CN117936073A - Remote real-time on-line monitoring management system for human health information - Google Patents
Remote real-time on-line monitoring management system for human health information Download PDFInfo
- Publication number
- CN117936073A CN117936073A CN202410084336.4A CN202410084336A CN117936073A CN 117936073 A CN117936073 A CN 117936073A CN 202410084336 A CN202410084336 A CN 202410084336A CN 117936073 A CN117936073 A CN 117936073A
- Authority
- CN
- China
- Prior art keywords
- unit
- patient
- data
- information
- 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.)
- Pending
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 54
- 230000036541 health Effects 0.000 title claims abstract description 22
- 238000012937 correction Methods 0.000 claims abstract description 41
- 238000011282 treatment Methods 0.000 claims abstract description 27
- 230000002159 abnormal effect Effects 0.000 claims abstract description 24
- 238000012545 processing Methods 0.000 claims description 34
- 230000009471 action Effects 0.000 claims description 24
- 238000013527 convolutional neural network Methods 0.000 claims description 23
- 201000010099 disease Diseases 0.000 claims description 20
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 20
- 238000002372 labelling Methods 0.000 claims description 16
- 238000000605 extraction Methods 0.000 claims description 11
- 238000012549 training Methods 0.000 claims description 10
- 238000005516 engineering process Methods 0.000 claims description 8
- 230000010354 integration Effects 0.000 claims description 8
- 239000008280 blood Substances 0.000 claims description 7
- 210000004369 blood Anatomy 0.000 claims description 7
- 230000036772 blood pressure Effects 0.000 claims description 7
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 6
- 230000036760 body temperature Effects 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 6
- 229910052760 oxygen Inorganic materials 0.000 claims description 6
- 239000001301 oxygen Substances 0.000 claims description 6
- 230000036387 respiratory rate Effects 0.000 claims description 5
- 238000010415 tidying Methods 0.000 claims description 4
- 238000003062 neural network model Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 2
- 238000000034 method Methods 0.000 description 14
- 238000003745 diagnosis Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 5
- 230000005540 biological transmission Effects 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000001914 filtration Methods 0.000 description 3
- 230000033001 locomotion Effects 0.000 description 3
- 238000011369 optimal treatment Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 208000024172 Cardiovascular disease Diseases 0.000 description 1
- 206010008479 Chest Pain Diseases 0.000 description 1
- 208000017667 Chronic Disease Diseases 0.000 description 1
- 208000000059 Dyspnea Diseases 0.000 description 1
- 206010013975 Dyspnoeas Diseases 0.000 description 1
- WQZGKKKJIJFFOK-GASJEMHNSA-N Glucose Natural products OC[C@H]1OC(O)[C@H](O)[C@@H](O)[C@@H]1O WQZGKKKJIJFFOK-GASJEMHNSA-N 0.000 description 1
- 206010020772 Hypertension Diseases 0.000 description 1
- 206010020843 Hyperthermia Diseases 0.000 description 1
- 208000001953 Hypotension Diseases 0.000 description 1
- 206010021143 Hypoxia Diseases 0.000 description 1
- 208000019693 Lung disease Diseases 0.000 description 1
- 208000012902 Nervous system disease Diseases 0.000 description 1
- 208000025966 Neurological disease Diseases 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 210000003423 ankle Anatomy 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000003542 behavioural effect Effects 0.000 description 1
- 210000004204 blood vessel Anatomy 0.000 description 1
- 208000026106 cerebrovascular disease Diseases 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000002526 effect on cardiovascular system Effects 0.000 description 1
- 210000001513 elbow Anatomy 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 239000008103 glucose Substances 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 210000004247 hand Anatomy 0.000 description 1
- 230000005802 health problem Effects 0.000 description 1
- 208000019622 heart disease Diseases 0.000 description 1
- 230000004217 heart function Effects 0.000 description 1
- 210000001624 hip Anatomy 0.000 description 1
- 230000036031 hyperthermia Effects 0.000 description 1
- 230000036543 hypotension Effects 0.000 description 1
- 230000002631 hypothermal effect Effects 0.000 description 1
- 230000007954 hypoxia Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 208000015181 infectious disease Diseases 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 208000017169 kidney disease Diseases 0.000 description 1
- 210000003127 knee Anatomy 0.000 description 1
- 230000035790 physiological processes and functions Effects 0.000 description 1
- 230000002980 postoperative effect Effects 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000004202 respiratory function Effects 0.000 description 1
- 210000002832 shoulder Anatomy 0.000 description 1
- 230000006016 thyroid dysfunction Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 210000000707 wrist Anatomy 0.000 description 1
Abstract
The invention relates to the field of medical monitoring systems, in particular to a human health information remote real-time on-line monitoring management system, a patient information acquisition module, a medical information acquisition module and a medical information acquisition module, wherein the patient information acquisition module is used for acquiring medical information of a patient; the wearable data acquisition module is used for being worn on a patient to acquire the sign data; the primary early warning module is used for identifying the abnormal state of the patient based on the sensor data and generating primary warning information; the early warning correction module corrects the primary warning information by adopting a behavior mode obtained by video data which is acquired by video and corresponds to the wearing data, so as to obtain corrected warning information; the alarm module is used for sending a notification to relevant personnel of the patient based on the correction alarm information; and the suggestion module is used for matching the emergency treatment scheme based on the alarm information and sending the emergency treatment scheme to the patient and related persons. The invention realizes real-time monitoring, abnormal early warning and accurate treatment of the illness state of the patient.
