CN114259235A - Health state prediction method, apparatus, device, medium, and computer program product - Google Patents
Health state prediction method, apparatus, device, medium, and computer program product Download PDFInfo
- Publication number
- CN114259235A CN114259235A CN202111556964.0A CN202111556964A CN114259235A CN 114259235 A CN114259235 A CN 114259235A CN 202111556964 A CN202111556964 A CN 202111556964A CN 114259235 A CN114259235 A CN 114259235A
- Authority
- CN
- China
- Prior art keywords
- state
- health
- health state
- unknown
- physiological parameter
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The disclosure relates to the technical field of data processing and artificial intelligence, and provides a health status prediction method, device, equipment, medium and computer program product. The health state prediction method comprises the following steps: building and training a health state prediction model; estimating a group of physiological parameter feature vector frames corresponding to an unknown state by using the health state prediction model to obtain state likelihood probability corresponding to the unknown state; the health state is predicted based on the state likelihood probability corresponding to the unknown state, resulting in a predicted health state. The health state prediction model is constructed and trained by adopting a forward and backward algorithm of the hidden Markov model, the physiological parameter characteristic vector frame is estimated and predicted by utilizing the health state prediction model, the health state corresponding to the physiological parameter is obtained, the health state corresponding to a group of physiological parameters can be obtained in real time without professional staff, and the non-health state is fed back and early warned in time.
Description
Technical Field
The present disclosure relates to the field of data processing and artificial intelligence technologies, and in particular, to a method, an apparatus, a device, a medium, and a computer program product for predicting a health status based on physiological parameters.
Background
The monitoring of physiological data of human body is of great significance to exercise, medical treatment and physiological state prevention. The traditional physiological data acquisition means mostly depend on medical equipment in a hospital, and the medical equipment has the defects of high price, limited resources, poor comfort, incapability of automatically processing data and the like, so that the physiological data acquisition of daily health protection or special crowds such as customs personnel, epidemic prevention personnel, athletes and the like is greatly challenged, and is difficult to popularize in a large range.
The flexible electronic technology provides an effective technical approach for the popularization of physiological data monitoring. The high-performance circuit and the flexible material are integrated by a micro-nano observation technology and a preparation technology, so that the flexibility, the ductility and the miniaturization of the electronic device are realized. The flexible sensor prepared based on the flexible electronic technology has the advantages of wearing comfort, wireless transmission, low power consumption and the like, and greatly promotes the intellectualization, digitization, rapidness and simplification of a motion information acquisition way. In recent years, a series of innovative results are obtained in the research and development and manufacturing of flexible sensors, and the measurement of various human body physiological parameters such as electrocardio, myoelectricity, blood oxygen saturation, glucose concentration, temperature, acceleration, pressure and the like is realized.
Aiming at the requirement of monitoring human physiological data, researchers convert physiological signals into electric signals by a flexible design of a capacitive, resistive, piezoelectric, piezoresistive or photoelectric sensing module based on a flexible sensor design method, and finally realize accurate measurement of various human physiological parameters. Although the flexible sensors realize accurate measurement of human physiological parameters, the real-time comprehensive analysis of data still has great defects, so that the application range of the flexible sensors is greatly limited.
Disclosure of Invention
Technical problem to be solved
In view of the above, the present disclosure provides a method, an apparatus, a device, a medium, and a computer program product for health status prediction based on physiological parameters.
(II) technical scheme
In a first aspect of the present disclosure, a health status prediction method is provided, including: building and training a health state prediction model; estimating a group of physiological parameter feature vector frames corresponding to an unknown state by using the health state prediction model to obtain state likelihood probability corresponding to the unknown state; the health state is predicted based on the state likelihood probability corresponding to the unknown state, resulting in a predicted health state.
According to an embodiment of the present disclosure, the building and training of the health state prediction model is implemented using a hidden markov model forward-backward (Baum-Welch) algorithm. The method for constructing and training the health state prediction model by adopting a hidden Markov model forward-backward (Baum-Welch) algorithm comprises the following steps: acquiring a plurality of groups of health state physiological parameter characteristic vector frames corresponding to the health state, and merging the plurality of groups of health state physiological parameter characteristic vector frames to obtain a health state vector frame matrix; acquiring a plurality of groups of unhealthy state physiological parameter characteristic vector frames corresponding to unhealthy states, and merging the plurality of groups of unhealthy state physiological parameter characteristic vector frames to obtain an unhealthy state vector frame matrix; and inputting the health state vector frame matrix and the unhealthy state vector frame matrix into a hidden Markov model by adopting a forward-backward (Baum-Welch) algorithm to perform sample training to obtain a health state prediction model.
According to an embodiment of the present disclosure, the physiological parameters include at least electrocardiogram, blood oxygen and body temperature; in the step of acquiring a plurality of sets of health state physiological parameter feature vector frames corresponding to the health state, the acquiring process of each set of health state physiological parameter feature vector frames corresponding to the health state includes: respectively carrying out overlapping framing on each group of electrocardiogram, blood oxygen diagram and body temperature corresponding to the health state, and extracting the electrocardiogram characteristic value, the average blood oxygen concentration value and the average body temperature value of the group corresponding to the health state; carrying out matrix combination on each group of electrocardio characteristic values, average blood oxygen concentration values and average body temperature values corresponding to the health state to obtain a group of physiological parameter characteristic vector frames corresponding to the health state; in the step of acquiring a plurality of groups of non-health state physiological parameter feature vector frames corresponding to non-health states, the acquiring process of each group of non-health state physiological parameter feature vector frames corresponding to non-health states comprises: respectively carrying out overlapping framing on each group of electrocardiogram, blood oxygen diagram and body temperature corresponding to the unhealthy state, and extracting the electrocardiogram characteristic value, the average blood oxygen concentration value and the average body temperature value of the group corresponding to the unhealthy state; and carrying out matrix combination on the electrocardio characteristic value, the average blood oxygen concentration value and the average body temperature value of each group corresponding to the unhealthy state to obtain a group of unhealthy state physiological parameter characteristic vector frames corresponding to the unhealthy state.
