Respiratory nephropathy department patient sleep nursing system and method based on intelligent monitoring

Abstract

The invention relates to a respiratory nephropathy department patient sleep nursing system and method based on intelligent monitoring, equipment and a medium. Comprising a physical sign acquisition module, a data processing module, an environment monitoring module, an illness state prediction module and a nursing intervention module. The physical sign acquisition module is responsible for monitoring physiological parameters and sleep behaviors of a patient during sleep in real time, and the data processing module performs analysis and evaluation according to physiological feature data and sleep behavior data to obtain a sleep quality evaluation result of the patient. The environment monitoring module monitors environment parameters of a sleep environment of a patient in real time to obtain environment characteristic data. And the illness state prediction module predicts the illness state change of the patient by using a trained prediction model based on the environment feature data, the physiological feature data and the sleep behavior data to obtain a predicted illness state trend. And the nursing intervention module performs analysis according to the sleep evaluation result and the predicted illness state trend to obtain an environment regulation scheme suitable for sleep of the patient. And comprehensive monitoring and optimization of sleep and illness conditions of the patient are realized.

Description

Technical Field

[0001] The present invention belongs to the field of medical technology, and in particular relates to a sleep care system and method for patients with respiratory nephropathy based on intelligent monitoring. Background Art

[0002] With the development of medical technology, sleep care technology for patients with respiratory nephropathy based on intelligent monitoring has emerged. Due to the complexity of their condition, patients with respiratory nephropathy often need to pay close attention to their sleep conditions, including blood pressure, body temperature, blood oxygen, heart rate, respiratory rate and other indicators. Traditional nursing methods rely on manual monitoring, which is not only time-consuming and labor-intensive, but may also lead to inaccurate monitoring due to human factors. Existing Internet of Things technology can realize the function of optimizing the environment when the user is sleeping, but its evaluation and analysis of the sleep quality of the user at a certain stage still lacks certain scientificity and accuracy, making it difficult to achieve comprehensive monitoring and optimization of the patient's sleep and condition. Summary of the invention

[0003] Based on this, it is necessary to provide a sleep care system and method for respiratory and nephrology patients based on intelligent monitoring, which can realize comprehensive monitoring and optimization of patients' sleep and medical conditions, in response to the above technical problems.

[0004] In a first aspect, the present application provides a sleep care system for patients with respiratory nephropathy based on intelligent monitoring, comprising:

[0005] The vital sign acquisition module is used to monitor the patient's physiological parameters and sleep behavior during sleep in real time, and obtain the patient's physiological characteristic data at each monitoring time point and the sleep behavior data within each monitoring time period; the physiological characteristic data includes at least one of blood pressure value, body temperature value, blood oxygen value, heart rate value and respiratory rate; the sleep behavior data includes at least one of the number of tossing, number of awakenings, displacement and body posture maintenance time.

[0006] The data processing module is used to analyze and evaluate the patient's sleep quality based on the physiological characteristic data and sleep behavior data to obtain a sleep evaluation result.

[0007] The environmental monitoring module is used to monitor the environmental parameters of the patient's sleeping environment in real time and obtain environmental characteristic data corresponding to the patient's sleeping environment; the environmental parameters include at least one of indoor air quality, lighting conditions, humidity conditions, temperature conditions and noise conditions.

[0008] The condition prediction module is used to predict the patient's condition changes based on environmental characteristic data, physiological characteristic data and sleep behavior data using a trained prediction model to obtain a predicted condition trend.

[0009] The nursing intervention module is used to analyze the sleep assessment results and predict the disease trend to obtain an environmental adjustment plan suitable for the patient's sleep; the environmental adjustment plan is used to indicate the adjustment of environmental parameters.

[0010] In one embodiment, the patient's sleep quality is analyzed and evaluated based on the acquired physiological characteristic data and sleep behavior data to obtain a sleep evaluation result, including:

[0011] Acquire the patient's physiological characteristic data in normal sleep state at each monitoring time point; the physiological characteristic data include blood pressure value, body temperature value, blood oxygen value, heart rate value and respiratory rate.

[0012] According to the physiological characteristic data and the reference physiological characteristic data, the patient's physiological assessment index S1 is calculated using a formula.

[0013]

[0014] Wherein, S1 represents the patient's physiological assessment index; ω1, ω2, ω3, ω4, and ω5 represent the weight coefficients of blood pressure, body temperature, blood oxygen, heart rate, and respiratory rate, respectively; a0, b0, c0, d0, and e0 represent the reference blood pressure, reference body temperature, reference blood oxygen, reference heart rate, and reference respiratory rate, respectively; a i 、b i 、c i d i 、e i They respectively represent the blood pressure value, body temperature value, blood oxygen value, heart rate value and respiratory rate at the i monitoring time point; Δa, Δb, Δc, Δd, Δe respectively represent the preset blood pressure deviation threshold, body temperature deviation threshold, blood oxygen deviation threshold, heart rate deviation threshold and respiratory rate deviation threshold; i represents the monitoring time point, i=1,2,3...,c; c represents the total number of monitoring time points within the monitoring time period.

[0015] Obtain the patient's sleep behavior data in normal sleep state during each monitoring period; sleep behavior data includes the number of tossing and turning, the number of awakening times, the displacement and the length of time the posture is maintained.

[0016] According to the sleep behavior data and the reference sleep behavior data, the patient's sleep behavior index S2 is calculated using the following formula.

[0017]

[0018] Among them, S2 represents the patient's sleep behavior index, C represents the preset sleep behavior assessment correction factor, and f i , g i 、h i 、j iThey respectively represent the number of flipping, number of awakening, displacement and duration of posture maintenance of patient i during the monitoring time period; f, g, h, j respectively represent the reference number of flipping, reference number of awakening, reference displacement and reference duration of posture maintenance during the same time period; r represents the total number of monitoring time periods.

[0019] The sleep quality of the patient during the monitoring period is analyzed using a formula based on the physiological assessment index and the sleep behavior index to obtain the sleep assessment index M.

[0020] The sleep assessment index calculation formula is as follows:

[0021]

[0022] Among them, M represents the sleep assessment index during the patient's monitoring period; α1 and α2 represent the corresponding weight ratios of the physiological assessment index and the sleep behavior index, respectively.

[0023] The sleep evaluation index is judged based on the preset evaluation index threshold to obtain the sleep evaluation result.

[0024] Among them, when the sleep assessment index M reaches the assessment index threshold, the sleep assessment result is passed, and it is determined that there is no need to adjust the patient's current sleeping environment.

[0025] When the sleep assessment index M is less than the assessment index threshold, the sleep assessment result is failed, and it is determined that the patient's current sleep environment needs to be adjusted.

[0026] In one embodiment, the environment monitoring module further includes:

[0027] Air monitoring unit: The air monitoring unit is used to monitor the CO2, formaldehyde and water vapor content in the current indoor air, and obtain the air quality data and humidity condition data corresponding to the patient's sleeping environment.

[0028] Light monitoring unit: The intelligent light monitoring unit is used to monitor the current opening length of the curtains, the color temperature, intensity, irradiation position and irradiation area of ​​each outdoor light beam, and obtain the light condition data corresponding to the patient's sleeping environment.

[0029] The temperature monitoring unit is used to monitor the current indoor temperature value and the patient's current body temperature value to obtain the temperature condition data corresponding to the patient's sleeping environment.

[0030] The noise monitoring unit is used to monitor the current indoor sound pressure and sound frequency, and obtain the noise condition data corresponding to the patient's sleeping environment.

[0031] In one embodiment, it is characterized in that the disease prediction module further includes:

[0032] The data processing unit is used to assign different weight values ​​to the environmental characteristic data, physiological characteristic data and sleep behavior data according to actual conditions, and standardize or normalize the weighted data to obtain a predicted data set.

[0033] The prediction model training unit is used to verify the model trained based on historical data using cross-validation or a test set to obtain a trained disease prediction model; the disease prediction model includes any one of a time series analysis model, a machine learning model, and a deep learning model.

[0034] The prediction result output unit is used to predict the changes of the disease at different stages using the prediction data set and the trained disease prediction model to obtain the predicted disease trend.

[0035] In one embodiment, after obtaining the trained disease prediction model, the method further includes:

[0036] The data in the prediction data set are calculated to obtain the sum of the corresponding probabilities of causing the disease.

[0037] The predicted value of the patient's disease initiation is obtained based on the sum of the probabilities of disease initiation.

[0038] The predicted value of the patient's triggering condition was calculated using the following formula:

[0039]

[0040] Among them, C represents the predicted value, T represents the monitoring period, n represents the transformation coefficient, A represents the correction coefficient, t represents the stability coefficient of the data in the predicted data set, and G x It represents the sum of the probabilities of the data in the predicted data set causing the disease, f(kT) represents the adjustment function, and k represents a constant.

[0041] In one embodiment, the formula is used to calculate the data in the prediction data set to obtain the sum of the corresponding probabilities of causing the disease, including:

[0042] Use the following formula to analyze and calculate the weight value of the data in the prediction data set:

[0043]

[0044] Among them, G represents the weight value of the data, r represents the type of disease caused by the data, and e j Represents the weight value of the data in category j.

[0045] The data in the prediction data set are prioritized according to the weight value to obtain the corresponding prediction ranking result.

[0046] Use the following formula to select the target number of data from high to low based on the prediction sorting results to calculate the sum of the probabilities of the data in the prediction data set causing the disease:

[0047]

[0048] Among them, G x It represents the sum of the probabilities of the data in the prediction data set causing the disease, P y represents the probability value of the target data causing the disease, and m represents the number of data.

[0049] In one embodiment, the system further comprises:

[0050] The alarm warning module is used to judge the physiological characteristic data based on a preset range and obtain the corresponding judgment result; when the judgment result exceeds the corresponding preset range, an alarm message is issued.

[0051] The nursing advice module is used to generate targeted nursing advice based on the predicted disease trend; the nursing advice includes dietary advice, sleep reminders, exercise advice, and psychological adjustment advice.

[0052] In a second aspect, the present application also provides a sleep care method for patients with respiratory nephropathy based on intelligent monitoring, the method comprising:

[0053] Real-time monitoring of the patient's physiological parameters and sleep behavior during sleep, to obtain the patient's physiological characteristic data at each monitoring time point and the sleep behavior data within each monitoring time period; the physiological characteristic data include at least one of blood pressure value, body temperature value, blood oxygen value, heart rate value and respiratory rate; the sleep behavior data include at least one of the number of tossing and turning, number of awakenings, displacement and body posture maintenance time.

[0054] The patient's sleep quality is analyzed and evaluated based on the physiological characteristic data and sleep behavior data to obtain the sleep evaluation results.

[0055] Monitor the environmental parameters of the patient's sleeping environment in real time to obtain environmental characteristic data corresponding to the patient's sleeping environment; the environmental parameters include at least one of indoor air quality, lighting conditions, humidity conditions, temperature conditions and noise conditions.

[0056] Based on the environmental characteristic data, physiological characteristic data and sleep behavior data, the trained prediction model is used to predict the patient's condition changes and obtain the predicted condition trend.

[0057] Based on the analysis of the sleep assessment results and the predicted disease trend, an environmental adjustment plan suitable for the patient's sleep is obtained; the environmental adjustment plan is used to indicate the adjustment of environmental parameters.

[0058] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above-mentioned method when executing the computer program.

[0059] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the method described above are implemented.

[0060] The above-mentioned intelligent monitoring-based sleep care system and method for respiratory nephrology patients, computer equipment and storage medium, by real-time monitoring of the patient's physiological parameters and sleep behavior during sleep, obtains physiological characteristic data including at least one of blood pressure value, body temperature value, blood oxygen value, heart rate value and respiratory frequency, and sleep behavior data including at least one of the number of flipping, number of awakening, displacement and body posture maintenance time. At the same time, the environmental parameters of the patient's sleeping environment are monitored in real time to obtain environmental characteristic data including at least one of indoor air quality, lighting conditions, humidity conditions, temperature conditions and noise conditions. According to the physiological characteristic data and sleep behavior data, the patient's sleep quality is analyzed and evaluated to obtain a sleep evaluation result. Then, based on the environmental characteristic data, physiological characteristic data and sleep behavior data, the patient's condition changes are predicted using the trained prediction model to obtain a predicted condition trend. Finally, according to the sleep evaluation results and the predicted condition trend, an analysis is performed to obtain an environmental adjustment plan for indicating the patient's suitable sleep for adjusting environmental parameters. A good sleeping environment is created for the patient, thereby improving the patient's sleep quality, promoting the stability and recovery of the condition, and realizing comprehensive monitoring and optimization of the patient's sleep and condition. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0062] Figure 1 A structural block diagram of a sleep care system for respiratory and nephrological patients based on intelligent monitoring provided by an embodiment of the present invention;

[0063] Figure 2 A flowchart of analyzing and evaluating a patient's sleep quality based on acquired physiological characteristic data and sleep behavior data to obtain a sleep evaluation result provided by an embodiment of the present invention;

[0064] Figure 3 A structural block diagram of an environmental monitoring module provided by an embodiment of the present invention;

[0065] Figure 4 A structural block diagram of a disease prediction module provided by an embodiment of the present invention;

[0066] Figure 5 A structural block diagram of another sleep care system for respiratory and nephrological patients based on intelligent monitoring provided in an embodiment of the present invention.

[0067] Figure 6 A flowchart of a sleep care method for patients with respiratory nephropathy based on intelligent monitoring is provided for an embodiment of the present invention. DETAILED DESCRIPTION

[0068] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0069] Next, the implementation environment of the embodiment of the present application is described. Exemplarily, the implementation environment includes a patient-side monitoring device 101 , an environment monitoring device 102 , a server 103 and a smart device terminal 104 .

[0070] Patient-side monitoring equipment 101 includes a blood pressure monitor, a thermometer, a blood oxygen saturation monitor, a heart rate monitor, a respiratory rate monitor, a motion sensor, a wakefulness detection sensor, and the like. The blood pressure monitor measures the patient's blood pressure value during sleep in real time. For patients with respiratory and nephrological diseases, changes in blood pressure may reflect the body's stress state or fluctuations in the condition. For example, certain kidney diseases may cause abnormal increases or decreases in blood pressure. The thermometer accurately measures the patient's body temperature. In sleep care, changes in body temperature may indicate whether the patient has an infection, inflammation, or other physical abnormalities. The blood oxygen saturation monitor continuously monitors the patient's blood oxygen value. For patients with respiratory and nephrological diseases, respiratory function may be affected, resulting in a decrease in blood oxygen saturation. The heart rate monitor records the patient's heart rate value, and changes in heart rate can reflect the patient's heart function and the body's stress state. For patients with respiratory and nephrological diseases, the heart burden may be heavy, and abnormal changes in heart rate may indicate impaired heart function or worsening of the condition. The respiratory rate monitor monitors the patient's respiratory rate. During sleep, abnormal changes in respiratory rate may indicate airway obstruction, lung infection, or other respiratory problems. Motion sensors detect the patient's sleep behavior data such as the number of tossing and turning and the amount of displacement. These data can reflect the patient's sleep quality and comfort. For patients in the respiratory and nephrology department, frequent tossing may mean unstable sleep. Medical staff can adjust the patient's sleeping posture and provide a comfortable mattress or pillow based on the data from the motion sensor to improve the patient's sleep quality. The wakefulness detection sensor determines the number of awakenings by analyzing the patient's movements, sounds, etc. For patients in the respiratory and nephrology department, frequent awakenings may affect sleep quality and aggravate the condition. Through the wakefulness detection sensor, medical staff can understand the patient's sleep interruptions, analyze the causes and take corresponding measures.

[0071] Environmental monitoring equipment 102 such as temperature sensors, humidity sensors, light sensors, air quality monitors, noise monitors, etc. The temperature sensor is used to monitor the temperature of the patient's sleeping environment. If the temperature of the sleeping environment is too high or too low, it may cause discomfort to the patient and affect sleep. For example, high temperature may cause the patient to breathe rapidly, sweat more, and aggravate dyspnea. Low temperature may make the patient feel cold and cause respiratory spasm. The humidity sensor monitors the humidity conditions of the sleeping environment. Appropriate humidity helps to moisten and comfort the patient's respiratory tract. If the environmental humidity is too high, bacteria and mold may breed, increasing the risk of respiratory infection. Too low humidity will dry the respiratory mucosa, causing coughing and discomfort. The light sensor measures the light intensity of the sleeping environment. Good sleep requires appropriate light conditions. For patients in the respiratory nephrology department, too strong light may interfere with sleep and affect the biological clock. Medical staff can adjust the indoor lighting according to the data of the light sensor, keep the room dark or use blackout curtains during the patient's sleep to avoid strong light exposure. At the same time, appropriate light during the day can help patients adjust their biological clocks, improve their mental state during the day, and facilitate sleep at night. The air quality monitor detects indoor air quality, including harmful gas content, PM2.5 and other indicators. Medical staff can take corresponding measures to improve indoor air quality based on the data from the air quality monitor. The noise monitor evaluates the noise in the sleeping environment. Noise can interfere with the patient's sleep. For patients in the respiratory and nephrology department, a quiet sleeping environment can help relax the body and mind and relieve symptoms such as dyspnea. Medical staff can take measures to reduce noise based on the data from the noise monitor, such as using sound insulation materials, adjusting the sound of equipment operation, etc. At the same time, medical staff can also remind patients and their families to keep quiet and jointly create a quiet sleeping environment.

[0072] The server 103 can receive data from various intelligent monitoring devices and obtain key information such as the patient's respiratory rate and sleep status in real time. By analyzing and processing these data, medical staff can understand the patient's sleep condition in a timely manner so that they can quickly take corresponding nursing measures when abnormalities occur. For example, the server can store the patient's sleep data to provide a basis for subsequent disease analysis and treatment plan adjustment. Through the efficient operation of the server, this sleep care method based on intelligent monitoring can provide more accurate and timely nursing services for patients in the respiratory nephrology department, which helps to improve the patient's sleep quality and rehabilitation effect.

[0073] The intelligent device terminal 104 includes intelligent curtains, intelligent air purifiers, intelligent display screens, mobile phones, computers, etc. Intelligent curtains can automatically adjust the opening and closing degree of the curtains according to the data of the light sensor to create a suitable sleeping lighting environment for the patient. The intelligent air purifier automatically operates according to the data of the air quality monitor to improve the air quality of the patient's sleeping environment. When the indoor air quality is detected to be degraded, such as the increase in the content of harmful gases and the excessive PM2.5, the intelligent air purifier will automatically start the purification function to filter the pollutants in the air and provide fresh air for the patient. The intelligent display screen can be used as an interactive interface between patients and medical staff to display information such as the patient's sleep data, environmental parameters, and nursing recommendations. Patients can understand their sleep conditions and physical conditions through the intelligent display screen, and enhance their awareness of attention and management of their own health. Medical staff can also remotely monitor the patient's sleep and condition through the intelligent display screen, and adjust the nursing plan in time. In addition, the intelligent display screen can also provide some relaxing music, videos or natural landscapes to help patients relieve stress, relax and promote sleep. Mobile phones and computers are mainly used for data processing and management in this sleep care method. Medical staff can use professional software on mobile phones or computers to analyze data from various monitoring devices, including physiological characteristics data, sleep behavior data, and environmental characteristics data. Computers can run complex algorithms and models to conduct in-depth analysis of these data, evaluate patients' sleep quality, and predict disease trends. At the same time, mobile phones and computers can also be used to store and manage patients' medical records, nursing records, and other information, making it convenient for medical staff to access and update them at any time. In addition, computers can also connect and communicate with other devices to achieve collaborative work of the entire intelligent monitoring system.

[0074] In combination with the above-mentioned explanations of terms and implementation environment, the application scenarios of the embodiments of the present application are explained.

[0075] The sleep care system and method for respiratory nephrology patients based on intelligent monitoring provided in the embodiment of the present application obtains physiological characteristic data including at least one of blood pressure value, body temperature value, blood oxygen value, heart rate value and respiratory frequency, and sleep behavior data including at least one of tossing number, awakening number, displacement and posture maintenance time by real-time monitoring of the patient's physiological parameters and sleep behavior during sleep. At the same time, the environmental parameters of the patient's sleeping environment are monitored in real time to obtain environmental characteristic data including at least one of indoor air quality, lighting conditions, humidity conditions, temperature conditions and noise conditions. The patient's sleep quality is analyzed and evaluated according to the physiological characteristic data and sleep behavior data to obtain a sleep evaluation result. Then, based on the environmental characteristic data, physiological characteristic data and sleep behavior data, the patient's condition changes are predicted using the trained prediction model to obtain a predicted condition trend. Finally, according to the sleep evaluation results and the predicted condition trend, an analysis is performed to obtain an environmental adjustment plan for indicating the patient's suitable sleep for adjusting environmental parameters. A good sleeping environment is created for the patient, thereby improving the patient's sleep quality, promoting the stability and recovery of the condition, and realizing comprehensive monitoring and optimization of the patient's sleep and condition. Exemplarily, the intelligent monitoring-based sleep care system and method for respiratory and nephrology patients provided in the embodiments of the present application can be applied to at least one scenario including but not limited to the following scenarios.

[0076] First, the sleep care system and method for respiratory nephropathy patients based on intelligent monitoring are applied to real-time monitoring and early warning. During the patient's hospitalization in the respiratory nephropathy department, the patient-side monitoring device 101 continuously monitors the patient's vital signs, including respiratory rate, heart rate, blood oxygen saturation, etc. At the same time, the environmental monitoring device 102 monitors the temperature, humidity, air quality and other environmental factors of the ward in real time. These data will be transmitted to the server 103 in real time. The server 103 analyzes and processes the data, and immediately sends an early warning message to the intelligent device terminal 104 once it is found that the patient's vital signs fluctuate abnormally or the environmental factors exceed the appropriate range. For example, when the patient's blood oxygen saturation suddenly drops, the server will quickly notify the medical staff on duty. Medical staff can view the patient's specific monitoring data through the intelligent device terminal, and go to the ward for inspection and treatment in time. At the same time, if the environmental monitoring device detects that the temperature in the ward is too high or too low, it will also remind the medical staff to make adjustments to ensure that the patient is in a comfortable sleeping environment.

[0077] Second, the sleep care system and method for respiratory nephrology patients based on intelligent monitoring are applied to the formulation of personalized sleep care plans. Based on the data collected by the patient-side monitoring device 101 and the environmental monitoring device 102, the server 103 can formulate a personalized sleep care plan for each patient. The intelligent device terminal 104 is used by medical staff, who can view the detailed monitoring data of the patient and the care plan generated by the server. For patients with weak respiratory function, medical staff can adjust the patient's sleeping posture according to the plan to improve breathing conditions. If environmental monitoring shows that the noise is loud, medical staff can take measures to reduce the noise, such as adjusting the position of the doors and windows of the ward, adding sound insulation equipment, etc. At the same time, patients can also understand their sleep monitoring conditions and care suggestions through their own intelligent device terminals, and actively cooperate with medical staff for sleep care. For example, patients can adjust their work and rest time according to the suggestions, avoid using electronic devices before going to bed, etc.

[0078] Third, the sleep care system and method for respiratory nephrology patients based on intelligent monitoring are applied to remote monitoring and home care extension. After the patient is discharged from the hospital, the patient-side monitoring device 101 can continue to be used at home to monitor the patient's physical condition. The environmental monitoring device 102 can also be installed in the home environment to monitor the temperature, humidity, etc. of the home. These data are transmitted to the server 103 via the network, and medical staff can remotely monitor the patient's sleep and health status through the smart device terminal 104. If an abnormality is found, the medical staff can contact the patient in time to provide guidance and suggestions. In addition, the server can also continuously optimize the sleep care plan based on the patient's monitoring data at home, and provide patients with more accurate home care services. Patients and their families can also use smart device terminals to keep abreast of the patient's health status at any time and enhance their ability to manage and care for the disease.

[0079] In one embodiment, if Figure 1 As shown, a sleep care system for patients with respiratory nephropathy based on intelligent monitoring is provided. This embodiment uses the system applied to the above-mentioned server as an example, and may include:

[0080] The vital sign acquisition module 201 is used to monitor the patient's physiological parameters and sleep behavior during sleep in real time, and obtain the patient's physiological characteristic data at each monitoring time point and the sleep behavior data within each monitoring time period; the physiological characteristic data includes at least one of blood pressure value, body temperature value, blood oxygen value, heart rate value and respiratory rate; the sleep behavior data includes at least one of the number of tossing, number of awakenings, displacement and body posture maintenance time.

[0081] During the monitoring period, the user's movements are tracked in real time through the target monitoring algorithm, and the adjacent frame images of each turning over and waking up of the user are collected. For a certain turning over or waking up action of the user, the start frame image and the end frame image of the turning over or waking up action are screened out from the adjacent frame images of the turning over or waking up action, and the position information of the user's head, hands and legs in the image is extracted. By comparing the position information of the start frame image and the end frame image, the displacement of the user's head, hands and legs in the turning over action is calculated, and the maximum value is selected as the body displacement of the turning over action, which is recorded as the body displacement of the user's turning over. According to the time between the monitoring time point of the end frame image of the turning over action and the monitoring time point of the start frame image of the next turning over action, the user's posture maintenance time after the turning over action is determined, which is recorded as the posture maintenance time after the user's turning over.

[0082] The data processing module 202 is used to analyze and evaluate the patient's sleep quality based on the physiological characteristic data and the sleep behavior data to obtain a sleep evaluation result.

[0083] The data processing module receives the physiological characteristic data and sleep behavior data collected by the physical sign acquisition module. First, for the physiological characteristic data, including blood pressure, body temperature, blood oxygen, heart rate and respiratory rate, the module will analyze the changes of these data in different time periods. For example, observe whether the heart rate is stable and whether the respiratory rate fluctuates within the normal range. For sleep behavior data, such as the number of flips, the number of awakenings, the displacement and the length of time the body is maintained, the module will comprehensively consider the impact of these factors on sleep quality. If the number of flips is too much, it may mean that the patient's sleep is unstable; frequent awakenings will obviously reduce the sleep quality; large displacement may also reflect the patient's discomfort during sleep. Then, the data processing module will use specific algorithms and evaluation models to comprehensively analyze these physiological characteristic data and sleep behavior data. By comparing with the pre-set normal sleep quality indicators, the patient's sleep quality is evaluated. Finally, a detailed sleep evaluation result is obtained, which may include the classification of sleep quality, specific problems and possible influencing factors.

[0084] The environmental monitoring module 203 is used to monitor the environmental parameters of the patient's sleeping environment in real time and obtain environmental characteristic data corresponding to the patient's sleeping environment; the environmental parameters include at least one of indoor air quality, lighting conditions, humidity conditions, temperature conditions and noise conditions.

[0085] Indoor air quality includes monitoring of harmful gases, dust particles, etc. in the air. Good indoor air quality helps patients breathe smoothly and avoids respiratory discomfort caused by air pollution, which affects sleep. Lighting conditions are also crucial. Too strong or too weak light may disturb patients' sleep. The module monitors the light intensity and light time to ensure that the light in the sleeping environment is in the appropriate range. Humidity conditions should not be ignored either. Too high humidity may make people feel stuffy and uncomfortable, while too low humidity may cause dry skin and dry respiratory tract. The environmental monitoring module accurately measures the ambient humidity to provide a basis for adjusting to the appropriate sleeping humidity. Temperature conditions also have a great impact on sleep quality. Too high temperature can make people irritable and difficult to fall asleep; too low temperature can cause the body to be cold, affecting the depth and comfort of sleep. The module closely monitors temperature changes to ensure that the sleeping environment temperature is moderate. Excessive noise can stimulate the patient's nervous system and make it difficult for them to enter a deep sleep state. The environmental monitoring module detects the intensity and frequency of noise to create a quiet sleeping environment for patients as much as possible. By real-time monitoring of at least one environmental parameter such as indoor air quality, lighting conditions, humidity conditions, temperature conditions and noise conditions, the environmental monitoring module can obtain environmental characteristic data corresponding to the patient's sleeping environment.

[0086] The condition prediction module 204 is used to predict the patient's condition changes based on the environmental characteristic data, the physiological characteristic data and the sleep behavior data using a trained prediction model to obtain a predicted condition trend.

[0087] The disease prediction module includes a data processing unit, a prediction model training unit and a prediction result output unit. The data processing unit will assign different weight values ​​to the environmental characteristic data, physiological characteristic data and sleep behavior data according to the actual situation, and then standardize or normalize the weighted data to obtain a prediction data set. The prediction model training unit uses a model trained based on historical data, and verifies it using cross-validation or a test set to finally obtain a trained disease prediction model. The disease prediction model includes any one of a time series analysis model, a machine learning model and a deep learning model. The prediction result output unit uses the prediction data set and the trained disease prediction model to predict the changes in the disease at different stages, and then obtain the predicted disease trend.

[0088] The nursing intervention module 205 is used to analyze the sleep assessment results and the predicted disease trend to obtain an environmental adjustment plan suitable for the patient's sleep; the environmental adjustment plan is used to indicate the adjustment of environmental parameters.

[0089] The environmental adjustment plan includes adjusting the working level of the air purifier through the air monitoring unit to improve the indoor air quality and humidity conditions; adjusting the curtain opening length through the light monitoring unit to optimize the indoor lighting conditions; adjusting the temperature of the mattress through the temperature monitoring unit to provide a temperature more suitable for the patient's sleep; and issuing reminder messages through the noise monitoring unit to optimize indoor noise.

[0090] Receive the sleep assessment results from the data processing module and the predicted disease trend output by the disease prediction module and conduct in-depth analysis. If the sleep assessment results show that the patient's sleep quality is poor, combined with the possible adverse developments in the predicted disease trend, the nursing intervention module will comprehensively consider various factors to formulate an environmental adjustment plan for the patient's suitable sleep. For the indoor air quality in the environmental parameters, if the analysis finds that the current air quality is poor, it may be recommended to increase the operating intensity of the air purification equipment, or open the window for ventilation in time to improve the air quality. In terms of lighting conditions, if it is judged that the light is too strong and affects the patient's sleep, it may be proposed to adjust the shading degree of the curtains or adjust the brightness and opening time of the lighting equipment. For humidity conditions, if the humidity is not within the appropriate range, it may be indicated to increase or decrease the use time of the humidifier to achieve a suitable sleeping humidity environment. When the temperature condition is not conducive to the patient's sleep, the nursing intervention module may suggest adjusting the air conditioning temperature setting to ensure that the sleeping environment temperature is moderate. As for the noise condition, if the noise is too loud, it may be proposed to take sound insulation measures, such as installing soundproof curtains, using earplugs, etc.

[0091] The above-mentioned sleep care system for patients in the respiratory and nephrological department based on intelligent monitoring includes a physical sign acquisition module, a data processing module, an environmental monitoring module, a disease prediction module and a nursing intervention module. The physical sign acquisition module is responsible for real-time monitoring of the patient's physiological parameters and sleep behavior during sleep, and obtains at least one physiological characteristic data including blood pressure value, body temperature value, blood oxygen value, heart rate value, respiratory rate, etc., as well as at least one sleep behavior data such as the number of flipping, the number of awakening times, the displacement, and the length of time the body posture is maintained. The data processing module analyzes and evaluates the physiological characteristic data and the sleep behavior data to obtain the patient's sleep quality evaluation result. The environmental monitoring module monitors the environmental parameters of the patient's sleeping environment in real time, such as indoor air quality, lighting conditions, humidity conditions, temperature conditions, noise conditions, etc., to obtain environmental characteristic data. The disease prediction module predicts the patient's disease changes based on the environmental characteristic data, physiological characteristic data and sleep behavior data using the trained prediction model to obtain the predicted disease trend. The nursing intervention module analyzes the sleep evaluation results and the predicted disease trend to obtain an environmental adjustment plan suitable for the patient's sleep, which is used to indicate the adjustment of environmental parameters. Create a good sleeping environment for patients, thereby improving their sleep quality, promoting disease stabilization and recovery, and achieving comprehensive monitoring and optimization of patients' sleep and disease conditions.

[0092] In one embodiment, if Figure 2 As shown, analyzing and evaluating the patient's sleep quality based on the acquired physiological characteristic data and sleep behavior data to obtain a sleep evaluation result may include the following steps:

[0093] Step S301, obtaining physiological characteristic data of the patient in a normal sleep state at each monitoring time point; the physiological characteristic data includes blood pressure value, body temperature value, blood oxygen value, heart rate value and respiratory rate.

[0094] Step S302, calculating the patient's physiological assessment index S1 using a formula according to the physiological characteristic data and the reference physiological characteristic data.

[0095]

[0096] Wherein, S1 represents the patient's physiological assessment index; ω1, ω2, ω3, ω4, and ω5 represent the weight coefficients of blood pressure, body temperature, blood oxygen, heart rate, and respiratory rate, respectively; a0, b0, c0, d0, and e0 represent the reference blood pressure, reference body temperature, reference blood oxygen, reference heart rate, and reference respiratory rate, respectively; a i 、b i 、c i d i 、e i They respectively represent the blood pressure value, body temperature value, blood oxygen value, heart rate value and respiratory rate at the i monitoring time point; Δa, Δb, Δc, Δd, Δe respectively represent the preset blood pressure deviation threshold, body temperature deviation threshold, blood oxygen deviation threshold, heart rate deviation threshold and respiratory rate deviation threshold; i represents the monitoring time point, i=1,2,3...,c; c represents the total number of monitoring time points within the monitoring time period.

[0097] Step S303, obtaining the sleep behavior data of the patient in a normal sleep state during each monitoring time period; the sleep behavior data includes the number of tossing and turning, the number of awakening times, the displacement amount and the length of time the posture is maintained.

[0098] Step S304, according to the sleep behavior data and the reference sleep behavior data, the patient's sleep behavior index S2 is calculated using the following formula:

[0099]

[0100] Among them, S2 represents the patient's sleep behavior index, C represents the preset sleep behavior assessment correction factor, and f i , g i 、h i 、j iThey respectively represent the number of flipping, number of awakening, displacement and duration of posture maintenance of patient i during the monitoring time period; f, g, h, j respectively represent the reference number of flipping, reference number of awakening, reference displacement and reference duration of posture maintenance during the same time period; r represents the total number of monitoring time periods.

[0101] Step S305 , analyzing the sleep quality of the patient during the monitoring period using a formula based on the physiological assessment index and the sleep behavior index to obtain a sleep assessment index M.

[0102] The sleep assessment index calculation formula is as follows:

[0103]

[0104] Among them, M represents the sleep assessment index during the patient's monitoring period; α1 and α2 represent the corresponding weight ratios of the physiological assessment index and the sleep behavior index, respectively.

[0105] Step S306: judging the sleep evaluation index based on a preset evaluation index threshold to obtain a sleep evaluation result.

[0106] Step S307, wherein, when the sleep evaluation index M reaches the evaluation index threshold, the sleep evaluation result is passed, and it is determined that there is no need to adjust the patient's current sleeping environment.

[0107] Step S308: When the sleep evaluation index M is less than the evaluation index threshold, the sleep evaluation result is failed, and it is determined that the patient's current sleeping environment needs to be adjusted.

[0108] This embodiment can accurately understand the patient's physical condition and behavioral performance during sleep by obtaining the patient's physiological characteristic data at each monitoring time point and the sleep behavior data of each monitoring time period. The physiological assessment index and the sleep behavior index are calculated using a specific formula, and then the sleep assessment index is obtained, which can quantify the patient's sleep quality and provide a clear basis for judging whether the sleep environment needs to be adjusted. When the sleep assessment index reaches the threshold, it indicates that the patient's sleep environment is suitable and does not need to be adjusted, which helps the patient to continue to rest and recover in a good environment; when the sleep assessment index does not reach the threshold, it can be determined that there is a need to adjust the sleep environment, and then take corresponding environmental adjustment measures, such as adjusting indoor air quality, lighting conditions, humidity, temperature and noise, etc., to create a more conducive environment for patients to sleep, improve the patient's sleep quality, and promote the patient's recovery.

[0109] In one embodiment, if Figure 3 As shown, the environment monitoring module may also include:

[0110] The air monitoring unit 2031 is used to monitor the CO2, formaldehyde and water vapor content in the current indoor air, and obtain the air quality data and humidity condition data corresponding to the patient's sleeping environment.

[0111] The light monitoring unit 2032 is used to monitor the current opening length of the curtain, the color temperature, intensity, irradiation position and irradiation area of ​​each outdoor light beam, and obtain the light condition data corresponding to the patient's sleeping environment.

[0112] The temperature monitoring unit 2033 is used to monitor the current indoor temperature value and the patient's current perceived temperature value, and obtain the temperature condition data corresponding to the patient's sleeping environment.

[0113] The noise monitoring unit 2034 is used to monitor the current indoor sound pressure and sound frequency, and obtain the noise condition data corresponding to the patient's sleeping environment.

[0114] The air monitoring unit can ensure that patients breathe safe and suitable air with appropriate humidity by monitoring harmful gases such as formaldehyde and water vapor in the indoor air, avoiding air quality problems that affect the patient's respiratory system and sleep quality. The light monitoring unit monitors the length of curtain opening, the color temperature, intensity, irradiation position and irradiation area of ​​the outdoor light beam, which helps to create a suitable lighting environment for patients and avoid excessive or weak light interfering with sleep. The temperature monitoring unit monitors the indoor temperature value and the patient's perceived temperature value, which can ensure that the sleeping environment is within a comfortable temperature range and prevent the patient's sleep comfort and physical condition from being affected by excessively high or low temperatures. The noise monitoring unit monitors the indoor sound pressure and sound frequency, which can promptly detect the noise source and take measures to reduce the noise, providing patients with a quiet sleeping environment. In general, these monitoring units can fully grasp the various parameters of the patient's sleeping environment, provide accurate data support for subsequent disease prediction and nursing intervention, and help improve the patient's sleep quality and promote the patient's recovery process.

[0115] In one embodiment, if Figure 4 As shown, the disease prediction module may also include:

[0116] The data processing unit 2041 is used to assign different weight values ​​to the environmental characteristic data, physiological characteristic data and sleep behavior data according to actual conditions, and standardize or normalize the weighted data to obtain a prediction data set.

[0117] The prediction model training unit 2042 is used to verify the model trained based on historical data using cross-validation or a test set to obtain a trained disease prediction model; the disease prediction model includes any one of a time series analysis model, a machine learning model, and a deep learning model.

[0118] The prediction result output unit 2043 is used to predict the changes of the disease at different stages using the prediction data set and the trained disease prediction model to obtain the predicted disease trend.

[0119] The data processing unit assigns different weight values ​​to the environmental characteristic data, physiological characteristic data and sleep behavior data according to the actual situation, and performs standardization or normalization processing, so that different types of data can be analyzed on a unified scale, improving the comparability and reliability of the data. The prediction model training unit trains the model with historical data and verifies it through cross-validation or test sets to ensure that the obtained disease prediction model has high accuracy and stability. The disease prediction model covers a variety of types such as time series analysis models, machine learning models and deep learning models, which can be selected according to different needs and data characteristics, improving the flexibility and adaptability of the prediction. The prediction result output unit combines the prediction data set and the trained disease prediction model to predict the changes in the disease at different stages, which can provide medical staff with timely and accurate disease trend information, help to formulate personalized treatment and care plans in advance, improve the treatment effect and quality of life of patients, and also provide strong support for clinical decision-making in the respiratory and nephrology department.

[0120] In one embodiment, after obtaining the trained disease prediction model, the following steps may be further included:

[0121] Step S401, calculating the data in the prediction data set to obtain the sum of the corresponding probabilities of causing the disease.

[0122] Step S402, obtaining a predicted value of the patient's disease induction based on the sum of the probabilities of disease induction.

[0123] The predicted value of the patient's triggering condition was calculated using the following formula:

[0124]

[0125] Among them, C represents the predicted value, T represents the monitoring period, n represents the transformation coefficient, A represents the correction coefficient, t represents the stability coefficient of the data in the predicted data set, and G x It represents the sum of the probabilities of the data in the predicted data set causing the disease, f(kT) represents the adjustment function, and k represents a constant.

[0126] The adjustment function may be a linear function such as f(kT)=ak+bT, where a and b are weight coefficients.

[0127] By analyzing the predicted values, medical staff can understand in advance the possibility of patients developing specific conditions in the future. This helps medical staff to adjust treatment plans and nursing measures in a timely manner and take more proactive intervention measures to reduce the risk of worsening of patients' conditions. For example, if the predicted value shows that the patient is more likely to develop a condition, medical staff can increase the frequency of monitoring the patient, adjust the drug treatment plan, or provide more personalized nursing services, thereby improving the patient's treatment effect and quality of life. At the same time, this predicted value can also provide a reference for the hospital's resource allocation and management, so as to better provide medical services to patients.

[0128] In one embodiment, using a formula to calculate the data in the prediction data set to obtain the sum of the corresponding probabilities of causing the disease may include the following steps:

[0129] Step S501, using the following formula to analyze and calculate the weight value of the data in the prediction data set:

[0130]

[0131] Among them, G represents the weight value of the data, r represents the type of disease caused by the data, and e j Represents the weight value of the data in category j.

[0132] Step S502: Prioritize the data in the prediction data set according to the weight value to obtain a corresponding prediction ranking result.

[0133] Step S503, using the following formula, based on the prediction sorting results, select the target number of data in descending order for calculation, and obtain the sum of the probabilities of the data in the prediction data set causing the disease:

[0134]

[0135] Among them, G x It represents the sum of the probabilities of the data in the prediction data set causing the disease, P y represents the probability value of the target data causing the disease, and m represents the number of data.

[0136] In step S501, j Represents the weight value of the data in category j, such as the weight of environmental feature data is 0.2, the weight of physiological feature data is 0.5, and the weight of sleep behavior data is 0.3.

[0137] By analyzing and calculating the weight values ​​of the data in the prediction data set through a specific formula, the importance of each data in the disease prediction can be scientifically determined based on the type of disease caused by the data and the weight value of the data in the category. The data in the prediction data set is prioritized according to the weight value to obtain the prediction ranking result, which helps to highlight the key data and make the subsequent analysis more targeted.

[0138] In step S503, based on the prediction sorting results, the target number of data is selected to calculate the sum of the probabilities of the data in the prediction data set causing the disease, which can more efficiently utilize data resources and avoid unnecessary waste of calculations. In general, these steps provide a systematic and effective method for disease prediction, improve the accuracy and reliability of disease prediction, provide strong support for medical staff to formulate personalized treatment and care plans, and help better protect the health and safety of patients in the respiratory nephrology department.

[0139] In one embodiment, if Figure 5 As shown, the system also includes:

[0140] The alarm module 206 is used to judge the physiological characteristic data based on a preset range and obtain a corresponding judgment result; when the judgment result exceeds the corresponding preset range, an alarm message is issued.

[0141] The nursing suggestion module 207 is used to generate targeted nursing suggestions based on the predicted disease trend; the nursing suggestions include diet suggestions, sleep reminders, exercise suggestions, and psychological adjustment suggestions.

[0142] The alarm warning module continuously monitors physiological characteristic data, including blood pressure, body temperature, blood oxygen, heart rate, and respiratory rate. The module pre-sets the reasonable range of each physiological characteristic data. For example, for blood pressure, the normal blood pressure range will be set according to the specific conditions of different patients and medical standards; for body temperature, there will also be a normal range that conforms to the health status of the human body; the same is true for blood oxygen, heart rate, and respiratory rate. When the module judges the physiological characteristic data, it will compare the currently acquired physiological characteristic data with the corresponding preset range one by one. If a physiological characteristic data exceeds the corresponding preset range, a judgment result of exceeding the range will be obtained. At this time, the alarm warning module will immediately issue an alarm message. This alarm message can be presented in a variety of forms, such as sound reminders and pop-up warning windows on the smart device terminal of medical staff, so that medical staff can know the abnormality of the patient's physiological state at the first time. In this way, the alarm warning module can promptly remind medical staff to pay attention to changes in the patient's physical condition and take corresponding emergency treatment measures, thereby maximizing the protection of the patient's life safety and health.

[0143] The nursing advice module generates targeted nursing advice for patients based on the predicted condition trend obtained by the condition prediction module. If the predicted condition trend shows that the patient's condition may be at risk of worsening, or the patient's physical condition needs further improvement, the nursing advice module will formulate corresponding measures based on the specific situation.

[0144] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0145] In an exemplary embodiment, Figure 6 As shown, the present application also provides a sleep care method for patients with respiratory nephropathy based on intelligent monitoring, and the method may include the following steps:

[0146] Step S601, real-time monitoring of the patient's physiological parameters and sleep behavior during sleep, to obtain the patient's physiological characteristic data at each monitoring time point and the sleep behavior data within each monitoring time period; the physiological characteristic data includes at least one of blood pressure value, body temperature value, blood oxygen value, heart rate value and respiratory rate; the sleep behavior data includes at least one of the number of tossing, number of awakenings, displacement and body posture maintenance time.

[0147] Step S602: Analyze and evaluate the patient's sleep quality based on the physiological characteristic data and the sleep behavior data to obtain a sleep evaluation result.

[0148] Step S603, monitor the environmental parameters of the patient's sleeping environment in real time to obtain environmental characteristic data corresponding to the patient's sleeping environment; the environmental parameters include at least one of indoor air quality, lighting conditions, humidity conditions, temperature conditions and noise conditions.

[0149] Step S604, predicting the patient's condition change based on the environmental characteristic data, physiological characteristic data and sleep behavior data using the trained prediction model to obtain a predicted condition trend.

[0150] Step S605, analyzing the sleep assessment results and the predicted disease trend to obtain an environment adjustment plan suitable for the patient's sleep; the environment adjustment plan is used to indicate the adjustment of environmental parameters.

[0151] The above-mentioned intelligent monitoring-based sleep care system and method for respiratory nephrology patients, computer equipment and storage medium, by real-time monitoring of the patient's physiological parameters and sleep behavior during sleep, obtains physiological characteristic data including at least one of blood pressure value, body temperature value, blood oxygen value, heart rate value and respiratory frequency, and sleep behavior data including at least one of the number of flipping, number of awakening, displacement and body posture maintenance time. At the same time, the environmental parameters of the patient's sleeping environment are monitored in real time to obtain environmental characteristic data including at least one of indoor air quality, lighting conditions, humidity conditions, temperature conditions and noise conditions. According to the physiological characteristic data and sleep behavior data, the patient's sleep quality is analyzed and evaluated to obtain a sleep evaluation result. Then, based on the environmental characteristic data, physiological characteristic data and sleep behavior data, the patient's condition changes are predicted using the trained prediction model to obtain a predicted condition trend. Finally, according to the sleep evaluation results and the predicted condition trend, an analysis is performed to obtain an environmental adjustment plan for indicating the patient's suitable sleep for adjusting environmental parameters. A good sleeping environment is created for the patient, thereby improving the patient's sleep quality, promoting the stability and recovery of the condition, and realizing comprehensive monitoring and optimization of the patient's sleep and condition.

[0152] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the aforementioned system and method for sleep care of respiratory and nephrological patients based on intelligent monitoring are implemented.

[0153] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0154] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can refer to the partial description of the method embodiments. The device embodiments described above are only schematic, wherein the components described as separate parts may or may not be physically separated, and the parts displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the disclosed solution. A person of ordinary skill in the art can understand and implement it without paying any creative work.

[0155] The above-mentioned embodiments only express several implementation methods of the embodiments of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the patent of the embodiments of the present application. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the embodiments of the present application, and these all belong to the protection scope of the embodiments of the present application.

Claims

1. A sleep care system for patients with respiratory nephropathy based on intelligent monitoring, characterized in that: The system comprises: A physical sign acquisition module is used to monitor the patient's physiological parameters and sleep behavior during sleep in real time, and obtain the patient's physiological characteristic data at each monitoring time point and the sleep behavior data in each monitoring time period; the physiological characteristic data includes at least one of blood pressure value, body temperature value, blood oxygen value, heart rate value and respiratory rate; the sleep behavior data includes at least one of the number of tossing, number of awakening, displacement and body posture maintenance time; A data processing module, used to analyze and evaluate the patient's sleep quality based on the physiological characteristic data and the sleep behavior data to obtain a sleep evaluation result; An environmental monitoring module is used to monitor the environmental parameters of the patient's sleeping environment in real time and obtain environmental characteristic data corresponding to the patient's sleeping environment; the environmental parameters include at least one of indoor air quality, lighting conditions, humidity conditions, temperature conditions and noise conditions; A disease prediction module is used to predict the patient's disease changes based on the environmental characteristic data, physiological characteristic data and sleep behavior data using a trained prediction model to obtain a predicted disease trend; The nursing intervention module is used to analyze the sleep assessment results and the predicted disease trend to obtain an environmental adjustment plan suitable for the patient's sleep; the environmental adjustment plan is used to indicate the adjustment of the environmental parameters.

2. The system according to claim 1, characterized in that The step of analyzing and evaluating the patient's sleep quality based on the acquired physiological characteristic data and sleep behavior data to obtain a sleep evaluation result includes: Acquire physiological characteristic data of the patient in a normal sleep state at each monitoring time point; the physiological characteristic data includes blood pressure value, body temperature value, blood oxygen value, heart rate value and respiratory rate; According to the physiological characteristic data and the reference physiological characteristic data, the patient's physiological assessment index S1 is calculated using the formula: Wherein, S1 represents the patient's physiological assessment index; ω1, ω2, ω3, ω4, and ω5 represent the weight coefficients of blood pressure, body temperature, blood oxygen, heart rate, and respiratory rate, respectively; a0, b0, c0, d0, and e0 represent the reference blood pressure, reference body temperature, reference blood oxygen, reference heart rate, and reference respiratory rate, respectively; a i , b i 、c i ,d i 、e i Respectively represent the blood pressure value, body temperature value, blood oxygen value, heart rate value and respiratory rate at the i monitoring time point; Δa, Δb, Δc, Δd, Δe represent the preset blood pressure deviation threshold, body temperature deviation threshold, blood oxygen deviation threshold, heart rate deviation threshold and respiratory rate deviation threshold respectively; i represents the monitoring time point, i=1,2,3...,c; c represents the total number of monitoring time points within the monitoring time period; Obtaining the patient's sleep behavior data in a normal sleep state during each monitoring period; the sleep behavior data includes the number of tossing and turning, the number of awakening times, the displacement, and the length of time the posture is maintained; According to the sleep behavior data and the reference sleep behavior data, the patient's sleep behavior index S2 is calculated using the following formula: Among them, S2 represents the patient's sleep behavior index, C represents the preset sleep behavior assessment correction factor, and f i , g i 、h i 、j i represents the number of flipping, awakening, displacement and posture maintenance time of patient i in the monitoring time period; f, g, h, j represent the reference number of flipping, reference number of awakening, reference displacement and reference posture maintenance time in the same time period; r represents the total number of monitoring time periods; Based on the physiological assessment index and the sleep behavior index, a formula is used to analyze the sleep quality of the patient during the monitoring period to obtain a sleep assessment index M; The sleep assessment index calculation formula is as follows: Among them, M represents the sleep assessment index of the patient during the monitoring period; α1 and α2 represent the corresponding weight proportions of the physiological assessment index and the sleep behavior index respectively; The sleep evaluation index is judged based on a preset evaluation index threshold to obtain a sleep evaluation result; Wherein, when the sleep evaluation index M reaches the evaluation index threshold, the sleep evaluation result is passed, and it is determined that there is no need to adjust the patient's current sleeping environment; When the sleep evaluation index M is less than the evaluation index threshold, the sleep evaluation result is failed, and it is determined that there is a need to adjust the patient's current sleeping environment.

3. The system according to claim 1, characterized in that The environmental monitoring module also includes: The air monitoring unit is used to monitor the CO2, formaldehyde and water vapor content in the current indoor air, and obtain the air quality data and humidity condition data corresponding to the patient's sleeping environment. A light monitoring unit is used to monitor the current opening length of the curtains, the color temperature, intensity, irradiation position and irradiation area of ​​each outdoor light beam, and obtain light condition data corresponding to the patient's sleeping environment. The temperature monitoring unit is used to monitor the current indoor temperature value and the patient's current perceived temperature value to obtain temperature condition data corresponding to the patient's sleeping environment. The noise monitoring unit is used to monitor the current indoor sound pressure and sound frequency to obtain noise condition data corresponding to the patient's sleeping environment.

4. The system according to claim 1, characterized in that The disease prediction module also includes: A data processing unit, used to assign different weight values ​​to the environmental characteristic data, physiological characteristic data and sleep behavior data according to actual conditions, and to standardize or normalize the weighted data to obtain a prediction data set; A prediction model training unit, used to validate the model trained based on historical data using cross-validation or a test set to obtain a trained disease prediction model; the disease prediction model includes any one of a time series analysis model, a machine learning model, and a deep learning model; The prediction result output unit is used to predict the changes of the disease at different stages using the prediction data set and the trained disease prediction model to obtain the predicted disease trend.

5. The system according to claim 4, characterized in that After obtaining the trained disease prediction model, the method further includes: Calculating the data in the prediction data set to obtain the sum of the corresponding probabilities of causing the disease; Obtaining a predicted value of the patient's disease induction based on the sum of the probabilities of the disease induction; The predicted value of the patient's triggering condition was calculated using the following formula: Among them, C represents the predicted value, T represents the monitoring period, n represents the transformation coefficient, A represents the correction coefficient, t represents the stability coefficient of the data in the predicted data set, and G x It represents the sum of the probabilities of the data in the predicted data set causing the disease, f(kT) represents the adjustment function, and k represents a constant.

6. The system according to claim 5, characterized in that The formula used to calculate the data in the prediction data set to obtain the sum of the corresponding probabilities of causing the disease includes: Use the following formula to analyze and calculate the weight value of the data in the prediction data set: Among them, G represents the weight value of the data, r represents the type of disease caused by the data, and e j Represents the weight value of the data in category j; Prioritize the data in the prediction data set according to the weight value to obtain a corresponding prediction ranking result; The following formula is used to select the target number of data in descending order based on the prediction ranking results to calculate the sum of the probabilities of the data in the prediction data set causing the disease: Among them, G x It represents the sum of the probabilities of the data in the prediction data set causing the disease, P y represents the probability value of the target data causing the disease, and m represents the number of data.

7. The system according to claim 1, characterized in that The system further comprises: An alarm module is used to judge the physiological characteristic data based on a preset range to obtain a corresponding judgment result; when the judgment result exceeds the corresponding preset range, an alarm message is issued; The nursing advice module is used to generate targeted nursing advice based on the predicted disease trend; the nursing advice includes dietary advice, sleep reminders, exercise advice, and psychological adjustment advice.

8. A sleep care method for patients with respiratory nephropathy based on intelligent monitoring, characterized in that: The method comprises: Real-time monitoring of the patient's physiological parameters and sleep behavior during sleep, obtaining the patient's physiological characteristic data at each monitoring time point and sleep behavior data in each monitoring time period; the physiological characteristic data includes at least one of blood pressure value, body temperature value, blood oxygen value, heart rate value and respiratory rate; the sleep behavior data includes at least one of the number of tossing, number of awakening, displacement and body posture maintenance time; Analyze and evaluate the patient's sleep quality based on the physiological characteristic data and the sleep behavior data to obtain a sleep evaluation result; Real-time monitoring of environmental parameters of the patient's sleeping environment to obtain environmental characteristic data corresponding to the patient's sleeping environment; the environmental parameters include at least one of indoor air quality, lighting conditions, humidity conditions, temperature conditions and noise conditions; Based on the environmental characteristic data, physiological characteristic data and sleep behavior data, the patient's condition change is predicted using a trained prediction model to obtain a predicted condition trend; An analysis is performed based on the sleep assessment result and the predicted disease trend to obtain an environmental adjustment plan suitable for the patient's sleep; the environmental adjustment plan is used to indicate the adjustment of the environmental parameters.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the system or method according to any one of claims 1 to 8 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the system or method according to any one of claims 1 to 8 are implemented.

Images