CN114495425A - Ischemic cardiovascular disease monitoring and early warning system based on machine learning - Google Patents
Ischemic cardiovascular disease monitoring and early warning system based on machine learning Download PDFInfo
- Publication number
- CN114495425A CN114495425A CN202210131069.2A CN202210131069A CN114495425A CN 114495425 A CN114495425 A CN 114495425A CN 202210131069 A CN202210131069 A CN 202210131069A CN 114495425 A CN114495425 A CN 114495425A
- Authority
- CN
- China
- Prior art keywords
- early warning
- patient
- monitoring
- parathyroid hormone
- module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/04—Alarms for ensuring the safety of persons responsive to non-activity, e.g. of elderly persons
- G08B21/0438—Sensor means for detecting
- G08B21/0453—Sensor means for detecting worn on the body to detect health condition by physiological monitoring, e.g. electrocardiogram, temperature, breathing
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/04—Alarms for ensuring the safety of persons responsive to non-activity, e.g. of elderly persons
- G08B21/0438—Sensor means for detecting
- G08B21/0476—Cameras to detect unsafe condition, e.g. video cameras
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B25/00—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems
- G08B25/01—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems characterised by the transmission medium
- G08B25/08—Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems characterised by the transmission medium using communication transmission lines
Landscapes
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Emergency Management (AREA)
- Gerontology & Geriatric Medicine (AREA)
- General Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biophysics (AREA)
- Cardiology (AREA)
- Heart & Thoracic Surgery (AREA)
- Physical Education & Sports Medicine (AREA)
- Physiology (AREA)
- Pulmonology (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention discloses an ischemic cardiovascular disease monitoring and early warning system based on machine learning, which comprises a characteristic monitoring unit, a disease state aggravation prediction unit and a monitoring and early warning terminal, wherein the characteristic monitoring unit comprises a blood pressure real-time monitoring module, a face recognition camera module and a limb strength detection module, the limb strength detection module comprises a test shell, a pressing sliding component and an S-shaped flexibility detection chute, a reset sliding block mechanism is arranged on the inner side of the test shell, the pressing sliding component is connected above the reset sliding block mechanism through a connecting rod, the force detection component is arranged on the inner side of the pressing sliding component, and a signal closing base is arranged at the top end of the test shell. The error of the early warning signal is avoided, and timely and accurate early warning is carried out.
Description
Technical Field
The invention relates to the technical field of disease monitoring, in particular to an ischemic cardiovascular disease monitoring and early warning system based on machine learning.
Background
The cardiovascular disease is one of the most serious diseases threatening human beings in the world at present, ischemic cardiovascular disease comprises cerebral infarction, transient cerebral ischemia, coronary heart disease, myocardial infarction and the like, and the ischemic stroke and the coronary heart disease are generally called ischemic cardiovascular disease based on the fact that the main micro factors of the ischemic stroke and the coronary heart disease are basically the same, and if the ischemic stroke patient is determined and treated within a short time after the ischemic stroke patient is attacked, the patient has the opportunity of healthy life.
For patients with mild symptoms of sudden numbness of limbs, strength deterioration, dizziness, poor balance and the like on one side, serious stroke is likely to occur in the follow-up process, the onset symptoms of ischemic stroke are acute onset and have paroxysmal property, the patients cannot be pre-warned in time, the illness condition after onset is very rapid, the imaging examination result of the patients cannot be determined in time under the limitation of the existing conditions, the size of the current cerebral infarction area of the patients cannot be effectively determined, the prediction of the illness condition of the patients is influenced, the monitoring and pre-warning of the patients are not timely, the patients easily miss the optimal treatment time, and serious sequelae are caused, and therefore, the ischemic cardiovascular disease monitoring and pre-warning system based on machine learning is provided for solving the problems.
Disclosure of Invention
The invention aims to provide a machine learning-based ischemic cardiovascular disease monitoring and early warning system to solve the problems in the background technology.
