the eyes independent of the patients' perceptions or reactions
    • A61B3/14—Arrangements specially adapted for eye photography
    • 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
    • A61B5/02007—Evaluating blood vessel condition, e.g. elasticity, compliance
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/22—Ergometry; Measuring muscular strength or the force of a muscular blow
    • A61B5/224—Measuring muscular strength
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/48—Other medical applications
    • A61B5/4803—Speech analysis specially adapted for diagnostic purposes
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7271—Specific aspects of physiological measurement analysis
    • A61B5/7282—Event detection, e.g. detecting unique waveforms indicative of a medical condition
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0012—Biomedical image inspection
    • 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
    • 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30004—Biomedical image processing
    • G06T2207/30041—Eye; Retina; Ophthalmic
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
    • Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation

Abstract

The invention provides a cerebral apoplexy recurrence risk perception and behavior decision-making model construction system and method. The risk perception system comprises a data sensing layer, an edge analysis layer, a cloud early warning layer and a risk assessment layer; the data sensing layer sends physiological measurement parameters to the edge analysis layer; the edge analysis layer performs edge calculation analysis; when the analysis result meets a first preset condition, a feedback signal is sent to the data sensing layer, and the edge calculation analysis result is stored in a grouping mode; the cloud early-warning layer comprises a plurality of cloud early-warning databases of different categories; when the analysis result meets a second preset condition, the cloud early-warning layer performs cloud query calculation in a cloud early-warning database based on the edge calculation analysis result stored in a grouping mode; and the risk assessment layer receives cloud query calculation results of the cloud early warning layer to give a risk assessment value. The invention also discloses a recurrence risk decision-making system and a recurrence risk decision-making method. The technical scheme of the invention can effectively sense the recurrence risk of cerebral apoplexy.

