Information processing method and device for assisting assessment of volume load state of heart failure patient

Abstract

The application relates to the technical fields of data processing and intelligent medical treatment, and provides an information processing method and device for assisting in evaluating the volume load state of a heart failure patient, which comprises the following steps: acquiring original detection data of a user to be detected; the original detection data comprises physical sign data and heart detection data; determining initial volume load state information according to the original detection data; acquiring current user state information of the user to be detected; the current user state information at least comprises clinical symptoms, recent treatment and medication conditions and physical activity states; generating load state correction information according to the current user state information; correcting and processing the initial volume load state information by using the load state correction information to obtain target volume load state information; and performing feature recognition on the target volume load state information to obtain heart load feature information of the user to be detected, so that the accuracy of the information processing process for assisting in evaluating the volume load state of the heart failure patient can be improved.

Description

Technical Field

[0001] This application relates to the fields of data processing and smart healthcare technology, specifically to an information processing method and device for assisting in the assessment of volume overload status in patients with heart failure. Background Technology

[0002] Volume overload refers to the level of stress on the heart's pumping function caused by the amount of fluid in the body. Abnormalities in volume overload (such as volume overload or underload) are key factors affecting the progression of heart failure. Currently, the methods for identifying volume overload in heart failure patients are mainly divided into two categories: invasive hemodynamic monitoring (such as CVP and PAWP measurements) and non-invasive / minimally invasive testing (such as electrocardiography and echocardiography). The former is complex to operate and has low patient tolerance, while the latter mostly relies on single-dimensional data collection and analysis, is easily affected by the patient's pathological state, and lacks a targeted result correction mechanism, thus resulting in insufficient accuracy in identifying the characteristics of volume overload in heart failure patients. Summary of the Invention

[0003] This application provides an information processing method and apparatus for assisting in the assessment of the volume overload status of heart failure patients, which can effectively improve the accuracy of the information processing process for assisting in the assessment of the volume overload status of heart failure patients.

[0004] A first aspect of this application provides an information processing method for assisting in assessing the volume overload status of patients with heart failure, the method comprising:

[0005] Obtain the raw test data of the user to be tested; the raw test data includes vital sign data and cardiac test data;

[0006] Determine the initial capacity load status information based on the original data to be tested;

[0007] Obtain the current user status information of the user to be tested; the current user status information includes at least clinical symptoms, recent treatment and medication, and physical activity status.

[0008] Generate load status correction information based on current user status information;

[0009] The initial capacity load status information is corrected using load status correction information to obtain the target capacity load status information;

[0010] Feature recognition is performed on the target capacity load status information to obtain the cardiac load feature information of the user to be tested.

[0011] In this example, by acquiring the original data of the user to be tested, the initial volume load status information can be determined based on the original data. By acquiring the current user status information of the user to be tested, load status correction information can be generated based on the current user status information. The initial volume load status information can then be corrected using the load status correction information to obtain the target volume load status information. Furthermore, feature recognition can be performed on the target volume load status information to obtain the cardiac load feature information of the user to be tested. This helps to improve the accuracy of the information processing process for assisting in the assessment of the volume load status of heart failure patients.

[0012] A second aspect of this application provides an information processing device for assisting in assessing the volume overload status of patients with heart failure, the device comprising:

[0013] The first acquisition unit is used to acquire the original data to be tested from the user to be tested; the original data to be tested includes vital sign data and cardiac test data.

[0014] A determining unit is used to determine initial capacity load status information based on the original data to be detected;

[0015] The second acquisition unit is used to acquire the current user status information of the user to be detected; the current user status information includes at least clinical symptoms, recent treatment and medication, and physical activity status.

[0016] The generation unit is used to generate load status correction information based on the current user status information;

[0017] The first processing unit is used to correct the initial capacity load status information using the load status correction information to obtain the target capacity load status information;

[0018] The second processing unit is used to perform feature recognition on the target capacity load status information to obtain the cardiac load feature information of the user to be detected.

[0019] A third aspect of this application provides a terminal including a processor, an input device, an output device, and a memory, wherein the processor, input device, output device, and memory are interconnected, wherein the memory is used to store a computer program, the computer program including program instructions, and the processor is configured to invoke the program instructions to execute the step instructions as described in the first aspect of this application.

[0020] A fourth aspect of this application provides a computer-readable storage medium storing a computer program for electronic data interchange, wherein the computer program causes a computer to perform some or all of the steps described in the first aspect of this application.

[0021] A fifth aspect of this application provides a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps described in the first aspect of this application. The computer program product may be a software installation package. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This application provides a schematic diagram of the structure of an information processing system for assisting in the assessment of volume overload status in patients with heart failure.

[0024] Figure 2 This application provides a flowchart illustrating an information processing method for assisting in assessing the volume overload status of patients with heart failure.

[0025] Figure 3 This is a schematic diagram of the structure of a terminal provided in an embodiment of this application;

[0026] Figure 4 This application provides a schematic diagram of the structure of an information processing device that assists in assessing the volume overload status of patients with heart failure. Detailed Implementation

[0027] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0028] The terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.

[0029] In this application, the reference to "embodiment" means that a specific feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a mutually exclusive, independent, or alternative embodiment. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described in this application can be combined with other embodiments.

[0030] To better understand the information processing method for assisting in assessing the volume overload status of heart failure patients provided in this application embodiment, the following is a brief introduction to existing heart failure patient volume overload status feature recognition technology. Currently, information processing for assisting in the assessment of volume overload status in heart failure patients in clinical and engineering fields mainly focuses on two directions: invasive monitoring and non-invasive testing. Invasive monitoring, which uses hemodynamic parameters such as central venous pressure (CVP) and pulmonary artery wedge pressure (PAWP) as the core basis for judgment, is a commonly used standard method in clinical practice, but it suffers from complex operation and low patient tolerance, making it unsuitable for long-term dynamic monitoring scenarios such as home rehabilitation follow-up. Non-invasive testing often relies on the analysis of single-dimensional electrocardiogram data, such as extracting the RR interval (R-R Interval) to analyze heart rate variability, or combining echocardiography to measure cardiac volume. However, heart failure patients often have electrocardiogram waveform distortion and rhythm disturbances, and relying solely on the single R peak to extract interval data is prone to data distortion. Moreover, existing non-invasive testing solutions generally do not integrate real-time patient status information, such as key influencing factors like medication adjustments and physical activity intensity, and lack targeted assessment result correction mechanisms. Ultimately, this leads to insufficient accuracy in identifying volume overload status characteristics, making it difficult to meet the actual needs of individualized clinical diagnosis and disease tracking.

[0031] To address the aforementioned issues, this application provides a method for identifying volume overload characteristics in heart failure patients, applicable to non-invasive volume assessment in various scenarios such as in-hospital dynamic monitoring and home rehabilitation follow-up. This application targets the core pain point of irregular electrocardiograms in heart failure patients by extracting interval data through the collaborative use of R-peak and S-peak dual-peak techniques, combined with hyperbolic fusion to correct outliers, thus obtaining reliable heart rate fluctuation characteristics. Simultaneously, it integrates real-time medication, physical activity, and clinical symptom information to accurately correct initial load assessment results, forming a volume overload identification method that balances accuracy and convenience. This provides clinicians with real-time diagnostic information and also serves as a reference for self-health management by patients at home.

[0032] The information processing method for assisting in the assessment of volume overload status in heart failure patients provided in this application can be applied to information processing systems for assisting in the assessment of volume overload status in heart failure patients. Figure 1 A schematic diagram of an information processing system for assisting in the assessment of volume overload status in patients with heart failure is shown. Figure 1 As shown, this information processing system for assisting in the assessment of volume overload status in heart failure patients may include a data acquisition module, an initial volume overload status information determination module, a correction information generation module, a correction processing module, and a feature recognition module. The data acquisition module acquires the original data of the user to be tested, such as vital sign data, cardiac function data, and current user status information, providing basic data support for subsequent volume overload status analysis. The initial volume overload status information determination module determines the patient's initial volume overload status information based on the acquired vital sign and cardiac function data through data fusion and analysis. The correction information generation module determines the status deviation information based on the current user status information and further generates corresponding overload status correction information. The correction processing module uses the generated overload status correction information to correct the initial volume overload status information, obtaining accurate target volume overload status information. The feature recognition module extracts and analyzes features from the target volume overload status information, thereby completing a more accurate information processing for assisting in the assessment of volume overload status in heart failure patients.

[0033] Please see Figure 2 , Figure 2 This application provides a flowchart illustrating an information processing method for assisting in assessing the volume overload status of patients with heart failure. (See attached diagram.) Figure 2 As shown, this method is applied to an information processing system that assists in assessing the volume overload status of patients with heart failure. The method includes:

[0034] S10: Obtain the original test data of the user to be tested; the original test data includes vital sign data and cardiac test data.