Description
Technical Field
The invention relates to the field of medical monitoring systems, in particular to a remote real-time on-line monitoring management system for human health information.
Background
The remote monitoring of human body information, also called remote health monitoring or remote physiological parameter monitoring, is a technology for realizing real-time or quasi-real-time monitoring of human body physiological state by using advanced sensors, wireless communication technology and data processing algorithm. It is mainly used in the fields of medical care and health management, especially in the fields of chronic disease management, old man care, postoperative recovery, athlete training and the like.
The existing remote information monitoring mainly monitors human body data by using wearable equipment so as to judge the health degree of a monitored object. The patient wears various small and comfortable sensors such as heart rate monitors, blood pressure meters, blood glucose meters, thermometers, blood oxygen saturation detectors, motion sensors, etc., which can continuously or periodically measure and record key physiological indicators.
However, the above method may cause a large error in data due to inaccurate wearing method, so that the normal state of the patient cannot be found normally, and the effectiveness of monitoring is reduced.
Disclosure of Invention
The invention aims to provide a remote real-time on-line monitoring management system for human health information, which aims to correct a monitoring system by adopting video data so as to improve the accuracy of monitoring.
In order to achieve the aim, the invention provides a remote real-time on-line monitoring management system for human health information, which comprises a patient information acquisition module, a wearable data acquisition module, a primary early warning module, an early warning correction module, an alarm module and a suggestion module,
The patient information acquisition module is used for acquiring medical information of a patient;
the wearable data acquisition module is used for being worn on a patient to acquire sign data;
The primary early warning module is used for identifying the abnormal state of the patient based on the sensor data and generating primary warning information;
the early warning correction module corrects the primary warning information by adopting a behavior mode obtained by video data which is acquired by video and corresponds to the wearing data to obtain corrected warning information;
The alarm module is used for sending a notification to relevant personnel of the patient based on the correction alarm information;
The advice module is used for matching an emergency treatment scheme based on the alarm information and sending the emergency treatment scheme to the patient and related persons.
The patient information acquisition module comprises an information acquisition unit, an integration unit and an updating unit, wherein the information acquisition unit is used for acquiring all medical record information of a patient in a system, the integration unit is used for integrating all the medical record information to obtain tidying medical record data, and the updating unit is used for periodically updating the tidying medical record data.
Wherein the sign data includes heart rate, blood pressure, blood oxygen saturation, body temperature, and respiratory rate.
The primary early warning module comprises a sensing data acquisition unit, a data processing unit and a judging unit, wherein the sensing data acquisition unit is used for acquiring sensor data; the data processing unit is used for preprocessing the received data and removing invalid or abnormal values; and the judging unit is used for judging that the monitoring index exceeds a preset range based on the set threshold value and generating primary alarm information.
