Daily monitoring and management system for radiotherapy patients

Abstract

The invention discloses a radiotherapy patient daily monitoring management system, the system comprises a hardware system and a software system, the hardware system comprises an identity recognition module, a temperature heart rate blood oxygen health monitoring module and an information display storage and broadcast module, and the hardware system is used for collecting and storing current physiological data of a patient before each radiotherapy; the software system comprises a risk prediction module, and the risk prediction module captures the change rule of the physiological data of the radiotherapy patient obtained in the hardware system, obtains a prediction result, judges whether the radiotherapy patient is in an adverse reaction risk or not, accurately obtains the current physiological index data of the radiotherapy patient through the cooperative work of multiple modules, and carries out the prediction of the current physiological index data. And through the fitting of the risk prediction model, whether the radiotherapy patient may be in the adverse reaction in the future is predicted, so that more personalized and accurate treatment suggestions are provided for the patient, and the safety and effectiveness of radiotherapy are improved.

Description

Technical Field

[0001] The invention relates to the field of medical monitoring, and in particular to a daily monitoring and management system for radiotherapy patients. Background Art

[0002] As one of the main means of cancer treatment, radiotherapy plays an increasingly important role in current clinical medicine with the increase in cancer incidence and the advancement of radiotherapy technology. During radiotherapy, the collected data such as heart rate, heart rate waveform, temperature and blood oxygen saturation are closely related to the patient's physiological health status during radiotherapy. In terms of heart rate, its changes are related to cardiac function indicators such as ejection fraction (EF) and myocardial enzyme spectrum. Radiotherapy may affect cardiac function. When EF decreases or myocardial enzyme spectrum is abnormal, it is often accompanied by changes in heart rate. An increase in heart rate may indicate an increase in cardiac burden. At the same time, autonomic nervous function indicators such as heart rate variability (HRV) and blood pressure fluctuations also interact with heart rate. When autonomic nervous function imbalance caused by radiotherapy is manifested as decreased HRV and abnormal blood pressure, heart rate will also change accordingly. In terms of blood oxygen saturation, it is closely related to the lung function indicators arterial oxygen partial pressure and pulmonary diffusion function. Lung damage such as radiation pneumonia caused by radiotherapy will reduce arterial oxygen partial pressure and lung diffusion function, resulting in decreased blood oxygen saturation. When blood oxygen carrying capacity indicators such as hemoglobin (Hb) content and hematocrit (Hct) are abnormal, blood oxygen levels will also be affected. Changes in the blood system such as anemia caused by radiotherapy can reduce blood oxygen saturation by affecting Hb and Hct. In addition, inflammatory indicators such as cytokines such as C-reactive protein (CRP) and interleukin-6 (IL-6) increase when radiotherapy triggers an inflammatory response, which will increase the burden on the heart and lungs and affect heart rate and blood oxygen. Metabolic indicators such as blood sugar level fluctuations and lactate level changes are also related to heart rate and blood oxygen. Radiotherapy affects metabolism and causes abnormal blood sugar, which can cause heart rate changes, while increased lactate levels during tissue hypoxia are associated with decreased blood oxygen saturation and heart rate changes. Comprehensive monitoring of these data helps to comprehensively assess the physiological health status of radiotherapy patients, promptly detect and deal with radiotherapy complications, and ensure treatment effectiveness and patient safety. Traditional identity verification of patients before entering the machine room relies on manual confirmation by treatment technicians, which is not only inefficient but also prone to errors. In addition, during the radiotherapy cycle, there is a lack of attention to the patient's real-time physiological status on that day to assess whether the patient has a fever, low blood oxygen, etc. that makes him or her unsuitable for treatment. Summary of the invention

[0003] The purpose of the present invention is to provide a daily monitoring and management system for radiotherapy patients that can work in multiple modules in a collaborative manner, accurately acquire physiological indicator data of radiotherapy patients, and timely predict the risks of radiotherapy patients.

[0004] In order to solve the above technical problems, the present invention adopts the following technical solutions: including a hardware system and a software system, the hardware system includes an identity recognition module, a temperature, heart rate and blood oxygen health monitoring module, an information display storage and broadcast module, the hardware system is used to collect and store the patient's current physiological data before each radiotherapy, and the software system includes a risk prediction module, the risk prediction module captures the change law of the physiological data of the radiotherapy patient obtained in the hardware system and obtains the prediction result, and determines whether the radiotherapy patient is at risk of adverse reactions. The risk prediction module includes the following steps: Step 1: Data collection and organization: Collect the physiological index data of radiotherapy patients obtained by the hardware system after n measurements before radiotherapy, including heart rate, heart rate waveform, blood oxygen saturation, and body temperature, and organize the obtained physiological index data into time series data. ,in Represents the data of the i-th measurement; Step 2: Stationarity test: Use the unit root test to check the stationarity of the data. The test statistic is expressed as ,in is the autoregressive coefficient, is its standard error, according to the test statistic The critical value of the 5% significance level is used to compare and judge whether the data is stable. When the critical value is less than 5% significance level, the data is non-stationary and has unit root. After d-order difference, it becomes a stationary series. When the critical value is greater than or equal to the 5% significance level, the data is stable, and after testing and differentiation, the data of the stable sequence is finally obtained; Step 3: Determine the order of the prediction model: Determine the order (p, d, q) of the data model by observing the autocorrelation function and partial autocorrelation function graphs, where p is the autoregressive order, d is the difference order determined in step 2, and q is the moving average order; Step 4: Fitting the prediction model: Construct a prediction model based on the order (p, d, q) of the data model determined in step 3 and use the maximum likelihood estimation method to fit the time series data in step 1 to finally obtain the model parameters. The expression of the prediction model is: , where B is the lag operator, is a white noise sequence, , ; Step 5: Prediction and dynamic threshold calculation: Use the prediction model fitted in step 4 to predict the physiological index values ​​of the patient during the next radiotherapy and obtain the predicted value , using the quantile of the standard normal distribution to calculate the confidence interval as the dynamic threshold range, for a 95% confidence interval, the lower threshold , upper threshold ,in is the 97.5% quantile of the standard distribution, and is calculated as 1.96. is an estimate of the standard deviation of the residuals, The expression is ,in is the residual of the i-th day, is the residual mean; Step 6: Update the model and dynamic threshold according to the newly acquired time series data in step 1.

[0005] Furthermore, after the heart rate waveform is collected in step 1, it is filtered to obtain stable waveform data for the day, so that the heart rate is calculated by the number of peaks in a period of time, and finally the HRV, which interacts with the heart rate, is obtained, which is the heart rate variability index. The heart rate variability index includes SDNN, which is the standard deviation of all normal sinus beat intervals, and RMSSD, which is the root mean square of the difference between adjacent normal sinus beat intervals. The standard deviation expression of all normal sinus beat intervals is: ,in , is the ith normal sinus beat interval, N is the total number of heart beat intervals, and the root mean square expression of the difference between adjacent normal sinus beat intervals is: , the RR interval is the time interval between two heartbeats, and the difference between adjacent RR intervals is .

[0006] Furthermore, wavelet analysis is used to perform spectrum decomposition on the heart rate waveform obtained in step 1, and the heart rate waveform collected on that day is Perform discrete wavelet transform and assume is a wavelet function, where j represents the scale and k represents the position. The discrete wavelet transform coefficients of the heart rate waveform signal RR are Through inner product calculation, the expression of discrete wavelet transform coefficient is , let the wavelet coefficients at scale j be The corresponding frequency range is , then the expression of the power spectral density function is ,in is the frequency bandwidth corresponding to scale j, is the center frequency corresponding to this scale, is the Dirac function, when hour, ,when hour, , wavelet coefficients The energy reflects the energy distribution of the signal under scale j, and its calculation formula is: , calculate and obtain the low frequency power LF in the frequency range of 0.04-0.15Hz and the high frequency power HF in the frequency range of 0.15-0.4Hz, the low frequency power , the high frequency power .

[0007] Furthermore, an interpolation algorithm is used to supplement the missing data in step 1 to ensure data continuity, and the first-order difference is used to obtain stable data when the data is not stable.

[0008] Furthermore, the identity recognition module includes a Gravity HUSKYLENS face recognition module and a clock module. The HUSKYLENS face recognition module has a built-in control chip and pre-stores the patient's facial ID, judgment conditions, and processing procedures. It identifies the current patient on the day when the patient's physiological index data is measured, and records the patient's data for the day after the physiological index data measurement is completed. The clock module records the time node when each patient completes the measurement of the physiological index data. The temperature, heart rate, and blood oxygen health monitoring module includes an MLX90614 infrared temperature measurement module and a MAX30102 heart rate and blood oxygen module. The MLX90614 infrared temperature measurement module accurately obtains the current body temperature data of the current patient, and the MAX30102 heart rate and blood oxygen module accurately obtains the current heart rate and blood oxygen saturation data of the current patient. The information display, storage, and broadcast module includes a serial port screen display module, an MP3 voice broadcast module, and an SD card storage module. The serial port screen display module cooperates with the MP3 voice broadcast module to display and broadcast the current patient's basic information, the treatment room, the number of treatments, and the physiological index data in real time. The SD card storage module stores the patient's physiological index data obtained by the temperature, heart rate, and blood oxygen health monitoring module.

[0009] The daily monitoring and management system of the present invention has the following advantages: the technical solution of the present invention quickly and efficiently obtains the current physiological indicator data corresponding to the radiotherapy patient through the coordinated cooperation of multiple modules of the hardware system and the software system, and constructs and fits a prediction model of the risks that the radiotherapy patient may face after radiotherapy by processing the obtained data, so that the model captures the change law of the physiological indicator data of the radiotherapy patient during the radiotherapy process, and predicts and judges the trend of the physiological indicator data through the monitoring of the physiological indicator data, so that the attending physician can comprehensively evaluate the labor-saving health status of the radiotherapy patient, warn and treat the radiotherapy complications that may occur in the individual radiotherapy patient, and ensure the radiotherapy effect and radiotherapy safety of the patient during the radiotherapy process. On the other hand, the updatability of the prediction model and the dynamic threshold value also further improves the accuracy of the model prediction, avoiding the problem that some existing monitoring methods cannot be dynamically updated in time, resulting in inaccurate prediction results or even prediction errors. The dynamically updated prediction model and dynamic threshold value make the clinical decision of the attending physician more targeted, and the safety of the subsequent treatment process of the radiotherapy patient is also greatly improved, which is convenient for the treatment management of the entire radiotherapy process of the radiotherapy patient. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 It is a simplified flow chart of the daily monitoring and management system for radiotherapy patients.

[0011] Figure 2 It is the monitoring of a patient's actual heart rate data as well as predicted values ​​and dynamic thresholds during radiotherapy.

[0012] Figure 3 It is the monitoring of a patient's actual blood oxygen saturation data, predicted values ​​and dynamic thresholds during radiotherapy.

[0013] Figure 4 It is the monitoring of a patient's actual temperature data as well as predicted values ​​and dynamic thresholds during radiotherapy.

[0014] Figure 5 It is the residual QQ plot of the heart rate data of a patient in actual application.

[0015] Figure 6 It is the residual QQ diagram of the blood oxygen saturation data of a patient in actual application.

[0016] Figure 7 It is the residual QQ plot of the temperature data of a patient in actual application. DETAILED DESCRIPTION

[0017] In order to make the technical means, innovative features and functions implemented by the present invention easy to understand, the present invention will be further described below.

[0018] like Figure 1-7As shown, in an embodiment of the daily monitoring and management system for radiotherapy patients of the present invention, a hardware system and a software system are included. The hardware system includes an identity recognition module, a temperature, heart rate, and blood oxygen health monitoring module, and an information display storage and broadcast module. The hardware system is used to collect and store the current physiological data of the patient before each radiotherapy. The software system includes a risk prediction module. The risk prediction module captures the change pattern of the physiological data of the radiotherapy patient obtained in the hardware system and obtains the prediction result, and determines whether the radiotherapy patient is at risk of adverse reactions. The risk prediction module includes the following steps: Step 1: Data collection and organization: Collect the physiological index data of radiotherapy patients obtained by the hardware system after n measurements before radiotherapy, including heart rate, heart rate waveform, blood oxygen saturation, and body temperature, and organize the obtained physiological index data into time series data. In actual applications, some data may be missing. In this case, an interpolation algorithm is used to supplement the missing data to ensure data continuity. Represents the data of the i-th measurement; Step 2: Stationarity test: Use the unit root test to check the stationarity of the data. The test statistic is expressed as ,in is the autoregressive coefficient, is its standard error, according to the test statistic The critical value of the 5% significance level is used to compare and judge whether the data is stable. When the critical value is less than 5% significance level, the data is non-stationary and has unit root. After d-order difference, it becomes a stationary series. When the critical value is greater than or equal to the 5% significance level, the data is stable, and after testing and differentiation, the data of the stable sequence is finally obtained; Step 3: Determine the order of the prediction model: Determine the order (p, d, q) of the data model by observing the autocorrelation function and partial autocorrelation function graphs, where p is the autoregressive order, d is the difference order determined in step 2, and q is the moving average order; In actual application, the order (p, d, q) of the data model is generally determined by (1, 0, 1) and the subsequent model is constructed. When the commonly used order (1, 0, 1) cannot meet the application requirements, the required order can be determined in step 3 according to the actual requirements to construct the subsequent model. Step 4: Fitting the prediction model: Construct a prediction model based on the order (p, d, q) of the data model determined in step 3 and use the maximum likelihood estimation method to fit the time series data in step 1 to finally obtain the model parameters. The expression of the prediction model is: , where B is the lag operator, is a white noise sequence, , ; Step 5: Prediction and dynamic threshold calculation: Use the prediction model fitted in step 4 to predict the physiological index values ​​of the patient during the next radiotherapy and obtain the predicted value , using the quantile of the standard normal distribution to calculate the confidence interval as the dynamic threshold range, for a 95% confidence interval, the lower threshold , upper threshold ,in is the 97.5% quantile of the standard distribution, and is calculated as 1.96. is an estimate of the standard deviation of the residuals, The expression is ,in is the residual of the i-th day, is the residual mean; In this step, we can draw a QQ graph, i.e., a Quantile-Quantile graph, to test whether the residuals calculated in step 5 obey the normal distribution. We can draw the quantiles of the residuals and the quantiles of the theoretical normal distribution on the graph. Assuming that the residuals obey the normal distribution, the quantiles of the residuals should be roughly distributed around the quantiles of the theoretical normal distribution. On the contrary, if the quantiles of most residuals are significantly far away from the quantiles of the theoretical normal distribution, we can conclude that the residuals do not obey the normal distribution. Figure 5-7 As shown, Figure 5-7 They are the residual QQ graphs of the heart rate, blood oxygen saturation, and temperature data of a patient in actual application. It can be observed that the residual quantiles of the heart rate, blood oxygen saturation, and temperature data of this patient are basically distributed around the theoretical quantiles. It can be considered that the prediction model obtained by fitting in step 4 under the actual application state is effective and reliable, and its reliability and effectiveness have been verified and guaranteed; Step 6: Update the model and dynamic threshold according to the newly acquired time series data in step 1.

[0019] During radiotherapy, each frequency segment of the spectrum characteristics represents different physiological information. Under normal circumstances, the low frequency band (LF, 0.04 - 0.15Hz) mainly reflects the joint regulation of the sympathetic and parasympathetic nerves, and the high frequency band (HF, 0.15 - 0.4Hz) is mainly related to the heart rate fluctuations related to breathing. During radiotherapy, if the energy of the low frequency band increases, it may mean that the excitability of the sympathetic nerves is enhanced and the burden on the heart is increased; if the energy of the high frequency band decreases, it may mean that the regulatory effect of breathing on the heart rate is weakened and the coordination of cardiopulmonary function is reduced. By analyzing these spectrum changes, potential cardiopulmonary function abnormalities can be discovered before the patient has obvious symptoms, providing a basis for early intervention. In practical applications, after the heart rate waveform acquisition in step 1 is obtained, filtering processing can be performed to obtain stable waveform data for the day, so that the heart rate can be calculated by the number of peaks within a period of time, and finally HRV, which interacts with the heart rate, is obtained, that is, the heart rate variability index. The heart rate variability index includes SDNN, that is, the standard deviation of all normal sinus beat intervals, and RMSSD, that is, the root mean square of the difference between adjacent normal sinus beat intervals. The standard deviation of all normal sinus beat intervals is expressed as ,in , is the ith normal sinus beat interval, N is the total number of heart beat intervals, and the root mean square expression of the difference between adjacent normal sinus beat intervals is: , the RR interval is the time interval between two heartbeats, and the difference between adjacent RR intervals is On this basis, wavelet analysis is used to perform spectrum decomposition on the heart rate waveform obtained in step 1, and the heart rate waveform collected on that day is Perform discrete wavelet transform and assume is a wavelet function, where j represents the scale and k represents the position. The discrete wavelet transform coefficients of the heart rate waveform signal RR are Through inner product calculation, the expression of discrete wavelet transform coefficient is , let the wavelet coefficients at scale j be The corresponding frequency range is , then the expression of the power spectral density function is ,in is the frequency bandwidth corresponding to scale j, is the center frequency corresponding to this scale, is the Dirac function, when hour, ,when hour, , wavelet coefficients The energy reflects the energy distribution of the signal under scale j, and its calculation formula is: , calculate and obtain the low frequency power LF in the frequency range of 0.04 - 0.15Hz and the high frequency power HF in the frequency range of 0.15- 0.4Hz, the low frequency power , the high frequency power In practical applications, the change of scale j can be observed If the value of If it shows an upward trend on some scales, it can be considered that the energy in the corresponding frequency range is increasing. If a downward trend is observed on some scales, it can be considered that the energy in the corresponding frequency range is decreasing. During radiotherapy, if the energy in the scale related to low frequency is If the energy of the low-frequency part increases gradually, it can be considered that the energy of the low-frequency part is increasing, which may reflect physiological changes such as increased excitability of the sympathetic nerves. If it decreases gradually, it can be considered that the energy of the high-frequency part is decreasing, which may reflect the weakening of the regulatory effect of breathing on heart rate.

[0020] Similarly, in the actual radiotherapy process, if it is found that the patient's low-frequency energy begins to gradually increase from the 8th fraction after the start of radiotherapy, this may indicate that the patient's sympathetic nerve excitability is enhanced. Combined with the gradual increase in the patient's heart rate exceeding the dynamic threshold, it further indicates that the patient's heart burden is aggravated, and medical staff can give corresponding intervention measures accordingly. If it is found that the patient's high-frequency energy is reduced, for example, from the normal energy value of 0.3 Hz before radiotherapy to 0.15 Hz during radiotherapy and continues to decline, this may indicate that the patient's breathing has weakened in regulating the heart rate. At this time, medical staff can check the patient's respiratory condition, assess whether there is airway obstruction or respiratory function affected by radiotherapy, and pay close attention to whether there are signs of pulmonary complications such as radiation pneumonia, so as to timely warn and discover possible problems of patients before or in the early stage of radiotherapy discomfort and radiotherapy complications, and make targeted adjustments in treatment methods in a timely manner for discomfort and complications, so as to minimize the impact on the patient after radiotherapy, and provide more personalized and targeted precision treatment suggestions for prevention.

[0021] In the existing radiotherapy process, the identity verification of radiotherapy patients before entering the machine room depends on the manual confirmation of the treatment technicians, which is not only inefficient but also prone to errors. At the same time, during the radiotherapy cycle, the radiotherapy treatment process lacks attention to the patient's real-time physiological state on the day, so it is impossible to judge whether the current radiotherapy patient is suitable for the current round of radiotherapy by whether the radiotherapy patient has a fever, low blood oxygen and other conditions that are not suitable for treatment. In one embodiment of the present invention, the identity recognition module includes a Gravity HUSKYLENS face recognition module and a clock module. The Gravity The HUSKYLENS face recognition module has a built-in control chip and pre-stores the patient's facial ID, judgment conditions, and processing procedures. It identifies the current patient on the day when the patient's physiological index data is measured, and records the patient's data for the day after the physiological index data is measured. The clock module records the time node when each patient completes the measurement of physiological index data. The temperature, heart rate, and blood oxygen health monitoring module includes an MLX90614 infrared temperature measurement module and a MAX30102 heart rate and blood oxygen module. The MLX90614 infrared temperature measurement module accurately obtains the current body temperature data of the current patient, and the MAX30102 heart rate and blood oxygen module accurately obtains the current heart rate and blood oxygen saturation data of the current patient. The information display storage and broadcast module includes a serial port screen display The serial port screen display module cooperates with the MP3 voice broadcast module to display and broadcast the current patient's basic information, the treatment room, the number of treatments, and the physiological index data in real time. The SD card storage module stores the patient's physiological index data obtained by the temperature, heart rate, and blood oxygen health monitoring module. Through the coordinated operation of the identity recognition module, the temperature, heart rate, and blood oxygen health monitoring module, and the information display storage and broadcast module, the identity of the current radiotherapy patient is accurately identified, the real-time physiological index data of the radiotherapy patient is monitored in real time, and the real-time health data is fed back to the medical staff to better manage the patient's treatment process and avoid the failure to obtain the current physiological state of the radiotherapy patient during the radiotherapy process, thereby exposing the radiotherapy patient to unpredictable radiotherapy risks.

[0022] Although the present invention has been disclosed as above in terms of specific embodiments, they are not intended to limit the present invention. Any technician in this field may make slight changes and modifications without departing from the spirit and scope of the present invention. Therefore, the scope of protection of the present invention shall be determined by the scope of the attached claims.

Claims

1. A daily monitoring and management system for radiotherapy patients, characterized by: It includes a hardware system and a software system. The hardware system includes an identity recognition module, a temperature, heart rate, and blood oxygen health monitoring module, and an information display storage and broadcast module. The hardware system is used to collect and store the patient's current physiological data before each radiotherapy. The software system includes a risk prediction module. The risk prediction module captures the change pattern of the physiological data of the radiotherapy patient obtained in the hardware system and obtains the prediction result to determine whether the radiotherapy patient is at risk of adverse reactions. The risk prediction module includes the following steps: Step 1: Data collection and organization: Collect the physiological index data of radiotherapy patients obtained by the hardware system after n measurements before radiotherapy, including heart rate, heart rate waveform, blood oxygen saturation, and body temperature, and organize the obtained physiological index data into time series data. ,in Represents the data of the i-th measurement; Step 2: Stationarity test: Use the unit root test to check the stationarity of the data. The test statistic is expressed as ,in is the autoregressive coefficient, is its standard error, according to the test statistic The critical value of the 5% significance level is used to compare and judge whether the data is stable. When the critical value is less than 5% significance level, the data is non-stationary and has unit root. After d-order difference, it becomes a stationary series. When the critical value is greater than or equal to the 5% significance level, the data is stable, and after testing and differentiation, the data of the stable sequence is finally obtained; Step 3: Determine the order of the prediction model: Determine the order (p, d, q) of the data model by observing the autocorrelation function and partial autocorrelation function graphs, where p is the autoregressive order, d is the difference order determined in step 2, and q is the moving average order; Step 4: Fitting the prediction model: Construct a prediction model based on the order (p, d, q) of the data model determined in step 3 and use the maximum likelihood estimation method to fit the time series data in step 1 to finally obtain the model parameters. The expression of the prediction model is: , where B is the lag operator, is a white noise sequence, , ; Step 5: Prediction and dynamic threshold calculation: Use the prediction model fitted in step 4 to predict the physiological index values ​​of the patient during the next radiotherapy and obtain the predicted value , using the quantile of the standard normal distribution to calculate the confidence interval as the dynamic threshold range, for a 95% confidence interval, the lower threshold , upper threshold ,in is the 97.5% quantile of the standard distribution, and is calculated as 1.

96. is an estimate of the standard deviation of the residuals, The expression is ,in is the residual of the i-th day, is the residual mean; Step 6: Update the model and dynamic threshold according to the newly acquired time series data in step 1.

2. A daily monitoring and management system for radiotherapy patients according to claim 1, characterized in that: After the heart rate waveform is collected in step 1, it is filtered to obtain stable waveform data for the day, so as to calculate the heart rate through the number of peaks in a period of time, and finally obtain HRV, which interacts with the heart rate, i.e., the heart rate variability index. The heart rate variability index includes SDNN, i.e., the standard deviation of all normal sinus beat intervals, and RMSSD, i.e., the root mean square of the difference between adjacent normal sinus beat intervals. The standard deviation of all normal sinus beat intervals is expressed as ,in , is the ith normal sinus beat interval, N is the total number of heart beat intervals, and the root mean square expression of the difference between adjacent normal sinus beat intervals is: , the RR interval is the time interval between two heartbeats, and the difference between adjacent RR intervals is .

3. A daily monitoring and management system for radiotherapy patients according to claim 2, characterized in that: Use wavelet analysis to perform spectrum decomposition on the heart rate waveform obtained in step 1, and analyze the heart rate waveform collected on that day. Perform discrete wavelet transform and assume is a wavelet function, where j represents the scale and k represents the position. The discrete wavelet transform coefficients of the heart rate waveform signal RR are Through inner product calculation, the expression of discrete wavelet transform coefficient is , let the wavelet coefficients at scale j be The corresponding frequency range is , then the expression of the power spectral density function is ,in is the frequency bandwidth corresponding to scale j, is the center frequency corresponding to this scale, is the Dirac function, when hour, ,when hour, , wavelet coefficients The energy reflects the energy distribution of the signal under scale j, and its calculation formula is: , calculate and obtain the low frequency power LF in the frequency range of 0.04-0.15Hz and the high frequency power HF in the frequency range of 0.15-0.4Hz, the low frequency power , the high frequency power .

4. A daily monitoring and management system for radiotherapy patients according to claim 1, 2 or 3, characterized in that: Use the interpolation algorithm to supplement the missing data in step 1 to ensure data continuity, and use the first-order difference to obtain stable data when the data is not stable.

5. A daily monitoring and management system for radiotherapy patients according to claim 1, 2 or 3, characterized in that: The identity recognition module includes a Gravity HUSKYLENS face recognition module and a clock module. The HUSKYLENS face recognition module has a built-in control chip and pre-stores the patient's facial ID, judgment conditions, and processing procedures. It identifies the current patient on the day when the patient's physiological index data is measured, and records the patient's data for the day after the physiological index data measurement is completed. The clock module records the time node when each patient completes the measurement of the physiological index data. The temperature, heart rate, and blood oxygen health monitoring module includes an MLX90614 infrared temperature measurement module and a MAX30102 heart rate and blood oxygen module. The MLX90614 infrared temperature measurement module accurately obtains the current body temperature data of the current patient, and the MAX30102 heart rate and blood oxygen module accurately obtains the current heart rate and blood oxygen saturation data of the current patient. The information display, storage, and broadcast module includes a serial port screen display module, an MP3 voice broadcast module, and an SD card storage module. The serial port screen display module cooperates with the MP3 voice broadcast module to display and broadcast the current patient's basic information, the treatment room, the number of treatments, and the physiological index data in real time. The SD card storage module stores the patient's physiological index data obtained by the temperature, heart rate, and blood oxygen health monitoring module.

6. A daily monitoring and management system for radiotherapy patients according to claim 4, characterized in that: The identity recognition module includes a Gravity HUSKYLENS face recognition module and a clock module. The HUSKYLENS face recognition module has a built-in control chip and pre-stores the patient's facial ID, judgment conditions, and processing procedures. It identifies the current patient on the day when the patient's physiological index data is measured, and records the patient's data for the day after the physiological index data measurement is completed. The clock module records the time node when each patient completes the measurement of the physiological index data. The temperature, heart rate, and blood oxygen health monitoring module includes an MLX90614 infrared temperature measurement module and a MAX30102 heart rate and blood oxygen module. The MLX90614 infrared temperature measurement module accurately obtains the current body temperature data of the current patient, and the MAX30102 heart rate and blood oxygen module accurately obtains the current heart rate and blood oxygen saturation data of the current patient. The information display, storage, and broadcast module includes a serial port screen display module, an MP3 voice broadcast module, and an SD card storage module. The serial port screen display module cooperates with the MP3 voice broadcast module to display and broadcast the current patient's basic information, the treatment room, the number of treatments, and the physiological index data in real time. The SD card storage module stores the patient's physiological index data obtained by the temperature, heart rate, and blood oxygen health monitoring module.

Images