According to an embodiment of the present disclosure, before the step of estimating a set of frames of physiological parameter feature vectors corresponding to an unknown state by using the health state prediction model, the method further includes: a set of frames of physiological parameter feature vectors corresponding to unknown states is acquired.
According to an embodiment of the present disclosure, the acquiring a set of physiological parameter feature vector frames corresponding to an unknown state includes: respectively carrying out overlapping framing on a group of electrocardiograms, blood oxygen graphs and body temperatures corresponding to unknown states, and extracting an electrocardio characteristic value, an average blood oxygen concentration value and an average body temperature value of the group corresponding to the unknown states; and carrying out matrix combination on the electrocardio characteristic value, the average blood oxygen concentration value and the average body temperature value of the group corresponding to the unknown state to obtain a physiological parameter characteristic vector frame of the group corresponding to the unknown state.
According to an embodiment of the present disclosure, in the step of estimating a set of physiological parameter feature vector frames corresponding to an unknown state by using the health state prediction model to obtain a state likelihood probability corresponding to the unknown state, a maximum likelihood estimation method is used to estimate the set of physiological parameter feature vector frames corresponding to the unknown state to obtain the state likelihood probability corresponding to the unknown state.
According to an embodiment of the present disclosure, predicting the health state based on the state likelihood probability corresponding to the unknown state to obtain a predicted health state includes: presetting a threshold value of the state likelihood probability, judging whether the state likelihood probability corresponding to the unknown state is greater than the threshold value, and if so, determining that the unknown state is a healthy state; otherwise, the unknown state is an unhealthy state.
According to an embodiment of the disclosure, the method further comprises: and when the unknown state is the unhealthy state, carrying out early warning prompt.
In another aspect of the present disclosure, a health status prediction apparatus is provided, including: the model building and training module is used for building and training the health state prediction model; the estimation module is used for estimating a group of physiological parameter feature vector frames corresponding to an unknown state by using the health state prediction model to obtain state likelihood probability corresponding to the unknown state; and the prediction module predicts the health state based on the state likelihood probability corresponding to the unknown state to obtain the predicted health state.
According to an embodiment of the present disclosure, the apparatus further comprises: and the early warning prompting module is used for carrying out early warning prompting when the unknown state is a non-healthy state.
In still another aspect of the present disclosure, there is provided a health state prediction apparatus including: one or more processors; a memory storing a computer executable program which, when executed by the processor, causes the processor to implement the state of health prediction method.
In yet another aspect of the present disclosure, a storage medium containing computer-executable instructions that, when executed, implement the health state prediction method is provided.
In yet another aspect of the disclosure, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the health status prediction method.
(III) advantageous effects
According to the embodiment of the disclosure, the method, the apparatus, the device, the medium and the computer program product for predicting the health state based on the physiological parameter have the following advantages and beneficial effects:
1. the health state prediction method, the apparatus, the device, the medium and the computer program product based on the physiological parameters construct and train a health state prediction model by adopting a forward-backward (Baum-Welch) algorithm of a hidden Markov model, estimate and predict a physiological parameter feature vector frame by using the health state prediction model to obtain a health state corresponding to the physiological parameters, can acquire the health state corresponding to a group of physiological parameters in real time without professional staff, and feed back and early warn the unhealthy state in time.
2. According to the method, the device, the equipment, the medium and the computer program product for predicting the health state based on the physiological parameters, a state prediction model of the physiological parameters and corresponding states (including healthy and unhealthy states) is established according to electrocardio/blood oxygen/body temperature corresponding to different health state conditions, and prediction result information is fed back and early warned in real time, so that the unhealthy states are fed back and early warned through a vibrating element without professionals, the automation of the feedback and early warning is realized, and the instantaneity of the feedback and early warning is ensured.
3. The method, the device, the equipment, the medium and the computer program product for predicting the health state based on the physiological parameters can predict the health state of a specific population (such as customs personnel, epidemic prevention personnel, athletes and the like), can eliminate physiological data deviation caused by acceleration according to acceleration characteristics corresponding to different actions of an airplane, simultaneously considers psychological state fluctuation caused by the acceleration, and predict and feed back the physiological and psychological states of the specific population in real time by combining a state prediction model.
Drawings
The above and other objects, features and advantages of the present disclosure will become more apparent from the following description of embodiments of the present disclosure with reference to the accompanying drawings, in which:
fig. 1 is a flow chart of a method of health status prediction based on physiological parameters in accordance with an embodiment of the present disclosure.
Fig. 2 is a block diagram of a physiological parameter based health status prediction apparatus in accordance with an embodiment of the present disclosure.
Fig. 3 is a schematic diagram of a method of health status prediction based on physiological parameters, in accordance with an embodiment of the present disclosure.
Fig. 4 is an electrocardiogram corresponding to an unknown state according to embodiment 1 of the present disclosure.
Fig. 5 is a graph of blood oxygen saturation data corresponding to an unknown state in accordance with embodiment 1 of the present disclosure.
FIG. 6 is a graph of electro-cardio and aircraft acceleration data for a particular population according to example 2 of the present disclosure.
FIG. 7 is an enlarged view of a portion of a specific population of ECG sites according to example 2 of the present disclosure.
Fig. 8 is a graph of specific population blood oxygen saturation data in accordance with embodiment 2 of the present disclosure.
Fig. 9 is a block diagram of a physiological parameter based health status prediction device in accordance with an embodiment of the present disclosure.
[ reference numerals ]:
s1, S2, S3: step (ii) of
200: health state prediction device based on physiological parameters
201: model building and training module
202: estimation module
203: prediction module
204: early warning prompt module
900: health state prediction apparatus
910: processor with a memory having a plurality of memory cells
920: memory device
921: computer program
Detailed Description
Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. It should be understood that the description is illustrative only and is not intended to limit the scope of the present disclosure. In the following detailed description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the disclosure. It may be evident, however, that one or more embodiments may be practiced without these specific details. Moreover, in the following description, descriptions of well-known structures and techniques are omitted so as to not unnecessarily obscure the concepts of the present disclosure.
All terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art unless otherwise defined. It is noted that the terms used herein should be interpreted as having a meaning that is consistent with the context of this specification and should not be interpreted in an idealized or overly formal sense.