[0035] The raw data to be tested can refer to the basic test data used to assess the volume overload status of heart failure patients. This raw data may include, but is not limited to, vital signs data and cardiac test data. Vital signs data may include, but is not limited to, directly measurable physical indicators such as weight, blood pressure, heart rate, and urine output. Cardiac test data may include electrocardiogram (ECG) data, which may contain ECG characteristic information such as QRS complexes and P waves. The QRS complex is a complex wave in the ECG representing the ventricular depolarization process. Its typical morphology includes, but is not limited to, a combination of Q wave (the negative wave at the beginning of ventricular depolarization), R wave (the positive wave that appears after the Q wave), and S wave (the negative wave that appears after the R wave). The specific morphology varies due to individual differences and different test leads, and there may also be cases where Q wave, R wave, or S wave are missing, or there are polyphasic waveforms.

[0036] For example, vital signs data can be obtained through measurements using standard medical devices, such as electronic blood pressure monitors to measure systolic and diastolic blood pressure, scales to measure weight, and urine analyzers to record 24-hour urine output; cardiac data can be obtained by collecting continuous electrocardiogram data through electrocardiogram monitoring equipment to ensure that the data covers the complete electrocardiographic activity cycle and meets the needs of subsequent analysis.

[0037] S20: Determine the initial capacity load status information based on the original data to be detected.

[0038] Initial volume overload status information refers to the assessment results obtained after preliminary analysis of the original test data, which reflects the patient's baseline volume overload level (also known as baseline status). This baseline status can include volume overload, i.e., excessive body fluid volume, such as accompanied by lower extremity edema, pulmonary rales, and other related manifestations; adequate volume, i.e., body fluid volume within the normal physiological range, without related manifestations of excessive or insufficient fluid; and insufficient volume, i.e., insufficient body fluid volume, such as accompanied by decreased urine output, low blood pressure, and other related manifestations.

[0039] When determining initial volume overload status information, an assessment can be conducted based on the collected raw data to be tested, using pre-defined preliminary analysis logic (such as indicator threshold comparison, basic model calculation, etc.). Specifically, relevant indicators from vital signs data and cardiac test data can be combined and compared with the baseline standards for volume overload assessment of heart failure patients to determine the patient's initial volume overload baseline status, thereby clarifying their baseline status and forming initial volume overload status information. This application does not impose any limitations on this.

[0040] S30: Obtain the current user status information of the user to be detected; the current user status information includes at least clinical symptoms, recent treatment and medication, and physical activity status.

[0041] The current user status information refers to the real-time associated status data of the user being tested during capacity load testing. This current user status information may include clinical symptoms, such as the presence of chest tightness, shortness of breath, or difficulty breathing; recent medication use, such as the dosage, duration of use, and whether adjustments have been made for diuretics and antihypertensive drugs; and physical activity status, such as whether physical activity was performed before the test and the current activity intensity. This current user status information can be used to generate correction information to eliminate the interference of real-time status on the evaluation results.

[0042] When obtaining current user status information, it can be obtained comprehensively through medical staff's consultation records, real-time patient feedback, and clinical observation. It should be noted that this current user status information should focus on the current state at the time of testing. For example, whether the patient has symptoms of chest tightness and shortness of breath at the time of testing, whether the dosage of diuretics has been adjusted in the past 3 days, and whether the patient has engaged in physical activity such as walking in the hour before testing, to ensure the timeliness and relevance of the information.

[0043] S40: Generate load status correction information based on the current user status information.

[0044] Load status correction information refers to adjustment parameters or rules derived from current user status information, used to correct initial capacity load status information. This load status correction information can offset assessment biases caused by real-time user status (such as temporary physical activity or medication adjustments), ensuring that the final result more closely reflects the user's actual capacity load status.

[0045] During the generation of load status correction information, based on the acquired current user status information, and through preset status-offset correspondence rules, the direction and magnitude of the deviation that the real-time status may cause to the initial assessment results can be analyzed. For example, if the user engaged in excessive physical activity before the test, the initial assessment result may be biased towards "volume overload," and the corresponding correction information can be generated as specific parameters for downward adjustment; if the user recently increased the dosage of diuretics, the initial assessment result may be biased towards "volume underload," and the corresponding correction information can be generated as specific parameters for upward adjustment. This application does not impose any limitations on this.

[0046] S50: The initial capacity load status information is corrected using the load status correction information to obtain the target capacity load status information.

[0047] The target capacity load status information refers to the more accurate capacity load assessment result obtained after substituting load status correction information into preset correction logic and quantifying and correcting the initial capacity load status information. This target capacity load status information has eliminated real-time status interference and can be regarded as the core basis that can reflect the user's true capacity load level, providing a more accurate data foundation for subsequent feature identification.

[0048] Specifically, corresponding adjustment parameters and application rules can be extracted from the load status correction information, and combined with the specific numerical range of the initial capacity load status information, quantitative calculations are performed according to the application rules to accurately calibrate the initial capacity load status information. It can be understood that this correction process, through explicit parameter extraction and quantitative calculation, can counteract real-time status interference, thereby calibrating the initial assessment results to the user's actual capacity load level, resulting in more accurate and relevant target capacity load status information.

[0049] S60: Perform feature recognition on the target capacity load status information to obtain the cardiac load feature information of the user to be detected.

[0050] Understandably, cardiac load characteristics are intermediate data or reference indicators, and the final diagnosis needs to be made by the doctor by combining other information.

[0051] The cardiac load characteristic information can be the structured key features extracted after deep analysis of the target volume load status information. This cardiac load characteristic information can include heart rate fluctuation characteristics, such as fluctuation amplitude, fluctuation frequency, and fluctuation regularity; load level characteristics, such as the severity classification of volume overload / insufficiency; and dynamic change trend characteristics, such as the rate of increase or decrease in load status. It is understandable that this cardiac load characteristic information can provide accurate and direct data support for clinical diagnosis and treatment plan development.

[0052] Specifically, from the dimension of fluctuation characteristics, we can calculate the amplitude of heart rate changes per unit time, such as the maximum difference in heart rate per minute; the frequency of change, such as the number of heart rate fluctuations per hour; and whether the fluctuations are regular, such as whether the fluctuation intervals are uniform. From the dimension of load level characteristics, and by comparing with clinical grading standards, such as mild, moderate, and severe, and further combining the numerical range of target volume load status information, we can determine the severity of volume overload or underload. From the dimension of dynamic change trend characteristics, we can analyze the rate of change of load status within a certain period of time, such as the specific values ​​of load increase / decrease per hour. This allows us to extract structured cardiac load characteristic information that can be directly used for clinical reference.

[0053] By constructing a complete technical process encompassing raw data acquisition, initial state assessment, real-time state correction, target state determination, and feature extraction, the accuracy and practicality of volume load status assessment in heart failure patients can be significantly improved. On one hand, the dual-stage processing mode of initial assessment and load status correction allows for the generation of load status correction information, including adjustment parameters and application rules, based on the current user status information of the user being tested. This effectively counteracts the influence of interfering factors such as temporary physical activity, medication adjustments, and real-time clinical symptoms on the assessment results, avoiding the limitations of assessment based solely on raw data. This ensures that the final target volume load status information more closely reflects the patient's true physiological state, addressing the problems of traditional assessment methods being susceptible to external interference and lacking accuracy. On the other hand, the method provided in this application fully adapts to the clinical characteristics of heart failure patients, such as the potential irregularities in electrocardiograms and significant individual differences in status. By comprehensively collecting vital sign data and cardiac test data, the comprehensiveness and suitability of the assessment are ensured. Simultaneously, the obtained cardiac load characteristic information is structured, multi-dimensional data that can include key clinical reference content such as heart rate fluctuations, load levels, and dynamic trends. This can directly provide precise data support for doctors to formulate personalized treatment plans, reducing the difficulty of clinical decision-making.

[0054] In this example, by acquiring the original data of the user to be tested, the initial volume load status information can be determined based on the original data. By acquiring the current user status information of the user to be tested, load status correction information can be generated based on the current user status information. The initial volume load status information can then be corrected using the load status correction information to obtain the target volume load status information. Furthermore, feature recognition can be performed on the target volume load status information to obtain the cardiac load feature information of the user to be tested. This helps to improve the accuracy of the information processing process for assisting in the assessment of the volume load status of heart failure patients.

