CN107595243A - A kind of illness appraisal procedure and terminal device - Google Patents
A kind of illness appraisal procedure and terminal device Download PDFInfo
- Publication number
- CN107595243A CN107595243A CN201710632865.3A CN201710632865A CN107595243A CN 107595243 A CN107595243 A CN 107595243A CN 201710632865 A CN201710632865 A CN 201710632865A CN 107595243 A CN107595243 A CN 107595243A
- Authority
- CN
- China
- Prior art keywords
- data
- physiological data
- assessment result
- ecg
- terminal device
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Abstract
The embodiments of the invention provide a kind of illness appraisal procedure and terminal device, wherein, methods described includes：The original physiologic data of user are obtained, the original physiologic data are used to assess sleep apnea syndrome；The original physiologic data are handled, obtain desired physiological data；Input using the desired physiological data as deep learning model, is calculated illness assessment result, and the deep learning model is to train what is obtained according to the history physiological data of user.Using the present invention, user's physiological data of various dimensions can be utilized to calculate the illness assessment result of user in real time or periodically, to help doctor to provide effective reference information, help to give treatment in time.
Description
Technical field
The present invention relates to medical science and information intelligent field, more particularly to a kind of illness appraisal procedure and terminal device.
Background technology
Sleep apnea low-ventilatory syndrome (sign) is the not very bright and clear symptom of a kind of cause of disease at present and pathogenesis, is faced
Bed performance mainly has：Nighttime sleep snoring is with symptoms such as apnea and daytime drowsiness.Because apnea can cause
The hypercapnia and hypoxia at night of recurrent exerbation, therefore the complication such as coronary heart disease, diabetes, cranial vascular disease can be caused, sternly
Severe one can even cause night to die suddenly.How Accurate Diagnosis Sleep Apnea-hypopnea Syndrome, be night medical science weight
Want a ring.
Therefore a kind of reasonable, accurate evaluation scheme need to be proposed.
The content of the invention
Technical problem to be solved of the embodiment of the present invention is, there is provided a kind of illness appraisal procedure and terminal device, can
The illness assessment result of user is calculated in real time or periodically using user's physiological data of various dimensions, in time, reliably to help
Help doctor to give treatment to user, lift practicality.
In a first aspect, the embodiments of the invention provide a kind of illness appraisal procedure, methods described includes：
The original physiologic data of user are obtained, the original physiologic data are used to assess sleep apnea syndrome；
The original physiologic data are handled, obtain desired physiological data；
Input using the desired physiological data as deep learning model, is calculated illness assessment result, the depth
Degree learning model is to train what is obtained according to the history physiological data of user.
In some possible embodiments, the original physiologic data include dynamic physiology data, static physiological data with
And electrocardio ECG data, described that the original physiologic data are handled, obtaining desired physiological data includes：
The original physiologic data are classified, obtain the dynamic physiology data, the static physiological data and
The ECG data；
The dynamic physiology data and the static physiological data are pre-processed respectively, obtain dynamic intermediate data and
Static intermediate data, the pretreatment include at least one in the following：Data deduplication processing, dealing of abnormal data, data lack
Processing is filled up in mistake；
Feature extraction is carried out to the ECG data, obtains ECG characteristics；
The dynamic intermediate data, the static intermediate data and the ECG characteristics are merged, in obtaining
Between physiological data；
The middle physiological data is converted into the desired physiological data for possessing preset format.
In some possible embodiments, the ECG characteristics include at least one in the following：Temporal signatures number
According to, frequency domain character data, linear domain characteristic.
In some possible embodiments, methods described also includes：
When the illness assessment result is goal-based assessment result, the goal-based assessment result is prompted, and by the target
Assessment result is sent to the contact person that prestores, and the goal-based assessment result suffers from sleep apnea syndrome for instruction user.
In some possible embodiments, the deep learning model is the deep learning model of N layers, and N is more than 0 just
Integer, the deep learning pattern include any one of following：Long memory network LSTM models in short-term, gate repeat unit network
GRU models, Recognition with Recurrent Neural Network RNN models, recurrent neural network RNNs models.
Second aspect, the embodiments of the invention provide a kind of terminal device, the terminal device includes above-mentioned for performing
The functional unit of the method for first aspect.
The third aspect, the embodiments of the invention provide a kind of terminal device, including：Processor, memory, communication interface and
Bus；The processor, the memory are connected by the bus with the communication interface and complete mutual communication；Institute
State memory storage executable program code；The processor is by reading the executable program code stored in the memory
To run program corresponding with the executable program code, for performing a kind of illness appraisal procedure；Wherein, methods described
For the method described in any one of first aspect.
Fourth aspect, the invention provides a kind of computer-readable recording medium, the computer-readable recording medium is deposited
The program code performed by computing device is stored up.Described program code includes being used for the method for performing any one in the first aspect
Instruction.
5th aspect, the invention provides a kind of computer program product including instructing, when it runs on computers
When so that the method that computer performs any one of above-mentioned first aspect.
Terminal device can obtain the original physiologic data of user in the embodiment of the present invention, and the original physiologic data are used to comment
Estimate sleep apnea syndrome, then the original physiologic data are handled, obtain desired physiological data, finally by institute
Input of the desired physiological data as deep learning model is stated, illness assessment result is calculated, the deep learning model is
Train what is obtained according to the history physiological data of user；User physiological data of the deep learning model to various dimensions can so be used
Carry out that illness assessment result is calculated, to aid in doctor to give treatment in time, improve the practicality of illness assessment.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
There is the required accompanying drawing used in technology description to be briefly described, it should be apparent that, drawings in the following description are only this
Some embodiments of invention, for those of ordinary skill in the art, on the premise of not paying creative work, can be with
Other accompanying drawings are obtained according to these accompanying drawings.
Fig. 1 is a kind of schematic flow sheet of illness appraisal procedure of the embodiment of the present invention；
Fig. 2 is a kind of LSTM model schematics of the embodiment of the present invention；
Fig. 3 is a kind of schematic flow sheet of illness appraisal procedure of another embodiment of the present invention；
Fig. 4 is a kind of structural representation of terminal device of the embodiment of the present invention；
Fig. 5 is a kind of structural representation of terminal device of another embodiment of the present invention；
Fig. 6 is a kind of structural representation of terminal device of another embodiment of the present invention.
