IBS-D symptom dynamic monitoring and doctor-patient interaction terminal

Abstract

The invention relates to the technical field of medical information analysis, in particular to an IBS-D symptom dynamic monitoring and doctor-patient interaction terminal, which is characterized in that first feature medical information and second feature medical information are extracted through an irritable bowel feedback analysis model; performing data quantification calibration on the second feature medical information under the condition that the first feature medical information is included to obtain third feature medical information; combining the first feature medical information and the third feature medical information as key quantitative information to generate an IBS-D medical monitoring feature report; through the method, data quantification can be performed on monitored physiological information and communication information of IBS-D patients, and a medical monitoring feature report is generated based on the information, so that the application range of monitoring data to treatment data is expanded, communication information errors caused by diseases of the patients are reduced, and accurate data are provided for doctors for data reference.

Description

Technical Field

[0001] The present invention relates to the technical field of medical information analysis, and particularly to a dynamic monitoring terminal for IBS-D symptoms and doctor-patient interaction. Background Art

[0002] Diarrhea-predominant Irritable Bowel Syndrome (IBS-D) is a subtype of gastrointestinal disease of Irritable Bowel Syndrome (IBS). In addition to common gastrointestinal disease symptoms such as abdominal pain, abdominal distension, and diarrhea, patients with IBS-D usually also show great anxiety and depression. Moreover, the anxiety and depression of patients will also lead to the aggravation of the condition of IBS-D patients (gut-brain interaction). Therefore, in addition to normal drug treatment, emotional comfort for IBS-D patients is also one of the current treatment measures.

[0003] In the conventional treatment plan for IBS-D patients, doctors mostly detect the treatment effect and provide emotional comfort through the active outpatient follow-up of patients. There are problems such as inability to give timely feedback, high dropout rate, and serious consumption of medical resources. And relying solely on Internet communication has the following problems: patients are quite subjective when describing symptoms, etc., and it is impossible to reflect the objective physiological indicators of patients. Therefore, there is a lack of a more efficient treatment feedback method between doctors and patients. With the development of technology, it has become possible to remotely monitor various physiological information of IBS-D through medical devices such as bowel sound monitoring devices, remotely communicate with IBS-D patients, thereby reasonably adjusting medication and comforting patients, and it is possible to achieve remote treatment of IBS-D and save medical resources to the greatest extent.

[0004] However, there are still some problems in the treatment process. On the one hand, the main current bowel sound monitoring devices are disposable and have poor battery life, so the monitored data fed back is limited, and the feedback of treatment data has limitations. On the other hand, due to the anxiety and depression problems of IBS-D patients, the information conveyed by IBS-D patients during the communication process will also be affected by emotions and there is inaccuracy of information. And in order to prevent the condition of IBS-D patients from deteriorating due to emotional influence, doctors cannot get to the bottom of things like other diseases, resulting in a large error in the feedback of communication information data, which also has a certain impact on the accuracy of the feedback of treatment data.

[0005] Therefore, a dynamic monitoring terminal for IBS-D symptoms and doctor-patient interaction is proposed. Summary of the Invention

[0006] The object of the present invention is to provide a dynamic monitoring and doctor-patient interaction terminal for IBS-D symptoms, which extracts first characteristic medical information and second characteristic medical information through an irritable bowel feedback analysis model, and performs data quantization calibration on the second characteristic medical information in the case of including the first characteristic medical information to obtain third characteristic medical information; combines the first characteristic medical information and the third characteristic medical information as key quantization information to generate an IBS-D medical monitoring characteristic report; through this method, the physiological information and communication information of the monitored IBS-D patients can be quantized, and a medical monitoring characteristic report is generated based on these information, so as to expand the applicable range of monitoring data for treatment data, and at the same time reduce the communication information error caused by the disease of the patient, and provide accurate treatment feedback data for doctors for data reference.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] A dynamic monitoring and doctor-patient interaction terminal for IBS-D symptoms, comprising:

[0009] A medical information acquisition module, which acquires first medical information and second medical information of an IBS-D patient; the first medical information includes vital sign information and physiological activity information acquired by medical devices; the second medical information includes voice communication information and text communication information of the IBS-D patient;

[0010] A medical information analysis module, which transmits the first medical information to the irritable bowel feedback analysis model, judges whether there is first characteristic medical information of the first medical information, and if so, extracts the first characteristic medical information and stores the data;