Description

Cerebral apoplexy recurrence risk perception and behavior decision model construction system and method
Technical Field
The invention belongs to the technical field of cerebral apoplexy diagnosis, and particularly relates to a cerebral apoplexy recurrence risk sensing system based on cloud computing, a cerebral apoplexy recurrence risk decision-making system, a cerebral apoplexy recurrence risk sensing and decision-making method based on cloud computing and a computer program instruction for realizing the method.
Background
Cerebral stroke is a group of cerebrovascular diseases characterized by acute brain tissue damage due to sudden rupture of cerebral vessels or blockage of blood vessels, which includes hemorrhagic and ischemic strokes. Cerebral apoplexy has the characteristics of high morbidity, high mortality and high disability rate. Investigation shows that the urban and rural total cerebral apoplexy is the first cause of death in China at present and becomes the primary cause of disability of adults in China.
The onset of cerebral stroke is often accompanied by motor, linguistic and perceptual disturbances of the patient. Rehabilitation therapy of cerebral apoplexy patients is the most effective method for reducing the disability rate of cerebral apoplexy and can reduce the influence of dyskinesia on normal life of patients. In clinic, in order for rehabilitation therapists to effectively evaluate the state of the motor function of a patient and reasonably make a rehabilitation treatment plan of the patient, the patient must be monitored by systematic rehabilitation treatment.
The Chinese patent application with the application number of CN202010805622.7 provides a cerebral apoplexy patient early warning system, which comprises: a unit for generating a patient information uploading command by the early warning center server, wherein the patient information uploading command comprises a destination terminal identity identifier; a unit for transmitting the generated patient information upload command to a base station by the pre-warning center server, wherein the base station communicates with the first relay node; means for, if it is determined that the remaining storage space of the buffer for the second relay node is still less than the buffer remaining space lower limit, not sending any message regarding congestion to the base station by the first relay node; and if the remaining storage space of the buffer for the second relay node is determined to be greater than the lower limit of the remaining storage space of the buffer, transmitting, by the first relay node, a first transmission channel congestion relief report to the base station, wherein the first transmission channel congestion relief report includes an identity identifier of the first mobile terminal, a congestion relief indication, and the remaining storage space of the buffer for the second relay node.
However, no relevant technical solution is seen in the prior art for the perception and decision of risk of recurrence of cerebral stroke.
Disclosure of Invention
In order to solve the technical problems, the invention provides a cerebral apoplexy recurrence risk perception and behavior decision-making model construction system and method. The risk perception system comprises a data sensing layer, an edge analysis layer, a cloud early warning layer and a risk assessment layer; the data sensing layer sends physiological measurement parameters to the edge analysis layer; the edge analysis layer performs edge calculation analysis; when the analysis result meets a first preset condition, a feedback signal is sent to the data sensing layer, and the edge calculation analysis result is stored in a grouping mode; the cloud early-warning layer comprises a plurality of cloud early-warning databases of different categories; when the analysis result meets a second preset condition, the cloud early-warning layer performs cloud query calculation in a cloud early-warning database based on the edge calculation analysis result stored in a grouping mode; and the risk assessment layer receives cloud query calculation results of the cloud early warning layer to give a risk assessment value.
Specifically, the technical scheme of the invention comprises five aspects, and is specifically introduced as follows:
in a first aspect, the invention provides a cerebral apoplexy recurrence risk perception system based on cloud computing, wherein the risk perception system comprises a data sensing layer, an edge analysis layer, a cloud early warning layer and a risk assessment layer;
the data sensing layer comprises a plurality of intelligent sensors and is used for performing multi-step sensing detection on a patient after cerebral apoplexy to obtain at least one physiological measurement parameter;
the edge analysis layer comprises at least one edge calculation unit;
after the data sensing layer detects physiological measurement parameters, the physiological measurement parameters are sent to the edge analysis layer;
the edge analysis layer performs edge calculation analysis on the physiological measurement parameters;
when the edge calculation analysis result meets a first preset condition, a feedback signal is sent to the data sensing layer, and the edge calculation analysis result is stored in a grouping mode;
the cloud early-warning layer comprises a plurality of cloud early-warning databases of different categories;