Embodiment
In order that those skilled in the art more fully understand the present invention program, below in conjunction with the embodiment of the present invention
Accompanying drawing, the technical scheme in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment is only
The embodiment of a part of the invention, rather than whole embodiments.Based on the embodiment in the present invention, ordinary skill people
The every other embodiment that member is obtained under the premise of creative work is not made, it should all belong to the model that the present invention protects
Enclose.
Term " first ", " second " and " the 3rd " in description and claims of this specification and above-mentioned accompanying drawing is (such as
Fruit presence) etc. be used for distinguish different objects, not for description particular order.In addition, term " comprising " and they are any
Deformation, it is intended that cover non-exclusive include.Such as contain the process of series of steps or unit, method, system, product
Or equipment the step of being not limited to list or unit, but the step of alternatively also include not listing or unit, or can
Selection of land is also included for the intrinsic other steps of these processes, method, product or equipment or unit.
Fig. 1 is referred to, is a kind of schematic flow sheet of illness appraisal procedure of the embodiment of the present invention, the embodiment of the present invention
Methods described can be applied in terminals with communications network functionality such as smart mobile phone, tablet personal computer, intelligent wearable devices
In equipment, it can specifically be realized by the processor of these terminal devices.The methods described of the embodiment of the present invention also includes following step
Suddenly.
Step S102, terminal device obtains the original physiologic data of user, and the original physiologic data, which are used to assess, sleeps
Apnea syndrome.
In this application, the original physiologic data are for assessing or determining whether user is comprehensive with sleep apnea
The data of disease are closed, the original physiologic data associate with the sleep apnea syndrome.Generally, the original physiologic data
Including but not limited to electrocardio ECG data, heart rate data, breath data, temperature data, pulse data, height data, weight data
Etc., the present invention does not limit.
Step S104, described terminal device is handled the original physiologic data, obtains desired physiological data.
The terminal device can be handled the original physiologic data, such as format conversion processing etc., obtain mesh
Physiological data is marked, is specifically described below.Generally, the desired physiological data are the data for possessing preset format, described pre-
If form includes but is not limited to integer type form, decimal format, octodenary form etc., the present invention does not limit.
Step S106, described terminal device calculates using the desired physiological data as the input of deep learning model
To illness assessment result, the deep learning model is to train what is obtained according to the history physiological data of user.
Input of the terminal device using the desired physiological data as deep learning model, has using with time series
The deep learning model of association calculates illness assessment result correspondingly.The illness assessment result is used to indicate the user
Whether with sleep apnea syndrome (alternatively referred to as OSAS).
The embodiment of the present invention is described below.
First, it is specific as follows that three kinds of embodiments are there are in step S104：
In the first embodiment, the terminal device carries out the amount of same data magnitude to the original physiologic data
Change, the original physiologic data are converted into the desired physiological data for possessing unified preset format.
The original physiologic data can be that terminal that the terminal device is detected using sensor or described is set
For what is obtained by network from server side, the present invention does not limit.
The preset format includes but is not limited to the forms such as the decimal system, octodenary.Preferably, the application will be described original
Physiological data is converted into user's physiological data of integer type.For example, using the quantizing rule of ten series magnitudes, same quantity is controlled
Desired physiological data after level quantization are between 0 to 10.
In second of embodiment, the terminal device is handled the original physiologic data, such as duplicate removal processing
Deng obtaining middle physiological data.Further, the terminal device carries out same data magnitude to the middle physiological data
Quantify, the middle physiological data is converted into the desired physiological data for possessing unified preset format.
Quantization on the middle physiological data can be found in the associated description in the first foregoing embodiment, here not
Repeat again.
In the third embodiment, the terminal device obtains the original physiologic data of user.Wherein, the original physiologic
Data may include dynamic physiology data, static physiological data and ECG data.The terminal device is to the original physiologic data
Handled, obtain middle physiology packet and include：The terminal device is classified the original physiologic data, is obtained described
Dynamic physiology data, the static physiological data and the ECG data；The terminal device is respectively to the dynamic physiology number
Pre-processed according to the static physiological data, obtain dynamic intermediate data and static intermediate data；The terminal device pair
The ECG data carries out feature extraction, obtains ECG characteristics；The terminal device is by the dynamic intermediate data, described quiet
State intermediate data and the ECG characteristics are merged, and obtain the middle physiological data, and the pretreatment includes following
At least one of in：Data deduplication processing, dealing of abnormal data, shortage of data fill up processing.
The dynamic physiology data refer to that in addition to ECG data other are used for sign can be with the use of time dynamic
Family data of physiological index, such as the heart rate data of user, pulse data, breath data etc..The static physiological data is use
In sign do not change over time or fixed duration in (such as 1 month) the user's data of physiological index that will not change, such as user
The data such as height, body weight.
Exemplarily such as, terminal device availability data analysis module is respectively according to every item number in the original physiologic data
The original physiologic data are divided into three classes according to each self-corresponding mark (such as title), are dynamic physiology data, static state
Physiological data and ECG data.Then, the terminal device can utilize Dynamic Data Processing module to the dynamic physiology data
Data deduplication is carried out, abnormal data is removed, even fills up missing data etc. processing, obtains middle dynamic data.Correspondingly, institute
Processing, such as the profit such as state terminal device and the static physiological data can be learnt and be trained using static data processing module
Static data is encoded with one-hot codings, obtains static intermediate data.Correspondingly, the terminal device can utilize ECG
Data processing module carries out feature extraction to the ECG data, obtains ECG characteristics.Further, the terminal device can
The dynamic intermediate data, the static intermediate data and the ECG characteristics are spelled using data concatenation module
Connect, merge, so as to obtain complete, accurate middle physiological data.Finally, the terminal device can utilize Feature Engineering module will
The middle physiological data is converted into the desired physiological data for possessing preset format.