The early warning correction module comprises a patient action image acquisition unit, a key point extraction unit, a convolutional neural network model identification unit and an early warning information correction unit, wherein the patient action image acquisition unit, the key point extraction unit, the convolutional neural network model identification unit and the early warning information correction unit are connected in sequence;
the patient action image acquisition unit is used for acquiring patient action image data;
the key point extraction unit is used for extracting key points of a human body from an original image by applying a human body posture estimation technology;
The convolutional neural network model identification unit is used for training a convolutional neural network model by using key points of a human body and identifying a behavior mode of a patient based on the convolutional neural network model;
The early warning information correction unit corrects primary warning information by combining the wearing data and the behavior mode.
The early warning correction module further comprises a labeling unit and a model correction unit, wherein the labeling unit is used for labeling the correctness of the identified behavior mode by the patient; the model correction unit is used for correcting the neural network model based on the labeling data.
Wherein the patient action image acquisition unit comprises an image acquisition subunit and an image processing subunit, the image acquisition subunit is used for collecting a video data set containing the posture actions of the patient; the image processing subunit is used for carrying out normalization processing on the image.
The alarm unit comprises a related personnel setting unit and an alarm unit, wherein the related personnel setting unit is used for setting related personnel associated with a patient; and the alarm unit is used for informing relevant personnel of the alarm information through various channels.
The suggestion module comprises a monitoring data acquisition unit, a disease matching unit, a scheme matching unit and a sending unit, wherein the monitoring data acquisition unit is used for acquiring video monitoring data and wearing data when the behavior mode is abnormal based on a time stamp; the disease matching unit is used for matching the medical information based on the wearing data to obtain corresponding disease items; the scheme matching unit is used for matching emergency treatment schemes in the database based on disease items; the sending unit is used for sending the video monitoring data and the emergency processing scheme to relevant personnel of the patient.
The invention relates to a remote real-time on-line monitoring and managing system for human health information, which is characterized in that a patient information acquisition module is used for acquiring medical information of a patient; the wearable data acquisition module is used for being worn on a patient to acquire sign data; the primary early warning module is used for identifying the abnormal state of the patient based on the sensor data and generating primary warning information; the early warning correction module corrects the primary warning information by adopting a behavior mode obtained by video data which is acquired by video and corresponds to the wearing data to obtain corrected warning information; the alarm module is used for sending a notification to relevant personnel of the patient based on the correction alarm information; the advice module is used for matching an emergency treatment scheme based on the alarm information and sending the emergency treatment scheme to the patient and related persons. The patient information acquisition module is responsible for collecting medical information of the patient. By interfacing with a hospital information system, the module can acquire key information such as medical history, diagnosis, treatment scheme and the like of a patient in real time. The wearable data acquisition module is mainly used for acquiring characteristic data such as heart rate, blood pressure, body temperature and the like. The module adopts a sensor technology to transmit the acquired data to a system server in real time, so that the real-time property and accuracy of the data are ensured. Through analysis of the data, the system can monitor vital signs of the patient in real time and provide a data basis for the early warning module. The primary early warning module is a key link for identifying abnormal states of the patient based on sensor data. The module adopts a preset algorithm and a preset threshold value to analyze the data transmitted by the wearable data acquisition module in real time. Once the data is found to be abnormal, the module immediately generates primary alarm information, and the early warning correction module corrects the primary alarm information by adopting video data corresponding to the wearing data by adopting a video acquisition technology. By analyzing the behavior pattern of the patient, the module can determine whether the patient has a real abnormal condition. The corrected alarm information is obtained, the illness state of the patient can be reflected more accurately, and the false alarm rate is reduced. The alarm module is responsible for sending notifications to patient related personnel, including healthcare personnel, patient family members, etc., based on the revised alarm information. The notification content contains detailed descriptions of abnormal conditions of the patient, processing advice and the like so that relevant personnel can quickly take measures to ensure the life safety of the patient. The suggestion module can provide targeted treatment suggestions for medical staff. Meanwhile, the module can continuously track the illness state of the patient, and adjust advice according to the illness state change, so that the patient is ensured to obtain the optimal treatment effect. The invention realizes real-time monitoring, abnormal early warning and accurate treatment of the illness state of the patient. The medical service quality is greatly improved, the medical risk is reduced, and the real convenience is brought to patients and medical staff.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a block diagram of a remote real-time on-line monitoring management system for human health information according to a first embodiment of the present invention.
Fig. 2 is a block diagram of a patient information acquisition module according to a second embodiment of the present invention.