And the shapes and sizes of the respective components in the drawings do not reflect actual sizes and proportions, but merely illustrate the contents of the embodiments of the present disclosure. Furthermore, in the claims, any reference signs placed between parentheses shall not be construed as limiting the claim.
Further still, the singular reference of "comprising" does not exclude the presence of elements or steps not listed in a claim. The singular reference of "a" or "an" preceding an element does not exclude the plural reference of such elements. The use of ordinal numbers such as "S1", "S2", "S3", etc., in the specification and claims to modify a step in a claim is not intended to imply any previous ordinal number with respect to the recited step, nor is the inclusion of a step in a different claim or a different order in a method of manufacture, and are used solely to distinguish one claimed step from another not so provided.
At present, a flexible sensor is adopted to measure various physiological parameters of a human body, and the following technologies are mainly disclosed: two snakelike wire arrays which are arranged in a staggered mode are used as capacitors and connected with inductors in series to form an LC resonance circuit, and finally the LC resonance circuit is packaged by Polyamide (PI) and Polydimethylsiloxane (PDMS) to obtain the strain sensor which can be attached to human skin flexibly. The strain sensor converts the strain of human skin into the capacitance change of the lead array, and reversely deduces the local strain of the skin through recording the resonant frequency of the circuit. The von-snow professor of Qinghua university develops a skin-like flexible temperature sensor based on the temperature resistance effect of metal, and the resistance change of a circuit caused by skin strain is far smaller than that caused by temperature by reasonably designing the configuration of a lead; and the flexible substrate containing irregular holes (the diameter is about hundreds of nanometers to tens of micrometers) is utilized, so that the waterproofness and the air permeability of the device are ensured, and the working time of the device after being attached to the skin is prolonged. The quality professor of the university of electronic technology takes a thin film formed by a carbon nanotube network as a conductive layer, and introduces a rectangular pyramid microstructure on the parallel surfaces of the thin films, so that the high-sensitivity flexible pressure sensor is finally prepared. A glucose catalytic enzyme is introduced into a current sensing module, the glucose concentration in sweat is converted into a current signal, the current signal is processed by a signal amplifier, a filter and a microcontroller which are integrated on a flexible substrate, and the current signal is transmitted to a mobile terminal such as a mobile phone in real time through Bluetooth.
Although these flexible sensors achieve accurate measurement of physiological parameters of human body, they still have great disadvantages in real-time comprehensive analysis of data. These flexible sensors only stay on a fragmented collection of single or multiple physiological data and do not allow comprehensive analytical processing of multiple physiological data. For physiological data such as body temperature, heart rate, acceleration and the like, monitored personnel can carry out comparison and judgment according to common knowledge; however, the physiological data such as myoelectricity, electrocardio, blood oxygen saturation and the like can be fed back to the monitored personnel only through the analysis of professional personnel, so that the flexible sensor can not provide early warning for part of physiological states of the monitored personnel in time. In addition, the fragmented physiological parameters can only judge a plurality of single health states, such as arrhythmia, premature beat and atrial fibrillation according to the electrocardio, fever according to the body temperature and the like; however, for less complex diseases, such as hyperthyroidism, comprehensive analysis of comprehensive indexes of the human body is required, which greatly limits the application range of the flexible sensor.
In view of this, it is an urgent technical problem to break through the application range limitation of the flexible sensor, obtain the health status corresponding to a set of physiological parameters in real time, and timely feed back and warn the unhealthy status.
For the technical problem, in the embodiment of the present disclosure, a health state prediction Model is constructed and trained by using a forward-backward (Baum-Welch) algorithm of a Hidden Markov Model (HMM), and a physiological parameter feature vector frame is estimated and predicted by using the health state prediction Model to obtain a health state corresponding to the physiological parameter, so that a health state corresponding to a group of physiological parameters can be obtained in real time without a professional, and a non-health state is fed back and early warned in time.
Embodiments of the present disclosure relate to the following terms: the hidden Markov model HMM is a probability model related to time sequence, and describes a process of generating an unobservable state random sequence by a hidden Markov chain randomly and generating an observation random sequence by each state, wherein the state sequence generated by the hidden Markov chain randomly is called a state sequence; each state generates an observation, and the resulting random sequence of observations, referred to as the observation sequence. Each position of the sequence can in turn be regarded as a time instant. Hidden markov models evaluate new observation sequences by performing statistics and training on processes that contain unknown parameters. The Baum-Welch algorithm is one of the hidden markov model algorithms.
An embodiment of the present disclosure provides a method for predicting a health state based on a physiological parameter, as shown in fig. 1, fig. 1 is a flowchart of a method for predicting a health state based on a physiological parameter according to an embodiment of the present disclosure. It should be noted that fig. 1 is only an example of an application scenario in which the embodiments of the present disclosure may be applied to help those skilled in the art understand the technical content of the present disclosure, but does not mean that the embodiments of the present disclosure may not be used in other environments or scenarios.
As shown in fig. 1, a method for health state prediction based on physiological parameters according to an embodiment of the present disclosure includes the following steps:
step S1: and constructing and training a health state prediction model.
In this step, the building and training of the health state prediction model is implemented by using a Baum-Welch algorithm of a hidden markov model, and specifically includes the following steps:
step S11: acquiring a plurality of groups of health state physiological parameter characteristic vector frames corresponding to the health state, and merging the plurality of groups of health state physiological parameter characteristic vector frames to obtain a health state vector frame matrix;
step S12: acquiring a plurality of groups of unhealthy state physiological parameter characteristic vector frames corresponding to unhealthy states, and merging the plurality of groups of unhealthy state physiological parameter characteristic vector frames to obtain an unhealthy state vector frame matrix;
step S13: and inputting the healthy state vector frame matrix and the unhealthy state vector frame matrix into a hidden Markov model for sample training by adopting a Baum-Welch algorithm to obtain a healthy state prediction model.