[0055] In one possible implementation, a method for determining initial capacity load status information based on the original data to be detected may include:

[0056] A1. Extract vital sign data and cardiac test data from the original data to be tested;

[0057] A2. Use the aforementioned vital sign data to perform load status analysis and obtain the first reference capacity load status information;

[0058] A3. Using the cardiac detection data, perform load status analysis to obtain second reference capacity load status information;

[0059] A4. The first reference capacity load status information and the second reference capacity load status information are fused together to obtain the initial capacity load status information.

[0060] The first reference capacity load status information refers to the intermediate assessment result obtained after load status analysis using physical characteristic data. This first reference capacity load status information can be regarded as an important component of the initial capacity load status information, reflecting the capacity load reference based on physical characteristics.

[0061] The second reference volumetric load information refers to the intermediate assessment result obtained after analyzing the load status using cardiac test data. This second reference volumetric load information complements the first reference volumetric load information and reflects the volumetric load reference based on cardiac electrophysiological activity.

[0062] Fusion processing refers to the process of comprehensively analyzing and cross-verifying the first reference capacity load status information and the second reference capacity load status information. Through this fusion processing, the evaluation advantages of the two types of data can be combined, thereby obtaining more comprehensive and reliable initial capacity load status information.

[0063] Specifically, when using vital sign data for load status analysis, the analysis can be based on preset rules relating vital signs to volume load. Specifically, the numerical range of various vital sign data can be analyzed by comparing them with clinical standards for volume load assessment in heart failure patients. For example, a significant increase in weight from baseline and a significant decrease in urine output can be identified as first reference volume load status information indicating a tendency towards volume overload; conversely, low blood pressure and persistently low urine output can be identified as first reference volume load status information indicating a tendency towards volume insufficiency. This allows the acquisition of the aforementioned first reference volume load status information.

[0064] When using cardiac monitoring data for load status analysis, the analysis can be based on the correspondence between electrocardiogram (ECG) characteristics and volume load. Specifically, features such as QRS complexes and P waves in ECG data can be analyzed, and combined with clinically known correlation patterns, such as the correspondence between rhythm changes and amplitude abnormalities of specific ECG waveforms and volume load abnormalities, a second reference volume load status information tending towards the corresponding volume load status can be derived.

[0065] During the fusion processing phase, the first and second reference volume load status information can be integrated and verified according to preset comprehensive judgment rules. Specifically, if both the first and second reference volume load status information point to the same volume load status information, then this same volume load status information is determined as the initial volume load status information. If there are differences between the first and second reference volume load status information, then quantitative analysis is performed by combining the weight coefficients of the two types of reference volume load status information to obtain the initial volume load status information. For example, if both types of reference volume load status information point to volume overload, then the initial volume load status information can be directly determined as volume overload. If there are differences between the two types of reference volume load status information, then quantitative analysis is performed by combining the weight coefficients of the two types of reference volume load status information to obtain initial volume load status information that can comprehensively reflect the patient's baseline volume load status.

[0066] In one possible implementation, if there is a difference between the first reference capacity load status information and the second reference capacity load status information, then a quantitative analysis is performed by combining the weight coefficients of the two types of reference capacity load status information to obtain initial capacity load status information. This includes: performing a credible quantification score on the first reference capacity load status information to obtain a first reference score; performing a credible quantification score on the second reference capacity load status information to obtain a second reference score; performing a weighted summation based on the first reference score and the second reference score to obtain a comprehensive weighted score; and obtaining the initial capacity load status information based on the comprehensive weighted score.

[0067] Specifically, the above-mentioned fusion processing can be weighted fusion processing. For example, the reliability quantification score can be performed on the first reference capacity load status information and the second reference capacity load status information respectively. The reliability quantification score range can be 0-100 points, which can be determined based on the completeness of data acquisition and the accuracy of the detection equipment. If the equipment accuracy meets medical-grade standards (such as the Chinese medical device industry standard "Electrocardiograph" and the Chinese national standard "Medical Electrical Equipment Part 1: General Requirements for Basic Safety and Basic Performance"), the basic reliability score is 90 points. For every 10% increase in the data missing rate, 5 points can be deducted. For example, if the urine output index in the vital signs data is missing, it is considered a 10% data missing rate, and 5 points are deducted. If the data acquisition environment meets the preset standards, such as the patient being at rest and there being no electromagnetic interference during the test, 5 points can be added. If the acquisition environment does not meet the standards, 5 points can be deducted. The reliability score is finally determined through the above multi-dimensional scoring rules.

[0068] Optionally, the initial volume overload status can be determined using the formula: Comprehensive Weighted Score = (First Reference Score × Weighting Coefficient of Physical Signs Data) + (Second Reference Score × Weighting Coefficient of Cardiac Examination Data), where the weighting coefficient for physical signs data is 0.4 and the weighting coefficient for cardiac examination data is 0.6. This weighting combination is an optimal value validated based on clinical data from 500 heart failure patients, effectively balancing the assessment weights of physical appearance and intrinsic cardiac function. Further, based on the range of the comprehensive weighted score: a comprehensive weighted score ≥ 80 points indicates volume overload; a comprehensive weighted score of 60-79 points indicates adequate volume; and a comprehensive weighted score < 60 points indicates insufficient volume.

[0069] Optionally, if there are differences between the two types of reference capacity load status information, such as the first reference capacity load status information favoring capacity overload and the second reference capacity load status information favoring adequate capacity, a comprehensive score can be calculated using the weighting coefficients and reliability scores of the two types of reference capacity load status information. For example, the weighted score of the first reference capacity load status information can be calculated using the formula: Weighted score of the first reference capacity load status information = its reliability score × weighting coefficient of vital sign data; Weighted score of the second reference capacity load status information = its reliability score × weighting coefficient of cardiac examination data. The capacity load status corresponding to the reference capacity load status information with the higher weighted score can then be taken as the initial capacity load status information.

[0070] For example, if the weighting coefficient for vital sign data is 0.4 and the weighting coefficient for cardiac test data is 0.6, the confidence score for the first reference volume overload status information (volume overload) is 85 points, and the weighted score for the first reference volume overload status information is 85 × 0.4 = 34 points; the confidence score for the second reference volume overload status information (volume adequate) is 90 points, and the weighted score for the second reference volume overload status information is 90 × 0.6 = 54 points. Therefore, the initial volume overload status information can be determined as the volume overload status corresponding to the second reference volume overload status information, i.e., adequate volume. It should be noted that the setting of the weighting coefficient is related to the clinical relevance of the data type and the detection accuracy. In the above embodiment, since vital sign data is easily affected by temporary conditions (such as diet and activity), the clinical relevance weighting can account for 40%; cardiac test data directly reflects cardiac function, has higher detection accuracy and stronger clinical relevance, and the weighting can account for 60%. Optionally, the above weighting coefficients can be flexibly adjusted according to clinical application scenarios. For example, for patients with stable chronic heart failure, the weighting coefficient of vital signs data can be adjusted to 0.5 and the weighting coefficient of cardiac test data can be adjusted to 0.5; for patients with acute heart failure in the acute phase, the weighting coefficient of cardiac test data can be increased to 0.7 to adapt to different diagnostic and treatment needs. This application does not impose any restrictions on this.

[0071] In this example, by splitting the original data to be tested into vital sign data and cardiac test data for separate analysis, and then further fusing them, the comprehensiveness and reliability of the initial volume overload status information are significantly improved. On the one hand, vital sign data, as an intuitive and measurable physical representation indicator, can directly reflect the patient's current basic physical state, while cardiac test data reflects intrinsic functional changes through cardiac electrophysiological activity characteristics. The two types of data complement each other, avoiding the one-sidedness of assessment based on a single data dimension, and making the intermediate assessment results more valuable. On the other hand, the fusion process can support direct judgment when the two types of reference information are consistent, ensuring assessment efficiency; and it can also introduce quantitative calculation methods for weighting coefficients and confidence scores when there are differences in the information. By determining the final result through explicit weighted score comparison, the comprehensive judgment process is quantifiable and traceable, thereby avoiding bias caused by subjective assumptions.

[0072] In one possible implementation, the cardiac detection data includes an initial electrocardiogram (ECG). When performing load status analysis using the cardiac detection data, QRS complexes and P complexes can be extracted from the initial ECG. First and second heart rate-related fluctuation information are then extracted based on these two types of fluctuations, respectively. The two types of fluctuation information are fused to obtain target fluctuation information, which can then be used to analyze and derive second reference capacity load status information. Specifically, a possible method for performing load status analysis using the cardiac detection data to obtain second reference capacity load status information may include:

[0073] B1. Extract the QRS wave from the initial electrocardiogram to obtain the QRS complex, and extract the P wave from the initial electrocardiogram to obtain the P complex;

[0074] B2. Extract heart rate fluctuations based on the QRS complex to obtain the first fluctuation information;

[0075] B3. Extract heart rate fluctuations based on the P wave group to obtain the second fluctuation information;

[0076] B4. The first fluctuation information and the second fluctuation information are fused to obtain the target fluctuation information;

[0077] B5. Perform load status analysis based on the target fluctuation information to obtain the second reference capacity load status information.