In order to achieve the purpose, the invention provides the following technical scheme: the ischemic cardiovascular disease monitoring and early warning system based on machine learning comprises a feature monitoring unit, a state condition aggravation prediction unit and a monitoring and early warning terminal, wherein the feature monitoring unit sends an early warning signal of the state of an illness to the monitoring and early warning terminal through a wireless network; the feature monitoring unit comprises a blood pressure real-time monitoring module, a facial recognition camera module and a limb strength detection module, the blood pressure real-time monitoring module, the facial recognition camera module and the limb strength detection module sequentially transmit data signals and are sequentially started, the blood pressure real-time monitoring module comprises blood pressure detection equipment, the blood pressure detection equipment monitors the blood pressure of a patient in real time, the facial recognition camera module comprises facial expression recognition camera equipment and a facial expression comparison database, and the facial expression recognition camera equipment determines the current facial abnormality of the patient according to the data comparison of the database; the limb strength detection module comprises a test shell, a pressing sliding assembly and an S-shaped flexibility detection chute, the S-shaped flexibility detection chute is used for detecting the flexibility of fingers, a reset sliding block mechanism is arranged on the inner side of the test shell, the pressing sliding assembly is connected above the reset sliding block mechanism through a connecting rod, a strength detection assembly is arranged on the inner side of the pressing sliding assembly and used for detecting the pressing strength of the fingers, and a signal closing base is arranged at the top end of the test shell and used for finally controlling an early warning signal for the initial generation of an illness state; the disease condition aggravation prediction unit comprises a parathyroid hormone detection module, a parathyroid hormone data processing module and a data analysis feedback module, wherein the parathyroid hormone detection module comprises a blood drawing detection mechanism and is used for drawing blood for detection of a patient, and the parathyroid hormone data processing module comprises normal parathyroid hormone level setting and compares the detected current parathyroid hormone level of the patient; the data analysis feedback module comprises a time measuring component, a patient daily parathyroid hormone statistical database, a parathyroid hormone prediction engine and a data secondary processing module, and eliminates influence factors of patient parathyroid hormone fluctuation according to a comparison result; the monitoring early warning terminal is used for receiving the early warning signal and determining the type of the early warning signal.
Further, slider mechanism resets includes slider assembly, guide bar subassembly and the elasticity subassembly that resets, the guide bar subassembly is worn to locate the slider assembly inboard, and the guide bar subassembly is used for the gliding direction of slider assembly, the elasticity subassembly that resets is located between slider assembly and the test shells inner wall, and the elasticity subassembly that resets is used for resetting after slider assembly slides, the slider assembly inboard is equipped with the reciprocal spout of straight line, the connecting rod is located the reciprocal spout of straight line and S type flexibility ratio detection spout inboard, and the reciprocal spout of straight line and S type flexibility ratio detection spout are used for fixing a position the connecting rod, realize pressing the definite of slider assembly position.
Further, strength detection subassembly bottom is equipped with pressure sensor, pressure sensor is used for detecting the finger pressure that presses sliding assembly and receive, the signal closes the base inboard and is equipped with the pressure control switch subassembly, it is protruding to press sliding assembly one side to be equipped with the control, the pressure control switch subassembly corresponds with the bellied position of control each other, opens the pressure control switch subassembly when pressing sliding assembly and signal closure base contact through the control arch.
Furthermore, a timer is arranged on the outer side of the testing shell and used for timing the normal reaction time of the patient.
Furthermore, the monitoring and early warning terminal is provided with three early warning signals of disease occurrence early warning, disease state aggravation early warning and disease state lightening early warning, and the disease state of the patient is predicted through different early warning signals.
Furthermore, the parathyroid hormone data processing module sends a primary early warning signal to the monitoring early warning terminal according to a comparison result, the time measuring component is used for determining the current time, the parathyroid hormone prediction engine predicts the parathyroid hormone fluctuation of the patient at the current time according to data extraction statistics in a daily parathyroid hormone statistical database of the patient, and the data secondary processing module carries out secondary processing on parathyroid hormone and sends a secondary early warning confirmation signal to the monitoring early warning terminal.
Further, a use method of the ischemic cardiovascular disease monitoring and early warning system based on machine learning comprises the following steps:
step one, in the bed rest process of a patient, wearing blood pressure detection equipment in a blood pressure real-time monitoring module on the body of the patient, installing facial expression recognition camera equipment in a facial recognition camera module above a bed head and recognizing facial expressions of the patient, and installing limb strength detection modules on two sides of the bed so that palms of the patient can quickly operate the limb strength detection modules;
after the blood pressure real-time monitoring module determines that the blood pressure of the patient suddenly rises, and the face recognition camera module determines that the face of the patient has the phenomena of back facial distortion, running water and the like, the limb strength detection module on the same side as the face with the abnormal condition is started;
step three, the patient operates the limb strength detection module to stop the early warning signal of the disease condition;
step four, the patient does not operate the limb strength detection module, and the monitoring and early warning terminal receives the disease condition initial early warning signal and sends out early warning;
and step five, performing blood drawing detection on the patient at regular time, and predicting the change degree of the condition of the patient according to the parathyroid hormone level of the patient.