In an embodiment of the present disclosure, the physiological parameters include at least electrocardiogram, blood oxygen and body temperature. In the step of acquiring multiple sets of health state physiological parameter feature vector frames corresponding to the health state in step S11, the acquiring process of each set of health state physiological parameter feature vector frames corresponding to the health state includes: respectively carrying out overlapping framing on each group of electrocardiogram, blood oxygen diagram and body temperature corresponding to the health state, and extracting the electrocardiogram characteristic value, the average blood oxygen concentration value and the average body temperature value of the group corresponding to the health state; and carrying out matrix combination on the electrocardio characteristic value, the average blood oxygen concentration value and the average body temperature value of each group corresponding to the health state to obtain a group of physiological parameter characteristic vector frames corresponding to the health state. In the step of acquiring multiple sets of physiological parameter feature vector frames corresponding to the unhealthy state in step S12, the acquiring process of each set of physiological parameter feature vector frames corresponding to the unhealthy state includes: respectively carrying out overlapping framing on each group of electrocardiogram, blood oxygen diagram and body temperature corresponding to the unhealthy state, and extracting the electrocardiogram characteristic value, the average blood oxygen concentration value and the average body temperature value of the group corresponding to the unhealthy state; and carrying out matrix combination on the electrocardio characteristic value, the average blood oxygen concentration value and the average body temperature value of each group corresponding to the unhealthy state to obtain a group of unhealthy state physiological parameter characteristic vector frames corresponding to the unhealthy state.
Step S2: and estimating a group of physiological parameter feature vector frames corresponding to the unknown state by using the health state prediction model to obtain the state likelihood probability corresponding to the unknown state.
In this step, before the step of estimating a set of frames of physiological parameter feature vectors corresponding to an unknown state by using the health state prediction model, the method further includes: a set of frames of physiological parameter feature vectors corresponding to unknown states is acquired.
In this step, the acquiring a set of physiological parameter feature vector frames corresponding to an unknown state includes: respectively carrying out overlapping framing on a group of electrocardiograms, blood oxygen graphs and body temperatures corresponding to unknown states, and extracting an electrocardio characteristic value, an average blood oxygen concentration value and an average body temperature value of the group corresponding to the unknown states; and carrying out matrix combination on the electrocardio characteristic value, the average blood oxygen concentration value and the average body temperature value of the group corresponding to the unknown state to obtain a physiological parameter characteristic vector frame of the group corresponding to the unknown state.
In this step, in the step of estimating a set of physiological parameter feature vector frames corresponding to an unknown state by using the health state prediction model to obtain a state likelihood probability corresponding to the unknown state, a maximum likelihood estimation method is used to estimate the set of physiological parameter feature vector frames corresponding to the unknown state to obtain the state likelihood probability corresponding to the unknown state.
Step S3: the health state is predicted based on the state likelihood probability corresponding to the unknown state, resulting in a predicted health state.
In this step, the predicting the health state based on the state likelihood probability corresponding to the unknown state to obtain a predicted health state includes: presetting a threshold value of the state likelihood probability, judging whether the state likelihood probability corresponding to the unknown state is greater than the threshold value, and if so, determining that the unknown state is a healthy state; otherwise, the unknown state is an unhealthy state.
In an embodiment of the disclosure, when the unknown state is an unhealthy state, the method for predicting a health state based on a physiological parameter further includes: and carrying out early warning prompt, namely carrying out feedback and early warning prompt on the unhealthy state.
It can be seen from the foregoing embodiments that, in the method for predicting a health state based on physiological parameters provided in the embodiments of the present disclosure, a health state prediction model is constructed and trained by using a Baum-Welch algorithm of a hidden markov model, and a physiological parameter feature vector frame is estimated and predicted by using the health state prediction model to obtain a health state corresponding to the physiological parameter, so that a health state corresponding to a group of physiological parameters can be obtained in real time without a professional, and a non-health state is fed back and pre-warned in time.
Based on the flowchart of the method for physiological parameter based health status prediction according to the embodiment of the present disclosure shown in fig. 1, fig. 2 schematically shows a block diagram of a physiological parameter based health status prediction apparatus according to an embodiment of the present disclosure.
As shown in fig. 2, a health state prediction apparatus 200 based on physiological parameters provided by the embodiment of the present disclosure includes a model building and training module 201, an estimation module 202, and a prediction module 203, wherein: the model construction and training module 201 is used for constructing and training a health state prediction model; the estimation module 202 is configured to estimate a set of physiological parameter feature vector frames corresponding to an unknown state by using the health state prediction model to obtain a state likelihood probability corresponding to the unknown state; the prediction module 203 predicts the health state based on the state likelihood probability corresponding to the unknown state, resulting in a predicted health state.
Further, the health status prediction apparatus 200 based on physiological parameters provided by the embodiment of the present disclosure further includes: and the early warning prompting module 204 is configured to perform early warning prompting when the unknown state is an unhealthy state.
It should be understood that the model construction and training module 201, the estimation module 202, the prediction module 203, and the early warning prompt module 204 may be combined and implemented in one module, or any one of them may be split into multiple modules. Or again, at least part of the functionality of one or more of these modules may be combined with at least part of the functionality of other modules and implemented in one module.
According to an embodiment of the present disclosure, at least one of the model building and training module 201, the estimation module 202, the prediction module 203, and the warning suggestion module 204 may be implemented at least in part as a hardware circuit, such as a Field Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a system on a chip, a system on a substrate, a system on a package, an Application Specific Integrated Circuit (ASIC), or may be implemented in hardware or firmware in any other reasonable manner of integrating or packaging a circuit, or in a suitable combination of three implementations of software, hardware, and firmware. Or again, at least one of the model building and training module 201, the estimation module 202, the prediction module 203 and the early warning suggestion module 204 may be at least partially implemented as a computer program module which, when executed by a computer, may perform the functions of the respective module.
Based on a flowchart of a method for physiological parameter based health status prediction according to an embodiment of the present disclosure shown in fig. 1 and a block diagram of a physiological parameter based health status prediction apparatus according to an embodiment of the present disclosure shown in fig. 2, fig. 3 schematically shows a schematic diagram of a physiological parameter based health status prediction method according to an embodiment of the present disclosure.
As shown in fig. 3, a method for predicting a health state based on physiological parameters provided by an embodiment of the present disclosure includes the following steps:
step 31: and acquiring and combining health state physiological parameter characteristic vector frames corresponding to the M groups of health states to obtain a health state vector frame matrix.