when the edge calculation analysis results stored in the group meet a second preset condition, the cloud early-warning layer executes cloud query calculation in the cloud early-warning databases of different categories based on the edge calculation analysis results stored in the group;
the risk assessment layer receives cloud query calculation results obtained by the cloud early-warning layer from the cloud early-warning database of the corresponding category, and gives a risk assessment value according to the cloud query calculation results, wherein the risk assessment value is used for representing recurrence risk of the patient after cerebral apoplexy operation.
In a second aspect of the invention, a cerebral apoplexy recurrence risk decision-making system is provided, the recurrence risk decision-making system includes a first image annotation model, a second speech regression analysis model and a third limb test model;
the recurrence risk decision-making system comprises a plurality of intelligent sensors, wherein the plurality of intelligent sensors comprise a fundus image sensor, a voice sensor and a muscle force sensor;
the fundus image sensor acquires a plurality of fundus images of the patient after cerebral apoplexy operation to obtain a fundus image sequence;
the voice sensor is used for performing voice test on the patient after cerebral apoplexy operation to obtain a voice test sequence;
the muscle force sensor is used for acquiring the limb muscle force of the patient after cerebral apoplexy operation and acquiring a limb muscle force sequence;
inputting the fundus image sequence into the first image annotation model, inputting the voice test sequence into the second voice regression analysis model, and inputting the limb muscle strength sequence into the third limb test model;
and obtaining a cerebral apoplexy recurrence risk decision result based on the output result of the first image annotation model, the second voice regression analysis model and/or the third limb test model.
In a third aspect of the present invention, there is further provided a cerebral apoplexy recurrence risk sensing and deciding method based on cloud computing, the method comprising the steps of:
s901: setting a risk perception period;
s903: when the risk perception period is reached, acquiring a fundus image sequence of a patient after cerebral apoplexy operation;
s905: determining the fundus abnormality degree of the patient after cerebral apoplexy based on the fundus image sequence;
s907: judging whether the fundus abnormality degree meets a fourth preset condition, if so, entering the next step, and if not; increasing the risk perception period, and returning to the step S903;
s909: acquiring a voice test sequence of the patient after cerebral apoplexy operation;
s911: determining the abnormal degree of the voice expression of the patient after the cerebral apoplexy operation based on the voice test sequence;
s913: judging whether the abnormal degree of the voice expression meets a fifth preset condition, if so, entering a risk decision step, wherein the risk decision step is executed by the cerebral apoplexy recurrence risk decision system in the second aspect.
The third aspect of the cerebral apoplexy recurrence risk decision-making system based on the second aspect is specifically implemented as follows:
s101: setting a risk perception period;
s103: when the risk perception period is reached, acquiring a fundus image sequence of a patient after cerebral apoplexy operation;
s105: determining the fundus abnormality degree of the patient after cerebral apoplexy based on the fundus image sequence;
s107: judging whether the fundus abnormality degree meets a sixth preset condition, if so, entering the next step, and if not; increasing the risk perception period, and returning to the step S103;
s109: acquiring a limb muscle strength sequence of the patient after cerebral apoplexy;
s111: determining the abnormal degree of the limb muscle strength of the patient after cerebral apoplexy based on the limb muscle strength sequence;
s113: judging whether the abnormal degree of the limb muscle strength meets a seventh preset condition, if so, entering the next step; otherwise, the risk perception period is reduced, and the step S103 is returned;
s115: acquiring a voice test sequence of the patient after cerebral apoplexy operation;
s117: determining the abnormal degree of the voice expression of the patient after the cerebral apoplexy operation based on the voice test sequence;
s119: judging whether the abnormal degree of the voice expression meets an eighth preset condition, if so, entering a risk decision step, wherein the risk decision step is executed by the cerebral apoplexy recurrence risk decision system in the second aspect.
The above-described method of the present invention may be automatically performed by program instructions through a terminal device including a processor and a memory, particularly an image processing terminal device, including a mobile terminal, a desktop terminal, a server cluster, etc., and thus, in a fifth aspect of the present invention, there is also provided a computer-readable storage medium having stored thereon computer program instructions; the program instructions are executed by an image terminal processing device comprising a processor and a memory for implementing all or part of the steps of the method according to the third or fourth aspect.