Compared with the prior art, the invention reasonably predicts the disease occurrence of the patient in the disease occurrence process of the patient through the sequential identification and monitoring of the blood pressure, the facial expression and the limb strength of the patient and through a plurality of groups of conditions, and more accords with the current life state of the patient.
Compared with the prior art, according to the invention, after the disease is suffered, the severity of the disease state of the patient after the disease is suffered is predicted according to the condition that the parathyroid hormone PTH of the patient with ischemic cerebral apoplexy is in negative correlation with the cerebral infarction area and the imaging examination result of the patient cannot be timely determined under the condition limitation by determining the level change of the parathyroid hormone in the patient, so that the timely early warning of the disease severity of the patient is ensured, and the error caused by the parathyroid hormone change caused by the factor of the patient is removed according to the determination of the disease suffering time of the patient, so that the accurate early warning of the aggravation of the disease state of the patient is ensured.
Drawings
In order to more clearly illustrate the technical solution of the present invention, the drawings needed to be used in the technical description of the present invention will be briefly introduced below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without inventive labor.
Fig. 1 is a schematic view of the overall structure of the present invention.
Fig. 2 is a schematic structural diagram of a limb strength detection module according to the present invention.
In the figure: 1. testing the shell; 2. a reset slide block mechanism; 3. pressing the sliding component; 4. a force detection assembly; 5. an S-shaped flexibility detection chute; 6. a signal closing base; 7. a timer.
Detailed Description
The present invention is further described with reference to specific embodiments, and all other embodiments obtained by a person of ordinary skill in the art without any inventive work are within the scope of the present invention.
Example 1
Referring to fig. 1-2, the invention provides a machine learning-based ischemic cardiovascular disease monitoring and early warning system, which comprises a feature monitoring unit, a disease condition aggravation prediction unit and a monitoring and early warning terminal, wherein the feature monitoring unit sends an early warning signal of the disease condition aggravation to the monitoring and early warning terminal through a wireless network, and the disease condition aggravation prediction unit sends the early warning signal of the disease condition aggravation to the monitoring and early warning terminal through the wireless network; the feature monitoring unit comprises a blood pressure real-time monitoring module, a facial recognition camera module and a limb strength detection module, the blood pressure real-time monitoring module, the facial recognition camera module and the limb strength detection module sequentially transmit data signals and are sequentially started, the blood pressure real-time monitoring module comprises blood pressure detection equipment, the blood pressure detection equipment monitors the blood pressure of a patient in real time, the facial recognition camera module comprises facial expression recognition camera equipment and a facial expression comparison database, and the facial expression recognition camera equipment determines the current facial abnormality of the patient according to the data comparison of the database; the limb strength detection module comprises a test shell 1, a pressing sliding assembly 3 and an S-shaped flexibility detection sliding chute 5, wherein the S-shaped flexibility detection sliding chute 5 is used for detecting the flexibility of fingers, a reset sliding block mechanism 2 is arranged on the inner side of the test shell 1, the pressing sliding assembly 3 is connected above the reset sliding block mechanism 2 through a connecting rod, a strength detection assembly 4 is arranged on the inner side of the pressing sliding assembly 3, the strength detection assembly 4 is used for detecting the pressing strength of the fingers, and a signal closing base 6 is arranged at the top end of the test shell 1 and used for finally controlling the early warning signal of the state of an illness; the disease condition aggravation prediction unit comprises a parathyroid hormone detection module, a parathyroid hormone data processing module and a data analysis feedback module, wherein the parathyroid hormone detection module comprises a blood drawing detection mechanism and is used for drawing blood for detection of a patient, and the parathyroid hormone data processing module comprises normal parathyroid hormone level setting and compares the detected current parathyroid hormone level of the patient; the data analysis feedback module comprises a time measuring component, a patient daily parathyroid hormone statistical database, a parathyroid hormone prediction engine and a data secondary processing module, and eliminates influence factors of patient parathyroid hormone fluctuation according to a comparison result; the monitoring early warning terminal is used for receiving the early warning signal and determining the type of the early warning signal.