Fig. 3 is a block diagram of a primary alarm module according to a second embodiment of the present invention.
Fig. 4 is a structural diagram of an early warning correction module according to a second embodiment of the present invention.
Fig. 5 is a block diagram of a patient movement image acquisition unit according to a second embodiment of the present invention.
Fig. 6 is a structural view of an alarm unit according to a second embodiment of the present invention.
Fig. 7 is a block diagram of a proposal module of the second embodiment of the invention.
The system comprises a patient information acquisition module 101, a wearable data acquisition module 102, a primary early warning module 103, an early warning correction module 104, an alarm module 105, a suggestion module 106, an information acquisition unit 201, an integration unit 202, an update unit 203, a sensing data acquisition unit 204, a data processing unit 205, a judgment unit 206, a patient action image acquisition unit 207, a key point extraction unit 208, a convolutional neural network model identification unit 209, an early warning information correction unit 210, a labeling unit 211, a model correction unit 212, an image acquisition subunit 213, an image processing subunit 214, a related personnel setting unit 215, an alarm unit 216, a monitoring data acquisition unit 217, a disease matching unit 218, a scheme matching unit 219 and a transmission unit 220.
Detailed Description
Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are illustrative and intended to explain the present invention and should not be construed as limiting the invention.
First embodiment
Referring to fig. 1, the invention provides a remote real-time on-line monitoring management system for human health information, which comprises a patient information acquisition module 101, a wearable data acquisition module 102, a primary early warning module 103, an early warning correction module 104, an alarm module 105 and a suggestion module 106, wherein the patient information acquisition module 101 is used for acquiring medical information of a patient; the wearable data acquisition module 102 is used for being worn on a patient to acquire sign data; the primary early warning module 103 is configured to identify an abnormal state of a patient based on sensor data, and generate primary alarm information;
The early warning correction module corrects the primary warning information by adopting a behavior mode obtained by video data which is acquired by video and corresponds to the wearing data to obtain corrected warning information; the alarm module 105 is used for sending a notification to relevant personnel of the patient based on the correction alarm information; the advice module 106 is configured to match an emergency treatment plan based on the alarm information and send the emergency treatment plan to the patient and the related person.
In the present embodiment, the patient information acquisition module 101 is responsible for collecting medical information of a patient. By interfacing with a hospital information system, the module can acquire key information such as medical history, diagnosis, treatment scheme and the like of a patient in real time. The wearable data acquisition module 102 is mainly used for acquiring characteristic data, such as heart rate, blood pressure, body temperature, etc. The module adopts a sensor technology to transmit the acquired data to a system server in real time, so that the real-time property and accuracy of the data are ensured. Through analysis of the data, the system can monitor vital signs of the patient in real time and provide a data basis for the early warning module. The primary pre-warning module 103 is a key element for identifying abnormal states of the patient based on the sensor data. The module adopts a preset algorithm and a preset threshold value to analyze the data transmitted by the wearable data acquisition module 102 in real time. Once the data is found to be abnormal, the module immediately generates primary alarm information, and the early warning correction module corrects the primary alarm information by adopting video data corresponding to the wearing data by adopting a video acquisition technology. By analyzing the behavior pattern of the patient, the module can determine whether the patient has a real abnormal condition. The corrected alarm information is obtained, the illness state of the patient can be reflected more accurately, and the false alarm rate is reduced. The alarm module 105 is responsible for sending notifications to patient-related personnel, including healthcare personnel, patient family members, etc., based on the revised alarm information. The notification content contains detailed descriptions of abnormal conditions of the patient, processing advice and the like so that relevant personnel can quickly take measures to ensure the life safety of the patient. Advice module 106 may provide medical personnel with targeted treatment advice. Meanwhile, the module can continuously track the illness state of the patient, and adjust advice according to the illness state change, so that the patient is ensured to obtain the optimal treatment effect. The invention realizes real-time monitoring, abnormal early warning and accurate treatment of the illness state of the patient. The medical service quality is greatly improved, the medical risk is reduced, and the real convenience is brought to patients and medical staff.