It should be noted that, in the different implementation manners of the above five aspects, the "preset conditions" defined by the "first" to "eighth" appearing do not necessarily represent a difference or no difference between the respective "preset conditions". The various "preset conditions" used in the judgment conditions in the above-described different technical solutions of the present invention may be reasonably set by those skilled in the art according to actual situations, and the present invention is not particularly limited thereto. In the following description of the specific embodiments, the relevant embodiments may also provide specific limitation to some "preset conditions", but these are only one or several examples of many reasonable arrangements, and are not intended to be exhaustive or to limit the actual protection scope of the present invention, and any "preset conditions" that meet the actual conditions should fall within the protection scope of the present invention.
Further advantages of the invention will be further elaborated in the description section of the embodiments in connection with the drawings.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed 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 other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a hierarchical diagram of a cloud computing based risk perception system for stroke recurrence in accordance with one embodiment of the present invention;
FIG. 2 is a schematic diagram of a data store for the system of FIG. 1;
FIG. 3 is a schematic diagram of a packet ring queue used by the system of FIG. 1;
FIG. 4 is a hierarchical diagram of a stroke recurrence risk decision-making system according to one embodiment of the present invention;
FIG. 5 is a main flow chart of a cerebral apoplexy recurrence risk sensing and deciding method based on cloud computing according to an embodiment of the present invention;
fig. 6 is a main flow chart of a cerebral apoplexy recurrence risk sensing and deciding method based on cloud computing according to another embodiment of the present invention.
Detailed Description
The invention will be further described with reference to the drawings and detailed description.
Referring to fig. 1, a hierarchical structure diagram of a cerebral apoplexy recurrence risk perception system based on cloud computing according to an embodiment of the present invention is shown.
In fig. 1, the risk perception system includes a data sensing layer, an edge analysis layer, a cloud early warning layer, and a risk assessment layer;
more specifically, the data sensing layer includes a plurality of intelligent sensors for performing a multi-step sensing of a post-stroke patient to obtain at least one physiological measurement parameter.
The edge analysis layer comprises at least one edge calculation unit;
after the data sensing layer detects physiological measurement parameters, the physiological measurement parameters are sent to the edge analysis layer;
the edge analysis layer performs edge calculation analysis on the physiological measurement parameters;
when the edge calculation analysis result meets a first preset condition, a feedback signal is sent to the data sensing layer, and the edge calculation analysis result is stored in a grouping mode; the cloud early-warning layer comprises a plurality of cloud early-warning databases of different categories;
when the edge calculation analysis results stored in the group meet a second preset condition, the cloud early-warning layer executes cloud query calculation in the cloud early-warning databases of different categories based on the edge calculation analysis results stored in the group;
the risk assessment layer receives cloud query calculation results obtained by the cloud early-warning layer from the cloud early-warning database of the corresponding category, and gives a risk assessment value according to the cloud query calculation results, wherein the risk assessment value is used for representing recurrence risk of the patient after cerebral apoplexy operation.
The cloud early-warning database of the cloud early-warning layer comprises a plurality of categories, and each category corresponds to different physiological measurement parameters; for example, an early warning database is used for early warning gait abnormal patterns; the other type of early warning database performs early warning on the abnormal muscle strength mode of the limb; the other type of early warning database is used for early warning the abnormal degree of the eye bottom image, and the like;
it should be noted that the above is only an illustrative example and is not exhaustive. And not as a specific limitation of the present invention, the key point is that there are multiple categories of pre-warning databases.
See fig. 2, based on fig. 1.
The plurality of intelligent sensors comprise a fundus image sensor, a voice sensor and a muscle force sensor;
the fundus image sensor acquires a plurality of fundus images of the patient after cerebral apoplexy;
the voice sensor is used for performing voice test on the patient after cerebral apoplexy operation;
the muscle force sensor is used for acquiring limb muscle force of the patient after cerebral apoplexy operation;
the physiological measurement parameters include a fundus image sequence, a voice test sequence, and a limb muscle strength value sequence.