Data prediction is described in detail exemplified by filling up missing data below.Due to user's physiology of hospital's collection
Data are not rule, for example heart rate data per minute can all may be collected, but the frequency acquisition of temperature data is not
It is fixed.Due in the handling process of dynamic physiology data, it is necessary to by user's physiological data (certainly including temperature data)
The form of equal length is uniformly processed into.Therefore need to fill up missing values, can because body temperature and time there may be linear relationship
Consider to fill up missing values using the method for linear regression.
In another example in the case of one kind is possible, oximetry data also per minute will not all collect correspondingly data.If
If keeping data format unified, filling up for missing values can be carried out using enthesis nearby, the purpose so handled is to make
Oximetry data will not produce larger fluctuation, so as to not interfere with data distortion or exception, not influence the study of model.
In an alternative embodiment, the terminal device carries out feature extraction using characteristic extracting module to the ECG data
Afterwards, any one or more in following three kinds of characteristics is obtained.Three kinds of characteristics are respectively：Temporal signatures number
According to, frequency domain character data and linear domain characteristic.It that is to say, the ECG characteristics include temporal signatures data, frequency domain
Any one or more in characteristic and linear domain characteristic, the embodiment of the present invention does not limit.Preferably, it is described
ECG characteristics include above-mentioned three kinds of characteristics.
The temporal signatures data are typically the electrocardiographic wave (i.e. ECG signal or ECG data) measured using continuous quantity,
The relation with analyzing time series between its heartbeat that is connected directly is calculated, such as：The temporal signatures data can be it is following in appoint
One：SDNN, SDANN, NN50 count, NN50 count etc..Wherein, SDNN is that normal heartbeat separation criteria is poor, and English is complete
Referred to as Standard Deviation of Normal to Normal.SDANN is that normal heartbeat separation criteria is poor in five minutes
Average value, English full name is Standard deviation of the averages of NN intervals in all
5-minute segments of the entire recording.NN50 count are that each pair normal heartbeat time interval is poor
Away from the number more than 50ms, English full name is Number of pairs of adjacent NN intervals differing
by more than 50ms in the entire recording.Number that NN50 count are NN50 and all normal
The ratio result of eartbeat interval sum, English full name is NN50 count divided by the total number of
all NN intervals。
What the frequency domain character data typically obtained with the following method, first step terminal device finds ECG data (i.e.
ECG signal) each Periodic identification point, such as zero crossing, minimax extreme point and some points that can be readily detected,
The cycle corresponding to the time conduct between RR points is typically used in ECG signal (i.e. ECG data), so the first step is detection ECG
The R points of signal；Second step seeks to calculate the time value between each periodic quantity, that is, RR points.3rd step, interpolation method；
Final step carries out Fourier transform, obtains frequency domain character data.The acquisition embodiment of the present invention on frequency domain character data is not
It is described in detail and limits.
The linear domain characteristic can generally obtain with the following method, and terminal device passes through nonlinear system
Theoretical and method is probed into ECG signal (i.e. ECG data), and linear domain is drawn by way of handling Poincare scatter diagram
Data.The acquisition embodiment of the present invention on linear domain characteristic is not detailed and limited.
Before step S106, the terminal device can obtain the history physiological data and history disease of one or more groups of users
Crux fruit.The history physiological data and the history illness result can be the True Datas of the collection of a period of time scope.
Alternatively, the history physiological data and the history illness result can be being prestored in the terminal device or logical
Cross what network obtained from other-end equipment or server, the present invention does not limit.Then the terminal device it is available with
The relevant mathematical modeling of time series is trained and learnt to the history physiological data and the history illness result, so as to
Obtain deep learning model.
Correspondingly in step s 106, the terminal device can be using the desired physiological data in step S104 as institute
The input of deep learning model is stated, the desired physiological data are calculated by the deep learning model, so as to obtain
Illness assessment result.Whether the illness assessment result suffers from sleep apnea syndrome for instruction user.
In an alternative embodiment, the deep learning model can be the deep learning model of n-layer, and n is just whole more than 0
Number.The deep learning pattern includes any one of following：Long memory network in short-term (Long Short-Term Memory,
LSTM) model, gate repeat unit network G RU models, Recognition with Recurrent Neural Network (Recurrent neural Network, RNN)
Model, recurrent neural network (Recurrent Neural Networks, RNNs) model, BP neural network model or other with
Data model of time series association etc., the present invention does not limit.
For example, by taking three-layer neural network LSTM models as an example.Such as Fig. 2, LSTM models include 2 layers of LSTM units (figure
It is shown as LSTMcell) and one layer of full connection (Fully Connected, FC) neutral net member (being illustrated as FC).Wherein every layer
LSTMcell and FC quantity does not limit.Mode input end can gather at input terminal equipment each moment, and treated
The desired physiological data (the concretely dynamic intermediate data in desired physiological data) of user, pass through three layers of LSTM model meters
Calculate, from illness assessment result corresponding to the output of model output end.
By taking the t4 moment as an example, mode input end inputs the desired physiological data of moment user, first layer and the second layer
LTSMcell can carry out linear or non-thread between feature extraction and study, such as learning data to the desired physiological data of input
Sexual intercourse etc..Because LSTMcell allows information selectively to be transmitted, therefore user's physiology before the t4 moment
Data (i.e. history physiological data) will pass through FC layers by selectively transmission together with the desired physiological data at t4 moment
For calculating the illness assessment result of the user, the illness assessment result calculated is exported to model output end by FC.
Specifically, the dynamic intermediate data on the one hand inputted at mode input end in the desired physiological data, by two
Layer LSTMcell cell processings, the dynamic intermediate data after being handled, are then inputted to FC layers again；On the other hand, will handle
ECG characteristics in the desired physiological data and static intermediate data afterwards is directly inputted into FC layers.Correspondingly, FC layers connect
After receiving above-mentioned three kinds of data, classification processing can be carried out to it, to be paid a home visit to Sleep Apnea-hypopnea Syndrome event
It is disconnected, so as to export visual illness assessment result from model output end.