The physiological parameters in this embodiment at least include electrocardiogram, blood oxygen and body temperature, wherein M is greater than or equal to 2000, and may be 2000. According to the embodiment of the disclosure, a potential signal is acquired by the patch type electrocardiograph, and is sent to the signal conditioning circuit to be filtered, amplified and the like to obtain an analog electrocardiograph signal meeting requirements, and then the analog electrocardiograph signal is converted into a digital signal by the 16-bit precise ADC circuit and is subjected to related digital signal processing, so that data such as electrocardiograph waveform, heart rate, lead connection state and the like can be obtained. Measuring the body temperature through the temperature resistance effect of a metal circuit in the surface mount type temperature monitor; the blood oxygen saturation can be calculated by detecting the absorption principle of arterial blood to light through the flexible blood oxygen sensor, converting the light intensity change of the detected part into an electric signal through the photoelectric element and combining with the scale factor. The signals are transmitted to a mobile terminal such as a mobile phone in real time through a Bluetooth module arranged in the sensor, and are displayed through an application program such as a mobile phone App on the mobile terminal.
In this embodiment, the process of acquiring the physiological parameter feature vector frame corresponding to each group of health states is as follows:
and 311, overlapping and framing the electrocardiogram, the blood oxygen diagram and the body temperature corresponding to each group of health states respectively to obtain an electrocardiogram characteristic vector matrix, an average blood oxygen concentration matrix and an average body temperature matrix corresponding to the group of health states.
In this step, the overlapping rate of the overlapping sub-frames is 30% -70%, and the window length is 50 ms-200 ms.
And step 312, performing matrix combination on the electrocardio characteristic vector matrix, the average blood oxygen concentration matrix and the average body temperature matrix corresponding to the group of health states to obtain a physiological parameter characteristic vector frame corresponding to the group of health states.
Step 32: acquiring and combining non-health state physiological parameter characteristic vector frames corresponding to M groups of non-health states to obtain a non-health state vector frame matrix.
In this embodiment, the acquiring process of the non-health state physiological parameter feature vector frame corresponding to each group of non-health states is as follows:
and 321, overlapping and framing the electrocardiogram, the blood oxygen diagram and the body temperature corresponding to each group of unhealthy states respectively to obtain an electrocardiogram characteristic vector matrix, an average blood oxygen concentration matrix and an average body temperature matrix corresponding to the group of unhealthy states.
And 322, combining the electrocardio characteristic vector matrix, the average blood oxygen concentration matrix and the average body temperature matrix corresponding to the group of unhealthy states to obtain a physiological parameter characteristic vector frame corresponding to the group of healthy, unhealthy or unknown states.
Step 33: and inputting the healthy state vector frame matrix and the unhealthy state vector frame matrix into Hidden Markov Models (HMMs) by adopting a Baum-Welch method, and carrying out sample training to obtain a state prediction model.
In the present embodiment, the number of hidden states in the hidden markov model is preferably N-5, and the probability distribution of each observation value is modeled by a 3 rd order gaussian mixture model. The same method is adopted to carry out modeling training on physiological states such as abnormal blood circulation, hyperthyroidism and the like and psychological states such as sympathetic nerve excitation and the like, so as to obtain a corresponding state prediction model.
Step 34: and acquiring a group of physiological parameter feature vector frames of an unknown state, inputting the physiological parameter feature vector frames into the state prediction model, and obtaining the state likelihood probability corresponding to the unknown state by adopting a maximum likelihood estimation method.
In this embodiment, the process of acquiring the physiological parameter feature vector frame corresponding to each unknown state is as follows:
step 341, overlapping and framing the electrocardiogram, the blood oxygen diagram and the body temperature corresponding to each group of unknown states respectively to obtain an electrocardiogram characteristic vector matrix, an average blood oxygen concentration matrix and an average body temperature matrix corresponding to the group of unknown states;
and 342, combining the electrocardio characteristic vector matrix, the average blood oxygen concentration matrix and the average body temperature matrix corresponding to the unknown state to obtain a physiological parameter characteristic vector frame corresponding to the unknown state.
The present embodiment makes the newly added (unknown state) observation sequence and the original sample sequence have the maximum likelihood function expectation under the likelihood probability through the maximum likelihood estimation (iterative and partial derivation). Finally, the observation sequence after testing is identified as the state corresponding to the HMMs which can generate the maximum likelihood probability, and the state likelihood probability corresponding to the unknown state can be obtained.
Step 35: judging whether the state likelihood probability corresponding to the group of unknown states is greater than a threshold value, if so, judging that the group of unknown states are healthy states; if not, the set of unknown states are unhealthy.
In this embodiment, when the set of unknown states is a healthy state, the healthy state may be displayed through the mobile app; when the set of unknown states are unhealthy, the unhealthy state may be displayed through the mobile app.
Step 36: and when the group of unknown states are unhealthy states, carrying out early warning prompt.
In this embodiment, a vibration element on the physiological parameter acquisition module (such as a patch electrocardiograph, a patch temperature monitor, and a flexible blood oxygen sensor) may be activated and vibrated to give an early warning to the person to be measured.
Example 1: a prediction of a physiological state;
the sensor wearing mode is as follows: the chest, the forehead and the back of the neck of a tested person are wiped by alcohol, and then the patch type electrocardiograph, the patch type temperature monitor and the flexible blood oxygen sensor are respectively pasted at the positions by using a medical pressure-sensitive adhesive tape, and the chest muscle group of a human body is avoided.
The test mode is as follows: the tested person moves such as walking, jumping in small amplitude and the like.
The electrocardio, temperature and blood oxygen data of a specific crowd are read through the sensor, and the corresponding health condition of the tested person is displayed by adopting the health condition prediction method based on the physiological parameters provided by the embodiment.
And (3) testing results: data measurement results on a human body are shown in fig. 4 and 5, fig. 4 is an electrocardiogram corresponding to an unknown state according to embodiment 1 of the present disclosure, and fig. 5 is a blood oxygen saturation data graph corresponding to an unknown state according to embodiment 1 of the present disclosure.