As a salient improvement of the present invention, embodiments of the present invention use a fundus image sensor to acquire multiple fundus images of a post-stroke patient for risk determination.
The fundus image sensor here may be a fundus camera.
The pupil of a person is small, the luminous flux of light irradiated into the pupil is small, the pupil automatically contracts after encountering strong light, and the luminous flux reaching the fundus is smaller, so that a professional fundus camera is needed to see the fundus in a larger range. The fundus camera is based on a fundus photography system based on optical imaging technology, illuminates the retina with white light LED illumination, and images fundus images on a sensor, thereby presenting the acquired pictures on a display screen.
The retina and the optic nerve are used as the direct extension of the metabrain, the fundus micro-blood vessel with high homology with the central nervous system is the only micro-circulation blood vessel which can be observed on the living body of the human body, and a reliable and easy observation window is provided for researching the central nervous system diseases. Since the 80 s of the last century, fundus photography technology began to be applied to explore the correlation of fundus lesions with cerebral stroke and showed unique advantages for studying cerebral stroke pathogenesis, but no specific scheme for cerebral stroke recurrence prediction and decision was seen.
As a more specific introduction, the edge analysis layer performs edge calculation analysis on the physiological measurement parameters, specifically including:
the data sensing layer firstly starts the fundus image sensor to obtain a plurality of fundus images of the patient after cerebral apoplexy operation, and sends the fundus images to a plurality of edge computing units;
each edge calculation unit performs edge calculation analysis on the plurality of fundus images to obtain fundus abnormality degrees of the patient after cerebral apoplexy;
and when the fundus abnormality degree is higher than a first preset level, sending a feedback signal to the data sensing layer, wherein the feedback signal is used for prompting the data sensing layer to start the voice sensor and/or the muscle force sensor.
As an example, the edge calculation unit performs an edge calculation analysis for the plurality of fundus images, the analysis content including: widespread and focal arteriolar constriction, arteriovenous intersection syndrome, arteriolar copper wire signs, arteriovenous tumors, cotton-wool spots, hard exudation, optic disk edema and the like;
the predetermined level may be a level 0-3, for example obtained using the Wong-Mitchel fundus fractionation method.
As another aspect, with continued reference to fig. 2, the edge analysis layer performs an edge calculation analysis on the physiological measurement parameters, specifically including:
the edge analysis layer performs edge calculation analysis on the voice test sequence acquired by the voice sensor of the data sensing layer to obtain the abnormal voice expression degree of the patient after cerebral apoplexy;
and when the voice expression abnormality degree is higher than a first preset level, storing the edge calculation analysis result group.
As an example, the first predetermined level is used to characterize the degree of difference of the speech test sequence from the standard speech sequence.
As another modification of the present invention, reference is next made to fig. 3.
The step of storing the edge calculation analysis results in groups specifically comprises the following steps:
storing the edge calculation analysis result by adopting a grouping annular queue;
the grouping ring queue comprises a plurality of storage blocks, wherein each storage block comprises a first storage space, a second storage space and a third storage space;
the first storage space is used for storing the fundus abnormality degree of the patient after cerebral apoplexy;
the second storage space is used for storing the abnormal voice expression degree of the patient after cerebral apoplexy; the third storage space is used for storing the abnormal degree of limb muscle strength of the patient after cerebral apoplexy.
The edge calculation analysis result stored in the grouping meets a second preset condition, and specifically comprises the following steps:
the grouping annular queue is provided with a storage space with fundus abnormality degree, voice expression abnormality degree and limb muscle strength abnormality degree which are all larger than a second preset level.
Obviously, when the technical scheme of the invention is used for relapse risk perception, the degree values of different abnormal parameters are required to be considered, and the abnormal sequence of the different parameters is also required to be considered, so that the speed of data reading and judging can be increased by adopting the implementation mode of the grouping annular queue, and meanwhile, the storage is updated and updated in a partition mode, so that the waste of storage space is avoided.
Referring next to fig. 4, fig. 4 is a hierarchical diagram of a stroke recurrence risk decision-making system according to an embodiment of the present invention.
In fig. 4, the recurrent risk decision system includes a first image annotation model, a second phonetic regression analysis model, and a third limb test model;