Second embodiment
Referring to fig. 2 to 7, the present invention further provides a remote real-time on-line monitoring and managing system for human health information based on the first embodiment, where the patient information acquisition module 101 includes an information acquisition unit 201, an integration unit 202 and an update unit 203, where the information acquisition unit 201 is configured to acquire all medical record information of a patient in the system, the integration unit 202 is configured to integrate all medical record information to obtain an ordered medical record data, and the update unit 203 is configured to update the ordered medical record data periodically.
The information acquisition unit 201 is a basic part of the patient information acquisition module 101. The unit is responsible for gathering all medical record information for the patient in the system. Such information includes, but is not limited to, personal information of the patient, a visit record, an inspection report, a diagnosis result, and the like. Through the operation of the information acquisition unit 201, a healthcare worker can conveniently acquire the complete medical record of a patient, and data support is provided for subsequent diagnosis and treatment. The integrating unit 202 is a processing link for integrating acquired medical record information. In this process, the integration unit 202 gathers medical record information of patients scattered around to form a complete medical record data. And format the various data for subsequent analysis. With the increase of the number of times of patient visits, the medical record information of the patients can be changed continuously. The update unit 203 can ensure that patient medical record data is always up to date so that healthcare workers can know the latest condition of the patient. In addition, the updating unit 203 can also automatically remind the medical staff of paying attention to the change of the illness state of the patient, so that the accuracy of diagnosis and treatment is improved.
The physical sign data includes heart rate, blood pressure, blood oxygen saturation, body temperature, and respiratory rate.
Heart rate is a basic indicator of heart function and is normally in the range of 60-100 beats/min. Too high or too low a heart rate may be indicative of heart disease or other physical condition. Blood pressure refers to the pressure of blood on the wall of a blood vessel during circulation, and the normal range is 90-140 mmHg and 60-90 mmHg. Both hypertension and hypotension may lead to physical health problems such as cardiovascular and cerebrovascular diseases, kidney diseases, etc.
The normal range of blood oxygen saturation is above 95%. Oxygen saturation of less than 90% may cause hypoxia, such as dyspnea, chest distress, etc. The body temperature is the internal heat balance of the human body, and the normal range is 36-37.2 ℃. Hyperthermia or hypothermia may be indicative of infection, thyroid dysfunction, and the like.
Respiratory rate is an indicator of respiratory function, and is normally in the range of 12-20 times per minute. Too fast or too slow a respiratory rate may be associated with lung diseases, neurological diseases, etc. The monitoring of these sign data helps to find abnormalities in time, providing effective diagnosis and intervention for the patient.
The primary early warning module 103 comprises a sensing data acquisition unit 204, a data processing unit 205 and a judging unit 206, wherein the sensing data acquisition unit 204 is used for acquiring sensor data; the data processing unit 205 is configured to pre-process the received data to remove invalid or abnormal values; the judging unit 206 is configured to generate an alarm message when the monitoring indicator is determined to exceed the preset range based on the set threshold value.
The sensing data obtaining unit 204 may obtain the sensor data detected by the wearable device, and then process the sensor data by the data processing unit 205, where the data processing unit 205 performs denoising and smoothing on the data by adopting a data filtering algorithm, such as kalman filtering and moving average filtering. This process helps to eliminate invalid and outliers in the data and improves the data quality. In addition, the data processing unit 205 may perform normalization processing on the data, so that the data acquired by different sensors has a unified standard, so as to facilitate subsequent analysis and judgment.
Finally, the judging unit 206 is a link for judging the monitoring index according to a preset threshold. The judging unit 206 monitors the data outputted from the data processing unit 205 in real time and compares the data with a preset threshold. When the monitoring index exceeds the preset range, the judging unit 206 immediately generates an alarm message. The alarm information can comprise contents such as an exceeding parameter, exceeding time, exceeding degree and the like, so that related personnel can quickly know the situation and take corresponding measures.
The early warning correction module comprises a patient action image acquisition unit 207, a key point extraction unit 208, a convolutional neural network model identification unit 209 and an early warning information correction unit 210, wherein the patient action image acquisition unit 207, the key point extraction unit 208, the convolutional neural network model identification unit 209 and the early warning information correction unit 210 are sequentially connected; the patient action image acquisition unit 207 is used for acquiring patient action image data; the key point extracting unit 208 is configured to extract key points of a human body from an original image by applying a human body posture estimating technique;
The convolutional neural network model identifying unit 209 is used for training a convolutional neural network model by using key points of a human body and identifying a behavior mode of a patient based on the convolutional neural network model; the early warning information correction unit 210 corrects the primary warning information by combining the wearing data and the behavior pattern.
