Urologic surgery postoperative rehabilitation effect monitoring method

Abstract

The invention relates to the field of medical care informatics, in particular to a urinary surgery postoperative rehabilitation effect monitoring method. The method comprises the steps that physiological data of a patient are collected in real time and preprocessed, and original signals are generated; performing time domain and frequency domain enhancement processing on the original signal to obtain a time domain enhanced signal and a frequency domain enhanced signal; and combining the time domain enhanced signal and the frequency domain enhanced signal, dynamically adjusting the composite signal based on the change amplitude of the composite signal, predicting the rehabilitation effect based on the obtained weighted composite signal, and generating personalized intervention suggestions to guide the rehabilitation process of the urinary surgery postoperative patient. The problems that a traditional postoperative rehabilitation monitoring method neglects comprehensive analysis on different signals and cannot flexibly cope with changes of all time points in the rehabilitation process of a patient, and the rehabilitation effect prediction accuracy is affected are solved; based on fixed rules or experience, personalized treatment scheme adjustment is lacked, and the optimal rehabilitation effect cannot be achieved.

Description

Technical Field

[0001] The present invention relates to the field of medical care informatics, and in particular to a method for monitoring postoperative rehabilitation effects in urology surgery. Background Art

[0002] After urological surgery, the patient's recovery process is often accompanied by varying degrees of risk of complications, such as postoperative bleeding, infection, urinary retention, and bladder dysfunction. If these complications are not detected and effectively intervened in a timely manner, they may prolong recovery time and even lead to more serious consequences. Therefore, timely and accurate monitoring of the patient's recovery status, early detection of potential complications, and implementation of targeted interventions have become key requirements in postoperative urological management.

[0003] Traditional postoperative rehabilitation monitoring methods rely on the physician's clinical judgment and the patient's subjective feedback, often failing to provide comprehensive, real-time health status data, resulting in potential issues not being promptly identified during the rehabilitation process. Furthermore, traditional postoperative rehabilitation monitoring methods suffer from common problems such as single signals, insufficient data analysis capabilities, and imperfect early warning mechanisms, making them difficult to meet complex clinical needs. With the advancement of intelligent medical technology, monitoring systems based on physiological signals have achieved remarkable application results in the medical field, especially in the fields of remote monitoring, chronic disease management, and postoperative rehabilitation. Data-driven intelligent monitoring methods have gradually become an important development direction.

[0004] Traditional postoperative rehabilitation monitoring methods have the following technical problems: they ignore the comprehensive analysis of different signals and are unable to effectively extract key information in the patient's rehabilitation process, resulting in weak predictive ability of rehabilitation progress and inability to flexibly respond to changes at various time points in the patient's rehabilitation process, affecting the accurate prediction of rehabilitation effects; traditional intervention recommendation methods are often based on fixed rules or experience, lack personalized treatment plan adjustments, and cannot be adaptively adjusted according to the patient's actual rehabilitation progress, so they may not achieve the best rehabilitation effect. Summary of the Invention

[0005] The present invention provides a method for monitoring the postoperative rehabilitation effect of urology surgery to solve the problem that traditional postoperative rehabilitation monitoring methods ignore the comprehensive analysis of different signals and cannot effectively extract key information in the patient's rehabilitation process, resulting in weak prediction ability of rehabilitation progress and inability to flexibly respond to changes at various time points in the patient's rehabilitation process, affecting the accurate prediction of rehabilitation effects; traditional intervention recommendation methods are often based on fixed rules or experience, lack personalized treatment plan adjustments, and cannot be adaptively adjusted according to the patient's actual rehabilitation progress, and therefore may not achieve the best rehabilitation effect.

[0006] The method for monitoring the postoperative rehabilitation effect of urology surgery of the present invention specifically includes the following technical solutions: The method for monitoring the rehabilitation effect after urological surgery includes the following steps: S1. Collecting the patient's physiological data in real time and performing preprocessing to generate an original signal; performing time domain and frequency domain enhancement processing on the original signal to obtain a time domain enhanced signal and a frequency domain enhanced signal; and combining the time domain enhanced signal and the frequency domain enhanced signal to obtain a composite signal; S2. Based on the change amplitude of the composite signal, the composite signal is dynamically adjusted to obtain a weighted composite signal; based on the weighted composite signal, the rehabilitation effect is predicted to obtain a predicted value of the rehabilitation effect, and personalized intervention suggestions are generated to guide the rehabilitation process of patients after urological surgery.

[0007] Preferably, the S1 specifically includes: Based on the original signal, the local signal strength and the global signal strength are calculated; the adjustment factors of the high-frequency components of the original signal and the adjustment factors of the low-frequency components of the original signal are introduced to perform nonlinear transformation on the original signal to enhance the time domain characteristics of the original signal; and the adjustment factors are introduced to control the ratio of the local signal strength to the global signal strength to obtain a time domain enhanced signal.

[0008] Preferably, the S1 specifically includes: The original signal is converted from the time domain to the frequency domain through Fourier transform, the frequency characteristics of the original signal are extracted, and the different frequency components are weighted to obtain the frequency domain enhanced signal.

[0009] Preferably, the S1 specifically includes: The time domain enhanced signal and the frequency domain enhanced signal are compounded by element-wise multiplication to obtain a composite signal.

[0010] Preferably, the S2 specifically includes: The change amount of the composite signal is obtained by calculating the change amplitude of the composite signal at the current moment and the previous moment, and the composite signal change amount is accumulated to calculate the dynamic weighting factor.

[0011] Preferably, the S2 specifically includes: Based on the dynamic weighting factor, the composite signal is dynamically adjusted to obtain a weighted composite signal.

[0012] Preferably, the S2 specifically includes: Based on the weighted composite signal, a periodic fluctuation adjustment factor is introduced. Combined with the periodic characteristics of the signal, the patient's rehabilitation progress is predicted and the predicted value of the rehabilitation effect is obtained.

[0013] Preferably, the S2 specifically includes: The patient's basic rehabilitation status value is introduced, the deviation between the predicted rehabilitation effect value and the patient's basic rehabilitation status value is calculated, and personalized intervention suggestions are generated: when the predicted rehabilitation effect value is lower than the patient's basic rehabilitation status value, it means that the intervention intensity needs to be increased; when the predicted rehabilitation effect value is higher than the patient's basic rehabilitation status value, it means that the intervention intensity needs to be reduced.

[0014] The beneficial effects of the technical solution of the present invention are: 1. The present invention calculates the change amplitude of the composite signal and adjusts the dynamic weighting factor of the composite signal. According to the timeliness and sensitivity of the change amplitude of the composite signal, the rehabilitation effect monitoring method is ensured to reflect the real changes of the composite signal at different time points. By adjusting the dynamic weighting factor, the rehabilitation effect monitoring method can more accurately capture the key dynamic changes in the patient's rehabilitation process, thereby improving the accuracy and sensitivity of rehabilitation effect prediction.

[0015] 2. The present invention can accurately predict the patient's rehabilitation progress through weighted composite signals, and generate personalized intervention recommendations based on the deviation between the predicted value of the rehabilitation effect and the patient's basic rehabilitation status value; when the rehabilitation progress is slow, enhanced intervention intensity is provided; and when the rehabilitation progress is fast, the intervention intensity is appropriately reduced to ensure the personalization and effectiveness of the treatment plan.

[0016] 3. Through accurate predictions of rehabilitation effects and real-time personalized intervention recommendations, it provides doctors with scientific data support and decision-making basis, which can effectively guide patients' postoperative rehabilitation process; doctors can understand the dynamic changes of patients' rehabilitation in real time, adjust treatment strategies, and ensure that every step of patients' rehabilitation is carried out under scientific guidance. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a flow chart of the method for monitoring the postoperative rehabilitation effect of urology surgery according to the present invention. DETAILED DESCRIPTION

[0018] In order to further illustrate the technical means and effects adopted by the present invention to achieve the predetermined purpose of the invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0019] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0020] The specific scheme of the method for monitoring the postoperative rehabilitation effect of urology surgery provided by the present invention is described in detail below with reference to the accompanying drawings.

[0021] Refer to the attached Figure 1 , which shows a flow chart of a method for monitoring the postoperative rehabilitation effect of urology surgery provided by an embodiment of the present invention, the method comprising the following steps: S1. Collecting the patient's physiological data in real time and performing preprocessing to generate an original signal; performing time domain and frequency domain enhancement processing on the original signal to obtain a time domain enhanced signal and a frequency domain enhanced signal; and combining the time domain enhanced signal and the frequency domain enhanced signal to obtain a composite signal; The patient's physiological data (such as electrocardiogram (ECG), blood oxygen saturation (SpO2), respiratory rate, and body temperature) are collected in real time through multi-channel physiological monitoring equipment and preprocessed to generate raw signals. The preprocessing process includes filtering, denoising, and standardization. The specific implementation process is as follows: Select appropriate filter types (including low-pass filters, high-pass filters, and band-pass filters) based on different physiological data characteristics, filter the physiological data, and obtain filtered physiological data. For example, for electrocardiogram signals, band-pass filters are usually used to remove power frequency noise and low-frequency drift, thereby removing environmental noise, equipment errors, and unnecessary high-frequency interference signals, making the signal more stable and easier to analyze. Then, the filtered physiological data is denoised through algorithms such as wavelet transform and Kalman filtering to further remove weak noise interference, improve signal quality, and obtain denoised physiological data; Finally, the Z-Score normalization method is used to perform mean normalization and variance normalization on each denoised physiological data, and the denoised physiological data from different sources and units are standardized to the same dimension to generate a preprocessed signal, i.e., the original signal, to ensure that each physiological data has the same importance during subsequent feature extraction and algorithm analysis; the filtering, denoising and normalization methods are all technical means well known to those skilled in the art and will not be elaborated here.

[0022] The original signal is enhanced in the time and frequency domains to perform nonlinear transformation on the original signal to enhance the perception of key signals in the patient's rehabilitation process. The time domain enhancement is performed by nonlinearly processing the local signal strength of the original signal and, based on traditional time domain enhancement technology, introducing an adjustment factor to control the relationship between local signal strength and global signal strength. This allows the time domain enhanced signal to be more meticulously enhanced according to the local and global characteristics of the signal, ultimately obtaining a time domain enhanced signal. The calculation formula for the time domain enhanced signal is as follows: , in, yes Time domain enhanced signal at the moment; This part enhances the time domain characteristics of the original signal through a variety of nonlinear transformations; yes The original signal at time t represents the preprocessed signal; is the total number of nonlinear transformations performed during signal enhancement, such as Fourier transform, wavelet transform, logarithmic transform, and smoothing filter, which is set by expert experience; It is The weighted coefficient of the nonlinear transformation is used to reflect the contribution of the nonlinear transformation to the time domain enhanced signal. It is obtained through experimental tuning and the value range is ; It is the adjustment factor of the high-frequency component of the original signal, obtained through experimental tuning; It is the adjustment factor of the low-frequency component of the original signal, obtained through experimental tuning, and its value range is ; It is a regulating factor used to control the time domain periodicity, which can affect the periodic characteristics of the time domain enhanced signal. It is obtained through experimental tuning and its value range is ; is the time parameter; This part further adjusts the signal enhancement by the ratio of local signal strength to global signal strength; yes The local signal strength at the time, which is obtained by calculating the change of the original signal (such as the amplitude fluctuation range, standard deviation, etc.) within a selected sliding window. The size of the sliding window is set according to expert experience; is the global signal strength of the entire original signal, which is obtained by calculating the root mean square value of the entire original signal; It is a regulating factor used to control the relationship between local signal strength and global signal strength to adjust the sensitivity of signal enhancement and ensure that time domain enhancement does not cause distortion. It is obtained through experimental tuning and has a value range of The calculation methods of the local signal strength and the global signal strength are well known to those skilled in the art and will not be described in detail here. The frequency domain enhancement converts the original signal from the time domain to the frequency domain through Fourier transform, extracts the frequency characteristics of the original signal, and performs weighted processing on different frequency components to adjust the importance of each frequency component to obtain a frequency domain enhanced signal. That is, based on the traditional frequency domain weighted enhancement method and Fourier transform, the Sigmoid function is introduced to smoothly adjust the gain of the frequency component and increase the weighted term of the maximum frequency component to meet the needs of postoperative rehabilitation monitoring in urology surgery. The calculation formula of the frequency domain enhanced signal is as follows: , in, It is a frequency domain enhanced signal, which means the result of the original signal being enhanced in the frequency domain; Is the original input signal Frequency domain representation obtained by Fourier transform; The Sigmoid function achieves flexible enhancement of the signal's frequency domain characteristics. The Sigmoid function can smoothly weight different frequency components and, by weighted addition with the maximum frequency component, ensure that the enhancement effect in the frequency domain is balanced without causing signal distortion or over-processing. Ultimately, it enhances the key frequency components related to the patient's recovery status while avoiding signal distortion caused by over-enhancement. It is a parameter used to control the frequency domain enhancement amplitude, which is obtained through experimental tuning and has a value range of ; is the current frequency component; is the key frequency point of the original signal, which is determined according to expert experience; It is a constant used to control the gain, which is adjusted according to experimental data or expert experience. The value range is ; Is the original input signal The maximum value of the frequency domain representation is obtained by performing Fourier transform; the Fourier transform is a technical means well known to those skilled in the art and will not be described in detail here.

[0023] Through element-wise multiplication, the time domain enhanced signal and the frequency domain enhanced signal are combined to obtain a composite signal, thereby obtaining more comprehensive signal information, which provides a basis for subsequent dynamic weighting and rehabilitation effect prediction. The calculation formula of the composite signal is: , in, yes The composite signal at each moment. The time domain enhanced signal and the frequency domain enhanced signal are fused into a unified composite signal, which contains all possible useful information about the patient's postoperative recovery process.

[0024] S2. Based on the change amplitude of the composite signal, the composite signal is dynamically adjusted to obtain a weighted composite signal; based on the weighted composite signal, the rehabilitation effect is predicted to obtain a predicted value of the rehabilitation effect, and personalized intervention suggestions are generated to guide the rehabilitation process of patients after urological surgery.

[0025] Based on the change amplitude of the composite signal, a dynamic weighting factor is calculated to further adjust the weight of the composite signal; the change amplitude of the composite signal determines the dynamic importance of the composite signal, which in turn affects the prediction of subsequent rehabilitation effects; the greater the change amplitude of the composite signal, the greater the influence of the composite signal at that time point on the overall rehabilitation process; by calculating the change amplitude of the composite signal at the current moment and the previous moment, the composite signal change amount is obtained, and the composite signal change amount is accumulated to obtain the dynamic weighting factor, ensuring that the weighting of the composite signal is timely and sensitive. Based on existing signal processing technology, the calculation formula of the dynamic weighting factor is defined as: , in, yes The dynamic weighting factor at each moment is used to dynamically adjust the weight of the composite signal according to the change amplitude of the composite signal at different time points; is the first time before the current moment Composite signal of time steps; is the number of backtracking steps, the value range is ; It is a constant used to smooth the signal changes. It is set according to the expert experience method and can be set to ; It is an exponential coefficient used to control the sensitivity of composite signal changes. The exponential form can make the sensitivity of composite signal changes more flexible, help better adapt to signal fluctuations at different time points and different change amplitudes, and thus optimize the monitoring and prediction of the patient's recovery process. It is obtained through experimental tuning and has a value range of ; It is the weight coefficient used to control the amplitude of the historical composite signal change, so as to adjust the influence of the historical composite signal on the dynamic weighting factor. The weight coefficient makes the adjustment effect of the historical composite signal more nonlinear through the exponential form. It is obtained through experimental tuning and the value range is ; It is an adjustment coefficient used to control the composite signal strength, so as to adjust the proportion of the dynamic weighting factor according to the strength of the composite signal. The exponential form is used to introduce nonlinearity and flexibility into the calculation of the dynamic weighting factor, so as to adapt to the needs of different signal amplitudes and dynamic changes, and further optimize the accuracy and robustness of the monitoring of postoperative rehabilitation effect of urology surgery. It is obtained through regression analysis and the value range is The aforementioned regression analysis is a well-known technique for those skilled in the art and will not be described in detail here. By accumulating the amplitude of historical composite signal changes, an adaptive dynamic weighting factor is generated, thereby enabling adjustments to the composite signal to better reflect the patient's actual recovery status.

[0026] Based on the dynamic weighting factor, the composite signal is dynamically adjusted to obtain a weighted composite signal. The calculation formula for weighted dynamic adjustment is: , in, yes Weighted composite signals at different moments. Based on the dynamic changes of the composite signal, different weights are assigned to the composite signal at different time points to ensure that the importance of the composite signal can be adaptively adjusted over time during the rehabilitation process.

[0027] Based on the weighted composite signal and the periodic characteristics of the signal, a rehabilitation effect prediction formula is constructed to predict the patient's rehabilitation progress, obtain the rehabilitation effect prediction value, and evaluate the patient's future rehabilitation status. The rehabilitation effect prediction value is calculated by combining the weighted composite signal with a series of adjustment factors. It is used to capture various dynamic changes in the patient's rehabilitation process and predict the patient's future rehabilitation status based on the patient's rehabilitation process, thereby providing a basis for subsequent treatment intervention. The rehabilitation effect prediction formula is as follows: , in, yes The predicted value of rehabilitation effect at the moment indicates the predicted result of the patient's postoperative rehabilitation status; is the total number of feature dimensions of the weighted composite signal; It is The weighted coefficient of each feature dimension is used to reflect the contribution of the weighted composite signal of each feature dimension to the predicted value of rehabilitation effect. It is obtained through experimental tuning and the value range is ; It is The feature dimensions are The weighted composite signal at time instant; It is a cyclical fluctuation regulating factor, which considers the impact of physiological cyclical fluctuations on the recovery process; It is the signal oscillation amplitude adjustment factor, which is used to control the amplitude of the periodic oscillation of the weighted composite signal. It is set by the patient's physiological state or clinical experience and has a value range of ; for The periodic factor related to time is used to control the periodic changes in the rehabilitation process. It is obtained through experimental tuning and has a value range of ; It is the exponential coefficient that weights the periodic changes in the rehabilitation process, and determines the degree of influence of periodic changes on the rehabilitation effect prediction value. It is obtained through experimental tuning and has a value range of The above formula can better capture the dynamic changes in the patient's rehabilitation process, making the prediction of rehabilitation effect more accurate and dynamic, and can be adaptively adjusted according to time and patient status.

[0028] By calculating the deviation between the predicted rehabilitation effect value and the patient's baseline rehabilitation status value, the corresponding treatment intensity and adjustment direction are determined, generating personalized intervention recommendations. Specifically, if the patient's rehabilitation progress is slow (i.e., the predicted rehabilitation effect value is lower than the patient's baseline rehabilitation status value), more intensive intervention is required; on the other hand, if the patient's rehabilitation progress is good (i.e., the predicted rehabilitation effect value is higher than the patient's baseline rehabilitation status value), the intervention intensity can be reduced. The patient's baseline rehabilitation status value is the patient's early postoperative monitoring data (such as electrocardiogram, blood oxygen saturation, body temperature, respiratory rate, etc.).

[0029] Through time domain signal enhancement, frequency domain signal enhancement, weighted dynamic adjustment, rehabilitation effect prediction and generation of personalized intervention suggestions, it provides doctors with a comprehensive, accurate and personalized rehabilitation effect monitoring method to effectively guide the rehabilitation process of patients after urological surgery.

[0030] In summary, the method for monitoring the postoperative rehabilitation effect of urology surgery was completed.

[0031] The order in which the embodiments of the invention are presented is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0032] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

[0033] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the scope of protection of the present invention.

Claims

1. A method for monitoring the postoperative rehabilitation effect of urology surgery, characterized in that: The following steps are involved: S1. Collect the patient's physiological data in real time and perform preprocessing to generate original signals; Performing time domain and frequency domain enhancement processing on the original signal to obtain a time domain enhanced signal and a frequency domain enhanced signal; Combining the time domain enhanced signal and the frequency domain enhanced signal to obtain a composite signal; S2. Based on the change amplitude of the composite signal, the composite signal is dynamically adjusted to obtain a weighted composite signal; based on the weighted composite signal, the rehabilitation effect is predicted to obtain a predicted value of the rehabilitation effect, and personalized intervention suggestions are generated to guide the rehabilitation process of patients after urological surgery.

2. The method for monitoring the postoperative rehabilitation effect of urology surgery according to claim 1, characterized in that: Said S1 specifically includes: Based on the original signal, the local signal strength and the global signal strength are calculated; the adjustment factors of the high-frequency components of the original signal and the adjustment factors of the low-frequency components of the original signal are introduced to perform nonlinear transformation on the original signal to enhance the time domain characteristics of the original signal; and the adjustment factors are introduced to control the ratio of the local signal strength to the global signal strength to obtain a time domain enhanced signal.

3. The method for monitoring the postoperative rehabilitation effect of urology surgery according to claim 2, characterized in that: Said S1 specifically includes: The original signal is converted from the time domain to the frequency domain through Fourier transform, the frequency characteristics of the original signal are extracted, and the different frequency components are weighted to obtain the frequency domain enhanced signal.

4. The method for monitoring the postoperative rehabilitation effect of urology surgery according to claim 3, characterized in that: Said S1 specifically includes: The time domain enhanced signal and the frequency domain enhanced signal are compounded by element-wise multiplication to obtain a composite signal.

5. The method for monitoring the postoperative rehabilitation effect of urology surgery according to claim 1, characterized in that: Said S2 specifically includes: The change amount of the composite signal is obtained by calculating the change amplitude of the composite signal at the current moment and the previous moment, and the composite signal change amount is accumulated to calculate the dynamic weighting factor.

6. The method for monitoring the postoperative rehabilitation effect of urology surgery according to claim 5, characterized in that: Said S2 specifically includes: Based on the dynamic weighting factor, the composite signal is dynamically adjusted to obtain a weighted composite signal.

7. The method for monitoring the postoperative rehabilitation effect of urology surgery according to claim 6, characterized in that: Said S2 specifically includes: Based on the weighted composite signal, a periodic fluctuation adjustment factor is introduced. Combined with the periodic characteristics of the signal, the patient's rehabilitation progress is predicted and the predicted value of the rehabilitation effect is obtained.

8. The method for monitoring the postoperative rehabilitation effect of urology surgery according to claim 7, characterized in that: Said S2 specifically includes: The patient's basic rehabilitation status value is introduced, the deviation between the predicted rehabilitation effect value and the patient's basic rehabilitation status value is calculated, and personalized intervention suggestions are generated: when the predicted rehabilitation effect value is lower than the patient's basic rehabilitation status value, it means that the intervention intensity needs to be increased; when the predicted rehabilitation effect value is higher than the patient's basic rehabilitation status value, it means that the intervention intensity needs to be reduced.

Images