CN115662629A - Heart failure monitoring system and prediction evaluation method thereof - Google Patents
Heart failure monitoring system and prediction evaluation method thereof Download PDFInfo
- Publication number
- CN115662629A CN115662629A CN202211240278.7A CN202211240278A CN115662629A CN 115662629 A CN115662629 A CN 115662629A CN 202211240278 A CN202211240278 A CN 202211240278A CN 115662629 A CN115662629 A CN 115662629A
- Authority
- CN
- China
- Prior art keywords
- data
- heart failure
- monitoring
- operational amplifier
- formula
- 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
- 206010019280 Heart failures Diseases 0.000 title claims abstract description 150
- 238000012544 monitoring process Methods 0.000 title claims abstract description 126
- 238000011156 evaluation Methods 0.000 title claims abstract description 26
- 238000004458 analytical method Methods 0.000 claims abstract description 43
- 238000000034 method Methods 0.000 claims abstract description 39
- 238000007726 management method Methods 0.000 claims abstract description 28
- 230000005540 biological transmission Effects 0.000 claims abstract description 27
- 238000013178 mathematical model Methods 0.000 claims abstract description 18
- 238000012545 processing Methods 0.000 claims abstract description 14
- 238000013500 data storage Methods 0.000 claims abstract description 7
- 238000003860 storage Methods 0.000 claims abstract description 6
- 238000004422 calculation algorithm Methods 0.000 claims description 29
- 239000013598 vector Substances 0.000 claims description 20
- 239000011159 matrix material Substances 0.000 claims description 18
- 238000005303 weighing Methods 0.000 claims description 12
- 238000005070 sampling Methods 0.000 claims description 10
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 9
- 238000006243 chemical reaction Methods 0.000 claims description 8
- 210000003414 extremity Anatomy 0.000 claims description 7
- 210000003141 lower extremity Anatomy 0.000 claims description 7
- 230000005856 abnormality Effects 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 6
- 238000013507 mapping Methods 0.000 claims description 6
- 238000012821 model calculation Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 4
- 230000001502 supplementing effect Effects 0.000 claims description 4
- 238000013523 data management Methods 0.000 claims description 3
- 230000036541 health Effects 0.000 claims description 3
- 239000013589 supplement Substances 0.000 claims description 3
- 238000013519 translation Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 9
- 201000010099 disease Diseases 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- DDRJAANPRJIHGJ-UHFFFAOYSA-N creatinine Chemical compound CN1CC(=O)NC1=N DDRJAANPRJIHGJ-UHFFFAOYSA-N 0.000 description 4
- 230000009466 transformation Effects 0.000 description 4
- 230000037396 body weight Effects 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 208000035475 disorder Diseases 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 208000024891 symptom Diseases 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 206010007556 Cardiac failure acute Diseases 0.000 description 2
- 208000024172 Cardiovascular disease Diseases 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 2
- 239000008280 blood Substances 0.000 description 2
- 210000004369 blood Anatomy 0.000 description 2
- 230000000747 cardiac effect Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000010835 comparative analysis Methods 0.000 description 2
- 229940109239 creatinine Drugs 0.000 description 2
- 238000009795 derivation Methods 0.000 description 2
- 238000003748 differential diagnosis Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000000737 periodic effect Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 239000000047 product Substances 0.000 description 2
- 238000012797 qualification Methods 0.000 description 2
- 230000007704 transition Effects 0.000 description 2
- 230000002485 urinary effect Effects 0.000 description 2
- 230000002861 ventricular Effects 0.000 description 2
- 208000031229 Cardiomyopathies Diseases 0.000 description 1
- 208000000059 Dyspnea Diseases 0.000 description 1
- 206010013975 Dyspnoeas Diseases 0.000 description 1
- 206010061218 Inflammation Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008081 blood perfusion Effects 0.000 description 1
- 230000004087 circulation Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 230000006735 deficit Effects 0.000 description 1
- 230000004064 dysfunction Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000000004 hemodynamic effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000004054 inflammatory process Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000002503 metabolic effect Effects 0.000 description 1
- 230000003680 myocardial damage Effects 0.000 description 1
- 230000002107 myocardial effect Effects 0.000 description 1
- 208000010125 myocardial infarction Diseases 0.000 description 1
- 238000005025 nuclear technology Methods 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000037081 physical activity Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000004088 pulmonary circulation Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000000087 stabilizing effect Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 208000011580 syndromic disease Diseases 0.000 description 1
Images
Landscapes
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The invention provides a heart failure monitoring system and a prediction evaluation method thereof, wherein the method comprises a portable sensing device and a heart failure monitoring management system, the heart failure monitoring management system is used for receiving monitoring data, determining a heart failure risk state alarm transmitted by the received monitoring data based on the determined maximum heart failure risk score and the reception of the transmission of the current monitoring data, displaying the monitoring data, transmitting the data to a data storage layer through an interface layer for centralized storage, analysis, processing and protection of the data, and performing optimized upgrading of a further mathematical model on the data. The invention can monitor the heart failure patient and effectively early warn the illness state of the heart failure patient, thereby reducing the re-hospitalization of the heart failure patient, improving the life quality of the patient to a great extent, and responding to the determination to provide proper treatment by further distinguishing the identified current heart failure risk state into four categories of standard, low, medium and high.
Description
Technical Field
The invention relates to the technical field of cardiovascular disease monitoring, in particular to a heart failure monitoring system and a prediction evaluation method using the system.
Background
The heart failure is a group of syndromes which are caused by various heart structural or functional diseases to cause ventricular filling and/or blood ejection function impairment, cardiac output cannot meet the metabolic needs of body tissues, and pulmonary circulation and/or body circulation congestion, and organ and tissue blood perfusion insufficiency are clinical manifestations, mainly including dyspnea, physical activity limitation and fluid retention. Cardiac insufficiency or dysfunction is theoretically a broader concept, and cardiac insufficiency with clinical symptoms is called heart failure (heart failure for short).
Heart failure is a severe manifestation or late stage of cardiovascular diseases, myocardial damage caused by any reasons such as myocardial infarction, cardiomyopathy, hemodynamic overload, inflammation and the like can cause the change of myocardial structure and function, and finally, the ventricular pump blood and/or filling function are low.