Specifically, slider mechanism 2 resets includes slider assembly, guide bar subassembly and the elasticity subassembly that resets, the guide bar subassembly is worn to locate the slider assembly inboard, and the guide bar subassembly is used for the gliding direction of slider assembly, the elasticity subassembly that resets is located between slider assembly and the test shells inner wall, and the elasticity subassembly that resets is used for resetting after slider assembly slides, slider assembly inboard is equipped with the reciprocal spout of straight line, the connecting rod is located the reciprocal spout of straight line and S type flexibility ratio detection spout 5 inboardly, and the reciprocal spout of straight line and S type flexibility ratio detection spout 5 are used for fixing a position the connecting rod, realize pressing the definite of 3 positions of slider assembly.
Specifically, 4 bottoms of strength determine module are equipped with pressure sensor, pressure sensor is used for detecting the finger pressure who receives pressing slide subassembly 3, 6 inboards of signal closure base are equipped with the pressure control switch subassembly, it is protruding to press 3 one sides of slide subassembly to be equipped with the control, the pressure control switch subassembly corresponds each other with the bellied position of control, opens the pressure control switch subassembly through the control arch when pressing slide subassembly 3 and the contact of signal closure base 6.
Specifically, the outer side of the test shell 1 is provided with a timer 7, and the timer 7 is used for timing the normal reaction time of the patient.
By adopting the technical scheme: according to the invention, through the sequential identification and monitoring of the blood pressure, the facial expression and the limb strength of the patient, the disease occurrence of the patient is reasonably predicted through multiple groups of conditions in the disease occurrence process of the patient, the current life state of the patient is more consistent, and when the limb strength of the patient is detected, the pressing force of the detection component 4 on the finger of the patient is detected, the S-shaped flexibility detection chute 5 detects the flexibility of the finger, the accuracy degree of the determination of the limb state of the patient is increased, the condition that the early warning signal is closed due to the mistaken touch of the patient in the motion process is avoided, the error of the early warning signal is avoided, and timely and accurate early warning is performed.
The ischemic cardiovascular disease monitoring and early warning system based on machine learning provided by the invention comprises the following steps: during the rest process of a patient lying in bed, a blood pressure detection device in a blood pressure real-time monitoring module is worn on the body of the patient, a facial expression recognition camera device in a facial recognition camera module is arranged above a bed head and recognizes the facial expression of the patient, a limb strength detection module is arranged on two sides of the patient bed, the palm of the patient can quickly operate the limb strength detection module, the blood pressure real-time monitoring module carries out real-time monitoring on the blood pressure of the patient, after the sudden rise of the blood pressure of the patient is determined, the facial recognition camera module operates, the facial expression recognition camera device recognizes the face of the patient and compares the recognition result with a facial expression comparison database, after the phenomena of the back face of the patient, the mouth corner, the running water and the like are determined, the limb strength detection module on the same side with the face is operated when the abnormal situation occurs, and a timer 7 starts up-down counting, the suggestion patient operates limbs strength detection module, and after the patient is sick, the patient's finger can't be sent out power in a flexible way, can't slide 3 with pressing down to make the signal close the unable count down termination with timer 7 of pressure control switch subassembly in the base 6, after timer 7 count down, detect early warning terminal and can send the early warning according to the count down end signal of timer 7.
Example 2
Referring to fig. 1-2, the present invention provides a machine learning-based ischemic cardiovascular disease monitoring and early warning system, and the same parts as those in embodiment 1 are not repeated in this embodiment, but the difference lies in a workflow of the machine learning-based ischemic cardiovascular disease monitoring and early warning system.