It should be noted that deep learning model (i.e. real-time) can export illness assessment result at any time.Specifically such as
Shown in Fig. 2, the output time of LSTM models is arbitrarily adjustable, and the parameter n in Fig. 2 could be arranged to any one more than 0
Real number.The benefit of this adjustable parameters be the output of illness assessment result can be it is real-time, so can be to sleep-respiratory
The real-time intervention for suspending low hypopnea syndrome is possibly realized with intervention, to aid in medical treatment.
In an alternative embodiment, the terminal device can prompt the illness assessment result.Mode on prompting includes
But the prompting modes such as sound, captions, picture, suspension windows, vibration are not limited to, the embodiment of the present invention does not limit.
In an alternative embodiment, when the illness assessment result is goal-based assessment result, the goal-based assessment knot is prompted
Fruit, and the goal-based assessment result is sent to the contact person that prestores, the goal-based assessment result is used for instruction user with sleep
Apnea syndrome.
Specifically, when the illness assessment result is to suffer from sleep apnea syndrome for instruction user, can send out
Go out the treatment etc. in time of alert notification related doctor.Alternatively, the illness assessment result can be also sent to by the terminal device
Prestore contact person, such as is sent to hospital or cloud server, expert's treatment system etc., to aid in doctor to complete treatment.
In an alternative embodiment, the deep learning model can employ the LSTM neutral net moulds in deep learning
The maximum difference of type, LSTM and traditional neural network algorithm is the information before can recalling, because the door of uniqueness acts on,
Therefore LSTM possesses memory function, has unique advantage for the event for being spaced very long in time series.
The deep learning framework that the deep learning model uses is the TensorFlow platforms under Google, the platform branch
Hold on-line study and large-scale distributed computing, Spark clusters, GPU are calculated and the implementation of hundreds of millions magnitude data processings.
Therefore the deep learning model can analyze the user physiological data relevant with time series, with reference to sleep apnea syndrome
Front and rear correlation, the dependent evaluation of illness is reliably completed, so as to improve the degree of accuracy of illness assessment.
The terminal device can include user equipment (User Equipment, UE), smart mobile phone (such as Android hands
Machine, IOS mobile phones etc.), PC, tablet personal computer, palm PC, mobile internet device (MID, Mobile Internet
Devices) or internet device, the embodiment of the present invention such as wearable intelligent equipment are not construed as limiting.
Terminal device can obtain the original physiologic data of user in the embodiment of the present invention, and the original physiologic data are used to comment
Estimate sleep apnea syndrome, then the original physiologic data are handled, obtain desired physiological data, finally by institute
Input of the desired physiological data as deep learning model is stated, illness assessment result is calculated, the deep learning model is
Train what is obtained according to the history physiological data of user；User physiological data of the deep learning model to various dimensions can so be used
Carry out that illness assessment result is calculated, to aid in doctor to give treatment in time, improve the practicality of illness assessment.
Fig. 3 is referred to, is another illness appraisal procedure provided in an embodiment of the present invention.Method as described in Figure 3, including
Step is implemented as follows：
Step S302, terminal device obtains the original physiologic data of user.
Step S304, described terminal device is classified the original physiologic data, obtain the dynamic physiology data,
The static physiological data and the ECG data；
Step S306, described terminal device is located in advance to the dynamic physiology data and the static physiological data respectively
Reason, obtains dynamic intermediate data and static intermediate data, the pretreatment includes at least one in the following：At data deduplication
Reason, dealing of abnormal data, shortage of data fill up processing.
Step S308, described terminal device carries out feature extraction to the ECG data, obtains ECG characteristics.
Execution sequence is not limited on step S306 and step S308, such as step is performed after step S308 can be first carried out
S306, the embodiment of the present invention are not construed as limiting.
Step S310, described terminal device is special by the dynamic intermediate data, the static intermediate data and the ECG
Sign data are merged, and obtain the middle physiological data.
The middle physiological data is converted into the desired physiological number for possessing preset format by step S312, described terminal device
According to.
Step S314, described terminal device calculates using the desired physiological data as the input of deep learning model
To illness assessment result, the deep learning model is to be trained to obtain according to the history physiological data and history illness result of user
's.
In an alternative embodiment, the deep learning model is the deep learning model of N layers, and N is the positive integer more than 0,
The deep learning pattern includes any one of following：Long memory network LSTM models in short-term, gate repeat unit network G RU moulds
Type, Recognition with Recurrent Neural Network RNN models, recurrent neural network RNNs models.
Step S316, when the illness assessment result is goal-based assessment result, the goal-based assessment result is prompted, and will
The goal-based assessment result is sent to the contact person that prestores, and the goal-based assessment result suffers from sleep apnea for instruction user
Syndrome.
, can be referring specifically to the correlation in embodiment described in Fig. 1 on the part that the embodiment of the present invention is not shown and does not describe
Description, is repeated no more here.
Refer to Fig. 4, be a kind of structural representation of terminal device of the embodiment of the present invention, the embodiment of the present invention it is described
Terminal device 400 includes：Acquiring unit 402, processing unit 404 and computing unit 406；Wherein：
The acquiring unit 402, obtains the original physiologic data of user, and the original physiologic data are exhaled for assessing sleep
Inhale pause syndrome；
The processing unit 404, for handling the original physiologic data, obtain desired physiological data；
The Tip element 406, for using the desired physiological data as the input of deep learning model, being calculated
Illness assessment result, the deep learning model are to train what is obtained according to the history physiological data of user.