the recurrence risk decision-making system comprises a plurality of intelligent sensors, wherein the plurality of intelligent sensors comprise a fundus image sensor, a voice sensor and a muscle force sensor;
the fundus image sensor acquires a plurality of fundus images of the patient after cerebral apoplexy operation to obtain a fundus image sequence;
the voice sensor is used for performing voice test on the patient after cerebral apoplexy operation to obtain a voice test sequence;
the muscle force sensor is used for acquiring the limb muscle force of the patient after cerebral apoplexy operation and acquiring a limb muscle force sequence;
inputting the fundus image sequence into the first image annotation model, inputting the voice test sequence into the second voice regression analysis model, and inputting the limb muscle strength sequence into the third limb test model;
and obtaining a cerebral apoplexy recurrence risk decision result based on the output result of the first image annotation model, the second voice regression analysis model and/or the third limb test model.
More specifically, in the above-described judgment process,
firstly, inputting the fundus image sequence into the first image annotation model to obtain a first output result; if the first output result meets a third preset condition, inputting the voice test sequence into the second voice regression analysis model;
or alternatively, the process may be performed,
and if the first output result meets a third preset condition, inputting the limb muscle strength sequence into the third limb test model.
Fig. 5 and 6 show two different embodiments of a cerebral stroke recurrence risk perception and decision method based on cloud computing, respectively.
In fig. 5, the method includes steps S901 to S913, and the specific implementation manner of each step is as follows:
s901: setting a risk perception period;
s903: when the risk perception period is reached, acquiring a fundus image sequence of a patient after cerebral apoplexy operation;
s905: determining the fundus abnormality degree of the patient after cerebral apoplexy based on the fundus image sequence;
s907: judging whether the fundus abnormality degree meets a fourth preset condition, if so, entering the next step, and if not; increasing the risk perception period, and returning to the step S903;
s909: acquiring a voice test sequence of the patient after cerebral apoplexy operation;
s911: determining the abnormal degree of the voice expression of the patient after the cerebral apoplexy operation based on the voice test sequence;
s913: judging whether the abnormal degree of the voice expression meets a fifth preset condition, if so, entering a risk decision step, wherein the risk decision step is executed by a cerebral apoplexy recurrence risk decision system shown in fig. 4.
In fig. 6, the method includes steps S101-S119, and each step is specifically implemented as follows:
s101: setting a risk perception period;
s103: when the risk perception period is reached, acquiring a fundus image sequence of a patient after cerebral apoplexy operation;
s105: determining the fundus abnormality degree of the patient after cerebral apoplexy based on the fundus image sequence;
s107: judging whether the fundus abnormality degree meets a sixth preset condition, if so, entering the next step, and if not; increasing the risk perception period, and returning to the step S103;
s109: acquiring a limb muscle strength sequence of the patient after cerebral apoplexy;
s111: determining the abnormal degree of the limb muscle strength of the patient after cerebral apoplexy based on the limb muscle strength sequence;
s113: judging whether the abnormal degree of the limb muscle strength meets a seventh preset condition, if so, entering the next step; otherwise, the risk perception period is reduced, and the step S103 is returned;
s115: acquiring a voice test sequence of the patient after cerebral apoplexy operation;
s117: determining the abnormal degree of the voice expression of the patient after the cerebral apoplexy operation based on the voice test sequence;
s119: judging whether the abnormal degree of the voice expression meets an eighth preset condition, if so, entering a risk decision step, wherein the risk decision step is executed by the cerebral apoplexy recurrence risk decision system according to any one of claims 7-8.
The above method of the present invention may be automatically executed by program instructions through terminal devices including processors and memories, particularly image processing terminal devices, including mobile terminals, desktop terminals, servers, server clusters, and the like. Thus, in further embodiments, there is also provided a computer readable storage medium having stored thereon computer program instructions; the program instructions are executed by an image terminal processing device comprising a processor and a memory for implementing all or part of the steps of the method described in fig. 5 or fig. 6.
It should be noted that, the related embodiments may also give specific limitation to a part of "preset conditions", but this is merely one or several examples of many reasonable arrangements, and is not intended to be an exhaustive limitation, and any "preset conditions" that meet the actual situations shall fall within the protection scope of the present invention.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.