The method comprises the following steps: when the patient does not have cerebral ischemic stroke, but the blood pressure real-time monitoring module determines that the blood pressure of the patient is suddenly increased due to other reasons, the facial recognition camera module recognizes the face of the patient, the phenomena of facial deflection, angular facial deflection, running water and the like do not occur, the subsequent detection is interrupted, after the blood pressure real-time monitoring module determines that the blood pressure of the patient is suddenly increased due to other reasons, the facial recognition camera module mistakenly recognizes the phenomena of facial deflection, angular deflection, running water and the like, the limb strength detection module is detected to operate, the timer 7 is started, the patient presses the finger to the pressing sliding assembly 3, the force detection assembly 4 receives constant pressure applied by the finger of the patient, then the finger of the patient moves to drive the pressing sliding assembly 3 to move in the direction of closing the base 6 by the signal, in the process, the connecting rod at the bottom end of the pressing sliding assembly 3 moves along the S-shaped activity detection chute 5, the pressing sliding component 3 moves in an S-shaped curve to detect finger flexibility of a patient, before countdown of the timer 7 is finished, the finger of the patient controls the pressing sliding component 3 to be in contact with the signal closing base 6, namely, the patient does not have the phenomena of limb numbness, poor flexibility and the like, disease early warning is not needed, the signal closing base 6 is internally provided with a pressure air conditioner control switch to close the timer 7, timing is stopped, and the situation that the detection early warning terminal sends out early warning is avoided
Example 3
Referring to fig. 1, the present invention provides a machine learning-based ischemic cardiovascular disease monitoring and early warning system, which includes a feature monitoring unit, a disease condition aggravation prediction unit, and a monitoring and early warning terminal, wherein the feature monitoring unit sends an early warning signal of an illness condition to the monitoring and early warning terminal through a wireless network, and the disease condition aggravation prediction unit sends the early warning signal of the illness condition aggravation to the monitoring and early warning terminal through the wireless network; the feature monitoring unit comprises a blood pressure real-time monitoring module, a facial recognition camera module and a limb strength detection module, the blood pressure real-time monitoring module, the facial recognition camera module and the limb strength detection module sequentially transmit data signals and are sequentially started, the blood pressure real-time monitoring module comprises blood pressure detection equipment, the blood pressure detection equipment monitors the blood pressure of a patient in real time, the facial recognition camera module comprises facial expression recognition camera equipment and a facial expression comparison database, and the facial expression recognition camera equipment determines the current facial abnormality of the patient according to the data comparison of the database; the limb strength detection module comprises a test shell 1, a pressing sliding assembly 3 and an S-shaped flexibility detection sliding chute 5, wherein the S-shaped flexibility detection sliding chute 5 is used for detecting the flexibility of fingers, a reset sliding block mechanism 2 is arranged on the inner side of the test shell 1, the pressing sliding assembly 3 is connected above the reset sliding block mechanism 2 through a connecting rod, a strength detection assembly 4 is arranged on the inner side of the pressing sliding assembly 3, the strength detection assembly 4 is used for detecting the pressing strength of the fingers, and a signal closing base 6 is arranged at the top end of the test shell 1 and used for finally controlling the early warning signal of the state of an illness; the disease condition aggravation prediction unit comprises a parathyroid hormone detection module, a parathyroid hormone data processing module and a data analysis feedback module, wherein the parathyroid hormone detection module comprises a blood drawing detection mechanism and is used for drawing blood for detection of a patient, and the parathyroid hormone data processing module comprises normal parathyroid hormone level setting and compares the detected current parathyroid hormone level of the patient; the data analysis feedback module comprises a time measuring component, a patient daily parathyroid hormone statistical database, a parathyroid hormone prediction engine and a data secondary processing module, and eliminates influence factors of patient parathyroid hormone fluctuation according to a comparison result; the monitoring early warning terminal is used for receiving the early warning signal and determining the type of the early warning signal.
Specifically, the monitoring and early warning terminal is provided with three early warning signals, namely a disease occurrence early warning signal, a disease state aggravation early warning signal and a disease state lightening early warning signal, and the disease state of the patient is predicted through different early warning signals.
Specifically, the parathyroid hormone data processing module sends a primary early warning signal to the monitoring early warning terminal according to a comparison result, the time measuring component is used for determining the current time, the parathyroid hormone prediction engine predicts parathyroid hormone fluctuation of a patient at the current time according to data extraction statistics in a daily parathyroid hormone statistical database of the patient, and the data secondary processing module carries out secondary processing on parathyroid hormone and sends a secondary early warning confirmation signal to the monitoring early warning terminal.
By adopting the technical scheme: according to the invention, after a patient is ill, according to the determination of the level change of parathyroid hormone in the patient body, the condition severity of the patient after the patient is ill is predicted according to the condition that the parathyroid hormone PTH of the patient with ischemic cerebral apoplexy is in negative correlation with the cerebral infarction area, and when the imaging examination result of the patient cannot be determined in time under the condition limitation, the timely early warning of the patient is ensured, and according to the determination of the disease onset time of the patient, the error caused by the parathyroid hormone change caused by the factors of the patient is removed, so that the accurate early warning of the aggravation of the condition of the patient is ensured.