Fig. 5 is please combined in the lump, is the structural representation of another terminal device of the embodiment of the present invention, the embodiment of the present invention
The terminal device 400 include above-mentioned acquiring unit 402, processing unit 404 and computing unit 406；Wherein：It is described original
Physiological data includes dynamic physiology data, static physiological data and electrocardio ECG data,
The processing unit 404, for the original physiologic data to be classified, obtain the dynamic physiology data,
The static physiological data and the ECG data；
The processing unit 404, it is additionally operable to respectively carry out in advance the dynamic physiology data and the static physiological data
Processing, obtains dynamic intermediate data and static intermediate data, the pretreatment includes at least one in the following：At data deduplication
Reason, dealing of abnormal data, shortage of data fill up processing；
The processing unit 404, it is additionally operable to carry out feature extraction to the ECG data, obtains ECG characteristics；
The processing unit 404, it is additionally operable to the dynamic intermediate data, the static intermediate data and the ECG
Characteristic is merged, and obtains middle physiological data；
The processing unit 404, it is additionally operable to for the middle physiological data to be converted into the desired physiological for possessing preset format
Data.
In some possible embodiments, the ECG characteristics include at least one in the following：Temporal signatures number
According to, frequency domain character data, linear domain characteristic.
In some possible embodiments, the terminal device also includes Tip element 410,
The Tip element 410, for when the illness assessment result is goal-based assessment result, prompting the target to comment
Estimate result, and the goal-based assessment result is sent to the contact person that prestores, the goal-based assessment result suffers from for instruction user
Sleep apnea syndrome.
The specific implementation for the unit being related in the embodiment of the present invention refers to Fig. 1 to Fig. 3 and corresponds to correlation in embodiment
The description of functional unit or implementation steps, will not be described here.
Fig. 6 is referred to, Fig. 6 is a kind of structural representation of terminal device disclosed in the embodiment of the present invention.The present embodiment
Terminal device 400 includes：At least one processor 601, communication interface 602, user interface 603 and memory 604, processor
601st, communication interface 602, user interface 603 can be connected with memory 604 by bus or other manner, the embodiment of the present invention
Exemplified by being connected by bus 605.Wherein,
Processor 601 can be general processor, such as central processing unit (Central Processing Unit,
CPU)。
Communication interface 602 can be wireline interface (such as Ethernet interface) or wave point (such as cellular network interface
Or use wireless lan interfaces), for being communicated with other-end or website.In the embodiment of the present invention, communication interface 602
Specifically for obtaining user's physiological data.
The concretely contact panel, including touch-screen and touch screen of user interface 603, for detecting the behaviour on contact panel
Instruct, user interface 603 can also be physical button or mouse.User interface 603 can also be display screen, for defeated
Go out, display image or data.
Memory 604 can include volatile memory (Volatile Memory), such as random access memory
(Random Access Memory, RAM)；Memory can also include nonvolatile memory (Non-Volatile
), such as read-only storage (Read-Only Memory, ROM), flash memory (Flash Memory), hard disk Memory
(Hard Disk Drive, HDD) or solid state hard disc (Solid-State Drive, SSD)；Memory 604 can also include upper
State the combination of the memory of species.Memory 604 is used to store batch processing code, and processor 601 is used to call memory 604
The program code of middle storage, perform following operation：
The original physiologic data of user are obtained, the original physiologic data are used to assess sleep apnea syndrome；
The original physiologic data are handled, obtain desired physiological data；
Input using the desired physiological data as deep learning model, is calculated illness assessment result, the depth
Degree learning model is to train what is obtained according to the history physiological data of user.
In some possible embodiments, the original physiologic data include dynamic physiology data, static physiological data with
And electrocardio ECG data, the processor 601 are used for：
The original physiologic data are classified, obtain the dynamic physiology data, the static physiological data and
The ECG data；
The dynamic physiology data and the static physiological data are pre-processed respectively, obtain dynamic intermediate data and
Static intermediate data, the pretreatment include at least one in the following：Data deduplication processing, dealing of abnormal data, data lack
Processing is filled up in mistake；
Feature extraction is carried out to the ECG data, obtains ECG characteristics；
The dynamic intermediate data, the static intermediate data and the ECG characteristics are merged, in obtaining
Between physiological data；
The middle physiological data is converted into the desired physiological data for possessing preset format.
In some possible embodiments, the ECG characteristics include at least one in the following：Temporal signatures number
According to, frequency domain character data, linear domain characteristic.
In some possible embodiments, the processor 601 is additionally operable to：
When the illness assessment result is goal-based assessment result, the goal-based assessment result is prompted, and by the target
Assessment result is sent to the contact person that prestores, and the goal-based assessment result suffers from sleep apnea syndrome for instruction user.
In some possible embodiments, the deep learning model is the deep learning model of N layers, and N is more than 0 just
Integer, the deep learning pattern include any one of following：Long memory network LSTM models in short-term, gate repeat unit network
GRU models, Recognition with Recurrent Neural Network RNN models, recurrent neural network RNNs models.
The embodiment of the present invention also provides a kind of computer-readable storage medium, wherein, the computer-readable storage medium can be stored with journey
Sequence, including the part or all of implementation step in the methods described embodiment described in the above method embodiment when program performs
Suddenly.
It should be noted that for foregoing each method embodiment, in order to be briefly described, therefore it is all expressed as a series of
Combination of actions, but those skilled in the art should know, the present invention is not limited by described sequence of movement because
According to the present invention, some steps can use other orders or carry out simultaneously.Secondly, those skilled in the art should also know
Know, embodiment described in this description belongs to preferred embodiment, and involved action and module are not necessarily of the invention
It is necessary.
In the above-described embodiments, the description to each embodiment all emphasizes particularly on different fields, and does not have the portion being described in detail in some embodiment
Point, it may refer to the associated description of other embodiment.
In several embodiments provided herein, it should be understood that disclosed device, can be by another way
Realize.For example, device embodiment described above is only schematical, such as the division of the unit, it is only one kind
Division of logic function, can there is an other dividing mode when actually realizing, such as multiple units or component can combine or can
To be integrated into another system, or some features can be ignored, or not perform.Another, shown or discussed is mutual
Coupling direct-coupling or communication connection can be by some interfaces, the INDIRECT COUPLING or communication connection of device or unit,
Can be electrical or other forms.
The unit illustrated as separating component can be or may not be physically separate, show as unit
The part shown can be or may not be physical location, you can with positioned at a place, or can also be distributed to multiple
On NE.Some or all of unit therein can be selected to realize the mesh of this embodiment scheme according to the actual needs
's.