[0011] Further, the first characteristic medical information is obtained through an abnormal irritable bowel physiological characteristic model of the irritable bowel feedback analysis model;

[0012] The abnormal irritable bowel physiological characteristic model includes a physiological characteristic data processing unit, a physiological characteristic data extraction unit, a physiological characteristic abnormality calculation unit and a physiological abnormality characteristic output unit;

[0013] The physiological characteristic data processing unit performs data preprocessing on the first medical information;

[0014] The physiological characteristic data extraction unit extracts IBS-D medical information characteristics from the preprocessed first medical information; the physiological characteristic data extraction unit includes 5 LSTM layers, 2 spatio-temporal convolutional layers, 1 attention mechanism and 1 feature activation layer; the physiological characteristic abnormality calculation unit judges whether there is the first characteristic medical information according to the IBS-D medical information characteristics; specifically:

[0015] σ IBS-D =fIBS-D (d F )·ω1·Cos(d F ,d U )+f IBS-D (d F )·ω2·Dtw(d F ,d U );

[0016] Among them, σ IBS-D is the similarity of the first characteristic medical information, f IBS-D (d F ) is the IBS-D medical information feature extracted from the first medical information; Cos is the cosine similarity algorithm, d F is the first medical information, d U is the abnormal medical information of IBS-D, Dtw is the dynamic time warping algorithm, and ω1 and ω2 are the feature similarity weights;

[0017] The physiological abnormality feature output unit outputs the first characteristic medical information and stores the data;

[0018] Transmit the second medical information to the irritable bowel syndrome feedback analysis model, compare the second medical information with the stored historical second medical information, generate the second characteristic medical information and store the data;

[0019] Furthermore, the second characteristic medical information is obtained according to the medical feedback information analysis model of the irritable bowel syndrome feedback analysis model;

[0020] The medical feedback information analysis model includes a medical feedback information processing unit, a medical feedback key information extraction unit, and a medical feedback weight calculation and output unit;

[0021] The medical feedback information processing unit performs data feature processing on the second medical information;

[0022] The medical feedback key information extraction unit compares the second medical information after data feature processing with the historical second medical information to extract key semantic features. The medical feedback key information extraction unit uses the Transformer model;

[0023] The medical feedback weight calculation and output unit calculates the feedback key weight according to the key semantic features and generates the second characteristic medical information; specifically:

[0024]

[0025] Among them, is the i-th feedback key weight, i ∈ (1, N j ), Nj is the total number of the second medical information for the j-th clustering category, where j ∈ (1, n) and n is the total number of clustering categories; ln is the natural logarithm function with base e, Num is the statistical quantity of key semantic features; Tran is the Transformer model, is the l-th second medical information, where l ∈ (1, M) and M is the total number of second medical information, Km is the semantic clustering feature label data, and β1 and β2 are feedback key weight parameters;

[0026] Medical information association module. If the first feature medical information exists, the second feature medical information is associated according to the first feature medical information to obtain the third feature medical information, and the third feature medical information is stored; specifically: Among them, is the j-th third feature medical information, where i ∈ (1, N j ), j ∈ (1, n);

[0027] If the first feature medical information does not exist, the second feature medical information is used as the third feature medical information for storage;

[0028] Medical monitoring feature report output module. If the first feature medical information exists, the first feature medical information and the third feature medical information are output to generate an IBS-D medical monitoring feature report; if the first feature medical information does not exist, the third feature medical information is output to generate the IBS-D medical monitoring feature report;

[0029] Furthermore, the initial report of the IBS-D medical monitoring feature report includes 1 IBS-D medical abnormality information label and K IBS-D medical dialogue information labels, where K ≥ 1; each IBS-D medical dialogue information label corresponds to k third feature medical information, where k ≥ 1; the IBS-D medical abnormality information label corresponds to the first feature medical information;

[0030] If the first feature medical information is not less than the abnormal medical information threshold, the initial report outputs the IBS-D medical abnormality information label; if the sum of the k third feature medical information is not less than the medical dialogue information threshold, the initial report outputs the corresponding IBS-D medical dialogue information label;

[0031] The IBS-D medical monitoring feature report is generated based on the output IBS-D medical abnormality information label and the output IBS-D medical dialogue information label.

[0032] Compared with the prior art, the beneficial effects of the present invention are:

[0033] 1. Based on the first medical information and the second medical information of IBS-D patients, analyze whether there is the first characteristic medical information through the irritable bowel syndrome feedback analysis model, and extract the second characteristic medical information according to the irritable bowel syndrome feedback analysis model and the first characteristic medical information. Through this method, the deep features of the physiological information monitored by IBS-D patients can be mined based on the existing data, the scope of use of the monitored physiological information can be enhanced, and at the same time, the key semantic information of IBS-D patients can be extracted based on the physiological information, reducing the error of communicating monitoring data, providing an accurate data basis for subsequent treatment data feedback, and facilitating doctors to refer to the data.

[0034] 2. Based on the deep features of the physiological information monitored by IBS-D patients and combined with the key semantic information of IBS-D patients, calculate the feedback key weight through the clustering method. Based on this method, the scope of data use of the monitored physiological information can be further increased, and at the same time, the semantic features of patients can be screened based on the monitored physiological information. Through this method, various data can be quantified, facilitating the subsequent calculation and feedback of treatment data, providing a quantified data basis for doctors' subsequent work, and facilitating doctors to refer to the data.

[0035] 3. The present invention monitors the deep features of the first characteristic medical information after data quantification and the third characteristic medical information after data screening, and converts the quantified data into an IBS-D medical monitoring feature report according to the initial report. Through this method, the error of communication information data caused by emotional problems of IBS-D patients can be minimized to the greatest extent, providing an accurate data basis for subsequent treatment data feedback, and facilitating doctors to refer to the data. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 It is a flowchart of the terminal system of the present invention;

[0037] Figure 2 It is an Internet of Things diagram of the terminal of the present invention;

[0038] Figure 3 It is a virtual device diagram of the abnormal irritable bowel physiological feature model and the medical feedback information analysis model of the irritable bowel syndrome feedback analysis model of the present invention;

[0039] Figure 4 It is a network structure diagram of the physiological feature data extraction unit of the present invention.

[0040] In the figure: 1. IBS-D patient; 2. Sensor; 3. Server; 4. Mobile terminal; 5. Network; 6. Doctor. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0041] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described 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. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0042] In addition to gastrointestinal disease symptoms, IBS-D patients are also prone to show emotions such as anxiety and depression, and these emotions will also affect the symptoms of IBS-D. Therefore, in addition to drug treatment, doctors also need to comfort the patients emotionally; however, there are still some problems in the treatment process. First, the monitoring instrument cannot monitor the patient in real time for a long time, resulting in certain limitations in the feedback of monitoring data for treatment; at the same time, due to the patient's emotions, the information communicated between the doctor and the patient will also be affected, resulting in errors in the communicated information and affecting the feedback of treatment data. For this reason, the present invention provides an IBS-D symptom dynamic monitoring and doctor-patient interaction terminal. Refer to Figure 1 and Figure 2 The technical solutions are as follows:

[0043] A medical information collection module, which acquires the first medical information and the second medical information of IBS-D patients; corresponding to Figure 2 In this process, the server 3 obtains the first medical information of the IBS-D patient 1 collected by the sensor 2 through the network 5; the server 3 obtains the second medical information of the IBS-D patient 1 collected by the mobile terminal 4 through the network 5;

[0044] A medical information analysis module, which transmits the first medical information to the irritable bowel feedback analysis model, determines whether there is the first characteristic medical information of the first medical information, and if so, extracts the first characteristic medical information and stores the data; transmits the second medical information to the irritable bowel feedback analysis model, compares the second medical information with the stored historical second medical information, generates the second characteristic medical information and stores the data; the medical information analysis module is completed in the Figure 2 server 3 in

[0045] A medical information association module, if there is the first characteristic medical information, associates the second characteristic medical information according to the first characteristic medical information to obtain the third characteristic medical information, and stores the third characteristic medical information; if there is no first characteristic medical information, uses the second characteristic medical information as the third characteristic medical information for storage; the medical information association module is completed in the Figure 2 server 3 in

[0046] A medical monitoring characteristic report output module, if the first characteristic medical information exists, outputs the first characteristic medical information and the third characteristic medical information to generate an IBS-D medical monitoring characteristic report; if the first characteristic medical information does not exist, outputs the third characteristic medical information to generate the IBS-D medical monitoring characteristic report; corresponding Figure 2 Specifically, the server 3 performs analysis and transmits the IBS-D medical monitoring characteristic report to the doctor 6 via the network 5 .

[0047] By establishing an irritable bowel feedback analysis model, it is possible to analyze and determine whether the first characteristic medical information of the IBS-D patient exists, and to extract the existing first characteristic medical information, and to screen it according to the second medical information of the IBS-D patient and the historical second characteristic medical information. Based on the above process, the deep data foundation of the existing monitoring data of the IBS-D patient can be mined, the monitoring range of the data depth can be improved, and a monitoring data foundation with richer data dimensions can be provided for the follow-up. At the same time, by comparing with the historical second characteristic medical information, the semantic information affected by the patient's emotions can be preliminarily screened, and the semantic information error caused by emotions can be reduced, the accuracy of the communication information data can be improved, and an accurate data foundation can be provided for the follow-up data feedback, which is convenient for doctors to refer to the data.

[0048] On this basis, the second characteristic medical information is further screened for key semantic information based on the first characteristic medical information to generate the third characteristic medical information, and the IBS-D medical monitoring characteristic report is generated by combining the first characteristic medical information and the third characteristic medical information. Through this step, the physiological characteristic information and the semantic characteristic information can be quantified and the corresponding weights can be generated. The initial report content in the IBS-D medical monitoring characteristic report can be weighted by the weights, and the corresponding medical monitoring characteristic report data can be obtained according to the weight calculation results for data feedback; based on this method, the actual data can be uniformly quantified, and the quantified data can facilitate the calculation of relevant data for the feedback work of the subsequent IBS-D medical monitoring characteristic report. Through these data, the communication information errors caused by emotional problems of IBS-D patients can be reduced, and at the same time, the data usage scope of physiological monitoring data can be expanded, providing an accurate data basis for subsequent data feedback, which is convenient for doctors to refer to data.

[0049] Embodiment 1

[0050] For the purpose of specific explanation, the following contents are combined for elaboration:

[0051] Medical information collection module, which acquires the first medical information and the second medical information of IBS-D patients; the first medical information includes vital sign information (such as, but not limited to, heartbeat, blood pressure, etc.) and physiological activity information (such as, but not limited to, bowel sounds, etc.) obtained by medical devices, and all the first medical information is obtained through relevant medical monitoring devices; the second medical information includes voice communication information and text communication information of IBS-D patients (such as, but not limited to, Internet communication platforms such as WeChat);

[0052] In the actual treatment process of IBS-D patients, in addition to using various physiological activities and vital sign information to monitor the patients' conditions to provide reference data for drug treatment; and since IBS-D patients are prone to emotional problems and it will affect the condition of IBS-D, so chat data is also one of the treatment reference data for IBS-D patients. Therefore, by obtaining these two types of comprehensive data, it helps to make the subsequent data analysis work more comprehensive, provides an accurate data basis for subsequent data feedback, and facilitates doctors to refer to the data;

[0053] Medical information analysis module, which transmits the first medical information to the irritable bowel syndrome feedback analysis model, determines whether there is the first characteristic medical information of the first medical information, and if so, extracts the first characteristic medical information and stores the data;

[0054] Furthermore, the first characteristic medical information is obtained through the abnormal irritable bowel physiological characteristic model of the irritable bowel syndrome feedback analysis model;

[0055] The abnormal irritable bowel physiological characteristic model includes a physiological characteristic data processing unit, a physiological characteristic data extraction unit, a physiological characteristic abnormality calculation unit, and a physiological abnormality characteristic output unit, as shown in the abnormal irritable bowel physiological characteristic model of Figure 3 ;

[0056] The physiological characteristic data processing unit preprocesses the first medical information; the physiological characteristic data extraction unit extracts the IBS-D medical information characteristics from the preprocessed first medical information; the physiological characteristic data extraction unit includes 5 LSTM layers, 2 spatio-temporal convolutional layers, 1 attention mechanism, and 1 feature activation layer; the physiological characteristic abnormality calculation unit determines whether there is the first characteristic medical information based on the IBS-D medical information characteristics; specifically:

[0057] σ IBS-D =f IBS-D (d F )·ω1·Cos(d F ,d U )+f IBS-D (d F )·ω2·Dtw(dF , d U );

[0058] Among them, σ IBS-D is the similarity of the first characteristic medical information, and f IBS-D (d F ) is the IBS-D medical information feature extracted from the first medical information; Cos is the cosine similarity algorithm, and d F is the first medical information, d U is the abnormal medical information of IBS-D, Dtw is the dynamic time warping algorithm, and ω1 and ω2 are the weights of feature similarity; d U is the abnormal historical physiological information and abnormal historical vital sign information combined with the expert-extracted and stored historical IBS-D patient monitoring data; ω1 and ω2 are default set to 0.5 and 0.5, and can be specifically changed according to the actual situation; f IBS-D (d F ) takes a value of 0 or 1, where 0 represents no abnormality and 1 represents an abnormality;

[0059] By mining the abnormal features in the deep data features of various physiological data and vital sign data of IBS-D patients as data weights for data quantification work, using the abnormal physiological data and abnormal vital sign data related to IBS-D as the data basis, and conducting similarity comparison in terms of data form, it is possible to increase the scope of use of monitoring data, alleviate the problem of data use limitations of current monitoring data, provide a data basis for subsequent IBS-D medical monitoring feature reports and communication information analysis, and facilitate doctors' data reference;

[0060] The physiological abnormality feature output unit outputs the first characteristic medical information and stores the data;

[0061] Transmit the second medical information to the irritable bowel feedback analysis model, compare the second medical information with the stored historical second medical information, generate the second characteristic medical information and store the data;

[0062] Furthermore, the second characteristic medical information is obtained according to the medical feedback information analysis model of the irritable bowel feedback analysis model; the medical feedback information analysis model includes a medical feedback information processing unit, a medical feedback key information extraction unit, and a medical feedback weight calculation and output unit, as shown in the medical feedback information analysis model of Figure 3 ; if it is text communication information, it is directly processed, and if it is voice communication information, the voice is converted into text, including but not limited to using the voice-to-text function of a chat communication platform, and open-source speech recognition models such as Whisper and Qwen2 can also be used;

[0063] Based on the communication information data of IBS-D patients, by extracting the semantic features therein, each key semantic feature in the IBS-D communication information data can be extracted. Based on this method, the error problem of the communication information data caused by the influence of emotional problems of IBS-D patients can be greatly reduced. At the same time, data reference can also be provided for subsequent feedback through the key semantic features;

[0064] The medical feedback information processing unit performs data feature processing on the second medical information; the data feature processing includes data format unification, punctuation data cleaning, and the maximum forward matching algorithm based on the dictionary;

[0065] The medical feedback key information extraction unit compares and extracts key semantic features from the second medical information and the historical second medical information after data feature processing. The medical feedback key information extraction unit uses the Transformer model; the historical second medical information is semantic feature data of the current patient and other patients stored in combination with expert experience without being affected by the emotions of the IBS-D disease;

[0066] The medical feedback weight calculation and output unit calculates the feedback key weight based on the key semantic features to generate the second feature medical information; specifically:

[0067]

[0068] Among them, is the i-th feedback key weight, i ∈ (1, N j )), N j is the total number of the second medical information of the j-th clustering category, j ∈ (1, n), n is the total number of clustering categories; ln is the logarithmic function with e as the base, Num is the statistical quantity of the key semantic features; Tran is the Transformer model, is the l-th second medical information, l ∈ (1, M), M is the total number of the second medical information, Km is the semantic clustering feature label data, and β1 and β2 are feedback key weight parameters; β1 + β2 = 1;

[0069] The clustering method is specifically to obtain the key semantics (such as, but not limited to, good, up, no, etc.) in the historical communication information data of IBS-D patients. According to expert experience, the default range for the goodness or badness represented by the semantics is 0 - 5, where 0 represents good and 5 represents bad, and it can be changed according to the actual situation; and corresponding weights are set for each key semantic. The weight represents the default relevance range with the IBS-D disease as 0 - 10, where 0 represents irrelevant and 10 represents completely relevant, and the range is not unique and can be changed according to the actual situation; the data weight of each semantic is specifically set according to expert experience;

[0070] Taking the semantic weight as the horizontal axis and the semantic quality as the vertical axis, a two-dimensional coordinate system is established. All key semantics are filled into the two-dimensional coordinate system according to the data corresponding to the weight and quality. Clustering is performed according to the k-means clustering algorithm, and the value of k is set according to expert experience. The central coordinates of each clustering range after clustering are used as the semantic weight and semantic quality of the clustering. The semantic clustering feature label data of each clustering range is calculated as follows:

[0071]

[0072] Among them, δ k-means is the semantic clustering feature label data of each clustering range, δ x is the abscissa of the clustering center, and δ y is the ordinate of the clustering center. is the maximum range of the abscissa (the default range is 10), is the maximum range of the ordinate (the default range is 5); Based on the key semantic features of the communication information data of IBS-D patients analyzed, these data are quantified, and combined with the clustering algorithm to analyze the key semantic meanings that the current patient wants to express. Through clustering these semantics combined with the clustering algorithm, the main meanings expressed by IBS-D patients can be analyzed, so as to reduce the error problem of semantic data caused by the emotional problems of IBS-D patients. At the same time, it can also provide a semantic data basis for subsequent feedback, facilitating doctors to refer to the data during the communication process;

[0073] Medical information association module. If the first characteristic medical information exists, the third characteristic medical information is obtained by associating the second characteristic medical information based on the first characteristic medical information, and the third characteristic medical information is stored; Specifically: Among them, is the j-th third characteristic medical information, i ∈ (1, N j )), j ∈ (1, n); Storing the third characteristic medical information includes the corresponding semantics and the calculation weights corresponding to the semantics; By identifying abnormal physiological data and abnormal vital sign data in the monitoring data by IBS-D patients, the key semantic features of IBS-D patients are further screened through these data. Through this method, the error problem of key semantic features caused by the emotional impact of patients due to IBS-D can be further reduced, providing a further data basis for subsequent data feedback, facilitating doctors to refer to the data;

[0074] If the first characteristic medical information does not exist, the second characteristic medical information is stored as the third characteristic medical information;

[0075] The medical monitoring feature report output module outputs the first feature medical information and the third feature medical information to generate an IBS-D medical monitoring feature report if the first feature medical information exists; if the first feature medical information does not exist, it outputs the third feature medical information to generate the IBS-D medical monitoring feature report.

[0076] Further, the initial report of the IBS-D medical monitoring feature report includes 1 IBS-D medical anomaly information label and K IBS-D medical dialogue information labels, where K≥1; each IBS-D medical dialogue information label corresponds to k pieces of the third feature medical information, where k≥1; the IBS-D medical anomaly information label corresponds to the first feature medical information; the medical dialogue information labels in the initial report are the data feedback labels of the IBS-D patient, such as whether there is pain, whether the diarrhea frequency increases, etc., and the corresponding semantics of the medical dialogue information labels are the third feature medical information. The data feedback labels and the corresponding semantics are set based on expert experience.

[0077] If the first feature medical information is not less than the abnormal medical information threshold, the initial report outputs the IBS-D medical anomaly information label; if the sum of the k pieces of the third feature medical information is not less than the medical dialogue information threshold, the initial report outputs the corresponding IBS-D medical dialogue information label.

[0078] The abnormal medical information threshold is obtained based on the mean value of the historical first feature medical information of historical IBS-D patients; the medical dialogue information threshold is also obtained based on the mean value of the historical third feature medical information of historical IBS-D patients.

[0079] Generate the IBS-D medical monitoring feature report based on the output IBS-D medical anomaly information label and the output IBS-D medical dialogue information label.

[0080] By establishing an initial report, all feedback problem data of IBS-D patients can be included to the greatest extent. At the same time, based on the abnormal data identified in the monitoring data and the key semantic features after analysis, the feedback problem data can be screened. Through this method, the applicable range of the monitoring data can be maximally improved, and the limitations of data use can be reduced; at the same time, according to the quantitative data of the key semantic features, it can be matched to the corresponding feature problems, and the error generated by the communication information data can be reduced through the method of converting the key semantic feature data, which is convenient for data feedback and provides accurate reference data for doctors.

[0081] Example Two

[0082] To specifically illustrate the accuracy analysis process of the abnormal irritable bowel physiological feature model of the irritable bowel feedback analysis model, the following content is elaborated:

[0083] A medical information collection module to obtain the first medical information and the second medical information of IBS-D patients; a medical information analysis module to transmit the first medical information to an irritable bowel feedback analysis model, determine whether there is a first characteristic medical information of the first medical information, and if so, extract the first characteristic medical information and store the data.

[0084] Further, the first characteristic medical information is obtained through an abnormal irritable bowel physiological feature model of the irritable bowel feedback analysis model; the abnormal irritable bowel physiological feature model includes a physiological feature data processing unit, a physiological feature data extraction unit, a physiological feature abnormality calculation unit, and a physiological abnormality feature output unit; by analyzing the monitored physiological data as time series data, it is possible to analyze whether the monitored physiological data and vital sign data of IBS-D patients show data abnormalities based on the existing data, and through identification, these abnormal data are automatically fed back, providing more explicit data references for doctors, and at the same time providing a basis for data analysis for subsequent feedback of communication information data, enhancing the applicability of IBS-D patient monitoring data.

[0085] The physiological feature data processing unit preprocesses the first medical information; the preprocessing includes Fourier noise reduction, time window data segmentation, and Z-score standardization.

[0086] The physiological feature data extraction unit extracts IBS-D medical information features from the preprocessed first medical information; the physiological feature data extraction unit includes 5 LSTM layers, 2 spatio-temporal convolutional layers, 1 attention mechanism, and 1 feature activation layer. As shown in Figure 4 , the LSTM layer corresponds to Figure 4 the memory layer in

[0087] Table 1 Abnormal recognition accuracy of the abnormal irritable bowel physiological feature model in 5 groups of simulated data

[0088] Simulated data set Abnormal recognition accuracy Abnormal recognition precision SED01 90.97％ 93.77％ SED02 91.31％ 93.62％ SED03 90.58％ 92.89％ SED04 90.69％ 93.54％ SED05 91.18％ 93.43％

[0089] As can be seen from Table 1, the accuracy rate of anomaly recognition is above 90%, and the precision rate is also about 93%, indicating a relatively high accuracy rate in identifying abnormal data.

[0090] The physiological feature anomaly calculation unit determines whether the first feature medical information exists based on the IBS-D medical information features for feature similarity.

[0091] The physiological anomaly feature output unit outputs the first feature medical information and stores the data.

[0092] Transmit the second medical information to the irritable bowel syndrome feedback analysis model, compare the second medical information with the stored historical second medical information, generate the second feature medical information and store the data.

[0093] The medical information association module, if the first feature medical information exists, associates the second feature medical information based on the first feature medical information to obtain the third feature medical information and stores the third feature medical information.

[0094] If the first feature medical information does not exist, use the second feature medical information as the third feature medical information for storage.

[0095] The medical monitoring feature report output module, if the first feature medical information exists, outputs the first feature medical information and the third feature medical information to generate an IBS-D medical monitoring feature report; if the first feature medical information does not exist, outputs the third feature medical information to generate the IBS-D medical monitoring feature report.

[0096] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A terminal for dynamic monitoring of IBS-D symptoms and interaction between doctors and patients, characterized in that: include: A medical information collection module, which obtains the first medical information and the second medical information of the IBS-D patient; The medical information analysis module transmits the first medical information to the irritable bowel feedback analysis model, determines whether there is first characteristic medical information of the first medical information, and if so, extracts the first characteristic medical information and stores the data; transmits the second medical information to the irritable bowel feedback analysis model, compares the second medical information with the stored historical second medical information, generates second characteristic medical information and stores the data; A medical information association module, if the first characteristic medical information exists, obtains third characteristic medical information by associating the second characteristic medical information with the first characteristic medical information, and stores the third characteristic medical information; if the first characteristic medical information does not exist, stores the second characteristic medical information as the third characteristic medical information; The medical monitoring characteristic report output module outputs the first characteristic medical information and the third characteristic medical information to generate an IBS-D medical monitoring characteristic report if the first characteristic medical information exists; if the first characteristic medical information does not exist, outputs the third characteristic medical information to generate the IBS-D medical monitoring characteristic report.

2. The IBS-D symptom dynamic monitoring and doctor-patient interaction terminal according to claim 1, characterized in that: The first medical information includes vital sign information and physiological activity information acquired by medical equipment; the second medical information includes voice communication information and text communication information of the IBS-D patient.

3. The IBS-D symptom dynamic monitoring and doctor-patient interaction terminal according to claim 1, characterized in that: The first medical information is transmitted to the irritable bowel feedback analysis model, and it is determined whether there is first characteristic medical information of the first medical information, and if so, the first characteristic medical information is extracted and stored, including: The first characteristic medical information is obtained through the abnormal irritable bowel physiological characteristic model of the irritable bowel feedback analysis model; The abnormal irritable bowel physiological characteristic model includes a physiological characteristic data processing unit, a physiological characteristic data extraction unit, a physiological characteristic abnormality calculation unit and a physiological abnormality characteristic output unit; The physiological characteristic data processing unit performs data preprocessing on the first medical information; The physiological characteristic data extraction unit extracts IBS-D medical information features from the preprocessed first medical information; the physiological characteristic data extraction unit includes 5 LSTM layers, 2 spatiotemporal convolution layers, 1 attention mechanism layer and 1 feature activation layer; the physiological characteristic abnormality calculation unit performs feature similarity based on the IBS-D medical information features to determine whether the first feature medical information exists; The abnormal physiological feature output unit outputs the first feature medical information and stores the data.

4. The IBS-D symptom dynamic monitoring and doctor-patient interaction terminal according to claim 3, characterized in that: The physiological characteristic abnormality calculation unit determines whether the first characteristic medical information exists based on the characteristic similarity of the IBS-D medical information characteristics, including: σ IBS-D =f IBS-D (d F )·ω1·Cos(d F ,d U )+f IBS-D (d F )·ω2·Dtw(d F ,d U ); Among them, σ IBS-D is the similarity of the first feature medical information, f IBS-D (d F ) is the IBS-D medical information feature extracted from the first medical information; Cos is the cosine similarity algorithm, d F For the first medical information, d U is the abnormal medical information of IBS-D, Dtw is the dynamic time planning algorithm, ω1 and ω2 are the feature similarity weights.

5. The IBS-D symptom dynamic monitoring and doctor-patient interaction terminal according to claim 1, characterized in that: Transmitting the second medical information to the irritable bowel feedback analysis model, performing data comparison between the second medical information and the stored historical second medical information, generating second characteristic medical information and storing the data, including: The second characteristic medical information is obtained according to the medical feedback information analysis model of the irritable bowel feedback analysis model; The medical feedback information analysis model includes a medical feedback information processing unit, a medical feedback key information extraction unit and a medical feedback weight calculation output unit; The medical feedback information processing unit performs data feature processing on the second medical information; The medical feedback key information extraction unit compares the second medical information after data feature processing with the historical second medical information to extract key semantic features, and the medical feedback key information extraction unit adopts a Transformer model; The medical feedback weight calculation output unit performs feedback key weight calculation based on the key semantic features to generate second feature medical information.

6. The IBS-D symptom dynamic monitoring and doctor-patient interaction terminal according to claim 5, characterized in that: The medical feedback weight calculation output unit calculates the feedback key weight according to the key semantic features, including: in, is the i-th feedback key weight, i∈(1,N j ), N j is the total number of the second medical information of the jth cluster category, j∈(1,n), n is the total number of cluster categories; ln is the logarithmic function with e as the base, Num is the number of key semantic features; Tran is the Transformer model, is the lth second medical information, l∈(1,M), M is the total number of second medical information, Km is the semantic clustering feature label data, β1 and β2 are the feedback key weight parameters.

7. The IBS-D symptom dynamic monitoring and doctor-patient interaction terminal according to claim 1, characterized in that: If the first characteristic medical information exists, obtaining the third characteristic medical information by associating the second characteristic medical information with the first characteristic medical information includes: in, is the jth third characteristic medical information, i∈(1,N j ), j∈(1,n); is the critical weight of the feedback of the ith item; IBS-D is the similarity of the first feature medical information; N j is the total number of the second medical information of the jth cluster category.

8. The IBS-D symptom dynamic monitoring and doctor-patient interaction terminal according to claim 1, characterized in that: If the first characteristic medical information exists, the first characteristic medical information and the third characteristic medical information are output to generate an IBS-D medical monitoring characteristic report; if the first characteristic medical information does not exist, the third characteristic medical information is output to generate the IBS-D medical monitoring characteristic report, including: The initial report of the IBS-D medical monitoring characteristic report includes 1 IBS-D medical abnormality information tag and K IBS-D medical dialogue information tags, K≥1; each of the IBS-D medical dialogue information tags corresponds to k third characteristic medical information, k≥1; the IBS-D medical abnormality information tag corresponds to the first characteristic medical information; If the first characteristic medical information is not less than the abnormal medical information threshold, the initial report outputs the IBS-D medical abnormal information label; if the sum of the k third characteristic medical information is not less than the medical dialogue information threshold, the initial report outputs the corresponding IBS-D medical dialogue information label; The IBS-D medical monitoring feature report is generated according to the output IBS-D medical abnormality information tag and the output IBS-D medical dialogue information tag.

Images