The ischemic cardiovascular disease monitoring and early warning system based on machine learning provided by the invention comprises the following steps: the method comprises the steps of detecting the fluctuation of parathyroid hormone of a patient before morbidity, transmitting the fluctuation to a daily parathyroid hormone statistical database of the patient, determining the level of parathyroid hormone which fluctuates smoothly in the daytime before the morbidity of the patient, taking the level as a reference, sending a disease early warning signal by a monitoring early warning terminal after the disease occurs in the daytime, reminding families or medical staff of the patient to cure and care the patient, drawing blood from the patient in the process, detecting a blood sample through a parathyroid hormone level detection module, determining the level of parathyroid hormone of the patient after the disease occurs, carrying out digitization on the parathyroid hormone level, transmitting the parathyroid hormone level into a parathyroid hormone data processing module, comparing the parathyroid hormone level of the patient after the disease occurs with the parathyroid hormone level of the patient before the morbidity of the patient, and drawing blood from the patient at regular time in the following period, the parathyroid hormone level of a patient is periodically detected, the parathyroid hormone level is compared with the previous detection data by a parathyroid hormone data processing module, the change of the parathyroid hormone level is determined, the disease condition change of the patient is predicted according to the condition that the parathyroid hormone PTH of the patient suffering from ischemic stroke is in negative correlation with the cerebral infarction area, the prediction result is received by a monitoring and early warning terminal, and an early warning signal is sent according to the prediction result.
Example 4
Referring to fig. 1, the present invention provides a machine learning-based ischemic cardiovascular disease monitoring and early warning system, and the same parts as those in embodiment 3 are not repeated in this embodiment, but the difference lies in a workflow of the machine learning-based ischemic cardiovascular disease monitoring and early warning system.
The method comprises the following steps: after the disease occurs at night, the parathyroid hormone data processing module compares the parathyroid hormone level after the disease occurs with the parathyroid hormone level before the disease does not occur, because the parathyroid hormone level in the patient body at night has circadian rhythm and can change, and an error exists in the comparison result, after the comparison result generates obvious fluctuation, a primary early warning signal is sent to the monitoring early warning terminal, and then the parathyroid hormone prediction engine extracts and counts data in a daily parathyroid hormone statistical database of the patient according to the current time measured by the time measuring component, predicts the parathyroid hormone level before the disease occurs of the patient at the current time, and takes the data as a reference, and compares the parathyroid hormone level after the disease occurs with the parathyroid hormone level fluctuation range of the patient at the current time period by the data secondary processing module, and determining the parathyroid hormone level fluctuation of the patient time, and sending a secondary early warning confirmation signal to the monitoring and early warning terminal according to the comparison result, so that the condition aggravation degree of the patient cannot be timely and accurately early warned due to the influence of the parathyroid hormone level fluctuation of the patient.
The above description is only for the preferred embodiments of the present invention, but the scope of the present invention is not limited thereto, and those skilled in the art should be construed as the scope of the present invention by equally or differently replacing the technical solutions and the inventive concepts of the present invention within the technical scope of the present invention.
Claims (7)
1. The utility model provides an ischemic cardiovascular disease monitoring and early warning system based on machine learning, includes that characteristic monitoring unit, state of illness aggravate prediction unit and monitoring and early warning terminal, its characterized in that: the characteristic monitoring unit sends an illness state initial early warning signal to a monitoring early warning terminal through a wireless network, and the illness state aggravation prediction unit sends an illness state aggravation early warning signal to the monitoring early warning terminal through the wireless network; the feature monitoring unit comprises a blood pressure real-time monitoring module, a facial recognition camera module and a limb strength detection module, the blood pressure real-time monitoring module, the facial recognition camera module and the limb strength detection module sequentially transmit data signals and are sequentially started, the blood pressure real-time monitoring module comprises blood pressure detection equipment, the blood pressure detection equipment monitors the blood pressure of a patient in real time, the facial recognition camera module comprises facial expression recognition camera equipment and a facial expression comparison database, and the facial expression recognition camera equipment determines the current facial abnormality of the patient according to the data comparison of the database; the limb strength detection module comprises a test shell, a pressing sliding assembly and an S-shaped flexibility detection chute, wherein a reset sliding block mechanism is arranged on the inner side of the test shell, the pressing sliding assembly is connected above the reset sliding block mechanism through a connecting rod, the strength detection assembly is arranged on the inner side of the pressing sliding assembly, and a signal closing base is arranged at the top end of the test shell; the disease condition aggravation prediction unit comprises a parathyroid hormone detection module, a parathyroid hormone data processing module and a data analysis feedback module, wherein the parathyroid hormone detection module comprises a blood drawing detection mechanism and is used for drawing blood for detection of a patient, and the parathyroid hormone data processing module comprises normal parathyroid hormone level setting and compares the detected current parathyroid hormone level of the patient; the data analysis feedback module comprises a time measuring component, a patient daily parathyroid hormone statistical database, a parathyroid hormone prediction engine and a data secondary processing module, and the data analysis feedback module eliminates influence factors of patient parathyroid hormone fluctuation according to a comparison result and sends a secondary early warning confirmation signal to the monitoring early warning terminal; the monitoring early warning terminal is used for receiving the early warning signal and determining the type of the early warning signal.