Claims (4)

1. The cerebral apoplexy recurrence risk perception system based on cloud computing comprises a data sensing layer, an edge analysis layer, a cloud early warning layer and a risk assessment layer;
the method is characterized in that:
the data sensing layer comprises a plurality of intelligent sensors and is used for performing multi-step sensing detection on a patient after cerebral apoplexy to obtain at least one physiological measurement parameter;
the plurality of intelligent sensors comprise a fundus image sensor, a voice sensor and a muscle force sensor;
the physiological measurement parameters comprise a fundus image sequence, a voice test sequence and a limb muscle strength value sequence;
the edge analysis layer comprises at least one edge calculation unit;
after the data sensing layer detects physiological measurement parameters, the physiological measurement parameters are sent to the edge analysis layer;
the edge analysis layer performs edge calculation analysis on the physiological measurement parameters, and specifically includes:
the edge analysis layer performs edge calculation analysis on the voice test sequence acquired by the voice sensor of the data sensing layer to obtain the abnormal voice expression degree of the patient after cerebral apoplexy;
when the voice expression abnormality degree is higher than a first preset level, storing edge calculation analysis results in a grouping mode;
the step of storing the edge calculation analysis results in groups specifically comprises the following steps:
storing the edge calculation analysis result by adopting a grouping annular queue;
the grouping ring queue comprises a plurality of storage blocks, wherein each storage block comprises a first storage space, a second storage space and a third storage space;
the first storage space is used for storing the fundus abnormality degree of the patient after cerebral apoplexy;
the second storage space is used for storing the abnormal voice expression degree of the patient after cerebral apoplexy;
the third storage space is used for storing the abnormal degree of limb muscle strength of the patient after cerebral apoplexy;
the cloud early-warning layer comprises a plurality of cloud early-warning databases of different categories;
when the edge calculation analysis results stored in the group meet a second preset condition, the cloud early-warning layer executes cloud query calculation in the cloud early-warning databases of different categories based on the edge calculation analysis results stored in the group;
the risk assessment layer receives cloud query calculation results obtained by the cloud early-warning layer from the cloud early-warning database of the corresponding category, and gives a risk assessment value according to the cloud query calculation results, wherein the risk assessment value is used for representing recurrence risk of the patient after cerebral apoplexy operation.
2. The cloud computing-based cerebral stroke recurrence risk perception system as claimed in claim 1, wherein:
the fundus image sensor acquires a plurality of fundus images of the patient after cerebral apoplexy;
the voice sensor is used for performing voice test on the patient after cerebral apoplexy operation;
the muscle force sensor is used for acquiring the limb muscle force of the patient after cerebral apoplexy operation.
3. The cloud computing-based cerebral stroke recurrence risk perception system as claimed in claim 2, wherein:
the edge analysis layer performs edge calculation analysis on the physiological measurement parameters, and further includes:
the data sensing layer firstly starts the fundus image sensor to obtain a plurality of fundus images of the patient after cerebral apoplexy operation, and sends the fundus images to a plurality of edge computing units;
each edge calculation unit performs edge calculation analysis on the plurality of fundus images to obtain fundus abnormality degrees of the patient after cerebral apoplexy;
and when the fundus abnormality degree is higher than a first preset level, sending a feedback signal to the data sensing layer, wherein the feedback signal is used for prompting the data sensing layer to start the voice sensor and/or the muscle force sensor.
4. The cloud computing-based cerebral stroke recurrence risk perception system as claimed in claim 1, wherein:
the edge calculation analysis result stored in the grouping meets a second preset condition, and specifically comprises the following steps:
the grouping annular queue is provided with a storage space with fundus abnormality degree, voice expression abnormality degree and limb muscle strength abnormality degree which are all larger than a second preset level.
CN202110573782.8A 2021-05-25 2021-05-25 Cerebral apoplexy recurrence risk perception and behavior decision model construction system and method Active CN113270196B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110573782.8A CN113270196B (en) 2021-05-25 2021-05-25 Cerebral apoplexy recurrence risk perception and behavior decision model construction system and method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110573782.8A CN113270196B (en) 2021-05-25 2021-05-25 Cerebral apoplexy recurrence risk perception and behavior decision model construction system and method