The mortality rate and the hospitalization rate of the heart failure are high, how to well monitor the severity of the heart failure patient and effectively give an early warning to the illness state of the heart failure patient, so that the hospitalization of the heart failure patient is reduced, the life quality of the patient is improved to a great extent, and the method has the advantages of being simple in process, convenient to use, and capable of improving the quality of life of the patient.
Currently, patients with confirmed heart failure are monitored and evaluated by adopting a relatively primitive means: the method has the advantages that the method is used for manually measuring the body weight, recording the daily input and output amount, measuring the urinary creatinine in a staged manner and the like, the method needs to consume large labor cost of medical workers, and errors of human factors are easily introduced, so that the evaluation of the actual state of illness of a patient is influenced; the treatment method cannot be quickly adjusted in real time according to the state of illness of the patient due to lack of continuous monitoring means; there is no better treatment for heart failure patients after hospitalization, but routine monitoring and adjustment of the periodic treatment method.
For the heart failure patients who are recovered at home, no effective means is available to know the actual illness state of the patients, and the patients are treated by hospitalization only after a plurality of uncomfortable symptoms appear. In this case, if the disease condition is aggravated, the treatment is not timely, if the symptom is false positive, the medical resource is wasted, the current real condition of the patient cannot be accurately obtained, and the following hidden dangers exist:
1. patients are diagnosed with heart failure, and are generally monitored and evaluated by adopting a relatively original means: the method has the advantages that the weight is measured manually, the daily input and output amount is recorded, the urinary creatinine is measured in stages, and the like, so that the method needs to consume higher labor cost of medical workers, and errors of human factors are easily introduced, so that the evaluation of the actual illness state of a patient is influenced;
2. the treatment method cannot be quickly adjusted in real time according to the illness state of the patient due to the lack of continuous monitoring means;
3. the readmission rate of heart failure patients is high, but no better treatment means is available after the patients are admitted, and the conventional monitoring and adjustment of the periodic treatment method are usually carried out in hospital.
Disclosure of Invention
In order to overcome the disadvantages of the prior art, it is an object of the present invention to provide a heart failure monitoring system and method thereof, which can well monitor heart failure patients, effectively early warn the state of illness of the heart failure patients, thereby reducing the re-hospitalization of the heart failure patients and greatly improving the quality of life of the patients, and provide appropriate treatment in response to the determination by enabling the identified current heart failure risk status to be further differentiated into four categories, standard, low, medium and high.
In order to solve the problems, the technical scheme adopted by the invention is as follows:
a heart failure monitoring system, comprising:
the portable sensing equipment is used for transmitting the collected heart failure monitoring data to the heart failure monitoring management system, selecting different data supplements for different monitoring types of the heart failure monitoring data, and supplementing the monitoring data when the monitoring data is judged to be missing;
the heart failure monitoring and management system is used for receiving monitoring data transmitted by the portable sensing equipment, determining a heart failure risk state alarm of the received monitoring data transmission based on the determined maximum heart failure risk score and the receiving of the current monitoring data transmission, displaying the monitoring data, transmitting the data to the data storage layer through the interface layer for centralized storage, analysis, processing and protection of the data, and performing optimization and upgrading on a mathematical model of the data;
the heart failure monitoring and managing system is also used for managing patient data and medical advice, simultaneously carrying out centralized monitoring on the currently managed patients, carrying out accurate prediction and evaluation on part or all of the data of the patients, and carrying out data transmission with the health cloud server, thereby realizing the prediction and early warning of heart failure.
According to the heart failure monitoring system provided by the invention, the portable sensing equipment comprises a power supply module, a wireless transmission module, a main control module, a physiological signal acquisition module and a weight acquisition module, wherein the power supply module is used for outputting power supplies for all functional modules of the portable sensing equipment, the wireless transmission module is connected with the main control module and is used for transmitting acquired data to the heart failure monitoring management system, the physiological signal acquisition module is connected with the main control module and is used for acquiring physiological electric signals, and the weight acquisition module is connected with the main control module and is used for acquiring body weight data of a human body.
According to the heart failure monitoring system provided by the invention, the physiological signal acquisition module comprises an eight-electrode biological signal acquisition unit consisting of two four-electrode biological signal acquisition circuits, each four-electrode biological signal acquisition circuit comprises four human body electrodes, a signal processing circuit and a high-precision impedance digital conversion chip, the signal processing circuit comprises a first operational amplifier, a second operational amplifier, a third operational amplifier and a fourth operational amplifier, the non-inverting input end of the first operational amplifier is connected with the VOUT end of the high-precision impedance digital conversion chip, the inverting input end of the first operational amplifier is connected with the output end, the first human body electrode is connected between the output end of the first operational amplifier and the inverting input end of the second operational amplifier, the output end of the second operational amplifier is connected with the second human body electrode, the sixth end of the third operational amplifier is connected with the high-precision impedance digital conversion chip, the third end of the third operational amplifier is connected with the third human body electrode, the second end of the third operational amplifier is connected with the second human body electrode, the fifth end of the third operational amplifier is connected with the output end of the fourth operational amplifier, and the non-inverting input end of the fourth operational amplifier is grounded;
or the physiological signal acquisition module is a signal acquisition unit consisting of a four-electrode biological signal acquisition circuit and is used for meeting the requirement of independently measuring the biological signals of the lower limbs.
According to the heart failure monitoring system provided by the invention, the weight acquisition module comprises a plurality of weighing sensors and a weighing chip CS1237, and the weighing sensors are respectively connected with the weighing chip CS1237 after being externally connected with a socket.
According to the present invention, there is provided a heart failure monitoring and management system, comprising:
the patient management module is used for inputting information of patients to be monitored and managing the monitored patients;
the medical advice management module is used for adding, editing and deleting information to be monitored of the patient;
the data management module is used for carrying out classified management on the data, so that the data checking and the deep analysis of medical personnel are facilitated;
the centralized monitoring display module is used for displaying the currently monitored patient information and the early warning information in a centralized manner;
the data statistics analysis module is used for carrying out information statistics on all the collected data of the patient so as to carry out multidimensional statistics on the system data;
and the data intelligent analysis module is used for integrating all the collected data of the patient, analyzing by adopting an HOHF algorithm to obtain a heart failure grade evaluation conclusion of the patient, and carrying out chart display on the conclusion obtained by analysis.
A predictive assessment method of a heart failure monitoring system is applied to the predictive early warning assessment of heart failure by the heart failure monitoring system, and comprises the following steps:
establishing an HOHF algorithm model;
collecting heart failure monitoring data through portable sensing equipment, performing signal processing on the collected monitoring data, and respectively extracting human body impedance data and limb conduction electrocardio data;
combining synchronously acquired weight data and current human body information data, performing threshold value and trend analysis on residual errors obtained by the characteristic data by adopting an HOHF algorithm model, evaluating and predicting the heart failure grade, and determining the heart failure risk state alarm of the received monitoring data transmission based on the determined maximum heart failure risk score and the reception of the current monitoring data transmission;
wherein, the HOHF algorithm model reveals the intrinsic change caused by the heart and body abnormity in daily life by identifying the characteristic data disorder; the HOHF algorithm model obtains an initial mathematical model through historical data, and the initial mathematical model is analyzed in real time in real-time monitoring to update the model.
According to the predictive assessment method of the heart failure monitoring system provided by the invention, the data for establishing the HOHF algorithm model comprises the following steps:
receiving the bioelectric signals and the weight collected by the portable sensing equipment and the height, the sex and the age collected synchronously, separating the bioelectric signals into limb lead electrocardio data and human body impedance data, and expressing as a formula (1):
LR=LL1+LL2-LR1-LR2
UR=AL1+AL2-AR1-AR2
BR=LR+UR (1)
wherein LR is lower limb impedance, UR is body impedance, and BR is body impedance.
According to the predictive assessment method of the heart failure monitoring system provided by the invention, the quality analysis and judgment of the collected data are also carried out, and the method comprises the following steps:
carrying out data splitting on received bioelectrical signal original data, and grouping the data according to preset interval time;
extracting characteristic parameters, including:
extracting a data offset skn, wherein the data offset skn is a third-order center distance of data and is expressed as a formula (2):
where x is raw data of the biological signal, μ is a first order distance, σ is a second order distance, and μ and σ are expressed as formula (3):
wherein n is the number of data;
extracting the data excess average value ann, wherein the data excess average value ann is the number of the data excess average value and is expressed as a formula (4):
amn=length(x>mean(x)) (4)
extracting approximate entropy ape, wherein ape is the approximate entropy of the data and is expressed as formula (5):
wherein:
the total number of distances estimated for the data, d is the individual distance data,expressed as formula (51);
extracting a delay autocorrelation coefficient atl, wherein atl is the autocorrelation coefficient of the delay part data and is expressed as formula (6):
wherein l is the length of a delay window and is set as an empirical value of 4;
after the characteristic parameters are extracted, performing model analysis to calculate a score S, comparing the calculated score S with an input threshold L, and if the score S is greater than the threshold, determining that the data is unqualified, wherein the calculation formula of the score S is formula (7);
S=skn+amn+ape+atl (7)
and (3) calculating the number of qualified data, and comprehensively analyzing to obtain a yield p, wherein the yield p is expressed as a formula (8):
P=qn/n (8)
wherein qn is the qualified data number, and n is the total data number.
According to the prediction evaluation method of the heart failure monitoring system provided by the invention, the heart failure grade is evaluated and predicted, and the method comprises the following steps:
integrating all acquired and obtained data parameters to obtain a data state set H to form a data matrix;
analyze and generate current data x in The similarity matrix D of (a): computing X using residual threshold comparison i Similarity between the column vectors and each column vector in the data state set H, and forming a similarity matrix D with the size of E by taking the first E column vectors with the highest similarity;
calculating parameter variable evaluation values: current feature data vector X i The mathematical model is a matrix XD, the mapping parameter of the vector in the model is q, and the model calculation formula is formula (9):
XW=||q(D)-q(x i )|| 2 (9)
a lagrange expression is established using the kunn-tak condition, expressed as equation (10):
L=q(D) T q(D)-2q(x i ) T q(D)+q(x i ) T q(x j )
establishing a current feature data vector X i Is expressed as equation (11):
wherein a is an expansion coefficient, and c is a translation coefficient;
the threshold difference Rx of the analysis data is expressed as formula (12):
Rx=Hk-x in (12)。
according to the predictive evaluation method of the heart failure monitoring system provided by the invention, after the threshold difference Rx is obtained through model calculation, an analysis model is calculated and expressed as a formula (13):
wherein p is a mapping parameter of the vector, rx is a threshold differential quantity, k and m are matrix dimensions, and h is a matrix length;
the evaluation value HFPI of the heart failure abnormality index was obtained, expressed as formula (14):
HFPI(x i )=-log 10 p(Rx) (14)
wherein i is the number of sampling points;
and classifying the abnormality indexes into four categories of standard, low, medium and high through a threshold value.
Therefore, compared with the prior art, the invention has the following beneficial effects:
1. the invention can carry out non-invasive routine detection on the heart failure patients according to the characteristics of the heart failure;
2. the invention fills the blank of routine monitoring of patients with heart failure, and can perform differential diagnosis on acute heart failure in time to provide treatment for the patients;
3. the product of the invention has simple and convenient operation mode, can quickly obtain an evaluation conclusion, clearly provides disease judgment data for doctors, and intuitively provides guidance for patients;
4. according to the method, healthy patients and patients with different heart failure severity degrees are analyzed, physiological parameter related data, weight data and the like can be analyzed through an HOHF algorithm, and the current heart failure prediction early warning level is obtained through analysis;
5. the method can obtain comparative analysis on the data, weight data and the like related to individual physiological parameters of a patient in a specific time period, thereby obtaining the change condition of the state of the patient;
6. the patient can monitor the patient by himself and check the evaluation result, so that the labor cost of medical staff can be greatly reduced;
7. the life habits of the patients can be adjusted according to the evaluation results, and the quality of life can be improved to the maximum extent while the readmission is reduced;
8. determining a transmitted heart failure risk status for a currently received data transmission based on the determined daily heart failure risk status; and determining a heart failure risk status alert for the currently received data transmission based on the determined maximum heart failure risk status and the reception of the currently received data transmission.
The present invention will be described in further detail with reference to the accompanying drawings and specific embodiments.
Drawings
FIG. 1 is a schematic diagram of an embodiment of a heart failure monitoring system of the present invention.
Fig. 2 is a schematic diagram of an architecture of an embodiment of a heart failure monitoring system according to the present invention.
FIG. 3 is a schematic diagram of a portable sensing device in an embodiment of a heart failure monitoring system of the present invention.
FIG. 4 is a circuit schematic of the master control circuit in an embodiment of a heart failure monitoring system of the present invention.
FIG. 5 is a schematic circuit diagram of a connection module in an embodiment of a heart failure monitoring system of the present invention.
FIG. 6 is a schematic circuit diagram of a power module in an embodiment of a heart failure monitoring system according to the present invention.
FIG. 7 is a schematic circuit diagram of a physiological signal acquisition module in an embodiment of a heart failure monitoring system according to the present invention.
FIG. 8 is a schematic circuit diagram of a weight acquisition module in an embodiment of a heart failure monitoring system according to the present invention.
Fig. 9 is a flow chart of the derivation of the HOHF algorithm model in an embodiment of the predictive assessment method for heart failure monitoring system of the present invention.
FIG. 10 is a flowchart illustrating quality analysis and determination of collected data according to an embodiment of the predictive assessment method of the heart failure monitoring system of the present invention.
FIG. 11 is a schematic diagram of bioelectric signals collected by a sensing device in an embodiment of a predictive assessment method for a heart failure monitoring system according to the present invention.
FIG. 12 is a flowchart of the extraction of the ECG characteristic parameters according to the embodiment of the predictive assessment method of the heart failure monitoring system of the invention.
FIG. 13 is a flowchart illustrating predictive alert analysis in an embodiment of a predictive assessment method for a heart failure monitoring system according to the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
A heart failure monitoring system embodiment:
referring to fig. 1 and 2, the present invention provides a heart failure monitoring system, which includes: the portable sensing device is used for transmitting the collected heart failure monitoring data to the heart failure monitoring management system, selecting different data supplements for different monitoring types of the heart failure monitoring data, and supplementing the monitoring data when the monitoring data is judged to be missing. Therefore, the portable sensing equipment is used for collecting and transmitting the monitoring data of the heart failure patient to the heart failure monitoring system and supplementing the data in real time.
The heart failure monitoring system comprises portable sensing equipment, a heart failure monitoring and management system and a heart failure prediction and early warning assessment method, bioelectric signals and weight data can be received from the portable sensing equipment, then the received data are subjected to deep analysis, a conclusion of heart failure grade assessment is obtained, and the conclusion is displayed.
In this embodiment, the heart failure monitoring and management system is configured to receive monitoring data transmitted by the portable sensing device, determine a heart failure risk state alarm of the received monitoring data transmission based on the determined maximum heart failure risk score and the reception of the current monitoring data transmission, display the monitoring data, transmit the data to the data storage layer through the interface layer, perform centralized storage, analysis, processing and protection of the data, and perform further optimization and upgrade of a mathematical model on the data;
in this embodiment, the heart failure monitoring and management system is further configured to manage patient data and medical orders, perform centralized monitoring on currently managed patients, perform accurate prediction and evaluation on part or all of the data of the patients, and perform data transmission with a health cloud server, thereby realizing prediction and early warning of heart failure.
In this embodiment, the system further includes a collector, a doctor end, an interface layer for providing services correspondingly, and a database layer for providing data storage.
The collector communicates with the collection terminal through a standard Bluetooth protocol in a task operation stage to obtain physiological parameter data reported by the collection terminal, and after the physiological parameter data are collected and sorted, the physiological parameter data are reported to the interface layer in a unified manner and are collected and stored by the interface layer.
The communication network form of the doctor end and the interface layer adopts a self-built internal local area network to operate, and the communication protocol adopts an Http/https protocol based on TCP/IP.
As shown in fig. 3, the portable sensing device includes a power module, a wireless transmission module, a main control module, a physiological signal collection module, and a weight collection module, the power module outputs power supplies for each functional module of the portable sensing device, the wireless transmission module is connected with the main control module for transmitting collected data to the heart failure monitoring management system, the physiological signal collection module is connected with the main control module for collecting physiological electrical signals, and the weight collection module is connected with the main control module for collecting body weight data of a human body.
Specifically, the physiological signal acquisition module comprises an eight-electrode biological signal acquisition unit consisting of two four-electrode biological signal acquisition circuits, each four-electrode biological signal acquisition circuit comprises four human body electrodes (namely two electrodes LL1 and LL2 of a left leg part, two electrodes LR1 and LR2 of a right leg part, two electrodes AL1 and AL2 of a left hand part, two electrodes AR1 and AR2 of a right hand part), a signal processing circuit and a high-precision impedance digital conversion chip, the signal processing circuit comprises a first operational amplifier, a second operational amplifier, a third operational amplifier and a fourth operational amplifier, the non-inverting input end of the first operational amplifier is connected with the VOUT end of the high-precision impedance digital conversion chip, the inverting input end of the first operational amplifier is connected with the output end, the first human body electrode is connected between the output end of the first operational amplifier and the inverting input end of the second operational amplifier, the output end of the second operational amplifier is connected with the second human body electrode, the sixth end of the third operational amplifier is connected with the non-inverting input end of the first operational amplifier, the third end of the third operational amplifier is connected with the third operational amplifier, the non-inverting input end of the third operational amplifier, the fourth operational amplifier is connected with the fourth operational amplifier, the non-inverting input end of the third operational amplifier, the fourth operational amplifier is connected with the high-inverting input end of the operational amplifier, and the operational amplifier, the operational amplifier;
or the physiological signal acquisition module is a signal acquisition unit consisting of a four-electrode biological signal acquisition circuit and is used for meeting the requirement of independently measuring the biological signals of the lower limbs.
In this embodiment, the weight acquisition module includes by a plurality of weighing sensor and weighing chip CS1237, and a plurality of weighing sensor are connected with weighing chip CS1237 behind the external socket respectively.
In this embodiment, the heart failure monitoring and management system includes:
the patient management module is used for inputting information of patients to be monitored and managing the monitored patients;
the medical advice management module is used for adding, editing and deleting information to be monitored of the patient;
the data management module is used for carrying out classified management on the data, so that the data checking and the deep analysis of medical personnel are facilitated;
the centralized monitoring display module is used for displaying the currently monitored patient information and the early warning information in a centralized manner;
the data statistics analysis module is used for carrying out information statistics on all collected data of the patient so as to carry out multidimensional statistics on system data, and the data statistics content mainly comprises: the total number of patients, the medical advice, the number of tasks, the task completion trend in nearly 30 days and the task distribution situation in nearly 30 days. The total number of people comprises women, men and unknown people, and the task distribution condition comprises plan number, execution number, completion number and report number. The personalized treatment means can be formulated through specific monitoring data changes, meanwhile, the data of a plurality of patients are transversely compared, and the characteristics of the disease are deeply analyzed;
and the data intelligent analysis module is used for integrating all the collected data of the patient, adopting HOHF algorithm analysis to finally obtain the heart failure grade evaluation conclusion of the patient, and carrying out chart display on the conclusion obtained by analysis, so that a user can conveniently read, compare and check the conclusion.
Specifically, the heart failure monitoring and management system is operated by nurses and doctors, is used for receiving data transmitted by the portable sensing equipment, displaying the monitored data, transmitting the data to the data storage layer through the interface layer for centralized storage, analysis, processing and protection of the data, and performing optimized upgrade on a mathematical model of the data.
The comprehensive management platform is operated by a doctor and used for managing patient data and medical advice, carrying out centralized monitoring on currently managed patients, carrying out key monitoring on key patients, carrying out statistical analysis on part or all data of a single patient, and carrying out data transmission with a data storage layer, thereby realizing accurate prediction and early warning of heart failure.
The wireless transmission module adopts Bluetooth wireless transmission and is used for transmitting the acquired data to the comprehensive management platform; the power supply module supplies power to each module to ensure the normal operation of the equipment; the main control chip controls the operation logic of each functional module and is used for integrating data, encrypting data, transmitting data and the like; the biological signal acquisition module adopts an eight-electrode mode and consists of an electrode plate, a related circuit and a chip.
In addition, the overall frame diagram of the control circuit of the portable sensing device is shown in fig. 3, the main control chip is integrated in the main control circuit, the main control circuit and the connection module are arranged in the connector module, the connector module is simultaneously connected with the power supply module, the electric quantity detection module, the physiological signal measurement circuit and the weight measurement circuit, a battery and a voltage stabilizing circuit are arranged in the power supply module, the main control circuit is shown in fig. 4, the connection module is shown in fig. 5, the power supply module is shown in fig. 6, the physiological signal measurement circuit is shown in fig. 7, and the weight acquisition module is shown in fig. 8.
An embodiment of a prediction evaluation method of a heart failure monitoring system comprises the following steps:
referring to fig. 9 to 13, the present embodiment provides a predictive assessment method for a heart failure monitoring system, which is applied to the above-mentioned heart failure monitoring system for performing predictive pre-warning assessment of heart failure, and the method includes the following steps:
establishing an HOHF algorithm model;
collecting heart failure monitoring data through portable sensing equipment, performing signal processing on the collected monitoring data, and respectively extracting human body impedance data and limb conduction electrocardio data;
combining synchronously acquired weight data and current human body information data, performing threshold value and trend analysis on residual errors obtained by the characteristic data by adopting an HOHF algorithm model, evaluating and predicting the heart failure grade, and determining the heart failure risk state alarm transmitted by the received monitoring data based on the determined maximum heart failure risk score and the reception of the current monitoring data transmission;
wherein, the HOHF algorithm model reveals the intrinsic change caused by the heart and body abnormity in daily life by identifying the characteristic data disorder; the HOHF algorithm model obtains an initial mathematical model through historical data, and the initial mathematical model is analyzed in real time in real-time monitoring to update the model.
In this embodiment, the data for establishing the HOHF algorithm model includes:
receiving the bioelectric signals and the weight collected by the portable sensing equipment and the height, the sex and the age collected synchronously, separating the bioelectric signals into limb lead electrocardio data and human body impedance data, and expressing as a formula (1):
LR=LL1+LL2-LR1-LR2
UR=AL1+AL2-AR1-AR2
BR=LR+UR (1)
wherein LR is lower limb impedance, UR is body impedance, and BR is body impedance.
In this embodiment, in some states, due to the irregular use or abnormal test environment in the test, the data acquired by the sensing device is not qualified, so that the analysis and the judgment of the algorithm are affected, and an incorrect conclusion is obtained. Therefore, before data analysis, quality judgment needs to be carried out on the data, unqualified data is removed, and if the data qualification rate is low, testing needs to be carried out again. The method also performs quality analysis and judgment on the collected data, as shown in fig. 10, which includes:
splitting data of received bioelectrical signal original data, and grouping the data according to preset interval time (for example, every 5 seconds is a group of data);
extracting characteristic parameters, including:
extracting a data offset skn, wherein the data offset skn is a third-order center distance of data and is expressed as a formula (2):
where x is raw data of the biological signal, μ is a first order distance, σ is a second order distance, and μ and σ are expressed by formula (3):
wherein n is the number of data;
extracting the data excess average amn, wherein the data excess average amn is the number of data exceeding the average value and is expressed as a formula (4):
amn=length(x>mean(x)) (4)
extracting approximate entropy ape, wherein ape is the approximate entropy of the data and is expressed as formula (5):
wherein:
the total number of distances estimated for the data, d is the individual distance data,expressed as formula (51);
extracting a delay autocorrelation coefficient atl, wherein atl is the autocorrelation coefficient of the delay part data and is expressed as formula (6):
wherein l is the length of a delay window and is set as an empirical value of 4;
after the characteristic parameters are extracted, performing model analysis to calculate a score S, comparing the calculated score S with an input threshold L, and if the score S is greater than the threshold, determining that the data is unqualified, wherein the calculation formula of the score S is formula (7);
S=skn+amn+ape+atl (7)
and (3) calculating the number of qualified data, and comprehensively analyzing to obtain a yield p, wherein the yield p is expressed as a formula (8):
P=qn/n (8)
wherein qn is the qualified data number, and n is the total data number.
And if the data yield is less than 0.7, the data is invalid data, the data needs to be tested again, if the data yield is more than or equal to 0.7, the data is valid data, and the next analysis can be carried out.
Therefore, the extracted characteristic parameters of the embodiment can maximally retain the biological signal characteristic data, and can accurately calculate the corresponding parameter variables.
In this embodiment, the evaluating and predicting the heart failure level includes:
integrating all acquired and obtained data parameters to obtain a data state set H to form a data matrix;
analyze and generate current data x in The similarity matrix D of (a): computing X using residual threshold comparison i Similarity between the column vectors and each column vector in the data state set H, and forming a similarity matrix D with the size of E by taking the first E column vectors with the highest similarity;
calculating parameter variable evaluation values: current feature data vector X i The mathematical model is a matrix XD, the mapping parameter of the vector in the model is q, and the model calculation formula is formula (9):
XW=||q(D)-q(x i )|| 2 (9)
a lagrange expression is established using the kunn-tak condition, expressed as equation (10):
L=q(D) T q(D)-2q(x i ) T q(D)+q(x i ) T q(x j )
establishing a current feature data vector X i Is expressed as the formula: ( 11 ):
Wherein a is an expansion coefficient, and c is a translation coefficient;
the threshold difference Rx of the analysis data is expressed as formula (12):
Rx=Hk-x in (12)。
after the threshold difference Rx is obtained by model calculation, an analysis model is calculated, which is expressed as formula (13):
wherein p is a mapping parameter of the vector, rx is a threshold differential quantity, k and m are matrix dimensions, and h is a matrix length;
the evaluation value HFPI of the heart failure abnormality index was obtained, and expressed as formula (14):
HFPI(x i )=-log 10 p(Rx) (14)
wherein i is the sampling point;
and finally, classifying the y1, y2 and y3 abnormal indexes into four categories of standard, low, medium and high through three thresholds, wherein the specific classification formula is as follows:
as can be seen, the lagrangian expression is selected in the embodiment, so that the order of a differential equation set of the lagrangian expression is low, the algorithm complexity is low, and the machine operation is facilitated; the purpose of selecting the multidimensional kernel function in the embodiment is that the multidimensional kernel function can better analyze and optimize data organization and storage modes.
Specifically, the predictive warning assessment method for the heart failure monitoring system adopts an HOHF algorithm, and mainly includes two electrodes (LL 1, LL 2) on the left leg, two electrodes (LR 1, LR 2) on the right leg, two electrodes (AL 1, AL 2) on the left hand, and two electrodes (AR 1, AR 2) on the right hand, as shown in fig. 11, for 8-electrode bioelectrical signals acquired by the portable sensing device. And respectively extracting body impedance, lower limb impedance and limb conduction electrocardiosignals by adopting a signal processing method, and evaluating and predicting the heart failure grade by adopting an HOHF algorithm model in combination with synchronously acquired weight data and data of height, age, sex and the like of the human body at the time.
The HOHF algorithm model mainly analyzes a threshold value and a trend of a residual error obtained by characteristic data, so that the accuracy of heart failure assessment and early warning is improved. The HOHF model reveals intrinsic changes caused by cardiac and body abnormalities in daily life by identifying characteristic data disorders. An initial mathematical model is obtained through historical data, then the initial mathematical model is analyzed in real time during monitoring, and the model is updated, so that the further improvement of the accuracy of assessment and early warning is achieved.
The method for deriving the HOHF algorithm model is a machine learning method which is established by longitudinal data of a user and is based on a nuclear technology and data driving, and is based on the interrelation of a plurality of variables and monitored individuals thereof. This model derivation method is therefore statistical and multivariate based.
As shown in fig. 9, the specific flow of the HOHF algorithm model includes: and receiving data, analyzing whether the qualification rate of the received data meets the requirement, if so, extracting characteristic parameters, integrating all the obtained data to establish a mathematical model, performing comparative analysis on the mathematical model and the initial data model to obtain a final analysis result, and finally outputting and displaying.
As shown in fig. 12, when extracting the electrocardiographic feature parameters, the following steps are further performed:
firstly, data preprocessing is carried out: filtering signal interference through a digital filter;
performing peak transformation on the data, wherein the specific formula is as follows:
in the formula, i and j represent the serial numbers of sampling points, wherein i is the serial number of the sampling point to be processed, x represents an electrocardiosignal sampling point sequence, x (i) is an input point, and y (i) is an output point and represents the amplitude of the ith sampling point after the peak value is transformed. PEAK _ transition _ WIDTH is the PEAK transformation WIDTH (10 sampling points are taken according to empirical values), and for the ith sampling point x (i), all sampling points in the range of PEAK _ transition before and after the point i are required to be used in the PEAK transformation process;
comparing the threshold value of the data after the wave crest transformation, and detecting the R wave of the electrocardio characteristic position:
calculating the heart rate through the detected corresponding positions, wherein the formula is as follows:
HR=60000/RR
wherein HR represents heart rate and RR represents RR interval of electrocardiographic waveform;
and outputting the electrocardio characteristic parameters after calculation, and carrying out the next algorithm analysis.
Therefore, the invention can carry out non-invasive routine detection on the heart failure patients according to the characteristics of the heart failure; the blank of routine monitoring of the heart failure patient is filled, and the differential diagnosis of the acute heart failure can be performed in time to provide treatment for the patient; the product has simple and convenient operation mode, can quickly obtain an evaluation conclusion, clearly provides disease judgment data for doctors, and intuitively provides guidance for patients; through analyzing healthy patients and patients with different heart failure severity degrees, physiological parameter related data, weight data and the like can be analyzed through an HOHF algorithm, and the current heart failure prediction early warning grade is obtained through analysis; the comparison analysis can be carried out on the data related to the individual physiological parameters, the weight data and the like of the patient in a specific time period, so that the change condition of the state of the patient can be obtained; the patient can monitor the patient by himself and check the evaluation result, so that the labor cost of medical staff can be greatly reduced; the patient can adjust the living habit according to the evaluation result, and the quality of life can be improved to the maximum extent while the readmission is reduced; determining a transmitted heart failure risk status for a currently received data transmission based on the determined daily heart failure risk status; and determining a heart failure risk status alert for the currently received data transmission based on the determined maximum heart failure risk status and the reception of the currently received data transmission.
All possible combinations of the technical features in the above embodiments may not be described for the sake of brevity, but should be considered as being within the scope of the present disclosure as long as there is no contradiction between the combinations of the technical features.
The above embodiments are only preferred embodiments of the present invention, and the protection scope of the present invention is not limited thereby, and any insubstantial changes and substitutions made by those skilled in the art based on the present invention are within the protection scope of the present invention.
Claims (10)
1. A heart failure monitoring system, comprising:
the portable sensing equipment is used for transmitting the collected heart failure monitoring data to the heart failure monitoring management system, selecting different data supplements for different monitoring types of the heart failure monitoring data, and supplementing the monitoring data when the monitoring data is judged to be missing;
the heart failure monitoring management system is used for receiving monitoring data transmitted by the portable sensing equipment, determining a heart failure risk state alarm transmitted by the received monitoring data based on the determined maximum heart failure risk score and the reception of the transmission of the current monitoring data, displaying the monitoring data, transmitting the data to the data storage layer through the interface layer for centralized storage, analysis, processing and protection of the data, and performing optimized upgrading on a mathematical model of the data;
the heart failure monitoring and managing system is also used for managing patient data and medical advice, carrying out centralized monitoring on the currently managed patients, accurately predicting and evaluating partial or all data of the patients, and transmitting the data with the health cloud server, so that the prediction and early warning of heart failure are realized.
2. The heart failure monitoring system of claim 1, wherein:
the portable sensing equipment comprises a power supply module, a wireless transmission module, a main control module, a physiological signal acquisition module and a weight acquisition module, wherein the power supply module outputs power supplies for all functional modules of the portable sensing equipment, the wireless transmission module is connected with the main control module and used for transmitting acquired data to a heart failure monitoring and management system, the physiological signal acquisition module is connected with the main control module and used for acquiring physiological electric signals, and the weight acquisition module is connected with the main control module and used for acquiring weight data of a human body.
3. The heart failure monitoring system of claim 1, wherein:
the physiological signal acquisition module comprises an eight-electrode biological signal acquisition unit consisting of two four-electrode biological signal acquisition circuits, each four-electrode biological signal acquisition circuit comprises four human body electrodes, a signal processing circuit and a high-precision impedance digital conversion chip, the signal processing circuit comprises a first operational amplifier, a second operational amplifier, a third operational amplifier and a fourth operational amplifier, the non-inverting input end of the first operational amplifier is connected with the VOUT end of the high-precision impedance digital conversion chip, the inverting input end of the first operational amplifier is connected with the output end, the first human body electrode is connected between the output end of the first operational amplifier and the inverting input end of the second operational amplifier, the output end of the second operational amplifier is connected with the second human body electrode, the sixth end of the third operational amplifier is connected with the VIN end of the high-precision impedance digital conversion chip, the third end of the third operational amplifier is connected with the third human body electrode, the second end of the third operational amplifier is connected with the second human body electrode, the fifth end of the third operational amplifier is connected with the output end of the fourth operational amplifier, and the non-inverting input end of the fourth operational amplifier is grounded;
or the physiological signal acquisition module is a signal acquisition unit consisting of a four-electrode biological signal acquisition circuit and is used for meeting the requirement of independently measuring the biological signals of the lower limbs.
4. The heart failure monitoring system of claim 1, wherein:
the weight acquisition module comprises a plurality of weighing sensors and a weighing chip CS1237, wherein the weighing sensors are respectively connected with the weighing chip CS1237 after being externally connected with a socket.
5. The heart failure monitoring system of claim 1, wherein:
the heart failure monitoring and management system comprises:
the patient management module is used for inputting information of patients to be monitored and managing the monitored patients;
the medical advice management module is used for adding, editing and deleting information to be monitored of the patient;
the data management module is used for carrying out classified management on the data, and is convenient for medical personnel to carry out data viewing and deep analysis;
the centralized monitoring display module is used for displaying the currently monitored patient information and the early warning information in a centralized manner;
the data statistics analysis module is used for carrying out information statistics on all the collected data of the patient so as to carry out multidimensional statistics on the system data;
and the data intelligent analysis module is used for integrating all the collected data of the patient, analyzing by adopting an HOHF algorithm to obtain a heart failure grade evaluation conclusion of the patient, and carrying out chart display on the conclusion obtained by analysis.
6. A predictive assessment method for a heart failure monitoring system, which is applied to a heart failure monitoring system according to any one of claims 1 to 5 for predictive pre-warning assessment of heart failure, the method comprising the steps of:
establishing an HOHF algorithm model;
collecting heart failure monitoring data through portable sensing equipment, performing signal processing on the collected monitoring data, and respectively extracting human body impedance data and limb conduction electrocardio data;
combining synchronously acquired weight data and current human body information data, performing threshold value and trend analysis on residual errors obtained by the characteristic data by adopting an HOHF algorithm model, evaluating and predicting the heart failure grade, and determining the heart failure risk state alarm transmitted by the received monitoring data based on the determined maximum heart failure risk score and the reception of the current monitoring data transmission;
wherein, the HOHF algorithm model reveals the intrinsic change caused by the heart and body abnormity in daily life by identifying the characteristic data disorder; the HOHF algorithm model obtains an initial mathematical model through historical data, and the initial mathematical model is analyzed in real time in real-time monitoring to update the model.
7. The method of claim 6, wherein the data for modeling the HOHF algorithm comprises:
receiving the bioelectric signals and the weight collected by the portable sensing equipment and the height, the sex and the age collected synchronously, separating the bioelectric signals into limb lead electrocardio data and human body impedance data, and expressing as a formula (1):
LR=LL1+LL2-LR1-LR2
UR=AL1+AL2-AR1-AR2
BR=LR+UR (1)
wherein LR is lower limb impedance, UR is body impedance, and BR is body impedance.
8. The method of claim 7, wherein performing quality analysis and determination of the collected data further comprises:
carrying out data splitting on received bioelectrical signal original data, and grouping the data according to preset interval time;
extracting characteristic parameters, including:
extracting a data skew skn, wherein the data skew skn is the third-order center distance of the data and is expressed as a formula (2):
where x is raw data of the biological signal, μ is a first order distance, σ is a second order distance, and μ and σ are expressed as formula (3):
wherein n is the number of data;
extracting the data excess average value ann, wherein the data excess average value ann is the number of the data excess average value and is expressed as a formula (4):
amn=length(x>mean(x)) (4)
extracting approximate entropy ape, wherein ape is the approximate entropy of the data and is expressed as formula (5):
wherein:
the total number of distances estimated for the data, d is the individual distance data,expressed as formula (51);
extracting a delay autocorrelation coefficient atl, wherein atl is the autocorrelation coefficient of the delay part data and is expressed as formula (6):
wherein l is the length of a delay window and is set as an empirical value of 4;
after the characteristic parameters are extracted, performing model analysis to calculate a score S, comparing the calculated score S with an input threshold L, and if the score S is greater than the threshold, determining that the data is unqualified, wherein the calculation formula of the score S is formula (7);
S=skn+amn+ape+atl (7)
and (3) calculating the number of qualified data, and comprehensively analyzing to obtain a yield p, wherein the yield p is expressed as a formula (8):
P=qn/n (8)
wherein qn is the qualified data number, and n is the total data number.
9. The method of claim 6, wherein:
evaluating and predicting the heart failure grade, comprising the following steps:
integrating all acquired and obtained data parameters to obtain a data state set H to form a data matrix;
analyze and generate current data x in The similarity matrix D of (a): computing X using residual threshold comparison i Similarity between the column vectors and each column vector in the data state set H, and forming a similarity matrix D with the size of E by taking the first E column vectors with the highest similarity;
calculating parameter variable evaluation values: current feature dataVector X i The mathematical model is a matrix XD, the mapping parameter of the vector in the model is q, and the model calculation formula is formula (9):
XW=||q(D)-q(x i )|| 2 (9)
a lagrange expression is established using the kunn-tak condition, expressed as equation (10):
L=q(D) T q(D)-2q(x i ) T q(D)+q(x i ) T q(x j )
establishing a current feature data vector X i Is expressed as equation (11):
wherein a is an expansion coefficient, and c is a translation coefficient;
the threshold difference Rx of the analysis data is expressed as formula (12):
Rx=Hk-x in (12)。
10. the method of claim 9, wherein:
after the threshold difference Rx is obtained by model calculation, an analysis model is calculated, which is expressed as formula (13):
wherein p is a mapping parameter of the vector, rx is a threshold differential quantity, k and m are matrix dimensions, and h is a matrix length;
the evaluation value HFPI of the heart failure abnormality index was obtained, and expressed as formula (14):
HFPI(X i )=-log 10 p(Rx) (14)
wherein i is the number of sampling points;
and classifying the abnormality indexes into four categories of standard, low, medium and high through a threshold value.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211240278.7A CN115662629A (en) | 2022-10-11 | 2022-10-11 | Heart failure monitoring system and prediction evaluation method thereof |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211240278.7A CN115662629A (en) | 2022-10-11 | 2022-10-11 | Heart failure monitoring system and prediction evaluation method thereof |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115662629A true CN115662629A (en) | 2023-01-31 |
Family
ID=84988450
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211240278.7A Pending CN115662629A (en) | 2022-10-11 | 2022-10-11 | Heart failure monitoring system and prediction evaluation method thereof |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115662629A (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104840186A (en) * | 2015-05-07 | 2015-08-19 | 中山大学 | Evaluation method of autonomic nervous function of patient suffering from CHF (Congestive Heart-Failure) |
CN106333660A (en) * | 2016-09-29 | 2017-01-18 | 深圳市埃微信息技术有限公司 | Body-fat scale capable of measuring conduction velocity of pulse wave |
CN110192853A (en) * | 2019-04-30 | 2019-09-03 | 杭州电子科技大学 | A kind of anomalous ecg appraisal procedure based on electrocardio entropy chart |
CN114067529A (en) * | 2021-11-23 | 2022-02-18 | 珠海弘昕医疗科技有限公司 | Daily monitoring system for heart failure prediction and early warning |
-
2022
- 2022-10-11 CN CN202211240278.7A patent/CN115662629A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104840186A (en) * | 2015-05-07 | 2015-08-19 | 中山大学 | Evaluation method of autonomic nervous function of patient suffering from CHF (Congestive Heart-Failure) |
CN106333660A (en) * | 2016-09-29 | 2017-01-18 | 深圳市埃微信息技术有限公司 | Body-fat scale capable of measuring conduction velocity of pulse wave |
CN110192853A (en) * | 2019-04-30 | 2019-09-03 | 杭州电子科技大学 | A kind of anomalous ecg appraisal procedure based on electrocardio entropy chart |
CN114067529A (en) * | 2021-11-23 | 2022-02-18 | 珠海弘昕医疗科技有限公司 | Daily monitoring system for heart failure prediction and early warning |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11476000B2 (en) | Methods and systems using mathematical analysis and machine learning to diagnose disease | |
EP3698707B1 (en) | Electrocardiogram information dynamic monitoring system, computer program and computer readable storage medium | |
US11350868B2 (en) | Electrocardiogram information processing method and electrocardiogram workstation system | |
US11783924B2 (en) | ECG information processing method and ECG workstation | |
Mei et al. | Automatic atrial fibrillation detection based on heart rate variability and spectral features | |
EP3692900A1 (en) | Artificial intelligence self-learning-based static electrocardiography analysis method and apparatus | |
CN112365978A (en) | Method and device for establishing early risk assessment model of tachycardia event | |
CN113317794B (en) | Vital sign analysis method and system | |
Lee et al. | Congestive heart failure patient monitoring using wearable Bio-impedance sensor technology | |
WO2023092825A1 (en) | Daily monitoring system for heart failure prediction and early warning | |
CN113288168A (en) | Wearable fatigue monitoring of intelligence and early warning system | |
CN116098595B (en) | System and method for monitoring and preventing sudden cardiac death and sudden cerebral death | |
TW202044280A (en) | Prediction model of atrial fibrillation and prediction system thereof | |
TWI688371B (en) | Intelligent device for atrial fibrillation signal pattern acquisition and auxiliary diagnosis | |
CN115662629A (en) | Heart failure monitoring system and prediction evaluation method thereof | |
Saadi et al. | Low-cost ecg monitoring system with classification using deep learning | |
US20220262516A1 (en) | Atrial Fibrillation Prediction Model And Prediction System Thereof | |
CN114831643B (en) | Electrocardiosignal monitoring devices and wearable equipment | |
CN114271804B (en) | Heart rate state auxiliary detection system, heart state monitoring system, heart state auxiliary detection method, heart state auxiliary detection storage medium and heart state auxiliary detection terminal based on consumer-level equipment | |
AU2021101272A4 (en) | An artificial intelligence based heart rate monitoring system for sports training | |
WO2024052677A1 (en) | An artificial intelligence enabled wearable ecg skin patch to detect sudden cardiac arrest | |
CN117940069A (en) | Method for generating a plurality of standard electrocardiographic data based on deep learning algorithm | |
Kim et al. | ECG Biomarker based Heart Disease Automation Detection Scheme | |
CN116942173A (en) | Electrocardiogram intelligent diagnosis and analysis device | |
CN114520054A (en) | Heart failure prediction module and heart failure prediction method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20230131 |
|
RJ01 | Rejection of invention patent application after publication |