In addition, each functional unit in various embodiments of the present invention can be integrated in a processing unit, also may be used
To be that unit is individually physically present, can also two or more units it is integrated in a unit.It is above-mentioned integrated
Unit can both be realized in the form of hardware, can also be realized in the form of SFU software functional unit.
If the integrated unit is realized in the form of SFU software functional unit and is used as independent production marketing or use
When, it can be stored in a computer read/write memory medium.Based on such understanding, technical scheme is substantially
The part to be contributed in other words to prior art or all or part of the technical scheme can be in the form of software products
Embody, the computer software product is stored in a storage medium, including some instructions are causing a computer
Equipment (can be personal computer, server or network equipment etc.) perform each embodiment methods described of the present invention whole or
Part steps.And foregoing storage medium includes：USB flash disk, read-only storage (ROM, Read-Only Memory), arbitrary access are deposited
Reservoir (RAM, Random Access Memory), mobile hard disk, magnetic disc or CD etc. are various can be with store program codes
Medium.
Described above, the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although with reference to before
Embodiment is stated the present invention is described in detail, it will be understood by those within the art that：It still can be to preceding
State the technical scheme described in each embodiment to modify, or equivalent substitution is carried out to which part technical characteristic；And these
Modification is replaced, and the essence of appropriate technical solution is departed from the scope of various embodiments of the present invention technical scheme.
Claims (10)
- A kind of 1. illness appraisal procedure, it is characterised in that including：The original physiologic data of user are obtained, the original physiologic data are used to assess sleep apnea syndrome；The original physiologic data are handled, obtain desired physiological data；Input using the desired physiological data as deep learning model, is calculated illness assessment result, the depth It is to train what is obtained according to the history physiological data of user to practise model.
- 2. according to the method for claim 1, it is characterised in that the original physiologic data include dynamic physiology data, quiet State physiological data and electrocardio ECG data, it is described that the original physiologic data are handled, obtain desired physiological packet Include：The original physiologic data are classified, obtain the dynamic physiology data, the static physiological data and described ECG data；The dynamic physiology data and the static physiological data are pre-processed respectively, obtain dynamic intermediate data and static state Intermediate data, the pretreatment include at least one in the following：Data deduplication processing, dealing of abnormal data, shortage of data are filled out Benefit processing；Feature extraction is carried out to the ECG data, obtains ECG characteristics；The dynamic intermediate data, the static intermediate data and the ECG characteristics are merged, obtain intermediate green Manage data；The middle physiological data is converted into the desired physiological data for possessing preset format.
- 3. according to the method for claim 2, it is characterised in that the ECG characteristics include at least one in the following： Temporal signatures data, frequency domain character data, linear domain characteristic.
- 4. according to the method for claim 1, it is characterised in that methods described also includes：When the illness assessment result is goal-based assessment result, the goal-based assessment result is prompted, and by the goal-based assessment As a result the contact person that prestores is sent to, the goal-based assessment result suffers from sleep apnea syndrome for instruction user.
- 5. according to the method any one of claim 1-4, it is characterised in that the deep learning model is the depth of N layers Learning model is spent, N is the positive integer more than 0, and the deep learning pattern includes any one of following：Long memory network in short-term LSTM models, gate repeat unit network G RU models, Recognition with Recurrent Neural Network RNN models, recurrent neural network RNNs models.
- A kind of 6. terminal device, it is characterised in that including：Acquiring unit, for obtaining the original physiologic data of user, the original physiologic data are used to assess sleep apnea Syndrome；Processing unit, for handling the original physiologic data, obtain desired physiological data；Computing unit, for the input using the desired physiological data as deep learning model, illness is calculated and assesses knot Fruit, the deep learning model are to train what is obtained according to the history physiological data of user.
- 7. terminal device according to claim 6, it is characterised in that the original physiologic data include dynamic physiology number According to, static physiological data and electrocardio ECG data,The processing unit, for the original physiologic data to be classified, obtain the dynamic physiology data, the static state Physiological data and the ECG data；The processing unit, it is additionally operable to respectively pre-process the dynamic physiology data and the static physiological data, obtains To dynamic intermediate data and static intermediate data, the pretreatment includes at least one in the following：Data deduplication processing, exception Processing is filled up in data processing, shortage of data；The processing unit, it is additionally operable to carry out feature extraction to the ECG data, obtains ECG characteristics；The processing unit, it is additionally operable to the dynamic intermediate data, the static intermediate data and the ECG characteristics Merged, obtain middle physiological data；The processing unit, it is additionally operable to for the middle physiological data to be converted into the desired physiological data for possessing preset format.
- 8. terminal device according to claim 7, it is characterised in that the ECG characteristics include it is following at least One：Temporal signatures data, frequency domain character data, linear domain characteristic.
- 9. according to the terminal device described in claim any one of 6-8, it is characterised in that it is single that the terminal device also includes prompting Member,The Tip element, for when the illness assessment result is goal-based assessment result, prompting the goal-based assessment result, And the goal-based assessment result is sent to the contact person that prestores, the goal-based assessment result suffers from sleep-respiratory for instruction user Suspend syndrome.