2. The machine learning-based ischemic cardiovascular disease monitoring and early warning system as claimed in claim 1, wherein: the slider mechanism resets includes slider assembly, guide bar subassembly and the elasticity subassembly that resets, slider assembly inboard is worn to locate by the guide bar subassembly, the elasticity subassembly that resets is located between slider assembly and the test shells inner wall, the slider assembly inboard is equipped with the reciprocal spout of straight line, the connecting rod is located the reciprocal spout of straight line and S type flexibility ratio detection spout inboard.
3. The machine learning-based ischemic cardiovascular disease monitoring and early warning system as claimed in claim 1, wherein: the strength detection subassembly bottom is equipped with pressure sensor, pressure sensor is used for detecting the finger pressure that presses down the slip subassembly and receive, the signal closes the base inboard and is equipped with the pressure control switch subassembly, it is protruding to press down slip subassembly one side to be equipped with the control, the pressure control switch subassembly corresponds with the bellied position of control each other.
4. The machine learning-based ischemic cardiovascular disease monitoring and early warning system as claimed in claim 1, wherein: and a timer is arranged on the outer side of the test shell.
5. The machine learning-based ischemic cardiovascular disease monitoring and early warning system as claimed in claim 1, wherein: the monitoring and early warning terminal is provided with three early warning signals of disease early warning, disease state aggravation early warning and disease state lightening early warning.
6. The machine learning-based ischemic cardiovascular disease monitoring and early warning system as claimed in claim 1, wherein: the parathyroid hormone data processing module sends a primary early warning signal to the monitoring early warning terminal according to a comparison result, the time measuring component is used for determining the current time, the parathyroid hormone prediction engine predicts parathyroid hormone fluctuation of a patient at the current time according to data extraction statistics in a daily parathyroid hormone statistical database of the patient, and the data secondary processing module carries out secondary processing on parathyroid hormone and sends a secondary early warning confirmation signal to the monitoring early warning terminal.
7. The use method of the machine learning-based ischemic cardiovascular disease monitoring and early warning system according to any one of claims 1 to 6, characterized in that: the method comprises the following steps:
step one, in the bed rest process of a patient, wearing blood pressure detection equipment in a blood pressure real-time monitoring module on the body of the patient, installing facial expression recognition camera equipment in a facial recognition camera module above a bed head and recognizing facial expressions of the patient, and installing limb strength detection modules on two sides of the bed so that palms of the patient can quickly operate the limb strength detection modules;
after the blood pressure real-time monitoring module determines that the blood pressure of the patient suddenly rises, and the face recognition camera module determines that the face of the patient has rear face skew, mouth angle skew and running water phenomena, the limb strength detection module on the same side as the face with the abnormal situation is started;
step three, the patient operates the limb strength detection module to stop the early warning signal of the state of illness;
step four, the patient does not operate the limb strength detection module, and the monitoring and early warning terminal receives the disease condition initial early warning signal and sends out early warning;
and step five, performing blood drawing detection on the patient at regular time, and predicting the change degree of the condition of the patient according to the parathyroid hormone level of the patient.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210131069.2A CN114495425B (en) | 2022-02-13 | 2022-02-13 | Ischemic cardiovascular disease monitoring and early warning system based on machine learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210131069.2A CN114495425B (en) | 2022-02-13 | 2022-02-13 | Ischemic cardiovascular disease monitoring and early warning system based on machine learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114495425A true CN114495425A (en) | 2022-05-13 |
| CN114495425B CN114495425B (en) | 2022-12-16 |
Family
ID=81479982