In this example, the body temperature is 38 ℃. As can be seen from the analysis of FIG. 4, the tested person has symptoms of sinus arrhythmia and atrial premature beat; by combining the variation trend of the fluctuation of the blood oxygen saturation in the vicinity of 45% in fig. 5 and combining the body temperature of 38 ℃, the method for predicting the health state provided by the embodiment is adopted, and the physiological state of the person is obtained and judged to be abnormal in blood circulation in real time, and is consistent with the symptoms of chest distress and weakness of the person to be tested.
Example 2: predicting physiological and psychological states of specific people;
the sensor wearing mode is as follows: wiping the chest and forehead of the tested person with alcohol, and respectively attaching the patch type electrocardiograph and the patch type temperature monitor to the positions by using a medical pressure-sensitive adhesive tape, wherein the chest muscle group of the human body is avoided. The flexible blood oxygen sensor is embedded into the lining of the helmet and worn by specific people.
The test mode is as follows: the specific crowd operates tail rotor stall in the airplane.
The method comprises the steps of reading electrocardio, temperature and blood oxygen data of a specific crowd through a sensor, and simultaneously reading triaxial acceleration of an airplane in real time.
And (3) testing results: the data measurement results for human body are shown in fig. 6, 7 and 8, fig. 6 is a diagram of electrocardiogram and aircraft acceleration data of specific population according to embodiment 2 of the present disclosure, fig. 7 is an enlarged view of a portion of electrocardiogram of specific population according to embodiment 2 of the present disclosure, and fig. 8 is a diagram of blood oxygen saturation data of specific population according to embodiment 2 of the present disclosure. The body temperature was 37.5 ℃.
As can be seen from the analysis of FIGS. 6 and 7, the room speed phenomenon exists in the tail rotor stall process of a specific population, and the room speed can be judged to be caused by the fact that the acceleration is gradually restored to be normal from a high g value in the tail rotor stall process by combining an acceleration data graph; by combining the change trend of the fluctuation of the blood oxygen saturation in the vicinity of 12% in fig. 8 and the body temperature of 37.5 ℃, the physiological state of a specific population is judged to be normal in real time and the psychological state is judged to be sympathetic excitation in real time by adopting the health state prediction method provided by the embodiment. By analyzing and judging electrocardio, temperature, blood oxygen and acceleration in real time, the early warning is carried out on specific people, and important physiological systems such as cervical vertebra and the like are protected from being damaged.
In the embodiment, the physiological state is predicted, and according to the relationship of the changes of the electrocardio/blood oxygen/body temperature corresponding to different physiological states along with time, the physiological parameters monitored in real time can quickly establish a state prediction model with the corresponding state, and the information of the prediction result is fed back to the tested person in real time; and predicting the physiological state of the specific population, eliminating physiological data deviation caused by acceleration according to acceleration characteristics corresponding to different actions of the airplane, simultaneously considering psychological state fluctuation caused by the acceleration, and predicting and feeding back the physiological and psychological states of the specific population in real time by combining a state prediction model.
It can be seen from the foregoing embodiments that, according to the method for predicting a health state based on physiological parameters provided in the embodiments of the present disclosure, a state prediction model of physiological parameters and corresponding states (including healthy and unhealthy states) is established according to electrocardio/blood oxygen/body temperature corresponding to different health state conditions, and prediction result information is fed back and pre-warned in real time, and the unhealthy state is fed back and pre-warned by a vibrating element without a professional, so that automation of the feedback and pre-warning is realized, and instantaneity of the feedback and pre-warning is ensured. The health state prediction method based on the physiological parameters can predict the health state of a specific population (such as customs personnel, epidemic prevention personnel, athletes and the like), can eliminate physiological data deviation caused by acceleration according to acceleration characteristics corresponding to different actions of an airplane, simultaneously considers psychological state fluctuation caused by the acceleration, and combined with a state prediction model, predicts the physiological and psychological states of the specific population and feeds back the physiological and psychological states in real time.
The embodiment of the present disclosure also provides a health status prediction apparatus based on physiological parameters, as shown in fig. 9, fig. 9 is a block diagram of a health status prediction apparatus 900 based on physiological parameters according to an embodiment of the present disclosure. The health state prediction apparatus 900 includes: one or more processors 910; a memory 920 storing a computer executable program that, when executed by the processor 910, causes the processor 910 to implement the method for predicting a health state based on a physiological parameter as illustrated in fig. 1.
In particular, processor 910 may include, for example, a general purpose microprocessor, an instruction set processor and/or related chip set and/or a special purpose microprocessor (e.g., an Application Specific Integrated Circuit (ASIC)), and/or the like. The processor 910 may also include onboard memory for caching purposes. The processor 410 may be a single processing unit or multiple processing units for performing different actions of a method flow according to embodiments of the disclosure.
The memory 920 may be, for example, any medium that can contain, store, communicate, propagate, or transport the instructions. For example, a readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, device, or propagation medium. Specific examples of the readable storage medium include: magnetic storage devices, such as magnetic tape or Hard Disk Drives (HDDs); optical storage devices, such as compact disks (CD-ROMs); a memory, such as a Random Access Memory (RAM) or a flash memory; and/or wired/wireless communication links.
The computer program 921 may be configured to have, for example, a computer program code including computer program modules. For example, in an example embodiment, the union code in computer program 921 may include at least one program module, including, for example, module 921A, module 921B, … …. It should be noted that the dividing manner and number of the modules are not fixed, and those skilled in the art may use suitable program modules or program module combinations according to actual situations, when these program modules are executed by the processor 910, the processor 910 may execute the health status prediction method according to the embodiment of the present disclosure or any variation thereof.
The embodiments of the present disclosure also provide a storage medium containing computer-executable instructions, which may be contained in the apparatus/device described in the above embodiments, or may exist separately without being assembled into the apparatus/device. The storage medium carries/contains one or more computer-executable instructions that, when executed, implement the method for predicting a health state based on a physiological parameter as illustrated in fig. 1.
According to embodiments of the present disclosure, a storage medium containing computer-executable instructions may be a computer-readable signal medium or a computer-readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In contrast, in the present disclosure, a computer-readable signal medium may include a propagated data signal with a computer-readable program and code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, fiber optic, radio frequency signals, etc., or any suitable combination thereof.
The present disclosure also provides a computer program product comprising: a computer program which, when being executed by a processor, implements the method for physiological parameter based health state prediction illustrated in fig. 1.
The present disclosure has been described in detail so far with reference to the accompanying drawings. From the above description, those skilled in the art should clearly recognize the present disclosure.
It is to be noted that, in the attached drawings or in the description, the implementation modes not shown or described are all the modes known by the ordinary skilled person in the field of technology, and are not described in detail. In addition, the above definitions of the respective elements are not limited to the specific structures, shapes or modes mentioned in the embodiments, and those skilled in the art may easily modify or replace them.
Of course, the present disclosure may also include other parts according to actual needs, and since the parts are not related to the innovation of the present disclosure, the details are not described herein.
Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the disclosure, various features of the disclosure are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various disclosed aspects. However, the disclosed method should not be interpreted as reflecting an intention that: that is, the claimed disclosure requires more features than are expressly recited in each claim. Rather, as the following claims reflect, disclosed aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this disclosure.
Further, in the drawings or description, the same drawing reference numerals are used for similar or identical parts. Features in various embodiments illustrated in the description may be freely combined to form a new scheme without conflict, and in addition, each claim may be taken alone as an embodiment or technical features in various claims may be combined to form a new embodiment. Further, elements or implementations not shown or described in the drawings are of a form known to those of ordinary skill in the art. Additionally, while exemplifications of parameters including particular values may be provided herein, it is to be understood that the parameters need not be exactly equal to the respective values, but may be approximated to the respective values within acceptable error margins or design constraints.
Unless a technical obstacle or contradiction exists, the above-described various embodiments of the present disclosure may be freely combined to form further embodiments, which are all within the scope of protection of the present disclosure.
While the present disclosure has been described in connection with the accompanying drawings, the embodiments disclosed in the drawings are intended to be illustrative of the preferred embodiments of the disclosure, and should not be construed as limiting the disclosure. The dimensional proportions in the drawings are merely schematic and are not to be understood as limiting the disclosure.
Although a few embodiments of the present general inventive concept have been shown and described, it would be appreciated by those skilled in the art that changes may be made in these embodiments without departing from the principles and spirit of the general inventive concept, the scope of which is defined in the claims and their equivalents.
The above-mentioned embodiments are intended to illustrate the objects, aspects and advantages of the present disclosure, and it should be understood that the above-mentioned embodiments are only examples of the present disclosure, and are not intended to limit the present disclosure, and any changes, equivalents, improvements, etc. made within the spirit and principle of the present disclosure should be included in the scope of the present disclosure.
Claims (14)
1. A method of predicting a state of health, comprising:
building and training a health state prediction model;
estimating a group of physiological parameter feature vector frames corresponding to an unknown state by using the health state prediction model to obtain state likelihood probability corresponding to the unknown state; and
the health state is predicted based on the state likelihood probability corresponding to the unknown state, resulting in a predicted health state.
2. The method of claim 1, wherein the constructing and training of the health state prediction model is performed using a hidden markov model forward-backward (Baum-Welch) algorithm.
3. The health state prediction method of claim 2, wherein the forward-to-backward (Baum-Welch) algorithm using hidden markov models implements the construction and training of the health state prediction model, comprising:
acquiring a plurality of groups of health state physiological parameter characteristic vector frames corresponding to the health state, and merging the plurality of groups of health state physiological parameter characteristic vector frames to obtain a health state vector frame matrix;
acquiring a plurality of groups of unhealthy state physiological parameter characteristic vector frames corresponding to unhealthy states, and merging the plurality of groups of unhealthy state physiological parameter characteristic vector frames to obtain an unhealthy state vector frame matrix;
and inputting the health state vector frame matrix and the unhealthy state vector frame matrix into a hidden Markov model by adopting a forward-backward (Baum-Welch) algorithm to perform sample training to obtain a health state prediction model.
4. The method of claim 3, wherein the physiological parameters at least include electrocardiogram, blood oxygen and body temperature;
in the step of acquiring a plurality of sets of health state physiological parameter feature vector frames corresponding to the health state, the acquiring process of each set of health state physiological parameter feature vector frames corresponding to the health state includes: respectively carrying out overlapping framing on each group of electrocardiogram, blood oxygen diagram and body temperature corresponding to the health state, and extracting the electrocardiogram characteristic value, the average blood oxygen concentration value and the average body temperature value of the group corresponding to the health state; carrying out matrix combination on each group of electrocardio characteristic values, average blood oxygen concentration values and average body temperature values corresponding to the health state to obtain a group of physiological parameter characteristic vector frames corresponding to the health state;
in the step of acquiring a plurality of groups of non-health state physiological parameter feature vector frames corresponding to non-health states, the acquiring process of each group of non-health state physiological parameter feature vector frames corresponding to non-health states comprises: respectively carrying out overlapping framing on each group of electrocardiogram, blood oxygen diagram and body temperature corresponding to the unhealthy state, and extracting the electrocardiogram characteristic value, the average blood oxygen concentration value and the average body temperature value of the group corresponding to the unhealthy state; and carrying out matrix combination on the electrocardio characteristic value, the average blood oxygen concentration value and the average body temperature value of each group corresponding to the unhealthy state to obtain a group of unhealthy state physiological parameter characteristic vector frames corresponding to the unhealthy state.
5. The method of claim 1, wherein the step of estimating a set of frames of physiological parameter feature vectors corresponding to unknown states using the health state prediction model is preceded by the step of:
a set of frames of physiological parameter feature vectors corresponding to unknown states is acquired.
6. The method of claim 5, wherein the physiological parameters at least include ecg, oximetry, and body temperature, and the obtaining a set of frames of physiological parameter feature vectors corresponding to the unknown state comprises:
respectively carrying out overlapping framing on a group of electrocardiograms, blood oxygen graphs and body temperatures corresponding to unknown states, and extracting an electrocardio characteristic value, an average blood oxygen concentration value and an average body temperature value of the group corresponding to the unknown states; and carrying out matrix combination on the electrocardio characteristic value, the average blood oxygen concentration value and the average body temperature value of the group corresponding to the unknown state to obtain a physiological parameter characteristic vector frame of the group corresponding to the unknown state.