Publications (2)

Publication Number Publication Date
CN113270196A CN113270196A (en) 2021-08-17
CN113270196B true CN113270196B (en) 2023-07-14

Family

ID=77232850

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110573782.8A Active CN113270196B (en) 2021-05-25 2021-05-25 Cerebral apoplexy recurrence risk perception and behavior decision model construction system and method

Country Status (1)

Country Link
CN (1) CN113270196B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116230212A (en) * 2023-04-04 2023-06-06 曜立科技(北京)有限公司 Diagnosis decision system for postoperative cerebral apoplexy review based on data processing
CN117612713A (en) * 2023-10-08 2024-02-27 郑州大学 Intelligent analysis system and method for cerebral apoplexy behavior based on cloud computing

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110415824A (en) * 2019-07-30 2019-11-05 广东工业大学 The risk assessment device and equipment of cerebral apoplexy wind
CN112489793A (en) * 2020-12-16 2021-03-12 郑州航空工业管理学院 Early warning system for stroke risk patient

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110738984B (en) * 2019-05-13 2020-12-11 苏州闪驰数控***集成有限公司 Artificial intelligence CNN, LSTM neural network speech recognition system
EP3758026A1 (en) * 2019-06-28 2020-12-30 Hill-Rom Services, Inc. Patient risk assessment based on data from multiple sources in a healthcare facility
CN111312398B (en) * 2019-12-17 2022-03-01 南通市第二人民医院 Method and device for establishing cerebral apoplexy recurrence prediction model
CN111430029B (en) * 2020-03-24 2021-04-16 浙江达美生物技术有限公司 Multi-dimensional stroke prevention screening method based on artificial intelligence
CN112183228B (en) * 2020-09-09 2022-07-08 青岛联合创智科技有限公司 Intelligent community endowment service system and method
CN112331349B (en) * 2020-11-03 2023-04-07 四川大学华西医院 Cerebral apoplexy relapse monitoring system

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110415824A (en) * 2019-07-30 2019-11-05 广东工业大学 The risk assessment device and equipment of cerebral apoplexy wind
CN112489793A (en) * 2020-12-16 2021-03-12 郑州航空工业管理学院 Early warning system for stroke risk patient

Also Published As

Publication number Publication date
CN113270196A (en) 2021-08-17

Similar Documents

Publication Publication Date Title
CN110516161B (en) Recommendation method and device
CN113270196B (en) Cerebral apoplexy recurrence risk perception and behavior decision model construction system and method
US20220270738A1 (en) Computerized systems and methods for military operations where sensitive information is securely transmitted to assigned users based on ai/ml determinations of user capabilities
US9747902B2 (en) Method and system for assisting patients
CN110024038A (en) The system and method that synthesis interacts are carried out with user and device
CN109545394B (en) Interrogation method and device
JP2015508296A (en) Brain function improvement system for dementia prevention and its operation method
KR101634619B1 (en) Dementia cognition evaluating device and apparatus performing the same
CN110753514A (en) Sleep monitoring based on implicit acquisition for computer interaction
CN110580953A (en) Disease diagnosis system and method adopting artificial intelligence
Boucart et al. Recognition of facial emotion in low vision: a flexible usage of facial features
CN110610754A (en) Immersive wearable diagnosis and treatment device
CN112185564B (en) Ophthalmic disease prediction method based on structured electronic medical record and storage device
CN113180647B (en) Behavior acquisition system and method for AI limb function rehabilitation pre-intervention
CN110415812A (en) Intelligent cerebral apoplexy assisting in diagnosis and treatment robot system based on artificial intelligence and Internet technology
CN112233309B (en) Emergency doctor quick calling method and device
Sarafidis et al. Why a clinical decision support system is needed for tinnitus?
CN115497621A (en) Old person cognitive status evaluation system
Deng et al. A machine Learning-Based monitoring system for attention and stress detection for children with autism spectrum disorders
CN111340778A (en) Glaucoma image processing method and equipment
Cordero-Mendieta et al. Support tool for presumptive diagnosis of Glaucoma using fundus image processing and artificial intelligence implementation
KR20150010430A (en) Improvement-effect of brain-function system for dementia prevention and method thereof
CN117373658B (en) Data processing-based auxiliary diagnosis and treatment system and method for depression
KR102612333B1 (en) Method for providing customized content to a specific user by referring to user metadata and hormone data in saliva and computing device using the same
KR102375580B1 (en) smart clothing type system for self-determination of mild cognitive impairment and prevention training

Legal Events

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