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210131069.2A Active CN114495425B (en) | 2022-02-13 | 2022-02-13 | Ischemic cardiovascular disease monitoring and early warning system based on machine learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114495425B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106343948A (en) * | 2016-09-30 | 2017-01-25 | 南京信息职业技术学院 | Cerebral infarction patient monitoring and early warning system |
| CN106419844A (en) * | 2016-09-30 | 2017-02-22 | 南京信息职业技术学院 | Monitoring and early warning method for cerebral thrombosis patients |
| US20190029606A1 (en) * | 2016-01-12 | 2019-01-31 | Yale University | System and method for diagnosing and notification regarding the onset of a stroke |
| CN110974158A (en) * | 2019-10-23 | 2020-04-10 | 重庆特斯联智慧科技股份有限公司 | Community patient identification and distress calling method, system method and system based on deep learning |
| CN111358449A (en) * | 2020-01-16 | 2020-07-03 | 董思羽 | Household device for monitoring cerebral apoplexy and early discovering and early warning |
| CN211633244U (en) * | 2020-01-14 | 2020-10-09 | 刘亚军 | Remote medical monitoring and early warning system |
-
2022
- 2022-02-13 CN CN202210131069.2A patent/CN114495425B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190029606A1 (en) * | 2016-01-12 | 2019-01-31 | Yale University | System and method for diagnosing and notification regarding the onset of a stroke |
| CN106343948A (en) * | 2016-09-30 | 2017-01-25 | 南京信息职业技术学院 | Cerebral infarction patient monitoring and early warning system |
| CN106419844A (en) * | 2016-09-30 | 2017-02-22 | 南京信息职业技术学院 | Monitoring and early warning method for cerebral thrombosis patients |
| CN110974158A (en) * | 2019-10-23 | 2020-04-10 | 重庆特斯联智慧科技股份有限公司 | Community patient identification and distress calling method, system method and system based on deep learning |
| CN211633244U (en) * | 2020-01-14 | 2020-10-09 | 刘亚军 | Remote medical monitoring and early warning system |
| CN111358449A (en) * | 2020-01-16 | 2020-07-03 | 董思羽 | Household device for monitoring cerebral apoplexy and early discovering and early warning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114495425B (en) | 2022-12-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP0327646A1 (en) | Apparatus for measuring biological signals | |
| WO2017156834A1 (en) | Intelligent gloves for measuring calorie consumption and monitoring hand gesture recognition, and estimation method and system | |
| JP2009501557A5 (en) | ||
| CN105204413A (en) | Information processing system and method used for wearable device | |
| CN107788969A (en) | The automatic testing method of QRS complex in a kind of electrocardiosignal | |
| US20180078191A1 (en) | Medical Toilet for Collecting and Analyzing Multiple Metrics | |
| KR20040095309A (en) | Sudden cardiac arrest monitoring system | |
| CN109464134B (en) | Pulse monitoring device and system | |
| KR102346824B1 (en) | System of providing complex living support solution by monitoring and analyzing biosignal based on artificial intelligence and operating method thereof | |
| CN102488512A (en) | Automatic alarm system for electrocatdiogram monitoring and alarm method thereof | |
| EP3836158A1 (en) | Doctor health monitoring system based on medical apparatus | |
| CN116098602B (en) | Non-contact sleep respiration monitoring method and device based on IR-UWB radar | |
| CN112568876A (en) | System and method for predicting health of old people based on LSTM multiple physiological parameters | |
| KR20190052870A (en) | Diagnosis system of drinking status of passengers | |
| CN114652303B (en) | Intelligent monitoring system | |
| CN114495425B (en) | Ischemic cardiovascular disease monitoring and early warning system based on machine learning | |
| KR20200062522A (en) | System, sever and method for preventing metabolic syndrome of pet using smart neck-band based on cloud | |
| CN112971852A (en) | Wireless probe, intelligent processing module and wireless fetal monitoring system for fetal monitoring | |
| CN208134216U (en) | A kind of steering wheel based on biosensor | |
| CN115770028A (en) | Blood pressure detection method, system, device and storage medium | |
| CN108670264A (en) | System is monitored based on arthrogryposis and the motion of knee joint fatigue strength of plantar pressure | |
| Okajima et al. | Methodology of ECG interpretation in the Nagoya program | |
| EP3968845A1 (en) | System and method for precise determination of a date of childbirth with a wearable device | |
| CA3126928A1 (en) | Systems, devices, and methods for detecting brain conditions from cranial movement due to blood flow in the brain | |
| WO2017209360A1 (en) | Grip-type biological signal measuring device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |