Wearable chest positive airway pressure dynamic monitoring system for heart failure patients and method thereof

Abstract

The present application relates to the field of medical monitoring equipment, in particular to a wearable chest impedance positive dynamic monitoring system for heart failure patients and a method thereof, comprising a chest impedance signal detection, signal processing, analog-digital conversion, a processor, a wireless communication module, a mobile client and a cloud platform, the chest impedance signal is converted into a digital signal after amplification, noise reduction and filtering, the processor extracts the respiratory waveform parameters, calculates the chest impedance ratio (the product of the peak-to-valley amplitude and the dynamic adjustment coefficient K1 of the tidal volume ratio, K1 increases with the extension of the inspiratory and expiratory time interval), and performs multi-level classification and early warning decision, the early warning information is transmitted to the mobile client through the wireless communication module, the data is uploaded to the cloud platform for deep analysis, personalized monitoring parameters are generated and feedback is provided, the chest impedance ratio parameter and its calculation method, combined with the dynamic adjustment coefficient K1, accurately reflect the lung fluid state, realize the super-early warning of heart failure, and have important significance for the health monitoring of heart failure patients.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of medical monitoring equipment, in particular to a wearable thoracic positive end-expiratory pressure dynamic monitoring system for heart failure patients and a method thereof, which is used for real-time monitoring of thoracic positive end-expiratory pressure changes of heart failure patients, early warning of pulmonary effusion conditions, and improvement of the quality of life and survival rate of heart failure patients. BACKGROUND

[0002] Heart failure is a common end-stage manifestation of cardiovascular disease. Heart failure patients often have pulmonary effusion, which causes symptoms such as dyspnea and decreased exercise tolerance, and seriously affects the quality of life. Early detection and timely intervention of pulmonary effusion are crucial for reducing the readmission rate and mortality of heart failure patients.

[0003] Currently, the monitoring methods for heart failure patients mainly include traditional methods such as regular hospital follow-up, weight monitoring, and symptom assessment, as well as remote monitoring methods such as remote electrocardiogram monitoring and weight monitoring developed in recent years. However, these methods have obvious shortcomings: on the one hand, the traditional follow-up interval is long, making it difficult to detect changes in the patient's condition in a timely manner; on the other hand, existing remote monitoring technologies mainly focus on parameters such as electrocardiogram and blood pressure, and lack monitoring of thoracic positive end-expiratory pressure changes that reflect pulmonary effusion, making it difficult to achieve early warning of pulmonary effusion in heart failure patients.

[0004] In addition, existing monitoring equipment is usually large in size and inconvenient to wear, making it difficult to achieve long-term continuous monitoring and resulting in poor user compliance. At the same time, existing monitoring systems mostly use fixed threshold warning mechanisms and do not consider individual differences among patients, resulting in a high false positive rate and insufficient warning accuracy.

[0005] Therefore, there is an urgent need for a monitoring system that can real-time and accurately monitor thoracic positive end-expiratory pressure changes in heart failure patients, early warn of pulmonary effusion conditions, and have good wearability and user compliance. SUMMARY

[0006] The purpose of the present application is to provide a wearable thoracic positive end-expiratory pressure dynamic monitoring system for heart failure patients and a method thereof, to solve the technical problems of insufficient monitoring of pulmonary effusion in heart failure patients, untimely warning, and low individualization in the prior art.

[0007] The present application provides a wearable thoracic positive end-expiratory pressure dynamic monitoring system for heart failure patients, which comprises:

[0008] a thoracic positive end-expiratory pressure signal detection module for collecting thoracic positive end-expiratory pressure signals of heart failure patients;

[0009] a signal processing module connected to the thoracic positive end-expiratory pressure signal detection module, for amplifying, noise-reducing, and filtering the thoracic positive end-expiratory pressure signals to generate processed thoracic positive end-expiratory pressure signals;

[0010] an analog-to-digital conversion module, connected to the signal processing module, for converting the processed intrathoracic positive end-expiratory pressure signal into a digital intrathoracic positive end-expiratory pressure signal;

[0011] a processor module, connected to the analog-to-digital conversion module, for extracting a respiratory waveform parameter based on the digital intrathoracic positive end-expiratory pressure signal, calculating a thoracic-antibody ratio, the thoracic-antibody ratio being a ratio of a peak-to-trough amplitude to a tidal volume multiplied by a dynamic adjustment coefficient K1, wherein the dynamic adjustment coefficient K1 increases as a time interval between an end of inspiration and an end of expiration increases, and performing a multi-level classification according to the calculated thoracic-antibody ratio to execute a pre-warning decision;

[0012] a wireless communication module, connected to the processor module, for transmitting the thoracic-antibody ratio and pre-warning information to a remote terminal;

[0013] a mobile client, communicatively connected to the wireless communication module, for receiving the thoracic-antibody ratio and pre-warning information, displaying a pre-warning state, and transmitting monitoring data to a cloud platform;

[0014] a cloud platform, communicatively connected to the mobile client, for storing historical monitoring data of a heart failure patient, performing a deep analysis according to the monitoring data, generating individualized monitoring parameters, and feeding back the individualized monitoring parameters to the mobile client.

[0015] Preferably, the intrathoracic positive end-expiratory pressure signal detection module is a dry electrode module, and a detection position of the dry electrode module is located at an intersection of a left anterior axillary line and an nth rib, where n ∈ [1, 6].

[0016] Preferably, the respiratory waveform parameter includes:

[0017] a signal peak, defined as a time point at an end of inspiration;

[0018] a signal trough, defined as a time point at an end of expiration;

[0019] a peak-to-trough amplitude, as an amplitude between a peak and a trough;

[0020] an amplitude between an end of inspiration and an end of expiration, as a tidal volume;

[0021] a sum of amplitudes between adjacent peaks and troughs, as an end-of-expiration-to-end-of-inspiration parameter.

[0022] Preferably, the multi-level classification of the thoracic-antibody ratio includes:

[0023] a thoracic-antibody ratio 1, with a judgment rule of thoracic-antibody ratio ≤ 2%;

[0024] a thoracic-antibody ratio 2, with a judgment rule of 2% < thoracic-antibody ratio ≤ 4%;

[0025] The thoracic impedance ratio 3 has a judgment rule that 4% < the thoracic impedance ratio ≤ 8%;

[0026] The thoracic impedance ratio 4 has a judgment rule that 8% < the thoracic impedance ratio ≤ 25%;

[0027] The thoracic impedance ratio 5 has a judgment rule that the thoracic impedance ratio > 25%.

[0028] Preferably, the processor module performs a hierarchical progressive early warning decision according to the multi-level classification of the thoracic impedance ratio, and specifically includes:

[0029] When the thoracic impedance ratio meets the thoracic impedance ratio 1, no alarm is given;

[0030] When the thoracic impedance ratio meets the thoracic impedance ratio 2, a mild early warning is performed, and a reminder mark and prompt information are displayed;

[0031] When the thoracic impedance ratio meets the thoracic impedance ratio 3, a primary early warning is performed, and a warning mark and prompt information are displayed;

[0032] When the thoracic impedance ratio meets the thoracic impedance ratio 4, a middle-level early warning is performed, and a serious alarm mark and alarm information are displayed;

[0033] When the thoracic impedance ratio meets the thoracic impedance ratio 5, a high-level early warning is performed, and an emergency alarm mark and alarm information are displayed.

[0034] Preferably, the cloud platform further includes:

[0035] A patient registration module for registering a heart failure patient and obtaining physiological characteristic data of the patient;

[0036] A data analysis module for generating individualized monitoring parameters based on the physiological characteristic data and historical monitoring data;

[0037] A prescription generation module for generating prescription information based on the monitoring data and the physiological characteristic data;

[0038] A physician interface module for receiving a physician's modification feedback on the prescription information and updating the individualized monitoring parameters according to the modification feedback.

[0039] Preferably, the physiological characteristic data includes the patient's age, height, weight, and gender.

[0040] Preferably, it further includes a vibration module connected to the processor module for providing a tactile early warning feedback when the thoracic impedance ratio exceeds a preset threshold.

[0041] As preferred, a positioning module is further included, connected with the processor module, for acquiring position information of the heart failure patient, and transmitting the position information to the cloud platform through the wireless communication module, so as to provide position information in an emergency.

[0042] The wearable thoracic paradoxus dynamic monitoring method for heart failure patients comprises:

[0043] A thoracic paradoxus signal of the heart failure patient is collected through a thoracic paradoxus signal detection module;

[0044] The thoracic paradoxus signal is amplified, denoised and filtered through a signal processing module to generate a processed thoracic paradoxus signal;

[0045] The processed thoracic paradoxus signal is converted into a digital thoracic paradoxus signal through an analog-digital conversion module;

[0046] Respiratory waveform parameters are extracted based on the digital thoracic paradoxus signal through a processor module, and a thoracic paradoxus ratio is calculated, the thoracic paradoxus ratio being a ratio of an amplitude between a peak and a valley to a tidal volume multiplied by a dynamic adjustment coefficient K1, wherein the dynamic adjustment coefficient K1 increases as a time interval between an end of inspiration and an end of expiration prolongs;

[0047] Multi-level classification is performed according to the calculated thoracic paradoxus ratio through the processor module, and a pre-warning decision is executed;

[0048] The thoracic paradoxus ratio and pre-warning information are transmitted to a mobile client through a wireless communication module;

[0049] The pre-warning state is displayed through the mobile client, and monitoring data is transmitted to a cloud platform;

[0050] Historical monitoring data of the heart failure patient are stored through the cloud platform, deep analysis is performed according to the monitoring data, individualized monitoring parameters are generated, and the individualized monitoring parameters are fed back to the mobile client.

[0051] The present application has the following beneficial effects:

[0052] 1. The thoracic paradoxus ratio parameter and its calculation method are innovatively proposed, combined with the dynamic adjustment coefficient K1, which can accurately reflect the lung fluid accumulation state of the heart failure patient, and realize super-early warning.

[0053] 2. The wearable dry electrode design is adopted, which is comfortable to wear, convenient for long-term continuous monitoring, and greatly improves patient compliance.

[0054] 3. The five-level classification system and the hierarchical progressive pre-warning decision mechanism based on the thoracic paradoxus ratio are adopted, which implements differentiated pre-warning strategies for different degrees of abnormalities, and effectively reduces the false positive rate.

[0055] 4. Through the three-layer collaborative architecture of edge device, mobile client and cloud platform, the complete closed loop from monitoring to intervention is realized, and the heart failure management efficiency is improved.

[0056] 5. Combined with physiological characteristic data of patients, individualized parameter optimization is carried out, so that the monitoring is more accurate and the early warning is more timely. BRIEF DESCRIPTION OF DRAWINGS

[0057] Figure 1 It is a whole architecture schematic diagram of the wearable thoracic positive inotropic dynamic monitoring system for heart failure patients of the application.

[0058] Figure 2 It is a structure schematic diagram of the thoracic positive inotropic signal detection module of the application.

[0059] Figure 3 It is a schematic diagram of the dry electrode arrangement position of the application.

[0060] Figure 4 It is a thoracic inotropic ratio calculation process schematic diagram of the application.

[0061] Figure 5 It is a hierarchical progressive early warning decision flowchart of the application.

[0062] Figure 6 It is a cloud platform function module schematic diagram of the application.

[0063] Figure 7 It is a wearable thoracic positive inotropic dynamic monitoring method flowchart for heart failure patients of the application. DETAILED DESCRIPTION

[0064] Please refer to the accompanying Figures 1-7 , the specific embodiments of the application will be described in detail below in conjunction with the drawings. It should be noted that the following embodiments are only used to illustrate the application, and are not used to limit the scope of the application.

[0065] As shown in Figure 1 , the application provides a wearable thoracic positive inotropic dynamic monitoring system for heart failure patients, which comprises a thoracic positive inotropic signal detection module 10, a signal processing module 20, an analog-to-digital conversion module 30, a processor module 40, a wireless communication module 50, a mobile client 60 and a cloud platform 70.

[0066] The thoracic positive inotropic signal detection module 10 is used for collecting the thoracic positive inotropic signal of the heart failure patient. Preferably, as Figure 2As shown, the chest positive end-expiratory pressure signal detection module 10 is a dry electrode module, including an electrode 11, an electrode seat 12 and a dry electrode seat 13, wherein the electrode 11 and the electrode seat 12 are integrated and fixed on the dry electrode seat 13. In an embodiment of the present application, the detection position of the dry electrode module is located at the intersection of the left anterior axillary line and the nth rib, where n ∈ [1, 6], as shown. Figure 3 The selection of this specific position is based on the anatomical characteristics of the human body, which can obtain the most accurate chest positive end-expiratory pressure signal.

[0067] Practice shows that when the dry electrode is placed at the intersection of the left anterior axillary line and the fourth rib, the quality of the chest positive end-expiratory pressure signal acquisition is optimal, the signal-to-noise ratio can reach more than 35 dB, and the changes in the chest positive end-expiratory pressure caused by breathing and lung effusion can be clearly captured.

[0068] The signal processing module 20 is connected with the chest positive end-expiratory pressure signal detection module 10, and is used for amplifying, denoising and filtering the chest positive end-expiratory pressure signal to generate a processed chest positive end-expiratory pressure signal. Specifically, the signal processing module 20 first pre-amplifies the original chest positive end-expiratory pressure signal, and the gain coefficient is usually set to 100-200 times; then the signal is filtered through a band-pass filter, and the filter band is set to 0.05 Hz-2 Hz to retain the signal components related to breathing; finally, the adaptive noise reduction algorithm is used to eliminate environmental interference and body motion artifacts, and the signal quality is improved.

[0069] The analog-to-digital conversion module 30 is connected with the signal processing module 20, and is used for converting the processed chest positive end-expiratory pressure signal into a digital chest positive end-expiratory pressure signal. In this embodiment, the analog-to-digital conversion module 30 uses a 16-bit AD converter, and the sampling rate is set to 100 Hz, which can accurately capture the slight changes within the breathing cycle.

[0070] The processor module 40 is connected with the analog-to-digital conversion module 30, and is used for extracting the breathing waveform parameters based on the digital chest positive end-expiratory pressure signal and calculating the chest pressure ratio. In a preferred embodiment of the present application, the processor module 40 uses an STM32 low-power microcontroller, and the operating frequency is set to 72 MHz to ensure real-time processing performance while minimizing power consumption.

[0071] The breathing waveform parameters extracted by the processor module 40 include:

[0072] 1. Signal peak, defined as the time point at the end of inspiration;

[0073] 2. Signal trough, defined as the time point at the end of expiration;

[0074] 3. The amplitude from the peak to the trough, as the amplitude between the peak and the trough;

[0075] 4. The amplitude between the end of inspiration and the end of expiration, as the tidal volume;

[0076] 5. The sum of the amplitudes between adjacent peaks and troughs as an end-tidal-inspiratory parameter.

[0077] In addition, the processor module 40 is also used to calculate the thoracic impedance ratio, which is the ratio of the peak-to-trough amplitude to the tidal volume multiplied by a dynamic adjustment coefficient K1, where the dynamic adjustment coefficient K1 increases as the time interval between the end of inspiration and the end of expiration increases. The calculation process is as shown in Figure 4 The specific calculation formula is:

[0078]

[0079] Where: CR is the thoracic impedance ratio, in percent (%); A pv is the peak-to-trough amplitude, in ohms (Ω); V t is the tidal volume, in milliliters (mL) or liters (L); K1(T) is the dynamic adjustment coefficient, which is a function of the time interval T, dimensionless; T is the time interval between the end of inspiration and the end of expiration, in seconds (s). The calculation formula for the dynamic adjustment coefficient K1 is:

[0080] K1(T) = 1 + α × (T - T ref ).

[0081] Where: α is the proportional coefficient, which is clinically verified to be set to 0.5 s -1 ; T ref is the reference time interval, which is usually set to 2 s, corresponding to the breathing period of a normal person at rest; when T < T ref , take K1(T) = 1.

[0082] The theoretical basis of this dynamic adjustment coefficient design is that when the pulmonary effusion of heart failure patients worsens, breathing becomes slow and laborious, and the breathing period is prolonged. By introducing a dynamic adjustment coefficient that increases as the breathing period increases, the sensitivity of the system to small changes can be improved, enabling ultra-early warning. Clinical studies have shown that this mechanism can advance the warning time by 12-24 hours, gaining valuable time for clinical intervention.

[0083] The processor module 40 performs multi-level classification based on the calculated thoracic impedance ratio and executes the warning decision. The multi-level classification of the thoracic impedance ratio includes:

[0084] 1. Thoracic impedance ratio 1, whose judgment rule is: thoracic impedance ratio ≤ 2%;

[0085] 2. Thoracic impedance ratio 2, whose judgment rule is: 2% < thoracic impedance ratio ≤ 4%;

[0086] 3. Thoracic impedance ratio 3, whose judgment rule is: 4% < thoracic impedance ratio ≤ 8%;

[0087] 4. Thoracic impedance ratio 4, whose judgment rule is: 8% < thoracic impedance ratio ≤ 25%;

[0088] 5. Thoracic impedance ratio 5, whose judgment rule is: thoracic impedance ratio > 25%.

[0089] This grading system is based on the clinical research data of 500 heart failure patients, which accurately maps the physiological and pathological mechanisms with the thoracic impedance ratio parameter, so that the monitoring system has the "disease progression stage awareness ability". The non-linear threshold distribution set between each level matches the non-linear effect of pulmonary edema on respiratory function.

[0090] The processor module 40 performs hierarchical progressive early warning decisions according to the multi-level classification of the thoracic impedance ratio, as shown in the following table: Figure 5 Specifically, it includes:

[0091] 1. When the thoracic impedance ratio meets thoracic impedance ratio 1, no alarm is given;

[0092] 2. When the thoracic impedance ratio meets thoracic impedance ratio 2, a mild early warning is given, and a reminder symbol and prompt information are displayed;

[0093] 3. When the thoracic impedance ratio meets thoracic impedance ratio 3, a primary early warning is given, and a warning symbol and prompt information are displayed;

[0094] 4. When the thoracic impedance ratio meets thoracic impedance ratio 4, a middle-level early warning is given, and a serious alarm symbol and alarm information are displayed;

[0095] 5. When the thoracic impedance ratio meets thoracic impedance ratio 5, a high-level early warning is given, and an emergency alarm symbol and alarm information are displayed.

[0096] The wireless communication module 50 is connected with the processor module 40, and is used for transmitting the thoracic impedance ratio and the early warning information to the mobile client 60. In the preferred embodiment of the present application, the wireless communication module 50 adopts the Bluetooth Low Energy (BLE) technology, the maximum transmission distance can reach 10 meters, the transmission rate is 1 Mbps, the continuous working power consumption is not more than 10 mW, and the demand of long-term wearing monitoring can be met.

[0097] The mobile client 60 is in communication connection with the wireless communication module 50, and is used for receiving the thoracic impedance ratio and the early warning information, displaying the early warning state, and transmitting the monitoring data to the cloud platform 70. Preferably, the mobile client 60 can be a portable device such as a smart phone or a smart watch, and the data display and interaction functions are realized through a special application program.

[0098] The cloud platform 70 is in communication connection with the mobile client 60, and is used for storing the historical monitoring data of the heart failure patient, performing deep analysis according to the monitoring data, generating personalized monitoring parameters, and feeding back the personalized monitoring parameters to the mobile client 60. As shown in the following table: Figure 6As shown, the cloud platform 70 further comprises a patient registration module 71, a data analysis module 72, a prescription generation module 73 and a physician interface module 74.

[0099] The patient registration module 71 is used to register heart failure patients and obtain physiological characteristic data of the patients. The data analysis module 72 is used to generate individualized monitoring parameters based on the physiological characteristic data and historical monitoring data. The prescription generation module 73 is used to generate prescription information based on the monitoring data and the physiological characteristic data. The physician interface module 74 is used to receive modification feedback of the prescription information by physicians and update the individualized monitoring parameters according to the modification feedback.

[0100] In a preferred embodiment of the present application, the physiological characteristic data comprises age, height, weight and gender of the patient. These data are crucial for accurately assessing the baseline lung function and chest positive end-expiratory pressure value of the patient. For example, patients over 70 years old usually have a baseline chest pressure ratio 1-2 percentage points higher than young patients even without pulmonary effusion; patients with a body mass index (BMI) over 30 usually have a chest positive end-expiratory pressure signal amplitude 15-20% lower than patients with normal weight. By considering these factors, the system can provide more personalized monitoring and early warning services.

[0101] In addition, the system of the present application further comprises a vibration module 80 connected with the processor module 40, which is used to provide tactile early warning feedback when the chest pressure ratio exceeds a preset threshold. The vibration module 80 adopts an eccentric motor design, and the vibration intensity is adjustable, with a maximum vibration intensity of 2.5G, which can provide effective prompts in noisy environments or when the patient has visual impairment.

[0102] The system of the present application further comprises a positioning module 90 connected with the processor module 40, which is used to obtain the location information of the heart failure patient and transmit the location information to the cloud platform 70 through the wireless communication module 50, so as to provide location information in emergency. The positioning module 90 integrates GPS and base station positioning dual positioning technology, with an outdoor positioning accuracy of 5-10 meters and an indoor positioning accuracy of 50-100 meters, meeting the needs of emergency rescue.

[0103] The present application also provides a wearable chest positive end-expiratory pressure dynamic monitoring method for heart failure patients, which comprises the following steps: Figure 7 As shown, the method comprises the following steps:

[0104] Step S1, acquiring the chest positive end-expiratory pressure signal of the heart failure patient through a chest positive end-expiratory pressure signal detection module;

[0105] Step S2, amplifying, denoising and filtering the chest positive end-expiratory pressure signal through a signal processing module to generate a processed chest positive end-expiratory pressure signal;

[0106] Step S3, converting the processed thoracic positive signal into a digital thoracic positive signal through an analog-digital conversion module;

[0107] Step S4, extracting a respiratory waveform parameter based on the digital thoracic positive signal through a processor module, calculating a thoracic positive ratio, which is the ratio of the peak-to-trough amplitude to the tidal volume multiplied by a dynamic adjustment coefficient K1, wherein the dynamic adjustment coefficient K1 increases as the time interval between the end of inspiration and the end of expiration increases;

[0108] Step S5, performing multi-level classification according to the calculated thoracic positive ratio through the processor module, and executing a warning decision;

[0109] Step S6, transmitting the thoracic positive ratio and warning information to a mobile client through a wireless communication module;

[0110] Step S7, displaying the warning state through the mobile client and transmitting monitoring data to a cloud platform;

[0111] Step S8, storing historical monitoring data of heart failure patients through the cloud platform, performing in-depth analysis according to the monitoring data, generating personalized monitoring parameters, and feeding back the personalized monitoring parameters to the mobile client.

[0112] In step S4, the extraction of the respiratory waveform parameter adopts a peak detection and local extremum algorithm. Specifically, first, the digital thoracic positive signal is window filtered with a window length of 16 points to remove high-frequency noise; then, the local maximum and minimum points of the signal are detected to determine the wave peak (end of inspiration time point) and wave trough (end of expiration time point), respectively. To improve detection accuracy, the system also sets constraints such as minimum peak interval (usually 2 seconds) and minimum peak-to-trough amplitude (usually 10% of the signal amplitude), effectively avoiding false peak detection problems.

[0113] The calculation formula of the thoracic positive ratio is the same as that of embodiment 1, but the calculation method of the dynamic adjustment coefficient K1 is further optimized in this embodiment, and an adaptive baseline correction mechanism is introduced:

[0114] K1(T=1+α×(T-T base ),

[0115] Wherein, α is still a proportional coefficient, set to 0.5s -1 ; T base is an adaptive baseline time interval, which is obtained through statistical analysis of the patient's respiratory data in the last 30 minutes, and the calculation formula is:

[0116]

[0117] Wherein: T iis the time interval between the end of inspiration and the end of expiration for the i th respiratory cycle; N is the number of respiratory cycles in the statistical window, usually taking a value of 10-20; β is a correction coefficient, usually set to 0.9-1.1, which can be dynamically adjusted according to individual differences of patients.

[0118] This adaptive baseline correction mechanism can adapt to the respiratory changes of patients in different activity states, further improving the sensitivity and specificity of monitoring. Clinical verification shows that compared with fixed reference values, this mechanism can reduce the false positive rate by about 30% while maintaining a high detection rate.

[0119] In step S5, in addition to the multi-level classification based on the chest-antibody ratio, the change trend and duration of the chest-antibody ratio are also considered in the execution of the early warning decision. For example, when the chest-antibody ratio is detected to continuously rise from chest-antibody ratio 1 to chest-antibody ratio 3, and the rising rate exceeds 0.5% / hour, the system will trigger a primary early warning in advance; when the chest-antibody ratio maintains at chest-antibody ratio 4 for more than 6 hours, the system will automatically upgrade to a high-level early warning. This comprehensive early warning mechanism can more timely reflect the changes in the patient's condition, providing a basis for early intervention.

[0120] In step S8, the deep analysis of the cloud platform uses multi-parameter fusion technology to correlate the chest-antibody ratio monitoring data with the patient's past medical history, medication, weather changes, and other multi-dimensional data for correlation analysis, establishing a personalized early warning model. Based on the gradient boosting decision tree algorithm, this model can automatically identify the key factors affecting the patient's chest-antibody ratio changes, and optimize the monitoring parameters and early warning thresholds accordingly. For example, for patients with a history of coronary heart disease, the system will appropriately lower the threshold of chest-antibody ratio 3 (from the standard 8% to 7%) to improve the early warning sensitivity; for patients receiving diuretic therapy, the system will extend the time window for early warning escalation to avoid excessive intervention.

[0121] In this embodiment, the workflow and clinical application scenarios of the system of the present application are further described.

[0122] First, the heart failure patient registers through the patient registration module of the cloud platform, providing basic physiological characteristic data such as age, height, weight, and gender. The system initializes the monitoring parameters based on these data, including the chest-antibody ratio grading threshold, dynamic adjustment coefficient parameters, etc.

[0123] The patient wears a chest-antibody monitoring device, which is usually fixed on the inside of clothing, with dry electrodes in direct contact with the skin at the intersection of the left anterior axillary line and the 4th rib. After the device is turned on, it first performs a baseline measurement of 2-5 minutes to determine the patient's basic chest-antibody state, and then begins continuous monitoring.

[0124] During routine monitoring, the system calculates the thoracic impedance ratio every 10 minutes and compares it with a pre-set threshold. If the thoracic impedance ratio exceeds the threshold for 3 consecutive calculations, the system starts the early warning process. The specific early warning strategies are as follows:

[0125] Thoracic impedance ratio 2 (2% < thoracic impedance ratio ≤ 4%): The mobile client displays a reminder message, suggesting that the patient take appropriate rest and reduce salt intake.

[0126] Thoracic impedance ratio 3 (4% < thoracic impedance ratio ≤ 8%): The mobile client issues an audible reminder and pushes health recommendations to the patient, such as increasing the dose of diuretics (if authorized by the doctor), strictly limiting fluid intake, etc.

[0127] Thoracic impedance ratio 4 (8% < thoracic impedance ratio ≤ 25%): The mobile client issues a strong sound alarm and provides tactile feedback through the vibration module. The system automatically sends an alarm SMS to the pre-set contacts (such as family members or community medical personnel).

[0128] Thoracic impedance ratio 5 (thoracic impedance ratio > 25%): The system triggers the highest level of alarm. In addition to sending an alarm to the pre-set contacts, it also automatically sends the patient's location information to the medical rescue center and pushes the warning information to the supervising physician through the physician interface module.

[0129] At the same time, all monitoring data are uploaded to the cloud platform in real time for storage and analysis. The cloud platform continuously optimizes monitoring parameters and early warning strategies by analyzing the patient's historical data and current state. For example, if it is found that a certain patient's thoracic impedance ratio is always slightly higher than the baseline at a certain time period (such as early morning), the system will automatically adjust the early warning threshold for that time period to avoid false positive alarms.

[0130] In addition, through the physician interface module, doctors can view the patient's monitoring data and warning records and adjust the treatment plan accordingly. The adjusted plan is formed into prescription information through the prescription generation module and pushed to the patient's mobile client to guide the patient's self-management.

[0131] Clinical studies have shown that the use of the system for heart failure management can reduce the readmission rate of patients by about 40%, and the number of emergency visits by about 50%, significantly improving the quality of life and prognosis of heart failure patients.

[0132] The above-described embodiments are only used to illustrate the present application, and are not intended to limit the present application. Those skilled in the art can make various changes and modifications without departing from the spirit and scope of the present application. Therefore, all equivalent technical solutions belong to the scope of the present application, and the patent protection scope of the present application should be defined by the claims.

Claims

1. A wearable thoracic positive inotropic dynamic monitoring system for heart failure patients, characterized in that, The application relates to a heart failure monitoring system, comprising: a chest positive signal detection module for collecting a chest positive signal of a heart failure patient; a signal processing module connected with the chest positive signal detection module, for amplifying, denoising and filtering the chest positive signal to generate a processed chest positive signal; an analog-digital conversion module connected with the signal processing module, for converting the processed chest positive signal into a digital chest positive signal; a processor module connected with the analog-digital conversion module, for extracting a respiratory waveform parameter based on the digital chest positive signal, and calculating a chest-antibody ratio, wherein the chest-antibody ratio is the ratio of the peak-to-valley amplitude to the tidal volume multiplied by a dynamic adjustment coefficient K1, wherein the dynamic adjustment coefficient K1 increases with the extension of the time interval between the end of inspiration and the end of expiration; the specific calculation formula of the chest-antibody ratio is: ， wherein: is a chest impedance ratio, in percent (%); is a peak-to-trough amplitude, in ohms (Ω); is a tidal volume, in milliliters (mL) or liters (L); is a dynamic adjustment coefficient, dimensionless, as a function of a time interval ; is a time interval between end-inspiration and end-expiration, in seconds (s), the processor module is further configured to perform a multi-stage classification according to the calculated chest impedance ratio, and execute an early warning decision. a wireless communication module connected with the processor module, for transmitting the chest-antibody ratio and early warning information to a remote terminal; a mobile client in communication connection with the wireless communication module, for receiving the chest-antibody ratio and early warning information, displaying the early warning state, and transmitting monitoring data to a cloud platform; a cloud platform in communication connection with the mobile client, for storing historical monitoring data of the heart failure patient, performing deep analysis on the monitoring data, generating individualized monitoring parameters, and feeding back the individualized monitoring parameters to the mobile client.

2. The wearable, thoracic, positive anti-dynamic monitoring system for heart failure patients of claim 1, wherein, The chest positive signal detection module is a dry electrode module, and the detection position of the dry electrode module is located at the intersection of the left anterior axillary line and the nth rib, wherein n [1, 6].

3. The wearable, chest-facing, positive thoracic impedance monitoring system for heart failure patients of claim 1, wherein, The respiratory waveform parameter comprises: a signal peak defined as the time point of the end of inspiration; a signal valley defined as the time point of the end of expiration; a peak-to-valley amplitude as the amplitude between the peak and the valley; an amplitude between the end of inspiration and the end of expiration as the tidal volume; the sum of the amplitudes between adjacent peaks and valleys as the end-of-expiration-to-end-of-inspiration parameter.

4. The wearable, chest-facing, positive thoracic impedance monitoring system for heart failure patients of claim 1, wherein, The multi-level classification of the chest-antibody ratio comprises: a chest-antibody ratio 1 with a judgment rule that the chest-antibody ratio is less than or equal to 2%; a chest-antibody ratio 2 with a judgment rule that 2% < the chest-antibody ratio < 4%; a chest-antibody ratio 3 with a judgment rule that 4% < the chest-antibody ratio < 8%; a chest-antibody ratio 4 with a judgment rule that 8% < the chest-antibody ratio < 25%; a chest-antibody ratio 5 with a judgment rule that the chest-antibody ratio > 25%.

5. The wearable, thoracic, positive anti-dynamic monitoring system for heart failure patients of claim 1, wherein, The processor module performs hierarchical progressive early warning decisions according to the multi-level classification of the chest-antibody ratio, and specifically comprises: when the chest-antibody ratio meets the chest-antibody ratio 1, no alarm is given; when the chest-antibody ratio meets the chest-antibody ratio 2, a mild early warning is given, and a reminder mark and prompt information are displayed; when the chest-antibody ratio meets the chest-antibody ratio 3, a primary early warning is given, and a warning mark and prompt information are displayed; when the chest-antibody ratio meets the chest-antibody ratio 4, a middle-level early warning is given, and a serious alarm mark and alarm information are displayed; when the chest-antibody ratio meets the chest-antibody ratio 5, a high-level early warning is given, and an emergency alarm mark and alarm information are displayed.

6. The wearable, chest-facing, positive thoracic dynamic monitoring system for heart failure patients of claim 1, wherein, The cloud platform further comprises: a patient registration module for registering the heart failure patient, and acquiring physiological characteristic data of the patient; a data analysis module configured to generate individualized monitoring parameters based on the physiological characteristic data and historical monitoring data; a prescription generation module configured to generate prescription information based on the monitoring data and the physiological characteristic data; a physician interface module configured to receive physician modification feedback on the prescription information and update the individualized monitoring parameters according to the modification feedback.

7. The wearable, chest-facing, positive thoracic dynamic monitoring system for heart failure patients of claim 6, wherein, The physiological characteristic data includes age, height, weight, and gender of the patient.

8. The wearable, chest-facing, positive thoracic dynamic monitoring system for heart failure patients of claim 1, wherein, The device further comprises a vibration module connected to the processor module, configured to provide a tactile early warning feedback when the chest compliance ratio exceeds a preset threshold.

9. The wearable, chest-facing, positive thoracic dynamic monitoring system for heart failure patients of claim 1, wherein, The device further comprises a positioning module connected to the processor module, configured to obtain location information of the heart failure patient and transmit the location information to the cloud platform through the wireless communication module, so as to provide location information in an emergency.

10. Wearable thoracic positive inotropic dynamic monitoring method for heart failure patients, using the system according to any one of claims 1 to 9, characterized in that, The device comprises: a chest positive inotropic signal detection module configured to collect a chest positive inotropic signal of the heart failure patient; a signal processing module configured to amplify, denoise, and filter the chest positive inotropic signal to generate a processed chest positive inotropic signal; an analog-to-digital conversion module configured to convert the processed chest positive inotropic signal into a digital chest positive inotropic signal; a processor module configured to extract a respiratory waveform parameter based on the digital chest positive inotropic signal, calculate a chest compliance ratio, and multiply the ratio of peak-to-valley amplitude to tidal volume by a dynamic adjustment coefficient K1, wherein the dynamic adjustment coefficient K1 increases as the time interval between the end of inspiration and the end of expiration increases; the processor module is configured to perform multi-level classification according to the calculated chest compliance ratio and execute early warning decision-making; a wireless communication module configured to transmit the chest compliance ratio and early warning information to a mobile client; the mobile client is configured to display early warning status and transmit monitoring data to a cloud platform; the cloud platform is configured to store historical monitoring data of the heart failure patient, perform deep analysis according to the monitoring data, generate individualized monitoring parameters, and feed back the individualized monitoring parameters to the mobile client.

Images