- 10. a kind of computer-readable recording medium, the computer-readable recording medium storage has computer program, and its feature exists In realization such as any one of claim 1 to 5 methods described when the computer program is executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710632865.3A CN107595243B (en) | 2017-07-28 | 2017-07-28 | Disease evaluation method and terminal equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710632865.3A CN107595243B (en) | 2017-07-28 | 2017-07-28 | Disease evaluation method and terminal equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107595243A true CN107595243A (en) | 2018-01-19 |
| CN107595243B CN107595243B (en) | 2021-08-17 |
Family
ID=61059652
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710632865.3A Active CN107595243B (en) | 2017-07-28 | 2017-07-28 | Disease evaluation method and terminal equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107595243B (en) |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108282533A (en) * | 2018-01-29 | 2018-07-13 | 百度在线网络技术（北京）有限公司 | intelligent monitoring method, device, wearable device and server |
| CN108652615A (en) * | 2018-03-24 | 2018-10-16 | 度特斯(大连)实业有限公司 | A kind of electrocardiogram (ECG) data pathological characters quantitative analysis method and device |
| CN109087706A (en) * | 2018-07-13 | 2018-12-25 | 浙江清华长三角研究院 | Human health appraisal procedure and assessment system based on sleep big data |
| CN109102896A (en) * | 2018-06-29 | 2018-12-28 | 东软集团股份有限公司 | A kind of method of generating classification model, data classification method and device |
| CN109411062A (en) * | 2018-09-30 | 2019-03-01 | 天津科技大学 | A method of diabetes and its complication are judged automatically using physiological parameter based on depth learning technology |
| CN109602410A (en) * | 2018-11-16 | 2019-04-12 | 青岛真时科技有限公司 | A kind of wearable device and its monitoring of pulse method |
| CN109637670A (en) * | 2018-12-04 | 2019-04-16 | 泰康保险集团股份有限公司 | Data processing method, device, medium and electronic equipment |
| CN109833031A (en) * | 2019-03-12 | 2019-06-04 | 西安交通大学 | It is a kind of that the sleep mode automatically method by stages of more physiological signals is utilized based on LSTM |
| CN110223280A (en) * | 2019-06-03 | 2019-09-10 | Oppo广东移动通信有限公司 | Phlebothrombosis detection method and phlebothrombosis detection device |
| CN110348500A (en) * | 2019-06-30 | 2019-10-18 | 浙江大学 | Sleep disturbance aided diagnosis method based on deep learning and infrared thermal imagery |
| CN111353972A (en) * | 2018-12-21 | 2020-06-30 | 财团法人工业技术研究院 | State evaluation system, diagnosis and treatment system and operation method thereof |
| CN111446002A (en) * | 2020-03-07 | 2020-07-24 | 华中科技大学 | Novel coronavirus patient state of illness classification system based on artificial intelligence |
| CN111565633A (en) * | 2018-03-30 | 2020-08-21 | 三星Sds 株式会社 | Time series data learning and analyzing method using artificial intelligence |
| CN111603138A (en) * | 2020-05-19 | 2020-09-01 | 杭州电子科技大学 | Sleep apnea monitoring system based on millimeter wave radar |
| CN111671426A (en) * | 2020-05-13 | 2020-09-18 | 北京航空航天大学 | Human body respiration state monitoring system and method based on flexible sensing and deep learning |
| CN111862068A (en) * | 2020-07-28 | 2020-10-30 | 福州大学 | Three-model comprehensive decision emotion prediction method fusing data missing data and images |
| CN113729709A (en) * | 2021-09-23 | 2021-12-03 | 中国科学技术大学先进技术研究院 | Neurofeedback apparatus, neurofeedback method, and computer-readable storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104545818A (en) * | 2015-01-29 | 2015-04-29 | 吉林大学 | Sleep apnea syndrome detection method based on pulse and blood oxygen signals |
| CN204971271U (en) * | 2015-08-24 | 2016-01-20 | 华南理工大学 | Old person health service system based on health service robot |
| CN106328122A (en) * | 2016-08-19 | 2017-01-11 | 深圳市唯特视科技有限公司 | Voice identification method using long-short term memory model recurrent neural network |
| CN106361277A (en) * | 2016-08-26 | 2017-02-01 | 中山大学 | Sleep apnea syndrome assessment method based on electrocardiogram signals |
| CN106473700A (en) * | 2016-08-26 | 2017-03-08 | 复旦大学 | Detecting system based on the OSAS of HRV frequency-domain analysis |
| CN106682220A (en) * | 2017-01-04 | 2017-05-17 | 华南理工大学 | Online traditional Chinese medicine text named entity identifying method based on deep learning |
| CN106691378A (en) * | 2016-12-16 | 2017-05-24 | 深圳市唯特视科技有限公司 | Deep learning vision classifying method based on electroencephalogram data |
| CN106901723A (en) * | 2017-04-20 | 2017-06-30 | 济南浪潮高新科技投资发展有限公司 | A kind of electrocardiographic abnormality automatic diagnosis method |
-
2017
- 2017-07-28 CN CN201710632865.3A patent/CN107595243B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104545818A (en) * | 2015-01-29 | 2015-04-29 | 吉林大学 | Sleep apnea syndrome detection method based on pulse and blood oxygen signals |
| CN204971271U (en) * | 2015-08-24 | 2016-01-20 | 华南理工大学 | Old person health service system based on health service robot |
| CN106328122A (en) * | 2016-08-19 | 2017-01-11 | 深圳市唯特视科技有限公司 | Voice identification method using long-short term memory model recurrent neural network |
| CN106361277A (en) * | 2016-08-26 | 2017-02-01 | 中山大学 | Sleep apnea syndrome assessment method based on electrocardiogram signals |
| CN106473700A (en) * | 2016-08-26 | 2017-03-08 | 复旦大学 | Detecting system based on the OSAS of HRV frequency-domain analysis |
| CN106691378A (en) * | 2016-12-16 | 2017-05-24 | 深圳市唯特视科技有限公司 | Deep learning vision classifying method based on electroencephalogram data |
| CN106682220A (en) * | 2017-01-04 | 2017-05-17 | 华南理工大学 | Online traditional Chinese medicine text named entity identifying method based on deep learning |
| CN106901723A (en) * | 2017-04-20 | 2017-06-30 | 济南浪潮高新科技投资发展有限公司 | A kind of electrocardiographic abnormality automatic diagnosis method |
Cited By (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108282533A (en) * | 2018-01-29 | 2018-07-13 | 百度在线网络技术（北京）有限公司 | intelligent monitoring method, device, wearable device and server |
| CN108652615A (en) * | 2018-03-24 | 2018-10-16 | 度特斯(大连)实业有限公司 | A kind of electrocardiogram (ECG) data pathological characters quantitative analysis method and device |
| CN111565633A (en) * | 2018-03-30 | 2020-08-21 | 三星Sds 株式会社 | Time series data learning and analyzing method using artificial intelligence |
| CN109102896A (en) * | 2018-06-29 | 2018-12-28 | 东软集团股份有限公司 | A kind of method of generating classification model, data classification method and device |
| CN109087706A (en) * | 2018-07-13 | 2018-12-25 | 浙江清华长三角研究院 | Human health appraisal procedure and assessment system based on sleep big data |
| CN109087706B (en) * | 2018-07-13 | 2022-12-02 | 浙江清华长三角研究院 | Human health assessment method and system based on sleep big data |
| CN109411062A (en) * | 2018-09-30 | 2019-03-01 | 天津科技大学 | A method of diabetes and its complication are judged automatically using physiological parameter based on depth learning technology |
| CN109602410A (en) * | 2018-11-16 | 2019-04-12 | 青岛真时科技有限公司 | A kind of wearable device and its monitoring of pulse method |
| CN109637670A (en) * | 2018-12-04 | 2019-04-16 | 泰康保险集团股份有限公司 | Data processing method, device, medium and electronic equipment |
| CN111353972B (en) * | 2018-12-21 | 2024-03-12 | 财团法人工业技术研究院 | State evaluation system, diagnosis and treatment system and operation method thereof |
| CN111353972A (en) * | 2018-12-21 | 2020-06-30 | 财团法人工业技术研究院 | State evaluation system, diagnosis and treatment system and operation method thereof |
| CN109833031B (en) * | 2019-03-12 | 2020-08-14 | 西安交通大学 | Automatic sleep staging method based on LSTM and utilizing multiple physiological signals |
| CN109833031A (en) * | 2019-03-12 | 2019-06-04 | 西安交通大学 | It is a kind of that the sleep mode automatically method by stages of more physiological signals is utilized based on LSTM |
| CN110223280B (en) * | 2019-06-03 | 2021-04-13 | Oppo广东移动通信有限公司 | Venous thrombosis detection method and venous thrombosis detection device |
| CN110223280A (en) * | 2019-06-03 | 2019-09-10 | Oppo广东移动通信有限公司 | Phlebothrombosis detection method and phlebothrombosis detection device |
| CN110348500A (en) * | 2019-06-30 | 2019-10-18 | 浙江大学 | Sleep disturbance aided diagnosis method based on deep learning and infrared thermal imagery |
| CN111446002A (en) * | 2020-03-07 | 2020-07-24 | 华中科技大学 | Novel coronavirus patient state of illness classification system based on artificial intelligence |
| CN111671426A (en) * | 2020-05-13 | 2020-09-18 | 北京航空航天大学 | Human body respiration state monitoring system and method based on flexible sensing and deep learning |
| CN111671426B (en) * | 2020-05-13 | 2022-07-12 | 北京航空航天大学 | Human body respiration state monitoring system and method based on flexible sensing and deep learning |
| CN111603138A (en) * | 2020-05-19 | 2020-09-01 | 杭州电子科技大学 | Sleep apnea monitoring system based on millimeter wave radar |
| CN111862068A (en) * | 2020-07-28 | 2020-10-30 | 福州大学 | Three-model comprehensive decision emotion prediction method fusing data missing data and images |
| CN111862068B (en) * | 2020-07-28 | 2022-09-13 | 福州大学 | Three-model comprehensive decision emotion prediction method fusing data missing data and images |
| CN113729709A (en) * | 2021-09-23 | 2021-12-03 | 中国科学技术大学先进技术研究院 | Neurofeedback apparatus, neurofeedback method, and computer-readable storage medium |
| CN113729709B (en) * | 2021-09-23 | 2023-08-11 | 中科效隆(深圳)科技有限公司 | Nerve feedback device, nerve feedback method, and computer-readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107595243B (en) | 2021-08-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107595243A (en) | A kind of illness appraisal procedure and terminal device | |
| CN107491638A (en) | A kind of ICU user's prognosis method and terminal device based on deep learning model | |
| US10467548B2 (en) | Method, apparatus and system for biometric identification | |
| US11617528B2 (en) | Systems and methods for reduced lead electrocardiogram diagnosis using deep neural networks and rule-based systems | |
| CN108135527A (en) | For the method, apparatus and system of bio-identification | |
| WO2016029166A1 (en) | Automated diagnosis based at least in part on pulse waveforms | |
| CN109864736A (en) | Processing method, device, terminal device and the medium of electrocardiosignal | |
| CN111063437A (en) | Personalized chronic disease analysis system | |
| JP6468637B2 (en) | Sleepiness estimation apparatus and sleepiness estimation program | |
| CN109273087A (en) | A kind of mental health index monitoring system | |
| CN109674474B (en) | Sleep apnea recognition method, device and computer readable medium | |
| US20130041275A1 (en) | System, apparatus and method for diagnosing seizures | |
| CN106618592A (en) | Remote blood glucose monitoring processing method and mobile terminal | |
| Ho et al. | A telesurveillance system with automatic electrocardiogram interpretation based on support vector machine and rule-based processing | |
| Pal et al. | Future of healthcare—sensor data-driven prognosis | |
| Tiwari et al. | Stress and anxiety measurement" in-the-wild" using quality-aware multi-scale hrv features | |
| CN109770904A (en) | Monitoring method, device, computer equipment and the storage medium of apnea | |
| JP7005921B2 (en) | Sleep state estimation device, sleep state estimation method and sleep state estimation program | |
| CN108182974B (en) | Disease evaluation method, terminal device and computer readable medium | |
| CN112914506A (en) | Sleep quality detection method, device and computer readable storage medium | |
| CN108198617A (en) | Illness appraisal procedure, terminal device and computer-readable medium | |
| Hartmann et al. | Identifying IIR filter coefficients using particle swarm optimization with application to reconstruction of missing cardiovascular signals | |
| CN114343585B (en) | Cognitive and behavioral disorder early warning method, device, equipment and storage medium | |
| CN107292244A (en) | A kind of stress recognition methods, smart machine and computer-readable recording medium | |
| CN114550932A (en) | Sleep apnea risk assessment method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |