An intelligent remote follow-up method and system for tumor patients

Abstract

The present invention discloses an intelligent remote follow-up method and system for cancer patients, which relates to the field of intelligent medical technology. The method comprises: collecting follow-up data through a remote medical terminal, processing the data to obtain a sequence of physical signs and symptoms, and generating a dynamic follow-up assessment score through a time series prediction model; performing semantic analysis on the patient's electronic medical record data based on a medical knowledge graph, extracting tumor stage classification data, radiotherapy and chemotherapy measurement data, weight and nutrition indicators, and laboratory test data, determining the basic risk coefficient, cumulative dose ratio, and body status score, and generating a baseline follow-up assessment score through a prediction model; and calculating a comprehensive follow-up grade and generating a next follow-up plan based on the dynamic follow-up assessment score and the baseline follow-up assessment score. The present invention improves the accuracy of patient status assessment, achieves precise allocation of medical resources, and effectively improves the quality and efficiency of remote follow-up.

Description

Technical Field

[0001] The present invention relates to the field of intelligent medical technology, and in particular to an intelligent remote follow-up method and system for tumor patients. Background Art

[0002] Remote follow-up management of cancer patients is an indispensable part of the contemporary cancer diagnosis and treatment system. Its development process has undergone a major transformation from traditional telephone follow-up to intelligent remote monitoring. Telemedicine systems based on Internet of Things technology and wearable devices have realized real-time collection of patients' physiological indicators, and the introduction of artificial intelligence and big data analysis technology has made the assessment of patients' status more accurate. However, the existing remote follow-up system still has problems such as insufficient data integration, a single evaluation model, and rigid follow-up strategies. Specifically, the current system often separates real-time monitoring data from electronic medical record information and lacks an effective multi-source heterogeneous data fusion mechanism; the evaluation model is mostly based on static indicators at a single time point, which makes it difficult to capture the dynamic changes in the patient's status; and the preset fixed-period follow-up model cannot adjust the follow-up frequency in a timely manner according to individual differences and changes in the patient's condition, resulting in inefficient allocation of medical resources.

[0003] More critically, existing technologies have significant limitations when dealing with the complex clinical characteristics of cancer patients. Traditional assessment methods struggle to effectively integrate multi-dimensional clinical features such as tumor staging information, treatment measurement data, nutritional status, and laboratory indicators, resulting in insufficiently accurate risk assessments. Furthermore, due to a lack of semantic analysis capabilities based on medical knowledge graphs, the system is unable to fully mine the implicit information in electronic medical records, impacting the reliability of assessment results. Furthermore, existing follow-up planning methods are relatively mechanical, failing to establish an effective linkage mechanism between dynamic and baseline assessments, making it impossible to achieve intelligent early warning and timely intervention for changes in patient status. Summary of the Invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] Therefore, the present invention provides an intelligent remote follow-up method and system for cancer patients, which can solve the problems mentioned in the background technology.

[0006] To solve the above technical problems, the present invention provides the following technical solutions: a method for intelligent remote follow-up of cancer patients, comprising: collecting follow-up data through a telemedicine terminal, the follow-up data including real-time vital sign monitoring data and symptom quantification data; standardizing the real-time vital sign monitoring data to obtain a vital sign indicator sequence; structurally processing the symptom quantification data to obtain a symptom feature vector; inputting the vital sign indicator sequence and the symptom feature vector into a time series prediction model to generate a dynamic follow-up assessment score; performing semantic analysis on the patient's electronic medical record data based on a medical knowledge graph to extract tumor staging classification data, radiotherapy and chemotherapy measurement data, weight and nutritional indicators, and laboratory test data; determining a baseline risk coefficient based on the tumor staging classification data; calculating a cumulative dose ratio based on the radiotherapy and chemotherapy measurement data; calculating a body state score based on the weight and nutritional indicators and the laboratory test data; inputting the baseline risk coefficient, the cumulative dose ratio, and the body state score into a prediction model to generate a baseline follow-up assessment score; and calculating a comprehensive follow-up level and generating a next follow-up plan based on the dynamic follow-up assessment score and the baseline follow-up assessment score.

[0007] As a preferred solution of the intelligent remote follow-up method for tumor patients described in the present invention, the standardized processing formula for the real-time vital sign monitoring data is expressed as:

[0008] ;

[0009] in, is the historical mean value of the jth physical sign indicator; is the historical standard deviation of the jth physical sign indicator; is the length of the time series; m is the number of physical signs; is the value of the i-th time point in the physical sign index sequence obtained after standardization; is the original value of the jth vital sign indicator at the i-th time point in the real-time vital sign monitoring data.

[0010] The structured processing formula for the symptom quantitative data is expressed as:

[0011] ;

[0012] in, is the weight coefficient of the kth symptom; p is the number of symptom indicators; T is the length of the observation time window; represents the value of the kth symptom at time t in the symptom quantification data; represents the historical maximum reference value of the kth symptom; Represents the value at time t in the symptom feature vector obtained after structured processing.

[0013] As a preferred solution of the intelligent remote follow-up method for tumor patients described in the present invention, the time series prediction model is constructed based on a convolutional neural network and a long short-term memory network.

[0014] Inputting the physical sign indicator sequence and the symptom feature vector into a time series prediction model to generate a dynamic follow-up assessment score includes the following steps: fusing the physical sign indicator sequence and the symptom feature vector with time series features in the time series prediction model:

[0015] ;

[0016] in, It represents the fused feature vector at time t in the time series prediction model, and the superscript f represents the fused feature dimension; represents the value of the vital sign indicator sequence at time t; represents the value of the symptom feature vector at time t; the symbol || represents the vector splicing operation.

[0017] The convolutional neural network in the time series prediction model is used to extract time series features from the fusion features:

[0018] ;

[0019] in, represents the f-dimensional fusion feature sequence from time tj to time t; Represents the j-th convolution kernel parameter; Represents the convolution layer bias term; K represents the convolution time window size; Represents the c-dimensional features output by the convolutional layer.

[0020] The output features of the convolutional neural network are input into the long short-term memory network to generate the dynamic follow-up assessment score:

[0021] ;

[0022] in, represents the dynamic follow-up assessment score; represents the feature mapping function of the lth layer of the long short-term memory network; represents the feature weight coefficient of the lth layer at time t; L represents the number of neural network layers; represents the risk volatility factor; Represents the normalization function.

[0023] If the rate of change of the physical sign indicator sequence is greater than the rate of change of the symptom feature vector, then:

[0024] ;

[0025] otherwise:

[0026] ;

[0027] in, Represents the gradient norm of the vital sign index sequence; represents the gradient norm of the symptom feature vector.

[0028] If the change trends of the physical sign indicator sequence and the symptom feature vector are consistent, then:

[0029] ;

[0030] otherwise:

[0031]

[0032] Among them, cov represents the covariance function; Represents the standard deviation of the physical sign indicator sequence; represents the standard deviation of the symptom feature vector.

[0033] As a preferred solution of the intelligent remote follow-up method for tumor patients described in the present invention, the basic risk coefficient is determined according to the tumor staging classification data, and the formula is expressed as follows:

[0034] ;

[0035] in, represents the basic risk coefficient at time t; S represents the number of tumor stage characteristics; represents the weight coefficient of the sth stage feature; represents the degree index of the s-th stage feature; Represents the time progression factor of the sth stage characteristic.

[0036] The calculation formula of the cumulative dose ratio is:

[0037] ;

[0038] in: It represents the cumulative dose ratio at time t; Indicates the The actual cumulative dose of the therapeutic drug; Indicates the The standard cumulative dose of a therapeutic drug; M represents the number of drug types; λ represents the time decay coefficient; Indicates the time interval since the last dose.

[0039] The calculation formula of the body status score is:

[0040] ;

[0041] in, represents the body state score at time t; N represents the number of state indicators; Indicates the The weight of each state indicator; represents the normalized value of the nth weight nutrition index; It represents the normalized value of the nth laboratory test index; Indicates the indicator volatility variance.

[0042] As a preferred embodiment of the intelligent remote follow-up method for cancer patients described in the present invention, the basic risk coefficient, the cumulative dose ratio, and the body status score are input into a prediction model to generate a baseline follow-up assessment score, which is expressed as follows:

[0043] ;

[0044] in, represents the baseline follow-up assessment score at time t; represents the normalization function; ε represents the smoothing factor; γ represents the time adjustment coefficient.

[0045] If the basic risk factor Greater than the basic risk coefficient of the previous moment , and the cumulative dose ratio Greater than the cumulative dose ratio of the previous moment ,but:

[0046] ;

[0047] otherwise .

[0048] If the body status score Less than the body status score at the previous moment ,but:

[0049] ;

[0050] otherwise .

[0051] in, Indicates the basic time adjustment coefficient; represents the basic smoothing factor; δ represents the state change threshold.

[0052] As a preferred embodiment of the intelligent remote follow-up method for tumor patients of the present invention, the comprehensive follow-up grade is calculated based on the dynamic follow-up evaluation score and the baseline follow-up evaluation score:

[0053] ;

[0054] in, represents the comprehensive follow-up grade at time t; represents the dynamic follow-up assessment score; represents the baseline follow-up assessment score; represents the dynamic follow-up assessment score sequence from the initial moment to moment t; represents the baseline follow-up assessment score sequence from the initial moment to moment t; ω represents the dynamic assessment weight coefficient; α represents the assessment bias adjustment coefficient.

[0055] As a preferred solution of the intelligent remote follow-up method for tumor patients of the present invention, the following steps are performed: generating the next follow-up plan based on the comprehensive follow-up level:

[0056] ;

[0057] in, represents the next follow-up time interval calculated at time t; represents the basic follow-up time interval; β represents the time adjustment coefficient of the comprehensive follow-up level; λ represents the dynamic change adjustment coefficient; Indicates the dynamic follow-up assessment score at the previous moment.

[0058] To further solve the above technical problems, the present invention provides the following technical solutions: an intelligent remote follow-up system for cancer patients, comprising: a data processing module for collecting follow-up data through a remote medical terminal, wherein the follow-up data includes real-time vital sign monitoring data and symptom quantification data, standardizing the real-time vital sign monitoring data to obtain a vital sign indicator sequence, and structurally processing the symptom quantification data to obtain a symptom feature vector, inputting the vital sign indicator sequence and the symptom feature vector into a time series prediction model to generate a dynamic follow-up evaluation score; an analysis and evaluation module for analyzing the patient's electronic medical records based on a medical knowledge graph. The data is semantically analyzed to extract tumor staging classification data, radiotherapy and chemotherapy measurement data, weight and nutrition indicators, and laboratory test data; the basic risk coefficient is determined based on the tumor staging classification data; the cumulative dose ratio is calculated based on the radiotherapy and chemotherapy measurement data; the body state score is calculated based on the weight and nutrition indicators and the laboratory test data; the basic risk coefficient, the cumulative dose ratio and the body state score are input into a prediction model to generate a baseline follow-up assessment score; a follow-up planning module is used to calculate a comprehensive follow-up level and generate a next follow-up plan based on the dynamic follow-up assessment score and the baseline follow-up assessment score.

[0059] A computer device includes a memory and a processor, wherein the memory stores a computer program, and is characterized in that when the processor executes the computer program, it implements the steps of the above-mentioned intelligent remote follow-up method for cancer patients.

[0060] A computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps of the intelligent remote follow-up method for cancer patients as described above are implemented.

[0061] Beneficial effects of the present invention: By constructing a dual analysis engine of a time series prediction model and a medical knowledge graph, the present invention achieves deep fusion and dynamic feature extraction of multi-source heterogeneous data, and effectively improves the accuracy and timeliness of remote follow-up by establishing feature association rules and a multi-level threshold judgment mechanism. Specifically, the beneficial effects of the present invention are reflected in: on the one hand, through the collaborative analysis of multi-dimensional features and dynamic weight adjustment, the accuracy of patient status assessment is improved; on the other hand, through the adaptive follow-up plan generation mechanism, the precise allocation of medical resources is achieved, effectively improving the quality and efficiency of remote follow-up. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0063] Figure 1 This is a schematic diagram of the overall process of an intelligent remote follow-up method for cancer patients proposed by the present invention;

[0064] Figure 2 This is a diagram of the computer equipment used in the intelligent remote follow-up method for tumor patients proposed by the present invention. DETAILED DESCRIPTION

[0065] To make the above-mentioned objects, features, and advantages of the present invention more clearly understood, the following detailed description of the specific embodiments of the present invention is given in conjunction with the accompanying drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in this field without creative work should fall within the scope of protection of the present invention.

[0066] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0067] Example 1, with reference to Figure 1 , which is an embodiment of the present invention, provides an intelligent remote follow-up method for cancer patients.

[0068] Figure 1 The figure shows the overall process of an intelligent remote follow-up method for cancer patients, including the following steps:

[0069] S1: Follow-up data are collected through telemedicine terminals. The follow-up data include real-time vital sign monitoring data and symptom quantification data. The real-time vital sign monitoring data are standardized to obtain a vital sign indicator sequence. The symptom quantification data are structured to obtain a symptom feature vector. The vital sign indicator sequence and symptom feature vector are input into the time series prediction model to generate a dynamic follow-up assessment score.

[0070] S1.1: Collect follow-up data through telemedicine terminals.

[0071] Among them, follow-up data include real-time vital sign monitoring data and symptom quantification data.

[0072] During the data collection phase of the telemedicine terminal, smart medical devices equipped with physiological parameter sensor modules first collect real-time vital sign monitoring data, including electrocardiogram (ECG) data, blood oxygen saturation, respiratory rate, body temperature, blood pressure, and other physiological indicators. This data is transmitted to the telemedicine terminal in real time via the Bluetooth low energy protocol. Preliminary data verification and outlier screening are performed on the terminal to ensure data authenticity and validity.

[0073] During the collection of symptom quantification data, the telemedicine terminal uses a built-in medical-grade electronic scale system to record objective indicators such as the patient's 24-hour pain intensity, average daily sleep duration, daily food intake, and daily activity level. A fixed time window data collection strategy, combined with information such as data collection timestamps and device numbers, establishes a standardized data collection flow. This data is then uploaded to the medical data center in real time via an encrypted channel, providing a reliable data foundation for subsequent data processing and analysis.

[0074] S1.2: Standardize the real-time vital sign monitoring data to obtain a vital sign indicator sequence, and structure the symptom quantification data to obtain a symptom feature vector.

[0075] Standardized processing formula for real-time vital sign monitoring data:

[0076] ;

[0077] in, is the historical mean value of the jth physical sign indicator; is the historical standard deviation of the jth physical sign indicator; is the length of the time series; m is the number of physical signs; is the value of the i-th time point in the physical sign index sequence obtained after standardization; is the original value of the jth vital sign indicator at the i-th time point in the real-time vital sign monitoring data.

[0078] The structured processing formula for symptom quantitative data is as follows:

[0079] ;

[0080] in, is the weight coefficient of the kth symptom; p is the number of symptom indicators; T is the length of the observation time window; represents the value of the kth symptom at time t in the symptom quantification data; represents the historical maximum reference value of the kth symptom; Represents the value at time t in the symptom feature vector obtained after structured processing.

[0081] S1.3: Input the physical sign indicator sequence and symptom feature vector into the time series prediction model to generate a dynamic follow-up assessment score.

[0082] Specifically, the time series prediction model is built based on convolutional neural networks and long short-term memory networks.

[0083] S1.3.1: In the time series prediction model, the physical sign indicator sequence and the symptom feature vector are fused into time series features:

[0084] ;

[0085] in, It represents the fused feature vector at time t in the time series prediction model, and the superscript f represents the fused feature dimension; Represents the value of the vital sign index sequence at time t; Represents the value of the symptom feature vector at time t; the symbol || represents the vector concatenation operation.

[0086] S1.3.2: Convolutional neural network in time series prediction model extracts time series features from fusion features:

[0087] ;

[0088] in, represents the f-dimensional fusion feature sequence from time tj to time t; Represents the j-th convolution kernel parameter; Represents the convolution layer bias term; K represents the convolution time window size; Represents the c-dimensional features output by the convolutional layer.

[0089] S1.3.3: Input the output features of the convolutional neural network into the long short-term memory network to generate dynamic follow-up assessment scores:

[0090] ;

[0091] in, represents the dynamic follow-up assessment score; Represents the feature mapping function of the lth layer of the long short-term memory network; represents the feature weight coefficient of the lth layer at time t; L represents the number of neural network layers; represents the risk volatility factor; Represents the normalization function.

[0092] Feature relationship rules:

[0093] 1. Dynamic adjustment rules for feature weights:

[0094] If the rate of change of the physical sign index sequence is greater than the rate of change of the symptom characteristic vector, then:

[0095] ;

[0096] otherwise:

[0097] ;

[0098] in, Represents the gradient norm of the vital sign index sequence; Represents the gradient norm of the symptomatic eigenvector.

[0099] 2. Calculation rules for risk volatility factors:

[0100] If the changing trends of the physical sign index sequence and the symptom feature vector are consistent, then:

[0101] ;

[0102] otherwise:

[0103]

[0104] Among them, cov represents the covariance function; Indicates the standard deviation of the physical sign index series; represents the standard deviation of the symptom feature vector.

[0105] This embodiment details the specific implementation of a time series prediction model. First, in the feature fusion phase, a vector concatenation approach is used to construct fused features. This fusion method preserves the complete temporal information of the vital sign indicator sequence and symptom feature vector. Compared to simple weighted combination, vector concatenation avoids mutual interference between features, making subsequent feature extraction more accurate. For example, when a patient's vital signs such as temperature and blood pressure change, this fusion approach preserves their independent change characteristics, preventing them from being obscured by changes in other features. In the feature extraction phase, the present invention implements local pattern recognition of the fused features. Specifically, the convolution kernel size K=3 is set, meaning that feature extraction is performed within a window of three time points. This setting effectively captures the short-term variations in vital sign indicators and symptom characteristics. The ReLU activation function further enhances the model's nonlinear expression capabilities, extracting more effective feature representations. In the evaluation score generation phase, a hierarchical feature mapping function adopts a two-layer structure: the first layer has a dimension of 64, and the second layer has a dimension of 32. This design enables the extraction of deep features layer by layer. Furthermore, a risk volatility factor is introduced to ensure that the evaluation score can respond promptly to abnormal changes in health status.

[0106] In addition, in this embodiment, the dynamic adjustment of feature weights is achieved through the gradient norm ratio. When , it means that the change of physical signs is more significant, and the weight update formula is The weight of physical signs will be automatically increased, so that the model pays more attention to physical sign changes. Conversely, when the symptom changes are more significant, the model will increase the weight of the symptom accordingly. The calculation of the risk fluctuation factor is based on the covariance of physical signs and symptom characteristics, through the formula When the changing trends of the two types of features are consistent, the change in health status is highly credible; when the changing trends are inconsistent, the model will increase the risk factor, raising the vigilance of the assessment. For example, if the physical signs are normal but the symptoms are abnormal, the increase in the risk factor may indicate a potential health risk.

[0107] Through the above-mentioned implementation, the present invention's time series prediction model effectively integrates and dynamically evaluates physical signs and symptom characteristics, providing reliable technical support for remote follow-up. Tests have shown that the model accurately captures changing health trends and promptly identifies potential health risks, significantly improving both assessment accuracy and timeliness compared to traditional fixed-weight models.

[0108] S2: Perform semantic analysis on the patient's electronic medical record data based on the medical knowledge graph, extract tumor staging classification data, radiotherapy and chemotherapy measurement data, weight and nutrition indicators, and laboratory test data, determine the basic risk coefficient based on the tumor staging classification data, calculate the cumulative dose ratio based on the radiotherapy and chemotherapy measurement data, calculate the body status score based on the weight and nutrition indicators and laboratory test data, input the basic risk coefficient, cumulative dose ratio and body status score into the prediction model to generate the baseline follow-up assessment score.

[0109] S2.1: Perform semantic analysis on the patient's electronic medical record data based on the medical knowledge graph to extract tumor staging classification data, radiotherapy and chemotherapy measurement data, weight and nutrition indicators, and laboratory test data. The formula is expressed as:

[0110] ;

[0111] in, represents the d-dimensional structured medical data extracted at time t, including tumor staging classification data, radiotherapy and chemotherapy measurement data, weight and nutrition indicators, and laboratory test data; G represents the medical knowledge graph; represents the electronic medical record data of the target patient at time t; Represents the semantic analysis mapping function based on the knowledge graph.

[0112] It should be noted that this formula performs semantic analysis of electronic medical record data based on the medical knowledge graph, effectively converting unstructured electronic medical record data into standardized structured data. Through the semantic mapping capabilities of the medical knowledge graph, multi-dimensional clinical features such as tumor staging classification data, radiotherapy and chemotherapy measurement data, weight and nutritional indicators, and laboratory test data can be accurately identified and extracted, avoiding the subjective biases and omissions that may occur in traditional manual extraction methods, and improving the accuracy and comprehensiveness of data extraction. At the same time, the formula uses a time-series processing method, marking data at different times with timestamps, which facilitates subsequent analysis of the dynamic changes in the patient's condition and provides a reliable data foundation for accurate assessment of the patient's status.

[0113] S2.2: Determine the basic risk factor based on tumor stage classification data. The formula is:

[0114] ;

[0115] in, represents the basic risk coefficient at time t; S represents the number of stage features in the tumor stage classification data; Represents the weight coefficient of the sth stage feature in the tumor stage classification data; Represents the degree index of the sth stage feature in the tumor stage classification data; Represents the time progression factor of the sth stage characteristic.

[0116] It should be noted that the calculation formula of the basic risk coefficient introduces the time progression factor on the basis of the traditional tumor staging assessment method. , transforming the static stage characteristics into dynamic evaluation indicators. The introduction of This multidimensional, comprehensive calculation method not only considers the static characteristics of tumor staging but also incorporates the temporal characteristics of disease progression, achieving a transition from discrete staging to continuous risk assessment, significantly improving the accuracy and timeliness of risk assessment. Furthermore, the use of a weighted summation approach makes this assessment method highly interpretable and scalable, facilitating dynamic adjustment and optimization in clinical practice.

[0117] S2.3: Calculate the cumulative dose ratio based on the chemoradiotherapy data, and calculate the physical status score based on the weight, nutritional indicators and laboratory test data.

[0118] Specifically, the calculation formula for the cumulative dose ratio is:

[0119] ;

[0120] in: It represents the cumulative dose ratio at time t; Indicates the first The actual cumulative dose of the therapeutic drug; Indicates the The standard cumulative dose of a therapeutic drug; M represents the number of drug types; λ represents the time decay coefficient; Indicates the time interval since the last dose.

[0121] The cumulative dose ratio formula combines the normalized dose ratio and the time decay characteristics, and uses the numerator and the denominator The ratio structure of , realizes the unified quantification of the cumulative dose of multiple therapeutic drugs. In particular, the time decay term is introduced , scientifically simulates the drug's metabolic process in the body, avoiding the limitation of traditional cumulative dose calculation methods that treat administration at different time points as equivalent. Through dynamic adjustment of the time decay coefficient λ, it not only ensures the continuity of long-term medication history but also highlights the timeliness of recent dosing, making dose assessment more consistent with clinical practice. This time-weighted cumulative dose assessment method provides a more accurate reference for dosing, facilitates timely adjustment of treatment plans, and reduces the risk of drug accumulation.

[0122] The calculation formula for the body status score is:

[0123] ;

[0124] in, represents the body status score at time t; N represents the number of status indicators in weight and nutritional indicators and laboratory test data; Indicates the The weight of each state indicator; represents the normalized value of the nth weight nutrition index; It represents the normalized value of the nth laboratory test index; Indicates the indicator volatility variance.

[0125] It should be noted that the body state score formula proposes a new comprehensive evaluation method for body state. The product form of wittily realizes the coordinated evaluation of weight nutrition index and laboratory test index, overcoming the limitation of independent evaluation of each index in traditional methods. The weight coefficient introduced in the formula This enables the evaluation system to differentiate weights based on the clinical importance of different indicators, thus improving the pertinence of the evaluation. As a dynamic correction factor, it effectively smooths abnormal fluctuations in indicators and improves the stability of assessment results. This multi-dimensional indicator-integrated assessment method not only enhances the comprehensiveness of body status assessment, but also ensures the reliability of assessment results through adaptive adjustment of variance terms, providing a more accurate quantitative reference for understanding the patient's overall condition.

[0126] S2.4: Input the basic risk factor, cumulative dose ratio, and body status score into the prediction model to generate the baseline follow-up assessment score, which is expressed as follows:

[0127] ;

[0128] in, represents the baseline follow-up assessment score at time t; It represents the normalization function of the time series forecasting model; ε represents the smoothing factor of the time series forecasting model; γ represents the time adjustment coefficient of the time series forecasting model.

[0129] It should be noted that the baseline follow-up assessment score formula is based on the fraction structure A dynamic balance mechanism between risk factors and protective factors has been cleverly established, in which the molecular Represents the cumulative effect of disease risk and treatment burden, the denominator It reflects the patient's body tolerance. The introduction of ε effectively avoids the calculation singularity when the denominator approaches zero. In particular, through the time adjustment term The evaluation score is gradually adjusted with the follow-up time, avoiding the sharp fluctuation of the evaluation results in the early stage of follow-up. The application of ensures the numerical comparability of assessment scores, providing a unified metric for assessment results across different patients and at different time periods. This multi-factor, dynamic and balanced assessment mechanism provides a more scientific, quantitative basis for developing follow-up plans, effectively improving the accuracy and reliability of follow-up assessments.

[0130] If the basic risk factor Greater than the basic risk coefficient of the previous moment , and the cumulative dose ratio Greater than the cumulative dose ratio of the previous moment ,but:

[0131] ;

[0132] otherwise .

[0133] If the body status score Less than the body status score at the previous moment ,but: ;

[0134] otherwise ;

[0135] in, Indicates the basic time adjustment coefficient; represents the basic smoothing factor; δ represents the state change threshold.

[0136] Preferably, the present invention realizes accurate capture and timely response to changes in patient status through the above two feature association rules. In the association rule between the basic risk coefficient and the dose ratio, when it is detected that the risk and treatment load increase at the same time, the formula Dynamically adjust the time adjustment coefficient to make the assessment system respond faster to high-risk conditions. At the same time, in the dynamic adjustment rule of the body state, the threshold δ is introduced as the judgment standard for the deterioration of the body state. When the body state is detected to be significantly deteriorating, the formula Adaptively adjust the smoothing factor to enhance the assessment model's sensitivity to changes in the body's condition. This dual-feature association mechanism not only improves the intelligence level of remote follow-up assessments, but also provides early warning of changes in the patient's condition, providing reliable decision-making support for clinicians to adjust follow-up strategies in a timely manner, effectively improving the accuracy and timeliness of remote follow-up for cancer patients. In particular, when the body's condition deteriorates sharply or treatment risks suddenly increase, this mechanism can quickly adjust assessment parameters to ensure that follow-up assessment results accurately reflect the patient's actual condition, providing a scientific basis for medical staff to take timely intervention measures.

[0137] S3: Based on the dynamic follow-up assessment scores and the baseline follow-up assessment scores, calculate the comprehensive follow-up level and generate the next follow-up plan.

[0138] S3.1: Calculate the comprehensive follow-up level based on the dynamic follow-up assessment score and the baseline follow-up assessment score:

[0139] ;

[0140] in, represents the comprehensive follow-up grade at time t; represents the dynamic follow-up assessment score; represents the baseline follow-up assessment score; represents the dynamic follow-up assessment score sequence from the initial moment to moment t; represents the baseline follow-up assessment score sequence from the initial moment to moment t; ω represents the dynamic assessment weight coefficient; α represents the assessment bias adjustment coefficient.

[0141] If the comprehensive follow-up level If the calculation results meet the following conditions, the corresponding follow-up level and corresponding measures are determined:

[0142] 1. If the comprehensive follow-up level is The rate of change is less than the stable threshold, and the dynamic follow-up assessment score Baseline follow-up assessment scores If the ratio is close to 1, it is determined to be a stable level;

[0143] 2. If the comprehensive follow-up level Greater than the comprehensive follow-up level of the previous moment , and the dynamic follow-up assessment score The growth rate exceeded the baseline follow-up assessment score If the growth rate is lower than , it is determined to be at the observation level;

[0144] 3. If any of the following conditions are met, the warning level is determined:

[0145] Dynamic follow-up assessment score Greater than the baseline follow-up assessment score for two consecutive times Warning threshold;

[0146] Comprehensive follow-up level The rising rate exceeds the warning threshold and the duration exceeds the warning time window.

[0147] 4. If any of the following conditions are met, it will be determined as an emergency level:

[0148] Dynamic follow-up assessment score Baseline follow-up assessment scores The deviation term Exceeding the emergency threshold;

[0149] Comprehensive follow-up grade for three consecutive times They all show an accelerating upward trend, and the most recent rate of change exceeds the emergency change threshold.

[0150] Among them, the stability threshold is a key parameter for determining the stability of cancer patients' condition. Its calculation fully considers the historical statistical characteristics of the patient's physical sign indicator sequence and symptom feature vector. Specifically, the threshold is based on the dynamic follow-up assessment score. Historical fluctuation range and baseline follow-up assessment scores The baseline interval is determined comprehensively. In practical applications, the standard deviation of the evaluation scores within the sliding time window can be used as a benchmark, combined with the disease progression patterns in the medical knowledge graph for dynamic calibration. Preferably, the threshold can be set at 1.5 to 2 times the standard deviation, which ensures sensitivity to fluctuations in the disease state while avoiding misjudgments caused by random fluctuations.

[0151] Early warning thresholds primarily serve to identify early risks during remote follow-up. Their setting is based on quantitative assessment criteria for tumor progression in clinical medicine. This threshold is determined by analyzing mutational signatures within the physical sign indicator sequence and the clustering characteristics of symptom feature vectors, combined with a comprehensive analysis of chemoradiotherapy data and systemic status scores. The system prioritizes machine learning methods, analyzing the characteristics of early warning events in historical patient data to extract key inflection points in risk evolution, thereby establishing quantitative criteria for early warning determination. In follow-up scenarios for specific cancer types, this threshold can be customized based on disease characteristics and treatment plans.

[0152] The emergency change threshold focuses on the early signs of rapid deterioration of the disease, and its setting is based on the second-order derivative characteristics of the dynamic follow-up assessment score. This threshold is mainly determined based on the acceleration characteristics in the time series prediction model. Combined with the development law of clinical critical and severe diseases, it is preferred to set the threshold to 0.15~0.25. Specifically, when it is detected that the acceleration of the change in the assessment score exceeds the threshold range, the emergency response mechanism is triggered. In practical applications, for different types of tumors, fine adjustments can be made within this range according to their progression speed: for relatively slowly progressing tumors (such as thyroid cancer), it can be around 0.15, while for faster progressing tumors (such as pancreatic cancer), it can be around 0.25 to ensure that the system can capture signs of rapid deterioration of the disease in a timely manner.

[0153] The emergency threshold is the most stringent monitoring parameter in the entire remote follow-up system, and its setting is based on the characteristic pattern of critical events extracted from medical big data analysis. Through retrospective analysis of critical events in historical data, it is preferred to set the threshold to 0.35~0.45. When the deviation between the dynamic follow-up assessment score and the baseline follow-up assessment score exceeds this interval, it indicates that the patient's status has significantly deviated from the expected trajectory. Specifically, 0.40 can be taken as the standard value for general cancer patients, which can be reduced to 0.35 for elderly patients or patients with serious underlying diseases, and appropriately increased to 0.45 for patients with good physical condition and strong tolerance, so as to achieve stratified and precise management.

[0154] It should be noted that the calculation formula for the comprehensive follow-up level proposes a three-dimensional integrated comprehensive follow-up level calculation method. and The normalization of dynamic evaluation and baseline evaluation is realized, overcoming the problem of inconsistent dimensionality of the two evaluation scores. Specifically, the deviation term is introduced. It captures the degree of difference between dynamic and baseline assessments, ensuring equivalent treatment of positive and negative deviations through absolute value calculations. This multi-dimensional, comprehensive calculation method not only balances the impact of immediate and baseline status but also enables flexible configuration of assessment strategies through adjustment of the weight coefficient ω, providing a more comprehensive and accurate quantitative basis for graded assessments during remote follow-up.

[0155] S3.2: Generate the next follow-up plan based on the comprehensive follow-up level:

[0156] ;

[0157] in, represents the next follow-up time interval calculated at time t; represents the basic follow-up time interval; β represents the time adjustment coefficient of the comprehensive follow-up level; λ represents the dynamic change adjustment coefficient; Indicates the dynamic follow-up assessment score at the previous moment.

[0158] It should be noted that this formula is based on the exponential function The core structure of the method realizes the nonlinear mapping relationship between the follow-up frequency and the comprehensive follow-up level. , enabling real-time adjustments to follow-up plans based on the rate of change in the patient's condition, automatically shortening the follow-up interval when large fluctuations are detected. This adaptive follow-up mechanism, based on the dynamic changes in the patient's condition, effectively addresses the lack of targetedness of traditional fixed-period follow-up plans. It avoids excessive follow-up of stable patients while ensuring that high-risk patients receive timely medical intervention, significantly improving the timeliness of remote follow-up and the efficiency of medical resource utilization.

[0159] In summary, the present invention achieves deep fusion and dynamic feature extraction of multi-source heterogeneous data by constructing a dual analysis engine of a time series prediction model and a medical knowledge graph, and effectively improves the accuracy and timeliness of remote follow-up by establishing feature association rules and a multi-level threshold judgment mechanism. Specifically, the beneficial effects of the present invention are reflected in: on the one hand, through the collaborative analysis of multi-dimensional features and dynamic weight adjustment, the accuracy of patient status assessment is significantly improved; on the other hand, through the adaptive follow-up plan generation mechanism, the precise allocation of medical resources is achieved, effectively improving the quality and efficiency of remote follow-up.

[0160] Example 2, an embodiment of the present invention, provides an intelligent remote follow-up system for cancer patients, comprising: a data processing module for collecting follow-up data through a telemedicine terminal, the follow-up data including real-time vital sign monitoring data and symptom quantification data; standardizing the real-time vital sign monitoring data to obtain a vital sign indicator sequence; and structuring the symptom quantification data to obtain a symptom feature vector. The vital sign indicator sequence and symptom feature vector are input into a time series prediction model to generate a dynamic follow-up assessment score.

[0161] The analysis and evaluation module is used to perform semantic analysis of the patient's electronic medical record data based on the medical knowledge graph, extract tumor staging classification data, radiotherapy and chemotherapy measurement data, weight and nutritional indicators, and laboratory test data, determine the basic risk coefficient based on the tumor staging classification data, calculate the cumulative dose ratio based on the radiotherapy and chemotherapy measurement data, and calculate the body status score based on the weight and nutritional indicators and laboratory test data. The basic risk coefficient, cumulative dose ratio, and body status score are input into the prediction model to generate the baseline follow-up assessment score;

[0162] The follow-up planning module is used to calculate the comprehensive follow-up level and generate the next follow-up plan based on the dynamic follow-up assessment score and the baseline follow-up assessment score.

[0163] Example 3, reference Figure 2, which is an embodiment of the present invention, differs from the previous embodiment in that: if the functions described are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or the portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage media include various media capable of storing program code, such as USB flash drives, mobile hard drives, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical disks.

[0164] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0165] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, and then editing, interpreting, or processing in another suitable manner as necessary, and then storing it in a computer memory.

[0166] It should be understood that various components of the present invention may be implemented using hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods may be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof may be used: a discrete logic circuit having logic gate circuits for implementing logic functions on data signals, an application-specific integrated circuit having suitable combinational logic gate circuits, a programmable gate array (PGA), a field-programmable gate array (FPGA), etc.

[0167] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. An intelligent remote follow-up method for cancer patients, characterized in that: include: Collecting follow-up data through a telemedicine terminal, the follow-up data including real-time vital sign monitoring data and symptom quantification data, standardizing the real-time vital sign monitoring data to obtain a vital sign index sequence, and structuring the symptom quantification data to obtain a symptom feature vector, inputting the vital sign index sequence and the symptom feature vector into a time series prediction model to generate a dynamic follow-up assessment score; performing semantic analysis on the patient's electronic medical record data based on a medical knowledge graph, extracting tumor staging classification data, radiotherapy and chemotherapy measurement data, weight and nutritional indicators, and laboratory test data; determining a basic risk coefficient based on the tumor staging classification data; calculating a cumulative dose ratio based on the radiotherapy and chemotherapy measurement data; calculating a body state score based on the weight and nutritional indicators and the laboratory test data; inputting the basic risk coefficient, the cumulative dose ratio, and the body state score into a prediction model to generate a baseline follow-up assessment score; Calculating a comprehensive follow-up grade and generating a next follow-up plan based on the dynamic follow-up assessment score and the baseline follow-up assessment score; The basic risk coefficient is determined according to the tumor stage classification data, and the formula is expressed as: ； in, represents the basic risk coefficient at time t; S represents the number of tumor stage characteristics; represents the weight coefficient of the sth stage feature; represents the degree index of the s-th stage feature; represents the time progression factor of the sth stage characteristic; The calculation formula of the cumulative dose ratio is: ； in: It represents the cumulative dose ratio at time t; Indicates the The actual cumulative dose of the therapeutic drug; Indicates the The standard cumulative dose of a therapeutic drug; M represents the number of drug types; λ represents the time decay coefficient; Indicates the time interval since the last dose; The calculation formula of the body status score is: ； in, represents the body state score at time t; N represents the number of state indicators; Indicates the The weight of each state indicator; represents the normalized value of the nth weight nutrition index; It represents the normalized value of the nth laboratory test index; It represents the indicator volatility variance; The basic risk coefficient, the cumulative dose ratio, and the body status score are input into a prediction model to generate a baseline follow-up assessment score, which is expressed as follows: ； in, represents the baseline follow-up assessment score at time t; represents the normalization function; ε represents the smoothing factor; γ represents the time adjustment coefficient; If the basic risk factor Greater than the basic risk coefficient of the previous moment , and the cumulative dose ratio Greater than the cumulative dose ratio of the previous moment ,but: ； otherwise ; If the body status score Less than the body status score at the previous moment ,but: ； otherwise ; in, Indicates the basic time adjustment coefficient; represents the basic smoothing factor; δ represents the state change threshold.

2. The intelligent remote follow-up method for cancer patients according to claim 1, characterized in that: The standardized processing formula for the real-time vital sign monitoring data is expressed as: ； in, is the historical mean value of the jth physical sign indicator; is the historical standard deviation of the jth physical sign indicator; is the length of the time series; m is the number of physical signs; is the value of the i-th time point in the physical sign index sequence obtained after standardization; is the original value of the jth vital sign indicator at the i-th time point in the real-time vital sign monitoring data; The structured processing formula for the symptom quantitative data is expressed as: ； in, is the weight coefficient of the kth symptom; p is the number of symptom indicators; T is the length of the observation time window; represents the value of the kth symptom at time t in the symptom quantification data; represents the historical maximum reference value of the kth symptom; Represents the value at time t in the symptom feature vector obtained after structured processing.

3. The intelligent remote follow-up method for cancer patients according to claim 2, characterized in that: The time series prediction model is constructed based on convolutional neural networks and long short-term memory networks; Inputting the physical sign indicator sequence and the symptom feature vector into a time series prediction model to generate a dynamic follow-up assessment score includes the following steps: In the time series prediction model, the physical sign indicator sequence and the symptom feature vector are subjected to time series feature fusion: ； in, It represents the fused feature vector at time t in the time series prediction model, and the superscript f represents the fused feature dimension; represents the value of the vital sign indicator sequence at time t; represents the value of the symptom feature vector at time t; the symbol || represents a vector concatenation operation; The convolutional neural network in the time series prediction model is used to extract time series features from the fusion features: ； in, represents the f-dimensional fusion feature sequence from time tj to time t; Represents the j-th convolution kernel parameter; Represents the convolution layer bias term; K represents the convolution time window size; Represents the c-dimensional features output by the convolutional layer; The output features of the convolutional neural network are input into the long short-term memory network to generate the dynamic follow-up assessment score: ； in, represents the dynamic follow-up assessment score; represents the feature mapping function of the lth layer of the long short-term memory network; represents the feature weight coefficient of the lth layer at time t; L represents the number of neural network layers; represents the risk volatility factor; represents the normalization function; If the rate of change of the physical sign indicator sequence is greater than the rate of change of the symptom feature vector, then: ； otherwise: ； in, Represents the gradient norm of the vital sign index sequence; represents the gradient norm of the symptom feature vector; If the change trends of the physical sign indicator sequence and the symptom feature vector are consistent, then: ； otherwise: ； Among them, cov represents the covariance function; Represents the standard deviation of the physical sign indicator sequence; represents the standard deviation of the symptom feature vector.

4. The intelligent remote follow-up method for cancer patients according to claim 3, characterized in that: The comprehensive follow-up grade is calculated according to the dynamic follow-up assessment score and the baseline follow-up assessment score: ； in, represents the comprehensive follow-up grade at time t; represents the dynamic follow-up assessment score; represents the baseline follow-up assessment score; represents the dynamic follow-up assessment score sequence from the initial moment to moment t; represents the baseline follow-up assessment score sequence from the initial moment to moment t; ω represents the dynamic assessment weight coefficient; α represents the assessment bias adjustment coefficient.

5. The intelligent remote follow-up method for cancer patients according to claim 4, characterized in that: Generate the next follow-up plan based on the comprehensive follow-up level: ； in, represents the next follow-up time interval calculated at time t; represents the basic follow-up time interval; β represents the time adjustment coefficient of the comprehensive follow-up level; λ represents the dynamic change adjustment coefficient; Indicates the dynamic follow-up assessment score at the previous moment.

6. An intelligent remote follow-up system for cancer patients, based on the intelligent remote follow-up method for cancer patients according to any one of claims 1 to 5, characterized in that: include, a data processing module for collecting follow-up data through a telemedicine terminal, the follow-up data including real-time vital sign monitoring data and symptom quantification data, performing standardization processing on the real-time vital sign monitoring data to obtain a vital sign indicator sequence, performing structured processing on the symptom quantification data to obtain a symptom feature vector, inputting the vital sign indicator sequence and the symptom feature vector into a time series prediction model to generate a dynamic follow-up assessment score; an analysis and evaluation module for performing semantic analysis on the electronic medical record data of the patient based on a medical knowledge graph, extracting tumor staging classification data, radiotherapy and chemotherapy measurement data, weight and nutritional indicators, and laboratory test data, determining a basic risk coefficient based on the tumor staging classification data, calculating a cumulative dose ratio based on the radiotherapy and chemotherapy measurement data, calculating a body state score based on the weight and nutritional indicators and the laboratory test data, inputting the basic risk coefficient, the cumulative dose ratio, and the body state score into a prediction model, and generating a baseline follow-up assessment score; The follow-up planning module is used to calculate the comprehensive follow-up level and generate the next follow-up plan based on the dynamic follow-up assessment score and the baseline follow-up assessment score.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the intelligent remote follow-up method for tumor patients according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the intelligent remote follow-up method for tumor patients according to any one of claims 1 to 5 are implemented.

Images