The patient action image acquisition unit 207 may employ a high resolution camera to ensure that detailed information of the patient action is captured. The acquired image data will be used for subsequent processing and analysis. The keypoint extraction unit 208 then applies a human body posture estimation technique to the original image to extract human body keypoints. These key points typically include various joint locations of the human body, such as the shoulders, elbows, wrists, waists, knees, ankles, etc. OpenPose is an open source human body pose estimation tool that can be used to extract human body keypoints from images.
On the basis of the extraction of the key points, the convolutional neural network model identification unit 209 trains the key points of the human body to construct a convolutional neural network model. Training the model by using the marked data set, and then designing a CNN model suitable for time sequence data processing, wherein the CNN model is possibly combined with a cyclic neural network (such as LSTM) to form a deep learning model for capturing the time continuity and the context dependence; manually labeling each frame or each section of video according to the action type of the behavior, converting the video into category labels such as walking, sitting, lifting hands and the like, dividing the whole data set into a training set, a verification set and a test set, wherein the general proportion can be set to 70%, 15% and 15% so as to ensure the effectiveness of model training and the evaluation of generalization performance; training the CNN model by using a training set; after training, evaluating the model performance on the test set, and predicting new data by using the trained CNN model to obtain the classification result of each gesture action.
Finally, the early warning information correction unit 210 corrects the primary warning information by combining the data provided by the wearable device and the result of convolutional neural network model recognition. The method is favorable for improving the early warning accuracy, avoiding false alarm and missing alarm and providing more reliable decision basis for medical staff.
The early warning correction module further comprises a labeling unit 211 and a model correction unit 212, wherein the labeling unit 211 is used for labeling the correctness of the identified behavior mode by the patient; the model correction unit 212 is configured to correct the neural network model based on the labeling data.
The labeling unit 211 is used for ensuring the accuracy of the recognition result, and the patient can label the recognized behavior pattern correctly. This step is critical because accurate labeling can help the model better understand the behavioral characteristics of the patient, thereby improving the accuracy of the identification.
The patient action image acquisition unit 207 comprises an image acquisition subunit 213 and an image processing subunit 214, the image acquisition subunit 213 being adapted to collect a video dataset comprising patient posture actions; the image processing subunit 214 is configured to normalize an image.
The image acquisition subunit 213 is responsible for collecting video data sets containing patient posture actions. To ensure accuracy and integrity of the data, we have employed a high definition camera to capture each motion of the patient. Meanwhile, in order to ensure the real-time performance of the data, a data transmission module is also designed to transmit the video data acquired in real time to the image processing subunit 214. Next, the image processing subunit 214 performs normalization processing on the collected images. The main purpose of the normalization process is to eliminate image noise and illumination effects, thereby improving the sharpness of the image. In addition, the normalization processing is also beneficial to reducing the scale of the image data and improving the efficiency of subsequent image analysis and processing.
The alarm unit 216 comprises a related personnel setting unit 215 and an alarm unit 216, wherein the related personnel setting unit 215 is used for setting related personnel associated with a patient; the alarm unit 216 is configured to notify relevant personnel of alarm information through various channels.
The related person setting unit 215 is responsible for configuring related persons associated with the patient so that they can be promptly notified when an emergency occurs. The design concept of such a setup unit is to ensure that the patient gets timely attention and assistance when encountering problems. The alarm unit 216 is responsible for informing the relevant personnel of the alarm information through various channels in certain situations. These channels include telephone calls, text messages, emails, etc. to ensure that the alert information is communicated to the relevant personnel at a first time. The alarm unit 216 operates on the principle that upon receipt of an alarm signal, an associated notification procedure is automatically triggered, thereby ensuring that the patient and associated personnel are contacted in a minimum amount of time.
The suggestion module 106 includes a monitoring data acquisition unit 217, a disease matching unit 218, a scheme matching unit 219, and a transmission unit 220, where the monitoring data acquisition unit 217 is configured to acquire video monitoring data and wearing data when the behavior pattern is abnormal based on the time stamp; the disease matching unit 218 is configured to match the medical information with the wearable data to obtain a corresponding disease item; the scheme matching unit is used for matching emergency treatment schemes in the database based on disease items; the transmitting unit 220 is configured to transmit the video monitoring data and the emergency treatment plan to a patient-related person.
The monitoring data acquisition unit 217 is responsible for collecting video monitoring data and wearing data when the behavior pattern is abnormal according to the time stamp. So that possible diseases can be matched from these data. Next, the disease matching unit 218 processes the collected wearing data and matches it with medical information, thereby determining a disease item to which the patient suffers. Specifically, each item of numerical value can be compared according to a specific item, and a corresponding disease item can be obtained when one or more items of numerical values are abnormal.
After determining the disease item, the scheme matching unit can search and match the corresponding emergency treatment scheme in the database according to the disease item. Finally, the transmitting unit 220 is responsible for transmitting the video surveillance data and the emergency treatment plan to patient-related personnel, such as family members, medical staff, etc. The method ensures timeliness and accuracy of information transmission, and is beneficial to timely treatment and care of patients. Therefore, the monitoring data and the medical information are fully utilized, and the rapid identification of diseases and the provision of a personalized emergency treatment scheme are realized. The medical service system is not only beneficial to improving the quality and efficiency of medical service, but also hopefully changes the traditional medical service mode, and brings better medical experience for patients.
The above disclosure is only a preferred embodiment of the present invention, and it should be understood that the scope of the invention is not limited thereto, and those skilled in the art will appreciate that all or part of the procedures described above can be performed according to the equivalent changes of the claims, and still fall within the scope of the present invention.
Claims (9)
1. A remote real-time on-line monitoring and managing system for human health information is characterized in that,
Comprises a patient information acquisition module, a wearable data acquisition module, a primary early warning module, an early warning correction module, an alarm module and a suggestion module,
The patient information acquisition module is used for acquiring medical information of a patient;
the wearable data acquisition module is used for being worn on a patient to acquire sign data;
The primary early warning module is used for identifying the abnormal state of the patient based on the sensor data and generating primary warning information;
the early warning correction module corrects the primary warning information by adopting a behavior mode obtained by video data which is acquired by video and corresponds to the wearing data to obtain corrected warning information;
The alarm module is used for sending a notification to relevant personnel of the patient based on the correction alarm information;
The advice module is used for matching an emergency treatment scheme based on the alarm information and sending the emergency treatment scheme to the patient and related persons.
2. The remote real-time on-line monitoring and managing system for human health information according to claim 1, wherein,
The patient information acquisition module comprises an information acquisition unit, an integration unit and an updating unit, wherein the information acquisition unit is used for acquiring all medical record information of a patient in a system, the integration unit is used for integrating all the medical record information to obtain tidying medical record data, and the updating unit is used for periodically updating the tidying medical record data.
3. The remote real-time on-line monitoring and management system for human health information according to claim 2, wherein,
The physical sign data includes heart rate, blood pressure, blood oxygen saturation, body temperature, and respiratory rate.
4. The remote real-time on-line monitoring and managing system for human health information according to claim 3, wherein,
The primary early warning module comprises a sensing data acquisition unit, a data processing unit and a judging unit, wherein the sensing data acquisition unit is used for acquiring sensor data; the data processing unit is used for preprocessing the received data and removing invalid or abnormal values; and the judging unit is used for judging that the monitoring index exceeds a preset range based on the set threshold value and generating primary alarm information.
5. The remote real-time on-line monitoring and managing system for human health information according to claim 4, wherein,
The early warning correction module comprises a patient action image acquisition unit, a key point extraction unit, a convolutional neural network model identification unit and an early warning information correction unit, wherein the patient action image acquisition unit, the key point extraction unit, the convolutional neural network model identification unit and the early warning information correction unit are connected in sequence;
the patient action image acquisition unit is used for acquiring patient action image data;
the key point extraction unit is used for extracting key points of a human body from an original image by applying a human body posture estimation technology;
The convolutional neural network model identification unit is used for training a convolutional neural network model by using key points of a human body and identifying a behavior mode of a patient based on the convolutional neural network model;
The early warning information correction unit corrects primary warning information by combining the wearing data and the behavior mode.
6. The remote real-time on-line monitoring and managing system for human health information according to claim 5, wherein,
The early warning correction module further comprises a labeling unit and a model correction unit, wherein the labeling unit is used for labeling the identified behavior mode correctly by a patient; the model correction unit is used for correcting the neural network model based on the labeling data.
7. The remote real-time on-line monitoring and managing system for human health information according to claim 6, wherein,
The patient action image acquisition unit comprises an image acquisition subunit and an image processing subunit, wherein the image acquisition subunit is used for collecting a video data set containing the posture actions of the patient; the image processing subunit is used for carrying out normalization processing on the image.
8. The remote real-time on-line monitoring and managing system for human health information according to claim 7, wherein,
The alarm unit comprises a related personnel setting unit and an alarm unit, wherein the related personnel setting unit is used for setting related personnel associated with a patient; and the alarm unit is used for informing relevant personnel of the alarm information through various channels.
9. The remote real-time on-line monitoring and managing system for human health information according to claim 8, wherein,
The suggestion module comprises a monitoring data acquisition unit, a disease matching unit, a scheme matching unit and a sending unit, wherein the monitoring data acquisition unit is used for acquiring video monitoring data and wearing data when the behavior mode is abnormal based on a time stamp; the disease matching unit is used for matching the medical information based on the wearing data to obtain corresponding disease items; the scheme matching unit is used for matching emergency treatment schemes in the database based on disease items; the sending unit is used for sending the video monitoring data and the emergency processing scheme to relevant personnel of the patient.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410084336.4A CN117936073A (en) | 2024-01-19 | 2024-01-19 | Remote real-time on-line monitoring management system for human health information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410084336.4A CN117936073A (en) | 2024-01-19 | 2024-01-19 | Remote real-time on-line monitoring management system for human health information |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117936073A true CN117936073A (en) | 2024-04-26 |
Family
ID=90769774
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410084336.4A Pending CN117936073A (en) | 2024-01-19 | 2024-01-19 | Remote real-time on-line monitoring management system for human health information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117936073A (en) |
-
2024
- 2024-01-19 CN CN202410084336.4A patent/CN117936073A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108717678B (en) | Wisdom endowment system | |
| Ali et al. | Real-time heart pulse monitoring technique using wireless sensor network and mobile application | |
| AU2006325153B2 (en) | Residual-based monitoring of human health | |
| CN108899084A (en) | A kind of wisdom endowment health monitoring system | |
| CN105411554A (en) | Wireless non-invasive human physiological parameter collection, detection and intelligent diagnosis system | |
| JP4189298B2 (en) | Infant movement analysis system | |
| CN115769302A (en) | Epidemic disease monitoring system | |
| KR20130118512A (en) | System and method for monitoring the health of a patient using face recognition technology | |
| CN116649940B (en) | Remote monitoring system and method for wearable equipment | |
| CN114883006A (en) | Health monitoring and dynamic management system based on big data and application | |
| US20230298760A1 (en) | Systems, devices, and methods for determining movement variability, illness and injury prediction and recovery readiness | |
| KR20200056674A (en) | Integrated system, server and method for managing chronic disease of pet | |
| Aditya et al. | Real time patient activity monitoring and alert system | |
| CN116098595B (en) | System and method for monitoring and preventing sudden cardiac death and sudden cerebral death | |
| US20240032820A1 (en) | System and method for self-learning and reference tuning activity monitor | |
| CN116825337A (en) | Patient safety nursing early warning system | |
| CN117936073A (en) | Remote real-time on-line monitoring management system for human health information | |
| JP2014092945A (en) | Physical condition determination system and physical condition determination method | |
| US20160228067A1 (en) | System and method for intelligent monitoring of patient vital signs | |
| Tan et al. | Remote patient monitoring system | |
| Qomariyah et al. | IoT-based COVID-19 Patient Vital Sign Monitoring | |
| Seethalakshmi et al. | A Review on Wearable Epileptic Seizure Prediction System | |
| Rammo et al. | Comatose patient monitoring system based on (IoT) | |
| JP6903368B1 (en) | Swallowing evaluation device, swallowing evaluation system, swallowing evaluation method and swallowing evaluation program | |
| KR20230026604A (en) | Method and apparatus for calibrating real time physiological signal acquisition device and smart nursing system using the same |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination |