Digestive tract health data analysis method and system

Abstract

The invention relates to the technical field of intelligent medical monitoring and health data analysis, and particularly discloses a digestive tract health data analysis method and system. Differential frequency and sound intensity data generated by intestinal tract movement are collected in real time through a multi-source sensor array deployed on the body surface of the abdomen; the method comprises the following steps: extracting an intestinal motion rhythm stability characteristic value by combining empirical mode decomposition and Hilbert transform, calculating a borborygmus intensity variation characteristic value by adopting a normalization and Haar wavelet decomposition method, constructing an intestinal function state characteristic vector, and inputting the intestinal function state characteristic vector into a health assessment model trained on the basis of a random forest algorithm to obtain a health assessment result. According to the system and the method, individual digestive tract health scores and health level indexes are output, multi-type abnormal early warning signals are triggered, a closed-loop management system from data acquisition, intelligent analysis to risk early warning is constructed, and the intelligent level of early recognition and health management of digestive tract diseases is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent medical monitoring and health data analysis, and particularly to a method and system for analyzing digestive tract health data. Background Art

[0002] Currently, the monitoring of digestive tract health mainly relies on means such as endoscopy, imaging examinations, or laboratory tests. These methods usually have invasiveness, high costs, and are difficult to achieve continuous dynamic monitoring. In recent years, the technology for evaluating digestive tract function based on bowel sound analysis has gradually attracted attention. It collects the sound signals generated by intestinal peristalsis and combines signal processing algorithms to extract features to evaluate the intestinal health status. However, existing technologies mostly use single sensors or traditional spectrum analysis methods, which are difficult to effectively capture the non-linear and non-stationary characteristics of intestinal movement, resulting in insufficient sensitivity and specificity in feature extraction. In addition, existing methods lack adaptability to individual differences in data processing and fail to establish an effective multi-feature fusion evaluation model, restricting their application in real-time health monitoring and early anomaly warning.

[0003] The existing technology has the following deficiencies:

[0004] A key but often overlooked problem in existing bowel sound analysis technology is the lack of effective decoupling of the coupling between intestinal motility fluctuations and rhythm disorders. Traditional methods usually only rely on single frequency-domain or time-domain features (such as average sound intensity, main frequency analysis), while ignoring the dynamic association between frequency stability and intensity variation during intestinal peristalsis, making it difficult to distinguish different pathological patterns such as "peristaltic rhythm disorder type" and "motility fluctuation abnormal type". In addition, existing technologies mostly use fixed thresholds or linear models for anomaly judgment, unable to adapt to individual differences in intestinal movement (such as the influence of factors like diet and physiological cycle), and prone to misjudgment. The present invention realizes the independent quantification and collaborative analysis of rhythm stability and motility fluctuations through the empirical mode decomposition of differential frequency data combined with Hilbert instantaneous frequency analysis, and the extraction of wavelet energy ratio features of sound intensity data, thereby accurately identifying coupling anomalies and achieving personalized health assessment based on a random forest model, effectively making up for the deficiencies of the existing technology. Summary of the Invention

[0005] The purpose of the present invention is to provide a method and system for analyzing digestive tract health data to solve the problems in the above background.

[0006] The purpose of the present invention can be achieved through the following technical solutions:

[0007] A method for analyzing digestive tract health data includes the following steps:

[0008] S1: Real-time collect the differential frequency data and sound intensity data of intestinal peristalsis sounds through a multi-source sensor array deployed on the abdominal body surface;

[0009] The multi-source sensor array includes a broadband microphone sensor and a sound pressure sensor;

[0010] S2: Construct a differential frequency feature sequence from the collected differential frequency data, analyze the differential frequency feature sequence, and calculate the intestinal motility rhythm stability eigenvalue according to the analysis result for evaluating the regularity of intestinal peristalsis;

[0011] S3: Normalize the sound intensity data, construct an intensity fluctuation sequence, and calculate the bowel sound intensity variation eigenvalue according to the intensity fluctuation sequence for identifying whether there is abnormal fluctuation in intestinal motility;

[0012] S4: Construct an intestinal function state feature vector from the intestinal motility rhythm stability eigenvalue and the bowel sound intensity variation eigenvalue, input it into the health assessment model for analysis, generate a digestive tract health level index according to the analysis result, and output a digestive tract health abnormality warning signal.

[0013] As a further solution of the present invention: The evaluation of the regularity of intestinal peristalsis specifically includes:

[0014] Obtain the differential frequency data of the intestinal peristalsis sound, construct a differential frequency feature sequence from the collected differential frequency data, analyze the differential frequency feature sequence, calculate the intestinal motility rhythm stability eigenvalue according to the analysis result, and judge whether the intestinal motility rhythm stability eigenvalue is greater than or equal to a preset threshold. If so, the intestinal peristalsis is irregular; if not, the intestinal peristalsis is regular.

[0015] As a further solution of the present invention: The process of obtaining the intestinal motility rhythm stability eigenvalue is as follows:

[0016] Obtain the differential frequency data sequence collected during intestinal peristalsis, perform empirical mode decomposition on the differential frequency data sequence to obtain a group of intrinsic mode functions and a residual term;

[0017] Apply the Hilbert transform to each intrinsic mode function to obtain its corresponding analytic signal and instantaneous frequency, and the calculation expression is;

[0018] Based on the instantaneous frequency of each intrinsic mode function, calculate the ratio of the variance to the mean of the instantaneous frequency within the entire time range to obtain a frequency stability index;

[0019] Perform weighted averaging on the frequency stability indexes of all intrinsic mode functions to obtain the intestinal motility rhythm stability eigenvalue.

[0020] As a further solution of the present invention: The identification of whether there is abnormal fluctuation in intestinal motility specifically includes:

[0021] Obtain the sound intensity data of intestinal peristalsis sounds, normalize the sound intensity data, construct an intensity fluctuation sequence, calculate the characteristic value of the variation in bowel sound intensity according to the intensity fluctuation sequence, and determine whether the characteristic value of the variation in bowel sound intensity is greater than or equal to a preset threshold. If so, there is abnormal fluctuation in intestinal motility. If not, there is no abnormal fluctuation in intestinal motility.

[0022] As a further solution of the present invention: the characteristic value of the variation in bowel sound intensity specifically includes:

[0023] Obtain the sound intensity data of intestinal peristalsis sounds and normalize the sound intensity data;

[0024] Perform first-level Haar wavelet decomposition on the normalized sound intensity data to obtain approximation coefficients and detail coefficients;

[0025] Calculate the energy of the approximation coefficients and the energy of the detail coefficients at each scale;

[0026] Calculate the ratio of the detail energy to the approximation energy at each scale, and construct an energy fluctuation sequence in the order of the scales for the obtained ratios;

[0027] Calculate the ratio of the average value to the standard deviation of all the ratios in the energy fluctuation sequence to obtain the characteristic value of the variation in bowel sound intensity.

[0028] As a further solution of the present invention: constructing the intestinal motility rhythm stability characteristic value and the characteristic value of the variation in bowel sound intensity into an intestinal function state characteristic vector and inputting it into a health assessment model for analysis specifically includes:

[0029] Obtain the intestinal motility rhythm stability characteristic value and the characteristic value of the variation in bowel sound intensity of the digestive tract, construct the intestinal motility rhythm stability characteristic value and the characteristic value of the variation in bowel sound intensity into an intestinal function state characteristic vector, and input it into a health assessment model. Using minimizing the error between the predicted digestive tract health score and the actual digestive tract health score as the training objective of the health assessment model, train the health assessment model, and output the digestive tract health score according to the trained health assessment model. The health assessment model is a random forest model.

[0030] As a further solution of the present invention: the training process of the health assessment model is:

[0031] Obtain the intestinal motility rhythm stability characteristic values, bowel sound intensity variation characteristic values, and digestive tract health scores of multiple groups of subjects, and form a training data set from them, which is divided into a training set and a validation set. Use a random forest model to minimize the mean square error between the predicted digestive tract health score and the actual digestive tract health score as the objective function for model training. In each training iteration, generate multiple decision trees through bootstrap sampling, and randomly select a feature subset when splitting nodes to enhance the model's generalization ability.

[0032] As a further solution of the present invention: The generation of the digestive tract health level index according to the analysis result specifically includes:

[0033] Judge whether the digestive tract health score of the digestive tract is greater than or equal to a preset threshold. If so, the corresponding digestive tract health status is normal; if not, the corresponding digestive tract health status is abnormal.

[0034] As a further solution of the present invention: Based on the evaluation result of abnormal digestive tract health status, it is judged that the individual has a risk of abnormal digestive tract function, and the system will automatically trigger a health abnormality warning signal; based on the normal digestive tract health status, it is considered that its digestive tract function status is normal and no health abnormality warning signal is issued.

[0035] A digestive tract health data analysis system, including:

[0036] A data acquisition module, which collects the differential frequency data and sound intensity data of intestinal peristalsis sounds in real time through a multi-source sensor array deployed on the abdominal body surface;

[0037] A rhythm stability analysis module, which constructs the collected differential frequency data into a differential frequency feature sequence, analyzes the differential frequency feature sequence, and calculates the intestinal motility rhythm stability characteristic value according to the analysis result for evaluating the regularity of intestinal peristalsis;

[0038] An intestinal motility abnormality analysis module, which normalizes the sound intensity data, constructs an intensity fluctuation sequence, and calculates the bowel sound intensity variation characteristic value according to the intensity fluctuation sequence for identifying whether there is abnormal fluctuation in intestinal motility;

[0039] A digestive tract health assessment and warning module, which constructs the intestinal motility rhythm stability characteristic value and the bowel sound intensity variation characteristic value into an intestinal function status feature vector, inputs it into a health assessment model for analysis, generates a digestive tract health level index according to the analysis result, and outputs a digestive tract health abnormality warning signal.

[0040] The beneficial effects of the present invention:

[0041] (1) The present invention collects, in real time, the information on the change in sound frequency and intensity generated during intestinal peristalsis through a multi-source sensor array deployed on the abdominal body surface, and constructs a high-precision and high-robustness intestinal rhythm stability feature extraction mechanism by combining the empirical mode decomposition and Hilbert transform joint analysis method. This mechanism can adaptively decompose the non-linear and non-stationary differential frequency signals into multiple intrinsic mode functions, and further obtain the instantaneous frequency information of each mode component through the Hilbert transform, calculate the ratio of its variance to the mean as the frequency stability index, and finally obtain the intestinal movement rhythm stability eigenvalue through weighted average, so as to achieve a refined description of the regularity of intestinal peristalsis. At the same time, in terms of dynamic fluctuation detection, the system normalizes the collected sound intensity data, and uses the first-level Haar wavelet decomposition technology to extract the approximation coefficient and detail coefficient, and then calculates the energy distribution and its ratio at different scales to form an energy fluctuation sequence, and uses the ratio of its mean to the standard deviation as the bowel sound intensity variation eigenvalue to identify whether there is abnormal fluctuation in intestinal motility. This method not only has good time-frequency localization ability to capture the transient change trend of bowel sound intensity, but also enhances the discriminant ability of features for pathological or functional abnormalities through the multi-scale energy ratio method, improves the anti-interference performance and individual adaptability of the system in complex environments, is significantly superior to traditional methods based on Fourier transform or simple time-domain statistics, and has higher sensitivity and clinical application value.

[0042] (2) The present invention takes the intestinal function state feature vector constructed by fusing the intestinal movement rhythm stability eigenvalue and the bowel sound intensity variation eigenvalue as the input and feeds it into a health assessment model trained based on the random forest algorithm to achieve accurate modeling and dynamic assessment of the individual's digestive tract health status. During the training process of this model, bootstrap sampling is used to generate multiple decision trees, and a feature subset random selection mechanism is introduced during node splitting, effectively enhancing the generalization ability and anti-interference performance of the model; its optimization goal is to minimize the mean square error between the predicted score and the actual health score comprehensively evaluated by clinicians, ensuring that the output result has good clinical consistency. In practical applications, the system compares the health score output by the model with a preset threshold, automatically divides the health level, and combines the abnormal type recognition mechanism to judge whether it is an abnormality of "peristaltic rhythm disorder type", "dynamic fluctuation abnormality type" or "comprehensive dysfunction type", so as to generate multi-dimensional warning information. The warning signal can be pushed to users or medical staff in real time through wearable devices, intelligent terminals or remote medical platforms, realizing a closed-loop management process from data collection, feature extraction, model prediction to risk feedback. This method not only improves the personalization and intelligence level of digestive tract health assessment, but also provides efficient and reliable technical support for early intervention, continuous monitoring and remote health management of diseases. Description of the Drawings

[0043] The present invention will be further described below in conjunction with the accompanying drawings.

[0044] Figure 1 is a flowchart of a method for analyzing digestive tract health data according to the present invention;

[0045] Figure 2 is a flowchart of a digestive tract health data analysis system according to the present invention. Specific embodiments

[0046] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0047] Please refer to Figure 1 As shown, the present invention is a method for analyzing digestive tract health data, including the following steps:

[0048] S1: Real-time collect the differential frequency data and sound intensity data of intestinal peristalsis sounds through a multi-source sensor array deployed on the abdominal body surface;

[0049] The multi-source sensor array includes a broadband microphone sensor and a sound pressure sensor;

[0050] S2: Construct a differential frequency feature sequence from the collected differential frequency data, analyze the differential frequency feature sequence, and calculate the intestinal motility rhythm stability feature value according to the analysis result for evaluating the regularity of intestinal peristalsis;

[0051] S3: Normalize the sound intensity data, construct an intensity fluctuation sequence, and calculate the bowel sound intensity variation feature value according to the intensity fluctuation sequence for identifying whether there is abnormal fluctuation in intestinal motility;

[0052] S4: Construct an intestinal function state feature vector from the intestinal motility rhythm stability feature value and the bowel sound intensity variation feature value, input it into a health assessment model for analysis, generate a digestive tract health level index according to the analysis result, and output a digestive tract health abnormality warning signal.

[0053] In S1, real-time collect the differential frequency data and sound intensity data of intestinal peristalsis sounds through a multi-source sensor array deployed on the abdominal body surface, specifically including:

[0054] Real-time acquisition of intestinal peristalsis sound signals is achieved through a multi-source sensor array deployed on the abdominal surface of the subject. The multi-source sensor array includes at least one broadband microphone sensor and multiple sound pressure sensors. The broadband microphone sensor is used to capture the full-band bowel sound signals generated during intestinal peristalsis. It has a high frequency response range (such as 20 Hz to 20 kHz) and can effectively capture the sound changes caused by intestinal movement. The sound pressure sensor is used to measure the local abdominal cavity pressure fluctuations caused by intestinal peristalsis and assist in extracting the differential frequency information related to bowel sounds.

[0055] In the specific implementation process, the subject attaches the sensor array to the abdominal area, such as typical bowel sound generating areas around the umbilicus, left lower abdomen, etc. After starting the acquisition system, each sensor synchronously records the time-domain waveform of the sound generated by intestinal peristalsis and the corresponding pressure change signal. Through spectral analysis of the original audio signal collected by the broadband microphone sensor and combining with the pressure change curve obtained by the sound pressure sensor, the differential frequency data of intestinal peristalsis sound is calculated. At the same time, the sound intensity peak and fluctuation amplitude in the audio signal are extracted to construct a sound intensity data sequence, which serves as the input basis for the subsequent feature extraction module. The entire acquisition process is non-invasive, continuous, and has good time resolution, and can accurately reflect the dynamic changes of individual intestinal movement.

[0056] In S2, the collected differential frequency data is constructed into a differential frequency feature sequence, and the differential frequency feature sequence is analyzed. According to the analysis results, the intestinal movement rhythm stability characteristic value is calculated to evaluate the regularity of intestinal peristalsis, specifically including:

[0057] Obtain the differential frequency data of intestinal peristalsis sound, construct the collected differential frequency data into a differential frequency feature sequence, analyze the differential frequency feature sequence, calculate the intestinal movement rhythm stability characteristic value according to the analysis results, and judge whether the intestinal movement rhythm stability characteristic value is greater than or equal to the preset threshold. If so, the intestinal peristalsis is irregular; if not, the intestinal peristalsis is regular.

[0058] The process of obtaining the intestinal movement rhythm stability characteristic value is as follows:

[0059] Obtain the differential frequency data sequence collected during intestinal peristalsis, perform empirical mode decomposition on the differential frequency data sequence to obtain a group of intrinsic mode functions and a residual term. The calculation expression is: ; where represents the number of intrinsic mode functions, represents the total number of intrinsic mode functions, represents the th intrinsic mode function, represents the final residual, represents the time acquisition point, Represents the differential frequency data sequence;

[0060] Apply the Hilbert transform to each intrinsic mode function to obtain its corresponding analytic signal, and the calculation expression is: ;

[0061] Apply the Hilbert transform to each intrinsic mode function to obtain its corresponding instantaneous frequency, and the calculation expression is: ;

[0062] Among them, represents the analytic signal, represents the instantaneous frequency, represents the instantaneous amplitude, represents the phase function, represents the imaginary unit;

[0063] Based on the instantaneous frequency of each intrinsic mode function, calculate the ratio of the variance to the mean of the instantaneous frequency within the entire time range to obtain the frequency stability index;

[0064] Perform weighted averaging on the frequency stability indices of all intrinsic mode functions to obtain the intestinal motility rhythm stability eigenvalue, and the calculation expression is: ;

[0065] Among them, represents the frequency stability index of the th intrinsic mode function, represents the intestinal motility rhythm stability eigenvalue.

[0066] It should be noted that: By adaptively decomposing the complex differential frequency data sequence into multiple intrinsic mode functions and a residual term, the present invention overcomes the problem of insufficient processing ability of traditional spectral analysis methods for non-linear and non-stationary signals; Subsequently, the Hilbert transform is used to obtain the instantaneous frequency of each intrinsic mode function component, and the ratio of its variance to the mean is calculated as the frequency stability index, and further the information of each component is fused through weighted averaging to construct an intestinal motility rhythm stability eigenvalue with clear physiological significance and strong anti-interference ability. This innovation not only improves the sensitivity of feature extraction to minute abnormal fluctuations of intestinal rhythm, but also enhances the robustness of the model to individual differences and environmental noise, providing reliable input for subsequent health assessment models, and having significant technological progressiveness and clinical application value.

[0067] In S3, normalize the sound intensity data, construct an intensity fluctuation sequence, and calculate the bowel sound intensity variation eigenvalue according to the intensity fluctuation sequence for identifying whether there are abnormal fluctuations in intestinal motility, specifically including:

[0068] Obtain the sound intensity data of intestinal peristalsis sounds, perform normalization processing on the sound intensity data, construct an intensity fluctuation sequence, calculate the characteristic value of the variation of bowel sound intensity based on the intensity fluctuation sequence, and determine whether the characteristic value of the variation of bowel sound intensity is greater than or equal to a preset threshold. If so, there is abnormal fluctuation in intestinal motility; if not, there is no abnormal fluctuation in intestinal motility.

[0069] The characteristic value of the variation of bowel sound intensity specifically includes:

[0070] Obtain the sound intensity data of intestinal peristalsis sounds, and the calculation expression for performing normalization processing on the sound intensity data is: ;

[0071] Among them, represents the normalized sound intensity data, represents the time acquisition point, represents the sound intensity data collected in real time, represents the maximum value in the sound intensity data, represents the minimum value in the sound intensity data;

[0072] Perform first-level Haar wavelet decomposition on the normalized sound intensity data to obtain approximation coefficients and detail coefficients;

[0073] Calculate the energy of the approximation coefficients at each scale, and the calculation expression is: ;

[0074] Among them, represents the energy of the approximation coefficients, represents the number of scales, represents the th approximation coefficient at a scale;

[0075] Calculate the energy of the detail coefficients at each scale, and the calculation expression is: ;

[0076] Among them, represents the energy of the detail coefficients, represents the th detail coefficient at a scale;

[0077] Calculate the ratio of the detail energy to the approximation energy at each scale, and construct an energy fluctuation sequence in the order of the scales for the obtained ratios;

[0078] Calculate the ratio of the average value to the standard deviation of all the ratios in the energy fluctuation sequence to obtain the characteristic value of the variation of bowel sound intensity.

[0079] It should be noted that: By normalizing the sound intensity data, the present invention eliminates the influence brought by individual differences and equipment acquisition deviations, and improves the comparability of the data; Subsequently, the first-level Haar wavelet transform is introduced to decompose the normalized sound intensity signal into approximation coefficients and detail coefficients at multiple scales, and by calculating the ratio of the detail energy to the approximation energy at each scale, an energy fluctuation sequence is constructed. Further, the ratio of the mean value to the standard deviation of this sequence is used as the bowel sound intensity variation eigenvalue, realizing a highly sensitive characterization of the intestinal motility fluctuation characteristics. This method not only has good time-frequency localization ability and can capture the transient change trend of the bowel sound intensity, but also enhances the discriminant ability of the features for pathological or functional abnormalities through the way of wavelet energy ratio, has strong robustness and clinical applicability, and significantly improves the accuracy and intelligent level of intestinal motility abnormality detection.

[0080] In S4, the intestinal motility rhythm stability eigenvalue and the bowel sound intensity variation eigenvalue are constructed into an intestinal function state feature vector, which is input into the health assessment model for analysis. According to the analysis results, a digestive tract health grade index is generated, and a digestive tract health abnormality warning signal is output, specifically including:

[0081] Obtain the intestinal motility rhythm stability eigenvalue and the bowel sound intensity variation eigenvalue of the digestive tract, construct the intestinal motility rhythm stability eigenvalue and the bowel sound intensity variation eigenvalue into an intestinal function state feature vector, and input it into the health assessment model. Taking minimizing the error between the predicted digestive tract health score and the actual digestive tract health score as the training objective of the health assessment model, train the health assessment model. According to the trained health assessment model, output the digestive tract health score. The health assessment model is a random forest model.

[0082] The training process of the health assessment model is as follows:

[0083] Obtain the intestinal motility rhythm stability eigenvalue, the bowel sound intensity variation eigenvalue and the digestive tract health score of multiple groups of subjects, and form a training data set, which is divided into a training set and a validation set. Adopt a random forest model, and use minimizing the mean square error between the predicted digestive tract health score and the actual digestive tract health score as the objective function for model training. In each training iteration, through bootstrap sampling, generate multiple decision trees, and randomly select a feature subset when splitting nodes to enhance the generalization ability of the model; After training, save the optimal model parameters and use them to predict the health score of the newly input intestinal function state feature vector, so as to realize the quantitative assessment of the individual's digestive tract health status.

[0084] Judge whether the digestive tract health score of the digestive tract is greater than or equal to a preset threshold. If so, the corresponding digestive tract health status is normal; if not, the corresponding digestive tract health status is abnormal.

[0085] Based on the assessment results of abnormal digestive tract health status, it is determined that the individual has a risk of abnormal digestive tract function, and the system will automatically trigger a health abnormality warning signal; if the digestive tract health status is normal, it is considered that the digestive tract function status is normal and no warning is issued.

[0086] At the same time as the warning is triggered, the system further combines the intestinal motility rhythm stability eigenvalue and the bowel sound intensity variation eigenvalue in the input intestinal function status feature vector, and compares them with their respective set preset thresholds respectively, so as to identify the specific type of abnormality.

[0087] If the rhythm stability eigenvalue is greater than or equal to its corresponding preset threshold and the intensity variation eigenvalue is less than its preset threshold, it is judged as an abnormality of "peristaltic rhythm disorder type";

[0088] If the rhythm stability eigenvalue is less than its preset threshold and the intensity variation eigenvalue is greater than or equal to its threshold, it is judged as an abnormality of "dynamic fluctuation abnormal type"; if both are greater than or equal to their respective preset thresholds, it is judged as an abnormality of "comprehensive dysfunction type".

[0089] Finally, the system conveys the warning information to the user or medical staff through a wearable device, a smart terminal or a remote medical platform in the form of sound and light prompts, screen displays, mobile phone push notifications, etc., and records the timestamp, relevant feature data and abnormal type classification of this warning event for subsequent health trend analysis, auxiliary diagnosis and formulation of personalized intervention suggestions. The entire warning process realizes a closed-loop management from data collection, feature extraction, model prediction to risk feedback, and has real-time, intelligent and clinical application value.

[0090] Please refer to Figure 2 As shown in the figure, a digestive tract health data analysis system includes:

[0091] A data collection module, which collects the differential frequency data and sound intensity data of intestinal peristalsis sounds in real time through a multi-source sensor array deployed on the abdominal body surface;

[0092] A rhythm stability analysis module, which constructs the collected differential frequency data into a differential frequency feature sequence, analyzes the differential frequency feature sequence, and calculates the intestinal motility rhythm stability eigenvalue according to the analysis result for evaluating the regularity of intestinal peristalsis;

[0093] An intestinal motility abnormality analysis module, which normalizes the sound intensity data, constructs an intensity fluctuation sequence, and calculates the bowel sound intensity variation eigenvalue according to the intensity fluctuation sequence for identifying whether there is abnormal fluctuation in intestinal motility;

[0094] Gastrointestinal health assessment and early warning module, which constructs an intestinal function state feature vector from the intestinal motility rhythm stability eigenvalue and the bowel sound intensity variation eigenvalue, inputs it into the health assessment model for analysis, generates gastrointestinal health level indicators according to the analysis results, and outputs gastrointestinal health abnormality early warning signals.

[0095] The working principle of the present invention: Through a multi-source sensor array deployed on the abdominal surface of the subject, including a broadband microphone sensor and a sound pressure sensor, synchronously collect the sound signals and pressure fluctuation data generated during intestinal peristalsis, and then extract the differential frequency and sound intensity information to construct highly sensitive physiological characteristic parameters. At the feature extraction level, the present invention innovatively introduces a method combining empirical mode decomposition (EMD) and Hilbert transform to accurately extract the intestinal motility rhythm stability eigenvalue, thereby quantitatively evaluating the regularity of intestinal peristalsis; at the same time, a normalization processing and Haar wavelet decomposition strategy are adopted to calculate the bowel sound intensity variation eigenvalue to identify whether there are abnormal fluctuations in intestinal motility. The above two key features are fused into a unified intestinal function state feature vector and sent as input into a health assessment model trained based on the random forest algorithm. This model is optimized with the goal of minimizing the mean square error between the predicted score and the clinical health score, and has good generalization ability and prediction accuracy. Finally, the system generates gastrointestinal health level indicators according to the model output, and combines a preset threshold judgment mechanism to output multiple categories of health abnormality early warning signals, covering various types such as "peristaltic rhythm disorder type", "dynamic fluctuation abnormal type", and "comprehensive dysfunction type", supporting personalized medical intervention and long-term health trend analysis. Overall, the present invention constructs a complete closed-loop management process from data collection to intelligent analysis to early warning feedback, and has high clinical practicability, technological advancement, and application expansion potential.

[0096] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data for software simulation to obtain a formula closest to the actual situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0097] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center in a wired or wireless (such as infrared, wireless, microwave, etc.) manner. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more sets of available media. The available media can be magnetic media (such as floppy disks, hard disks, magnetic tapes), optical media (such as DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0098] It should be understood that the term "and / or" in this document is merely a description of the association relationship between associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. Here, A and B can be singular or plural. In addition, the character " / " in this document generally represents an "or" relationship between the associated objects before and after, but it may also represent an "and / or" relationship, which can be specifically understood with reference to the context.

[0099] It should be understood that in various embodiments of the present application, the order numbers of the above processes do not mean the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0100] The above has described in detail one embodiment of the present invention, but the content described is only a preferred embodiment of the present invention and cannot be considered as limiting the scope of implementation of the present invention. Any equivalent changes and improvements made within the scope of the application of the present invention should still fall within the scope covered by the patent of the present invention.

Claims

1. A method for analyzing digestive tract health data, characterized in that, It includes the following steps: S1: Real-time collect the differential frequency data and sound intensity data of intestinal peristalsis sounds through a multi-source sensor array deployed on the abdominal body surface; The multi-source sensor array includes a broadband microphone sensor and a sound pressure sensor; S2: Construct the differential frequency data collected into a differential frequency feature sequence, analyze the differential frequency feature sequence, and calculate the intestinal motility rhythm stability eigenvalue according to the analysis result for evaluating the regularity of intestinal peristalsis; S3: Perform normalization processing on the sound intensity data, construct an intensity fluctuation sequence, and calculate the bowel sound intensity variation eigenvalue according to the intensity fluctuation sequence for identifying whether there is abnormal fluctuation in intestinal motility; S4: Construct the intestinal motility rhythm stability eigenvalue and the bowel sound intensity variation eigenvalue into an intestinal function state feature vector, input it into a health assessment model for analysis, generate a digestive tract health level index according to the analysis result, and output a digestive tract health abnormality warning signal.

2. The method for analyzing digestive tract health data according to claim 1, wherein The evaluation of the regularity of intestinal peristalsis specifically includes: Obtain the differential frequency data of intestinal peristalsis sounds, construct the differential frequency data collected into a differential frequency feature sequence, analyze the differential frequency feature sequence, calculate the intestinal motility rhythm stability eigenvalue according to the analysis result, and judge whether the intestinal motility rhythm stability eigenvalue is greater than or equal to a preset threshold. If so, the intestinal peristalsis is irregular; if not, the intestinal peristalsis is regular.

3. A method for analyzing digestive tract health data according to claim 2, characterized in that, The acquisition process of the intestinal motility rhythm stability eigenvalue is as follows: Obtain the differential frequency data sequence collected during intestinal peristalsis, perform empirical mode decomposition on the differential frequency data sequence to obtain a group of intrinsic mode functions and a residual term; Apply the Hilbert transform to each intrinsic mode function to obtain its corresponding analytic signal and instantaneous frequency, and the calculation expression is; Based on the instantaneous frequency of each intrinsic mode function, calculate the ratio of the variance to the mean of the instantaneous frequency within the entire time range to obtain a frequency stability index; Perform weighted averaging on the frequency stability indexes of all intrinsic mode functions to obtain the intestinal motility rhythm stability eigenvalue.

4. A method for analyzing digestive tract health data according to claim 1, characterized in that The identification of whether there is abnormal fluctuation in intestinal motility specifically includes: Obtain the sound intensity data of intestinal peristalsis sounds, perform normalization processing on the sound intensity data, construct an intensity fluctuation sequence, calculate the bowel sound intensity variation eigenvalue according to the intensity fluctuation sequence, and judge whether the bowel sound intensity variation eigenvalue is greater than or equal to a preset threshold. If so, there is abnormal fluctuation in intestinal motility; if not, there is no abnormal fluctuation in intestinal motility.

5. A method for analyzing digestive tract health data according to claim 4, characterized in that The bowel sound intensity variation eigenvalue specifically includes: Obtain the sound intensity data of intestinal peristalsis sounds and perform normalization processing on the sound intensity data; Perform first-level Haar wavelet decomposition on the normalized sound intensity data to obtain an approximation coefficient and a detail coefficient; Calculate the energy of the approximation coefficient and the energy of the detail coefficient at each scale; Calculate the ratio of the detail energy to the approximation energy at each scale, and construct an energy fluctuation sequence in the order of the scales for the obtained ratios; Calculate the ratio of the mean value to the standard deviation of all ratios in the energy fluctuation sequence to obtain the bowel sound intensity variation eigenvalue.

6. A method for analyzing digestive tract health data according to claim 1, characterized in that, Constructing the intestinal motility rhythm stability eigenvalue and the bowel sound intensity variation eigenvalue into an intestinal function state feature vector and inputting it into a health assessment model for analysis specifically includes: Obtaining the intestinal motility rhythm stability eigenvalue and the bowel sound intensity variation eigenvalue of the digestive tract, constructing the intestinal motility rhythm stability eigenvalue and the bowel sound intensity variation eigenvalue into an intestinal function state feature vector, and inputting it into a health assessment model. Using the minimization of the error between the predicted digestive tract health score and the actual digestive tract health score as the training objective of the health assessment model, training the health assessment model, and according to the trained health assessment model, outputting the digestive tract health score. The health assessment model is a random forest model.

7. A method for analyzing digestive tract health data according to claim 6, characterized in that, The training process of the health assessment model is as follows: Obtaining the intestinal motility rhythm stability eigenvalue, the bowel sound intensity variation eigenvalue, and the digestive tract health score of multiple groups of subjects, and forming a training data set from them, which is divided into a training set and a validation set. Using a random forest model, with the minimization of the mean square error between the predicted digestive tract health score and the actual digestive tract health score as the objective function for model training. In each training iteration, multiple decision trees are generated through bootstrap sampling, and a feature subset is randomly selected during node splitting to enhance the generalization ability of the model.

8. A method for analyzing digestive tract health data according to claim 1, characterized in that, Generating the digestive tract health level index according to the analysis result specifically includes: Judging whether the digestive tract health score of the digestive tract is greater than or equal to a preset threshold. If so, the corresponding digestive tract health state is normal; if not, the corresponding digestive tract health state is abnormal.

9. A method for analyzing digestive tract health data according to claim 1, characterized in that, Outputting the digestive tract health abnormality warning signal specifically includes: Based on the evaluation result of the abnormal digestive tract health state, it is judged that the individual has a risk of abnormal digestive tract function, and the system will automatically trigger a health abnormality warning signal; based on the normal digestive tract health state, it is considered that its digestive tract function state is normal, and no health abnormality warning signal is issued.

10. A digestive tract health data analysis system, characterized in that, For a digestive tract health data analysis method according to any one of claims 1-9, including: A data acquisition module, which collects the differential frequency data and sound intensity data of intestinal peristaltic sounds in real time through a multi-source sensor array deployed on the abdominal body surface; A rhythm stability analysis module, which constructs the collected differential frequency data into a differential frequency feature sequence, analyzes the differential frequency feature sequence, and calculates the intestinal motility rhythm stability eigenvalue according to the analysis result for evaluating the regularity of intestinal peristalsis; An intestinal motility abnormality analysis module, which normalizes the sound intensity data, constructs an intensity fluctuation sequence, and calculates the bowel sound intensity variation eigenvalue according to the intensity fluctuation sequence for identifying whether there is abnormal fluctuation in intestinal motility; A digestive tract health assessment and warning module, which constructs the intestinal motility rhythm stability eigenvalue and the bowel sound intensity variation eigenvalue into an intestinal function state feature vector, inputs it into a health assessment model for analysis, generates a digestive tract health level index according to the analysis result, and outputs a digestive tract health abnormality warning signal.

Images