7. The method of claim 1, wherein the step of estimating a set of frames of the physiological parameter feature vector corresponding to the unknown state by using the health state prediction model to obtain the state likelihood probability corresponding to the unknown state comprises estimating the set of frames of the physiological parameter feature vector corresponding to the unknown state by using a maximum likelihood estimation method to obtain the state likelihood probability corresponding to the unknown state.
8. The method of claim 1, wherein predicting the health state based on the state likelihood probability corresponding to the unknown state to obtain the predicted health state comprises:
presetting a threshold value of the state likelihood probability, judging whether the state likelihood probability corresponding to the unknown state is greater than the threshold value, and if so, determining that the unknown state is a healthy state; otherwise, the unknown state is an unhealthy state.
9. The health state prediction method of claim 8, further comprising:
and when the unknown state is the unhealthy state, carrying out early warning prompt.
10. A state of health prediction apparatus, comprising:
the model building and training module is used for building and training the health state prediction model;
the estimation module is used for estimating a group of physiological parameter feature vector frames corresponding to an unknown state by using the health state prediction model to obtain state likelihood probability corresponding to the unknown state;
and the prediction module predicts the health state based on the state likelihood probability corresponding to the unknown state to obtain the predicted health state.
11. The health state prediction device of claim 10, further comprising:
and the early warning prompting module is used for carrying out early warning prompting when the unknown state is a non-healthy state.
12. A state of health prediction device, comprising:
one or more processors;
a memory storing a computer executable program which, when executed by the processor, causes the processor to implement the health state prediction method of any one of claims 1-9.
13. A storage medium containing computer-executable instructions that, when executed, implement the health state prediction method of any one of claims 1-9.
14. A computer program product comprising a computer program, characterized in that the computer program realizes the health status prediction method of any one of claims 1-9 when executed by a processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111556964.0A CN114259235A (en) | 2021-12-18 | 2021-12-18 | Health state prediction method, apparatus, device, medium, and computer program product |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111556964.0A CN114259235A (en) | 2021-12-18 | 2021-12-18 | Health state prediction method, apparatus, device, medium, and computer program product |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114259235A true CN114259235A (en) | 2022-04-01 |
Family
ID=80827866
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111556964.0A Pending CN114259235A (en) | 2021-12-18 | 2021-12-18 | Health state prediction method, apparatus, device, medium, and computer program product |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114259235A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040230105A1 (en) * | 2003-05-15 | 2004-11-18 | Widemed Ltd. | Adaptive prediction of changes of physiological/pathological states using processing of biomedical signals |
| CN110464349A (en) * | 2019-08-30 | 2019-11-19 | 南京邮电大学 | A kind of upper extremity exercise function score method based on hidden Semi-Markov Process |
| CN113096792A (en) * | 2021-04-01 | 2021-07-09 | 宁波伟吉电力科技有限公司 | Intelligent health monitoring and early warning method and system based on machine learning |
-
2021
- 2021-12-18 CN CN202111556964.0A patent/CN114259235A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040230105A1 (en) * | 2003-05-15 | 2004-11-18 | Widemed Ltd. | Adaptive prediction of changes of physiological/pathological states using processing of biomedical signals |
| CN110464349A (en) * | 2019-08-30 | 2019-11-19 | 南京邮电大学 | A kind of upper extremity exercise function score method based on hidden Semi-Markov Process |
| CN113096792A (en) * | 2021-04-01 | 2021-07-09 | 宁波伟吉电力科技有限公司 | Intelligent health monitoring and early warning method and system based on machine learning |
Non-Patent Citations (1)
| Title |
|---|
| 赵力: "《语音信号处理》", 机械工业出版社, pages: 225 - 227 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3558101B1 (en) | Methods and systems for determining abnormal cardiac activity | |
| Heikenfeld et al. | Wearable sensors: modalities, challenges, and prospects | |
| KR102141617B1 (en) | Method, system and non-transitory computer-readable recording medium for estimating arrhythmia by using artificial neural network | |
| JP2019084343A (en) | Method and apparatus for high accuracy photoplethysmogram based atrial fibrillation detection using wearable device | |
| WO2016078258A1 (en) | Physiological sign detecting method and device, and computer storage medium | |
| US20210269046A1 (en) | Estimator generation apparatus, monitoring apparatus, estimator generation method, and computer-readable storage medium storing estimator generation program | |
| KR101205908B1 (en) | Mild cognitive impairment and Alzheimer's disease evaluation system using Gait dynamics and HRV monitoring and the method thereof | |
| KR20160029375A (en) | Method and device to monitor and analyzing bio signal of user | |
| JP6986161B2 (en) | Analysis of ECG data from remote portable sensor devices | |
| CN105769173A (en) | Electrocardiogram monitoring system with electrocardiosignal denoising function | |
| Chowdhury et al. | Machine learning in wearable biomedical systems | |
| Li et al. | Design of a wireless sensor system with the algorithms of heart rate and agility index for athlete evaluation | |
| JP6534192B2 (en) | Patient health composite score distribution and / or representative composite score based thereon | |
| Chen et al. | A wearable sensor system for neonatal seizure monitoring | |
| Rajan et al. | Feasibility analysis of portable electroencephalography based abnormal fatigue detection and tele-surveillance system | |
| Kozlovszky et al. | Cardiovascular and diabetes focused remote patient monitoring | |
| WO2022266392A1 (en) | Ml-based anomaly detection and descriptive root-cause analysis for biodata | |
| US20220167917A1 (en) | Respiratory disease monitoring wearable apparatus | |
| Lin et al. | Wearable cardiopulmonary function evaluation system for six-minute walking test | |
| Bansal | Real-Time Data Acquisition in Human Physiology: Real-Time Acquisition, Processing, and Interpretation—A MATLAB-Based Approach | |
| Rodriguez et al. | Towards automatic sensor-based triage for individual remote monitoring during mass casualty incidents | |
| CN114259235A (en) | Health state prediction method, apparatus, device, medium, and computer program product | |
| Alfarhan et al. | Wireless heart abnormality monitoring kit based on Raspberry Pi | |
| CN115349832A (en) | Vital sign monitoring and early warning system and method | |
| Hey et al. | Recent developments of ambulatory assessment methods |
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 |