[0078] The initial electrocardiogram (ECG) refers to the raw, unprocessed ECG signal record collected from cardiac monitoring data. This initial ECG fully reflects the raw waveform data of cardiac electrophysiological activity. The QRS complex is a continuous waveform in the ECG reflecting the ventricular depolarization process; the P wave complex is a set of waveforms in the ECG reflecting the atrial depolarization process, which can reflect the atrial electrical activity state and provide supplementary reference for heart rate fluctuation analysis.

[0079] The first fluctuation information can refer to the feature data related to heart rate changes extracted based on the QRS complex. This first fluctuation information may include, but is not limited to, heart rate (i.e., the maximum difference in heart rate per unit time), fluctuation frequency (i.e., the number of heart rate fluctuations per unit time), fluctuation regularity (i.e., whether the intervals of heart rate fluctuations are uniform), etc., which can directly reflect the heart rate changes associated with ventricular electrical activity.

[0080] The second fluctuation information can refer to feature data related to heart rate changes extracted based on the P wave group. This second fluctuation information may also include relevant features such as heart rate fluctuation amplitude, fluctuation frequency, and fluctuation regularity, which can be cross-validated with the first fluctuation information to enrich the comprehensiveness of heart rate fluctuation analysis.

[0081] Target fluctuation information refers to more comprehensive and integrated fluctuation data obtained by fusing the first and second fluctuation information. Target fluctuation information integrates the heart rate change characteristics corresponding to both types of wave groups, eliminating the limitations of single wave group analysis and providing a more comprehensive reflection of the true heart rate fluctuation state. Based on the target fluctuation information and combined with the clinical correlation between heart rate fluctuation and volume load, the volume load reference assessment results, i.e., the aforementioned second reference volume load state information, can be analyzed and obtained, providing more comprehensive and accurate support for determining the initial volume load state information.

[0082] Specifically, in the QRS complex and P wave complex extraction stage, an ECG waveform recognition algorithm can be used to analyze the initial ECG. Optionally, recognition thresholds such as waveform amplitude and duration can be set to filter out continuous waveforms that conform to the morphological characteristics of the QRS complex from the initial ECG. The start, end, and peak points of the Q wave, R wave, and S wave can be determined to form the QRS complex. At the same time, based on the morphological characteristics of the P wave, such as a positive waveform and a specific duration range, single or continuous P waves can be separated from the initial ECG to form the P wave complex, thereby ensuring the completeness and accuracy of the extraction of both types of wave complexes.

[0083] When extracting the first fluctuation information, analysis can be performed based on the RR interval in the QRS complex. The RR interval refers to the time interval between the R-wave peaks of two adjacent QRS complexes. Optionally, the values ​​of multiple consecutive RR intervals can be calculated, and the corresponding instantaneous heart rate can be obtained by converting "60 ÷ RR interval (seconds)". Furthermore, the maximum difference in instantaneous heart rate per unit time (e.g., 1 minute) can be calculated as the heart rate fluctuation amplitude. The number of times the instantaneous heart rate change exceeds a preset threshold (e.g., 5 beats / minute) per unit time (e.g., 1 hour) can be counted as the fluctuation frequency. Further, the regularity of fluctuation can be determined by analyzing whether the intervals of consecutive instantaneous heart rate changes are uniform. If the intervals of consecutive instantaneous heart rate changes are uniform, it can be determined as regular fluctuation; if the intervals of consecutive instantaneous heart rate changes are uneven, it can be determined as irregular fluctuation. Further integrating these three features (i.e., heart rate fluctuation amplitude, fluctuation frequency, and fluctuation regularity) forms the first fluctuation information.

[0084] For example, taking three sets of consecutive RR interval data collected within one hour as 1.0 seconds, 1.1 seconds, and 0.9 seconds as an example, assuming that a single heart rate change difference of ≥5 beats / minute is preset as one valid fluctuation, the corresponding instantaneous heart rates can be calculated as 60 beats / minute, 54.5 beats / minute, and 66.7 beats / minute, and the maximum difference in heart rate within one minute can be calculated as 12.2 beats / minute, thus obtaining the heart rate fluctuation amplitude. The differences between two adjacent heart rate changes are 5.5 beats / minute and 12.2 beats / minute, both exceeding the preset single heart rate change difference of ≥5 beats / minute, which can be recorded as two valid fluctuations. If only these three sets of data are collected within this period, then the number of valid fluctuations within one hour is 2, thus obtaining the fluctuation frequency. At the same time, it can be observed that the interval difference of consecutive RR intervals is 0.1 seconds and 0.2 seconds, and the intervals are inconsistent, which can be judged as irregular fluctuations. Further integrating the above three characteristics can form and obtain the first fluctuation information mentioned above.

[0085] When extracting the second fluctuation information, analysis can be performed based on the PP interval in the P wave group. The PP interval refers to the time interval between two adjacent P wave peaks. Optionally, for details on analysis based on the PP interval in the P wave group, please refer to the aforementioned detailed description of analysis based on the RR interval in the QRS complex. For example, the values ​​of multiple consecutive PP intervals can be calculated first, and the corresponding instantaneous heart rate can be obtained by using the formula "60 ÷ PP interval (seconds)". The maximum difference in instantaneous heart rate per unit time can be calculated to determine the amplitude of heart rate fluctuations. The number of times the heart rate change per unit time exceeds a preset threshold can be counted to obtain the fluctuation frequency. The uniformity of the instantaneous heart rate change intervals can be analyzed to determine the regularity of fluctuations. These three features can then be further integrated to form and obtain the aforementioned second fluctuation information.

[0086] In the fluctuation information fusion processing stage, a combination of feature overlay and weight allocation can be used. Specifically, similar features (i.e., heart rate fluctuation amplitude, fluctuation frequency, and fluctuation regularity) in the first and second fluctuation information can be numerically standardized to ensure that the values ​​of each feature are of the same order of magnitude. Optionally, the above-mentioned numerical standardization of similar features, i.e., the feature standardization process, can use the Z-score standardization algorithm. The formula can be: Standardized feature value = (Original feature value - Feature mean) / Feature standard deviation, where the feature mean and feature standard deviation can be obtained based on a joint ECG database of 1000 healthy individuals and heart failure patients. For example, the mean heart rate fluctuation amplitude is 8 beats / minute, and the standard deviation is 3 beats / minute; the mean fluctuation frequency is 2 beats / hour, and the standard deviation is 1 beat / hour. This ensures that similar features of the two types of fluctuation information are of the same order of magnitude after standardization, ensuring that the weights do not become ineffective due to differences in the range of feature values ​​during weighted fusion.

[0087] Furthermore, the weights of the two types of fluctuation information can be set based on clinical validation. In this embodiment, the weight allocation can be determined using a dual-dimensional algorithm considering both clinical relevance and data reliability. For example, firstly, the correlation between ventricular electrical activity (QRS complex) and volume overload in heart failure patients can be statistically analyzed (correlation = 85%), and the correlation between atrial electrical activity (P complex) and volume overload can be calculated (correlation = 60%). Then, the acquisition reliability of the two types of wave group data can be further considered; for example, the acquisition reliability of the QRS complex can be 90% due to its high waveform amplitude, while the acquisition reliability of the P complex can be 70% due to its low waveform amplitude. Optionally, the following formula can be used:

[0088]

[0089] Among them, W k R can represent the weight of the k-th type of fluctuation information, with a value range of [0,1]. The sum of the weights of all types of fluctuation information can be 1; k is the index of the fluctuation information category, which is a positive integer, i.e., k=1 corresponds to the first fluctuation information, k=2 corresponds to the second fluctuation information; k This can represent the clinical correlation coefficient between the k-th type of fluctuation information and the volume overload status of heart failure patients, with a value range of [0,1] (or equivalent percentage form). It can be used to quantify the clinicopathological relevance of this type of fluctuation information in reflecting volume overload abnormalities; S kThe data acquisition reliability coefficient can represent the k-th type of fluctuation information, with a value range of [0,1] (or equivalent percentage form). It can be used to quantify the completeness of data acquisition, anti-interference ability, and data validity of this type of fluctuation information; α can represent the importance ratio of clinical relevance, with a value of 0.6; β can represent the importance ratio of data reliability, with a value of 0.4 (i.e., in this embodiment, clinical relevance has a greater impact on the evaluation results, so it can account for 60%; data acquisition reliability affects data validity, so it can account for 40%, and this application does not limit this). R in the denominator of the formula... i With R k The definitions are completely identical, S i With S k The definitions are completely identical, R i and S i This can be used as a variable to refer to the category of fluctuation information in the summation operation; that is, i can be the category index when summing. It should be noted that the denominator in the above formula can represent the (R) for all fluctuation information categories (i.e., k from 1 to N, where N is the total number of fluctuation information categories; in this embodiment, N=2). k ×α+S k Summing the terms ×β can be used to normalize the weight calculation, ensuring that the weight proportions of each category are reasonable.

[0090] It should be noted that, based on clinical follow-up data from 300 heart failure patients, the following results were obtained: R1 = 85% (i.e., the correlation between QRS complex and ventricular electrical activity and volume overload), R2 = 60% (i.e., the correlation between P complex and atrial electrical activity and volume overload); it should also be noted that, based on performance testing of cardiac equipment, the following results were obtained: S1 = 90% (i.e., strong anti-interference ability of QRS complex waveform), S2 = 70% (i.e., susceptibility to interference of P complex waveform); further... Substituting the data step by step, we can obtain: First fluctuation information weight = (85×0.6+90×0.4) / [(85×0.6+90×0.4)+(60×0.6+70×0.4)] = (51+36) / [87+52] = 87 / 139≈0.625; Second fluctuation information weight = (60×0.6+70×0.4) / 139 = (36+28) / 139 = 64 / 139≈0.46. It should be noted that the sum of the weight coefficients is 1.0, which is an ideal case. The actual calculated value may change dynamically due to the data, but normalization will be performed when applying it.

[0091] For example, suppose the weight of the first fluctuation information associated with the QRS wave group can be set to 0.7, and the weight of the second fluctuation information associated with the P wave group can be set to 0.3. It should be noted that the fluctuation amplitude and fluctuation frequency have been processed according to the Z-score standardization algorithm described above to ensure the comparability of similar features before weighted calculation. For example, the target fluctuation amplitude = first fluctuation amplitude × 0.7 + second fluctuation amplitude × 0.3, and the target fluctuation frequency = first fluctuation frequency × 0.7 + second fluctuation frequency × 0.3. As for the fluctuation regularity, the judgment result of "irregularity" in the two types of fluctuation information can be taken, because if either fluctuation information is judged as irregular, the target fluctuation regularity is also irregular. Only when both types are judged as regular is the target fluctuation regularity regular. Thus, the above-mentioned target fluctuation information is further integrated.

[0092] During the load status analysis phase, analysis can be performed based on the clinical correspondence between target fluctuation information and volume load. Specifically, different heart rate fluctuation characteristic threshold ranges corresponding to different volume load states can be preset. For example, when volume is overloaded, the heart rate fluctuation amplitude is usually greater than 15 beats / minute, the fluctuation frequency is greater than 5 beats / hour, and the fluctuation regularity is irregular; when volume is adequate, the heart rate fluctuation amplitude is maintained at 5-10 beats / minute, the fluctuation frequency is 1-3 beats / hour, and the fluctuation regularity is regular; when volume is insufficient, the heart rate fluctuation amplitude is greater than 12 beats / minute, the fluctuation frequency is greater than 4 beats / hour, and the fluctuation regularity is irregular. By comparing the three characteristic parameters in the target fluctuation information with the preset heart rate fluctuation characteristic thresholds one by one, the volume load interval to which it belongs can be determined based on the comparison results, thereby obtaining the second reference volume load status information.

[0093] In this example, by accurately extracting QRS complexes and P waves from the initial electrocardiogram, and calculating two types of fluctuation information—including heart rate fluctuation amplitude, fluctuation frequency, and fluctuation regularity—the target fluctuation information is obtained through fusion processing. This information can be used to analyze volume overload status, thereby significantly improving the accuracy and comprehensiveness of the second reference volume overload status information. By extracting characteristic wave groups, the reliability of the basic data is ensured. Furthermore, a unified fluctuation information extraction logic is designed for the two types of wave groups, guaranteeing data comparability. Through weight allocation and feature integration during the fusion process, the limitations of single wave group analysis are eliminated, avoiding assessment bias caused by relying solely on ventricular or atrial electrical activity data. In addition, the clearly defined preset thresholds and judgment criteria in the scheme make the fluctuation information calculation process quantifiable and traceable. This not only improves the accuracy of the assessment results but also provides a standardized data foundation for subsequent fusion processing, further ensuring the reliability of the initial volume overload status information. This contributes to enhancing the clinical application value of the entire volume overload assessment process for heart failure patients.

[0094] In one possible implementation, considering the potential irregularity of electrocardiograms in heart failure patients, when extracting heart rate fluctuations based on the QRS complex, adjacent RR and SS intervals can be extracted from the QRS complex to construct a first fluctuation analysis curve and a second fluctuation analysis curve, respectively. These two curves are then fused to obtain a target fluctuation analysis map. This allows the extraction of first fluctuation information, including heart rate fluctuation amplitude, frequency, and regularity, from the target fluctuation analysis map. A possible method for extracting heart rate fluctuations based on the QRS complex to obtain first fluctuation information may include:

[0095] C1. Obtain the RR interval in two adjacent QRS waves to obtain the RR interval set, and obtain the SS interval in two adjacent QRS waves to obtain the SS interval set;

[0096] C2. Construct a volatility analysis chart based on the RR interval set to obtain the first volatility analysis curve;

[0097] C3. Construct a fluctuation analysis diagram based on the SS interval set to obtain the second fluctuation analysis curve;

[0098] C4. Merge the first and second wave analysis curves to obtain the target wave analysis diagram;

[0099] C5. Extract the first wave information based on the target wave analysis diagram.

[0100] It should be noted that, due to impaired myocardial function in heart failure patients, their electrocardiogram waveforms often exhibit irregularities such as morphological distortion and rhythm disturbances. Relying solely on a single R-peak for interval localization is highly susceptible to positioning errors due to waveform interference, leading to distorted data in subsequent heart rate fluctuation analysis. Therefore, this application's embodiments introduce the RR interval corresponding to the R-peak and the SS interval corresponding to the S-peak. This allows for mutual verification and supplementation of interval data from two peaks and two dimensions, effectively offsetting the errors of single-peak localization and providing a stable and reliable basic data source for subsequent fluctuation curve construction and analysis.

[0101] As mentioned above, the RR interval refers to the time interval between the R peaks of two adjacent QRS complexes, reflecting the ventricular electrical activity cycle. An RR interval set, on the other hand, refers to a dataset formed by arranging the RR intervals of multiple consecutive adjacent QRS complexes in chronological order of acquisition. This RR interval set can comprehensively record the changes in the ventricular electrical activity cycle over a period of time.

[0102] The SS interval refers to the time interval between the S-peak of one QRS complex and the S-peak of the next in two adjacent QRS complexes. This SS interval can supplement the RR interval, improving the accuracy of heart rate extraction. An SS interval set refers to a dataset formed by arranging the SS intervals of multiple consecutive adjacent QRS complexes in chronological order of acquisition. This SS interval set can be cross-validated with the RR interval set to adapt to the analysis needs of irregular electrocardiograms.

[0103] The first fluctuation analysis curve can refer to a curve formed using the RR interval set as the data source through data visualization or trend fitting. This first fluctuation analysis curve can intuitively reflect the changing trend of the RR interval over time and can indirectly reflect heart rate fluctuations. The second fluctuation analysis curve can refer to a curve formed using the SS interval set as the data source through the same construction logic as the first fluctuation analysis curve (i.e., through data visualization or trend fitting). This second fluctuation analysis curve can complement the first fluctuation analysis curve to reduce interference from irregular waveforms.

[0104] A target volatility analysis chart can refer to a comprehensive analysis chart obtained by fusing the first volatility analysis curve and the second volatility analysis curve. It can be understood that this target volatility analysis chart integrates the volatility characteristics of the two types of intervals, further enhancing the recognizability of volatility trends.

[0105] Specifically, based on the extracted QRS complexes, ECG waveform feature localization technology can be used to accurately identify the R-peak and S-peak of each QRS wave. The R-peak is the point with the highest positive amplitude in the QRS complex, and the S-peak is the point with the lowest negative amplitude following the R-peak. Optionally, for continuously acquired ECG data, adjacent QRS waves can be selected sequentially in chronological order. The time difference between the R-peak of the preceding and following QRS waves can be measured and recorded as an RR interval. This operation is repeated until all consecutive QRS pairs are traversed, and all RR intervals are organized according to the acquisition order to form the aforementioned RR interval set. Similarly, the time difference between the preceding and following S-peaks in two adjacent QRS waves can be measured and recorded as an SS interval. This process is repeated for all consecutive QRS pairs to form the aforementioned SS interval set.

[0106] For example, if the RR intervals corresponding to five consecutive QRS waves are 1.0 seconds, 1.1 seconds, 0.95 seconds, 1.05 seconds, and 0.9 seconds, the RR interval set [1.0, 1.1, 0.95, 1.05, 0.9] can be formed in sequence; if the corresponding SS intervals are 1.02 seconds, 1.11 seconds, 0.97 seconds, 1.03 seconds, and 0.92 seconds, the SS interval set [1.02, 1.11, 0.97, 1.03, 0.92] can be formed.

[0107] Specifically, time can be used as the horizontal axis (unit: minutes), and the values ​​of each interval in the RR interval set as the vertical axis (unit: seconds). Each data point in the RR interval set is marked on the coordinate system according to the collection time. Linear interpolation or moving average methods can be used to fit the discrete data points, further forming a smooth, continuous curve, i.e., the first fluctuation analysis curve mentioned above. It can be understood that the fluctuations of this curve directly correspond to the fluctuations of the RR interval, thus reflecting the potential trend of heart rate changes. For example, when the RR interval increases, the curve shifts upward, corresponding to a slower heart rate; when the RR interval decreases, the curve shifts downward, corresponding to a faster heart rate.

[0108] Specifically, the second wave analysis curve can be constructed using the same logic as the first wave analysis curve. This involves using the same time axis on the horizontal axis and the values ​​of each interval in the SS interval set on the vertical axis. After labeling the SS interval data points according to their acquisition time, a continuous curve can be formed using the same interpolation or fitting method, thus obtaining the second wave analysis curve. It should be noted that this ensures that the coordinate scale and fitting algorithm of the two curves are completely consistent, providing a consistent data foundation for subsequent fusion processing and avoiding fusion deviations caused by differences in construction methods.

[0109] Specifically, a fusion method combining curve feature overlay and outlier correction can be used to overlay the first and second fluctuation analysis curves on the same coordinate system to obtain the target fluctuation analysis graph. Optionally, for time points where the numerical deviation between the two curves is less than a preset deviation threshold (e.g., 0.05 seconds), the average of the two curves can be taken as the value of the target curve at that time point. For time points where the deviation exceeds the preset deviation threshold (often due to abnormal intervals caused by irregular ECG patterns), the values ​​of the two curves that show a consistent trend with adjacent time points can be used for correction. For example, if the RR interval is 0.8 seconds and the SS interval is 1.2 seconds at a certain time point, both exceeding the preset deviation threshold, and the RR and SS intervals at adjacent time points are both around 1.0 seconds, then 1.0 seconds can be taken as the value at that time point. Through the above fusion processing, a smooth, stable fluctuation analysis curve that accurately reflects the true heart rate fluctuation trend can be formed, i.e., the aforementioned target fluctuation analysis graph.

[0110] Optionally, when fusing the first and second wave analysis curves to obtain the target wave analysis chart, the outlier correction process during curve fusion can be found in the following formula:

[0111]

[0112] in, This can represent the interval value corresponding to the target fluctuation analysis graph at time t; This can represent the RR interval value corresponding to the first fluctuation analysis curve at time t; This can represent the SS interval value corresponding to the second fluctuation analysis curve at time t; T is the preset deviation threshold. It can represent that at time t, based on adjacent time points (t Trend correction values ​​obtained by fitting the interval data of 1 and t+1).

[0113] From the above formula, we can see that when t is | When |≥T, the average of the two is no longer taken directly, but rather the value is determined by the time points adjacent to time t (e.g., tt). 1. t The RR interval and SS interval values ​​at times t2 or t+1, t+2 are used to calculate reasonable values ​​that conform to the overall fluctuation trend, according to the previously set curve fitting method (such as linear interpolation, moving average). These values ​​(i.e.,...) Corrects interval abnormalities caused by irregular electrocardiograms.

[0114] Specifically, based on the target fluctuation analysis chart, its core features can be further extracted, such as heart rate fluctuation amplitude. This can be achieved by reading the maximum and minimum values ​​of the vertical axis (interval) in the target fluctuation analysis chart and converting them to the corresponding heart rate (heart rate = 60 ÷ interval). The difference between the maximum and minimum heart rate is the fluctuation amplitude. For fluctuation frequency, a preset interval change threshold (e.g., 0.1 seconds) can be used to count the number of times the interval change between adjacent time points in the target curve exceeds this threshold within a unit of time (e.g., 1 hour), which is the fluctuation frequency. For fluctuation regularity, the curve shape of the target fluctuation analysis chart can be analyzed. If the curve fluctuates evenly and the difference between adjacent interval changes is stable within a preset range (e.g., ±0.03 seconds), it can be determined as regular fluctuation. If the curve fluctuates irregularly and the difference between adjacent interval changes fluctuates greatly, it can be determined as irregular fluctuation. Further integrating these features allows the formation and acquisition of the first fluctuation information.

[0115] In this example, by accurately anchoring the clinical pain point of irregular electrocardiograms in heart failure patients, a dual-characteristic peak analysis method using R-peak and S-peak is adopted, overcoming the limitations of traditional single-peak analysis and effectively avoiding the interference of irregular waveforms on interval extraction. By constructing and fusing RR and SS interval fluctuation analysis curves separately, and combining them with preset thresholds to correct outliers, the interval data extraction process is made more stable and accurate. The entire analysis process is based on clear numerical judgment rules and curve fitting methods, ensuring that the analysis process is quantifiable and traceable. The obtained first fluctuation information can more realistically reflect the heart rate fluctuation status of heart failure patients, providing high-quality data support for subsequent volume load assessment, and significantly improving the adaptability and practical value of the overall technical solution in special clinical scenarios.

[0116] It should be noted that the analysis methods for cardiac test data in this application are not limited to the aforementioned RR / SS interval analysis. Information related to volume overload can also be extracted through other electrocardiographic features, such as: 1. Analyzing the correlation between morphological abnormalities and volume overload (e.g., a 40% increase in the risk of volume overload when Q wave depth > 0.3mV) based on the waveform morphology characteristics of the QRS complex (e.g., Q wave depth > 0.3mV); 2. Quantifying the intensity of atrial electrical activity based on the integral area of ​​the P wave (i.e., the area enclosed by the P wave waveform and the time axis), and then correlating it with the volume overload status (e.g., integral area > 0.1mV). When heart rate variability (HRV) is 3. Spectral analysis based on ECG signals (e.g., converting ECG signals to the frequency domain and extracting the energy proportions of low and high frequency bands) maps the volume load level through the frequency domain characteristics of heart rate variability. The above-mentioned analytical methods can be used individually or in combination, all capable of extracting volume load-related information. This application does not limit the specific methods used; the appropriate method can be flexibly selected based on the clinical scenario and data acquisition conditions.

[0117] In one possible implementation, when generating load state correction information based on the current user status information, state offset information can be determined based on the current user status information. Then, based on this state offset information, load state correction information is generated to adjust the initial capacity load state assessment results, achieving accurate calibration of the assessment results. Specifically, a possible method for generating load state correction information based on the current user status information may include:

[0118] D1. Determine the state offset information based on the current user state information;

[0119] D2. Generate load state correction information based on the state offset information.

[0120] Among them, state offset information refers to the quantitative information on the degree and direction of deviation of the current user's state information from the user's stable baseline state (such as resting state, routine medication state). This state offset information can clarify the user's current state and the potential trend and magnitude of its impact on the capacity load assessment results.

[0121] Based on the state offset information, adjustment criteria can be generated to correct the initial capacity load state information, namely the aforementioned load state correction information. Optionally, the load state correction information may include, but is not limited to, specific correction parameters, correction rules, and applicable scope, and can be directly applied to the optimization and adjustment of the initial assessment results.

[0122] Specifically, a standard parameter range for a user's stable baseline state can be preset, such as a physical activity level of 0 at rest, a fixed dose of routine medication, and no obvious clinical symptoms; the standard parameter range for this stable baseline state can be determined based on clinical big data statistics and medical research conclusions. The collected current user status information can be compared item by item with the standard parameter range. For example, for physical activity, the activity intensity can be divided into 0-4 levels, such as level 0 for rest, level 1 for mild activity, level 2 for moderate activity, level 3 for severe activity, and level 4 for strenuous activity. If the current user's activity level is level 2, compared to the baseline level 0, the deviation direction can be determined as "increased load," and the deviation magnitude can be quantified as 2. For medication adjustment information, if the user's diuretic dosage has recently increased by 20%, compared to the regular dosage, the deviation direction can be determined as "decreased load," and the deviation magnitude can be quantified as 1.2. For clinical symptoms, if the user has mild lower limb edema, compared to the baseline state without edema, the deviation direction can be determined as "increased load," and the deviation magnitude can be quantified as 1.5. Furthermore, by integrating all comparison results, a comprehensive offset value can be calculated according to preset weights, such as setting the weight of physical activity to 0.4, the weight of medication adjustment to 0.3, and the weight of clinical symptoms to 0.3, thereby forming complete state offset information to clarify the overall offset direction and comprehensive offset magnitude.

[0123] For example, if the user's current physical activity level is level 2 (moderate activity), the quantified deviation from the baseline level 0 is 2; a recent 20% increase in diuretic dosage results in a quantified deviation of 1.2; and the appearance of mild lower limb edema results in a quantified deviation of 1.5. The overall deviation can be calculated using the formula: Overall Deviation = (Physical Activity Deviation × 0.4) + (Medication Adjustment Deviation × 0.3) + (Clinical Symptom Deviation × 0.3), resulting in the overall deviation of (2 × 0.4) + (1.2 × 0.3) + (1.5 × 0.3) = 0.8 + 0.36 + 0.45 = 1.61. This deviation is further combined with the deviation direction "increased load" to form complete state deviation information. The above calculation logic is validated based on clinical follow-up data and can accurately quantify the impact of real-time status on volume load assessment.

[0124] Based on the determined state offset information, load state correction information can be generated by combining the preset offset information with the correction rule mapping relationship. The mapping relationship is constructed based on statistical analysis of retrospective clinical data from 1000 heart failure patients and a rule base of cardiology experts. Specifically, it can be based on: data foundation, such as collecting status information, volume load gold standard values ​​(e.g., central venous pressure), and initial assessment values ​​of patients with different New York Heart Association (NYHA) classifications (II-IV), comorbidities (hypertension, diabetes, etc.), to establish a related dataset; rule formulation, such as clarifying the quantitative correspondence between "overall deviation range" and "correction parameters" through statistical analysis (e.g., an overall deviation range of 1.5-2.0 corresponds to a 15% reduction, and 1.0-1.5 corresponds to a 10% increase), and being verified by three experts at the associate chief physician level or above to ensure compliance with clinical pathological logic (e.g., increased post-exercise load tends to lead to an overestimation of the initial assessment, requiring a reduction; decreased post-diuretic load tends to lead to an underestimation of the initial assessment, requiring an increase); and verification methods, such as using 5-fold cross-validation. After applying the mapping rules, the correction accuracy reached 88%, an improvement of 16 percentage points compared to the uncorrected version.

[0125] For example, if the status offset information is "load increased, overall offset magnitude 1.8", the corresponding generated correction parameter can be "initial capacity load assessment result reduced by 15%", and the correction rule is "this parameter is applicable to the assessment result adjustment within 1-2 hours after the activity"; if the status offset information is "load decreased, overall offset magnitude 1.2", the corresponding generated correction parameter can be "initial capacity load assessment result increased by 10%", and the correction rule is "this parameter is applicable to the assessment result adjustment within 24 hours after the medication dosage adjustment".

[0126] Understandably, the generation of correction information can strictly follow the mapping relationship between clinically validated offset information and correction rules to ensure the rationality and applicability of the generated correction parameters, thereby forming load state correction information containing specific correction values, applicable scenarios and application methods. This load state correction information can be directly used for subsequent correction processing of initial capacity load state information.

[0127] In this example, the logic of determining state offset information based on the current user state information and generating load state correction information accordingly achieves accurate calibration of the initial capacity load state assessment results, effectively solving the problem of result deviation caused by ignoring real-time changes in user state in traditional assessments. This embodiment quantifies real-time influencing factors such as temporary physical activity, medication adjustments, and clinical symptoms into state offset information, clarifying their direction and magnitude of influence on capacity load assessment, making the correction basis more targeted. At the same time, the generation of correction information relies on a preset clinical validation mapping relationship, combining multiple state factors with weight allocation to ensure the scientific and reasonable nature of the correction parameters, and includes specific applicable scenarios and application rules, avoiding the uncertainty caused by fuzzy adjustments. This can significantly improve the accuracy and adaptability of capacity load assessment results, providing a reliable guarantee for the determination of subsequent target capacity load state information, and further enhancing the clinical practical value of the overall assessment scheme.

[0128] For examples consistent with the above embodiments, please refer to... Figure 3 , Figure 3 A schematic diagram of a terminal structure provided in an embodiment of this application is shown in the figure. It includes a processor, an input device, an output device, and a memory. The processor, input device, output device, and memory are interconnected. The memory is used to store a computer program, which includes program instructions. The processor is configured to call the program instructions. The program includes instructions for performing the following steps.

[0129] Obtain the original test data of the user to be tested; the original test data includes vital sign data and cardiac test data;

[0130] The initial capacity load status information is determined based on the original data to be detected.

[0131] Obtain the current user status information of the user to be detected; the current user status information includes at least clinical symptoms, recent treatment and medication, and physical activity status.

[0132] Generate load status correction information based on the current user status information;

[0133] The initial capacity load status information is corrected using the load status correction information to obtain the target capacity load status information;

[0134] Feature recognition is performed on the target capacity load status information to obtain the cardiac load feature information of the user to be detected.

[0135] In this example, by acquiring the original data of the user to be tested, the initial volume load status information can be determined based on the original data. By acquiring the current user status information of the user to be tested, load status correction information can be generated based on the current user status information. The initial volume load status information can then be corrected using the load status correction information to obtain the target volume load status information. Furthermore, feature recognition can be performed on the target volume load status information to obtain the cardiac load feature information of the user to be tested. This helps to improve the accuracy of the information processing process for assisting in the assessment of the volume load status of heart failure patients.

[0136] The above mainly describes the solutions of the embodiments of this application from the perspective of the method execution process. It is understood that, in order to achieve the above functions, the terminal includes the corresponding hardware structure and / or software modules for executing each function. Those skilled in the art should readily recognize that, in conjunction with the units and algorithm steps of the various examples described in the embodiments provided herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0137] This application embodiment can divide the terminal into functional units according to the above method example. For example, each function can be divided into a separate functional unit, or two or more functions can be integrated into one processing unit. The integrated unit can be implemented in hardware or as a software functional unit. It should be noted that the unit division in this application embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0138] For those consistent with the above, please refer to Figure 4 , Figure 4 This application provides a schematic diagram of the structure of an information processing device for assisting in assessing the volume overload status of patients with heart failure. (See attached diagram.) Figure 4 As shown, the device includes:

[0139] The first acquisition unit 101 is used to acquire the original data to be tested from the user to be tested; the original data to be tested includes vital sign data and cardiac test data.

[0140] Determining unit 102 is used to determine initial capacity load status information based on the original data to be detected;

[0141] The second acquisition unit 103 is used to acquire the current user status information of the user to be detected; the current user status information includes at least clinical symptoms, recent treatment and medication, and physical activity status.

[0142] The generation unit 104 is used to generate load status correction information based on the current user status information;

[0143] The first processing unit 105 is used to correct the initial capacity load status information using the load status correction information to obtain the target capacity load status information;

[0144] The second processing unit 106 is used to perform feature recognition on the target capacity load status information to obtain the cardiac load feature information of the user to be detected.

[0145] In one possible implementation, the determining unit 102 is configured to determine initial capacity load status information based on the original data to be detected, specifically for:

[0146] Extract vital sign data and cardiac test data from the original data to be tested;

[0147] The load status analysis is performed using the aforementioned vital sign data to obtain the first reference capacity load status information;

[0148] The cardiac detection data is used to perform load status analysis to obtain second reference capacity load status information;

[0149] The first reference capacity load status information and the second reference capacity load status information are fused together to obtain the initial capacity load status information.

[0150] In one possible implementation, the cardiac detection data includes an initial electrocardiogram, and the determining unit 102 is used to perform load status analysis using the cardiac detection data to obtain second reference capacity load status information, specifically for:

[0151] The QRS complex is obtained by extracting the QRS wave from the initial electrocardiogram, and the P wave is obtained by extracting the P wave from the initial electrocardiogram.

[0152] Heart rate fluctuations are extracted based on the QRS complex to obtain the first fluctuation information;

[0153] Heart rate fluctuations are extracted based on the P wave group to obtain the second fluctuation information;

[0154] The first and second fluctuation information are fused together to obtain the target fluctuation information;

[0155] Load status analysis is performed based on the target fluctuation information to obtain the second reference capacity load status information.

[0156] In one possible implementation, the determining unit 102 is used to extract heart rate fluctuations based on the QRS complex to obtain first fluctuation information, specifically for:

[0157] Obtain the RR interval in two adjacent QRS waves to obtain the RR interval set, and obtain the SS interval in two adjacent QRS waves to obtain the SS interval set;

[0158] A volatility analysis graph is constructed based on the RR interval set to obtain the first volatility analysis curve;

[0159] A second volatility analysis curve is obtained by constructing a volatility analysis graph based on the SS interval set;

[0160] The first and second wave analysis curves are merged to obtain the target wave analysis chart.

[0161] The first wave information is obtained by extracting wave information based on the target wave analysis diagram.

[0162] In one possible implementation, the generation unit 104 is configured to generate load status correction information based on the current user status information, specifically for:

[0163] Determine the state offset information based on the current user state information;

[0164] Load state correction information is generated based on the state offset information.

[0165] In one possible implementation, the determining unit 102 is configured to fuse the first reference capacity load status information and the second reference capacity load status information to obtain initial capacity load status information, specifically for:

[0166] If both the first reference capacity load status information and the second reference capacity load status information point to the same capacity load status information, then the same capacity load status information is determined to be the initial capacity load status information.

[0167] If there is a difference between the first reference capacity load status information and the second reference capacity load status information, then the initial capacity load status information is obtained by combining the weight coefficients of the two types of reference capacity load status information for quantitative analysis.

[0168] Wherein, if there is a difference between the first reference capacity load status information and the second reference capacity load status information, a quantitative analysis is performed by combining the weight coefficients of the two types of reference capacity load status information to obtain the initial capacity load status information, including:

[0169] The first reference capacity load status information is subjected to a credibility quantification score to obtain the first reference score.

[0170] The second reference capacity load status information is subjected to a credibility quantification score to obtain the second reference score;

[0171] A comprehensive weighted score is obtained by performing a weighted summation based on the first reference score and the second reference score.

[0172] The initial capacity load status information is obtained based on the comprehensive weighted score.

[0173] This application also provides a computer storage medium storing a computer program for electronic data exchange, which causes a computer to perform some or all of the steps of any of the information processing methods for assisting in assessing the volume overload status of heart failure patients as described in the above method embodiments.

[0174] This application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program that causes a computer to perform some or all of the steps of any of the information processing methods for assisting in assessing the volume overload status of heart failure patients as described in the above method embodiments.

[0175] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0176] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0177] In the several embodiments provided in this application, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical or other forms.

[0178] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0179] Furthermore, the functional units in the various embodiments of the application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software program module.

[0180] If the integrated unit is implemented as a software program module and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0181] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage device, which may include: a flash drive, a read-only memory, a random access memory, a magnetic disk, or an optical disk, etc.

[0182] The embodiments of this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. An information processing method for assisting in the assessment of volume overload status in patients with heart failure, characterized in that, The method includes: Obtain the original test data of the user to be tested; the original test data includes vital sign data and cardiac test data; The initial capacity load status information is determined based on the original data to be detected. Obtain the current user status information of the user to be detected; the current user status information includes at least clinical symptoms, recent treatment and medication, and physical activity status. Generate load status correction information based on the current user status information; The initial capacity load status information is corrected using the load status correction information to obtain the target capacity load status information; Feature recognition is performed on the target capacity load status information to obtain the cardiac load feature information of the user to be detected; The step of determining the initial capacity load status information based on the original data to be detected includes: Extract vital sign data and cardiac test data from the original data to be tested; The load status analysis is performed using the aforementioned vital sign data to obtain the first reference capacity load status information; The cardiac detection data is used to perform load status analysis to obtain second reference capacity load status information; The first reference capacity load status information and the second reference capacity load status information are fused together to obtain the initial capacity load status information. The cardiac detection data includes an initial electrocardiogram. The step of using the cardiac detection data to perform load status analysis to obtain second reference capacity load status information includes: The QRS complex is obtained by extracting the QRS wave from the initial electrocardiogram, and the P wave is obtained by extracting the P wave from the initial electrocardiogram. Heart rate fluctuations are extracted based on the QRS complex to obtain the first fluctuation information; Heart rate fluctuations are extracted based on the P wave group to obtain the second fluctuation information; The first and second fluctuation information are fused together to obtain the target fluctuation information; Load status analysis is performed based on the target fluctuation information to obtain the second reference capacity load status information.

2. The information processing method for assisting in the assessment of volume overload status in patients with heart failure according to claim 1, characterized in that, The step of extracting heart rate fluctuations based on the QRS complex to obtain first fluctuation information includes: Obtain the RR interval in two adjacent QRS waves to obtain the RR interval set, and obtain the SS interval in two adjacent QRS waves to obtain the SS interval set; A volatility analysis graph is constructed based on the RR interval set to obtain the first volatility analysis curve; A second volatility analysis curve is obtained by constructing a volatility analysis graph based on the SS interval set; The first and second wave analysis curves are merged to obtain the target wave analysis chart. The first wave information is obtained by extracting wave information based on the target wave analysis diagram.

3. The information processing method for assisting in the assessment of volume overload status in patients with heart failure according to claim 2, characterized in that, The step of generating load status correction information based on the current user status information includes: Determine the state offset information based on the current user state information; Load state correction information is generated based on the state offset information.

4. The information processing method for assisting in the assessment of volume overload status in patients with heart failure according to claim 1, characterized in that, The step of fusing the first reference capacity load status information and the second reference capacity load status information to obtain initial capacity load status information includes: If both the first reference capacity load status information and the second reference capacity load status information point to the same capacity load status information, then the same capacity load status information is determined to be the initial capacity load status information. If there is a difference between the first reference capacity load status information and the second reference capacity load status information, then the initial capacity load status information is obtained by combining the weight coefficients of the two types of reference capacity load status information for quantitative analysis. Wherein, if there is a difference between the first reference capacity load status information and the second reference capacity load status information, a quantitative analysis is performed by combining the weight coefficients of the two types of reference capacity load status information to obtain the initial capacity load status information, including: The first reference capacity load status information is subjected to a credibility quantification score to obtain the first reference score. The second reference capacity load status information is subjected to a credibility quantification score to obtain the second reference score; A comprehensive weighted score is obtained by performing a weighted summation based on the first reference score and the second reference score. The initial capacity load status information is obtained based on the comprehensive weighted score.

5. An information processing device for assisting in assessing the volume overload status of patients with heart failure, characterized in that, The device includes: The first acquisition unit is used to acquire the original data to be tested from the user to be tested; the original data to be tested includes vital sign data and cardiac test data. A determining unit is used to determine initial capacity load status information based on the original data to be detected; The second acquisition unit is used to acquire the current user status information of the user to be detected; the current user status information includes at least clinical symptoms, recent treatment and medication, and physical activity status. The generation unit is used to generate load status correction information based on the current user status information; The first processing unit is used to correct the initial capacity load status information using the load status correction information to obtain the target capacity load status information; The second processing unit is used to perform feature recognition on the target capacity load status information to obtain the cardiac load feature information of the user to be detected. The determining unit is used to determine the initial capacity load status information based on the original data to be detected, specifically for: Extract vital sign data and cardiac test data from the original data to be tested; The load status analysis is performed using the aforementioned vital sign data to obtain the first reference capacity load status information; The cardiac detection data is used to perform load status analysis to obtain second reference capacity load status information; The first reference capacity load status information and the second reference capacity load status information are fused together to obtain the initial capacity load status information. The cardiac detection data includes an initial electrocardiogram. The step of using the cardiac detection data to perform load status analysis to obtain second reference capacity load status information includes: The QRS complex is obtained by extracting the QRS wave from the initial electrocardiogram, and the P wave is obtained by extracting the P wave from the initial electrocardiogram. Heart rate fluctuations are extracted based on the QRS complex to obtain the first fluctuation information; Heart rate fluctuations are extracted based on the P wave group to obtain the second fluctuation information; The first and second fluctuation information are fused together to obtain the target fluctuation information; Load status analysis is performed based on the target fluctuation information to obtain the second reference capacity load status information.

6. A terminal, characterized in that, The device includes a processor, an input device, an output device, and a memory, which are interconnected. The memory stores a computer program, which includes program instructions. The processor is configured to invoke the program instructions to perform the steps of the information processing method for assisting in assessing the volume overload status of a heart failure patient as described in any one of claims 1-4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, the computer program including program instructions that, when executed by a processor, cause the processor to perform the steps of the information processing method for assisting in the assessment of the volume overload status of a heart failure patient as described in any one of claims 1-4.

Images