Vascular age assessment methods, devices, electronic equipment and storage media

Abstract

This application provides a method, apparatus, electronic device, and storage medium for vascular age assessment. The method includes acquiring the photoplethysmography (PPG) signal of a finger of a wearable device; extracting features from the PPG signal to obtain multi-dimensional morphological features; acquiring information about the finger worn by the wearable device and an assessment model, and calibrating the multi-dimensional morphological features based on the finger information to obtain calibration features; and evaluating the calibration features based on the assessment model to obtain an estimated vascular age. This method can improve the accuracy of vascular age assessment.

Description

Technical Field

[0001] This application relates to the field of wearable device technology, and in particular to a method, device, electronic device and storage medium for vascular age assessment. Background Technology

[0002] Cardiovascular disease is a general term for a series of circulatory system diseases affecting the heart, arteries, veins, and microcirculation. It broadly refers to various organic and functional diseases caused by pathological changes such as vascular structural lesions, hemodynamic abnormalities, endothelial damage, atherosclerosis, decreased vascular elasticity, or abnormal cardiac function. Vascular age is an important indicator for assessing cardiovascular health and can directly reflect the actual degree of aging of the blood vessel walls.

[0003] Currently, vascular age can be assessed using wearable devices. These devices collect pulse wave signals from the body surface and combine them with a pre-trained machine learning assessment model to calculate a quantified vascular age value, enabling routine monitoring of cardiovascular health. However, the accuracy of vascular age assessment is currently not high. Summary of the Invention

[0004] The main objective of this application is to provide a method, device, electronic device, and storage medium for vascular age assessment, which can improve the accuracy of vascular age assessment.

[0005] To achieve the above objectives, this application proposes a method for assessing vascular age, comprising: Acquire the photoplethysmography (PPG) signal of the finger of the wearer of the wearable device; Feature extraction was performed on the photoplethysmography signal to obtain multi-dimensional morphological features; Acquire information about the fingers worn by the wearable device and an evaluation model, and calibrate multi-dimensional morphological features based on the information about the fingers worn to obtain calibrated features; The calibration features are evaluated based on the evaluation model to obtain an estimated vascular age.

[0006] Optionally, in one embodiment, multi-dimensional morphological features are calibrated based on information about the wearing finger to obtain calibrated features, including: Acquire baseline differences between different fingers and evaluate the training finger information corresponding to the model; Based on information from the worn finger, the trained finger, and baseline differences, multi-dimensional morphological features are calibrated to obtain calibrated features.

[0007] Optionally, in one embodiment, obtaining information about the finger wearing the wearable device includes: Receive wireless communication information from applications associated with wearable devices; The wearer's finger information is determined based on wireless communication information.

[0008] Optionally, in one implementation, the calibration features are evaluated based on an evaluation model to obtain an estimated vascular age, including: Acquire multiple calibration features corresponding to the repeated acquisition process according to a preset cycle; Each calibration feature is evaluated based on the evaluation model to obtain the estimated vascular age value corresponding to each calibration feature; A vascular age time series is established based on the estimated vascular age values ​​corresponding to each calibration feature, and risk warning is performed based on the vascular age time series.

[0009] Optionally, in one implementation, risk warning based on vascular age time series includes: The linear regression slope of the vascular age time series was calculated using a preset time window; When the slope exceeds the preset trend threshold, a trend deterioration warning is issued.

[0010] Optionally, in one embodiment, after evaluating the calibration features based on the evaluation model to obtain the estimated vascular age, the method further includes: The actual age of the wearer is obtained, and the risk assessment result is determined based on the age difference between the vascular age assessment value and the actual age. The risk assessment result includes: when the age difference is less than the first threshold, it is marked as a young vascular state; when the age difference is greater than the first threshold but less than the second threshold, it is marked as a normal state; when the age difference is greater than the second threshold but less than the third threshold, a yellow warning is issued; when the age difference exceeds the third threshold, a red warning is issued. The first threshold is a negative value, and the second and third thresholds are positive values.

[0011] Optionally, in one embodiment, the multidimensional morphological features include at least two of the following: time-domain features, amplitude features, and second-derivative features.

[0012] Another aspect of this application provides a vascular age assessment device, comprising: The acquisition unit is used to acquire the photoplethysmography (PPG) signal of the finger of the wearer of the wearable device; The extraction unit is used to extract features from the photoplethysmography (PPG) signal to obtain multi-dimensional morphological features. The calibration unit is used to acquire information about the fingers worn by the wearable device and the evaluation model, and to calibrate the multi-dimensional morphological features based on the information about the fingers worn to obtain calibration features; The evaluation unit is used to evaluate the calibration features based on the evaluation model to obtain an estimated vascular age.

[0013] Another aspect of this application provides an electronic device, comprising: Memory, transceiver, processor, and bus system; The memory is used to store programs; The processor is used to execute programs in memory, including methods for performing the aspects mentioned above; Bus systems are used to connect memory and processor to enable communication between them.

[0014] Another aspect of this application provides a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the methods described above.

[0015] As can be seen from the above technical solutions, the embodiments of this application have the following advantages: By acquiring the photoplethysmography (PPG) signal of the wearer's finger in real time and extracting multi-dimensional morphological features, and combining the information of the worn finger to complete the feature-specific calibration, the inherent differences in subcutaneous tissue thickness, vascular distribution, and signal transmission conditions of different fingers are offset. This makes the feature data input to the evaluation model more compatible with the model's operation logic, thereby outputting a reliable vascular age estimate and improving the accuracy of vascular age assessment. Attached Figure Description

[0016] Figure 1 This is a schematic diagram of the architecture of the vascular age assessment method provided in the embodiments of this application; Figure 2 This is a schematic flowchart of the vascular age assessment method provided in the embodiments of this application; Figure 3 This is a schematic diagram illustrating the specific execution process of the vascular age assessment procedure provided in the embodiments of this application; Figure 4 This is a schematic diagram of the structure of the wearable device provided in the embodiments of this application; Figure 5 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0018] It should be noted that although functional modules are divided in the device schematic diagram and a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first," "second," etc., in the specification, claims, and the aforementioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0019] The term “exemplary” as used herein means “serving as an example, embodiment, or illustration.” Any embodiment illustrated herein as “exemplary” is not necessarily to be construed as superior to or better than other embodiments.

[0020] In the embodiments of this application, the terms "module" or "unit" refer to a computer program or part of a computer program that has a predetermined function and works with other related parts to achieve a predetermined goal, and can be implemented wholly or partially using software, hardware (such as processing circuitry or memory), or a combination thereof. Similarly, a processor (or multiple processors or memory) can be used to implement one or more modules or units. Furthermore, each module or unit can be part of an overall module or unit that includes the functionality of that module or unit.

[0021] Furthermore, to better illustrate this application, numerous specific details are provided in the following detailed embodiments. Those skilled in the art should understand that this application can be implemented without certain specific details. In some instances, methods, means, components, and circuits well-known to those skilled in the art have not been described in detail in order to highlight the main points of this application.

[0022] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0023] Cardiovascular disease is a general term for a series of circulatory system diseases affecting the heart, arteries, veins, and microcirculation. It broadly refers to various organic and functional diseases caused by pathological changes such as vascular structural lesions, hemodynamic abnormalities, endothelial damage, atherosclerosis, decreased vascular elasticity, or abnormal cardiac function. Vascular age is an important indicator for assessing cardiovascular health and can directly reflect the actual degree of aging of the blood vessel walls.

[0024] Currently, vascular age can be assessed using wearable devices. These devices collect pulse wave signals from the body surface and combine them with a pre-trained machine learning assessment model to calculate a quantified vascular age value, enabling routine monitoring of cardiovascular health. However, the accuracy of vascular age assessment is currently not high.

[0025] Based on this, embodiments of this application provide a method for assessing vascular age, which can solve the above-mentioned technical problems.

[0026] System architecture and scenario description used in the embodiments of this application: Figure 1 This is a system architecture diagram of the vascular age assessment method according to an embodiment of this application. It includes a terminal 140, an Internet 130, a gateway 120, a server 110, etc.

[0027] Terminal 140 includes various forms of devices with display screens, such as desktop computers, laptops, PDAs (personal digital assistants), mobile phones, in-vehicle terminals, home theater terminals, dedicated terminals, intelligent voice interaction devices, smart home appliances, or aircraft. Furthermore, it can be a single device or a collection of multiple devices. Terminal 140 can communicate with the Internet 130 via wired or wireless means to exchange data.

[0028] Server 110 refers to a computer system that can provide certain services to terminal 140. Compared to ordinary terminal 140, server 110 has higher requirements in terms of stability, security, and performance. Server 110 can be a single high-performance computer in a network platform, a cluster of multiple high-performance computers, a portion of a single high-performance computer (e.g., a virtual machine), or a combination of portions of multiple high-performance computers (e.g., virtual machines).

[0029] Gateway 120, also known as an internetwork connector or protocol converter, is a computer system or device that acts as a translator, enabling network interconnection at the transport layer. It bridges the gap between two systems using different communication protocols, data formats, languages, or even completely different architectures. Gateways can also provide filtering and security functions. Messages sent from terminal 140 to server 110 are forwarded to the corresponding server 110 via gateway 120. Messages sent from server 110 to terminal 140 are also forwarded to the corresponding terminal 140 via gateway 120.

[0030] The vascular age assessment method provided in this application embodiment can be implemented independently in terminal 140, independently in server 110, or partially in terminal 140 and partially in server 110.

[0031] When the vascular age assessment method provided in this application embodiment is implemented alone in the terminal 140, the terminal 140 acquires the photoplethysmography (PPG) signal of the wearer of the wearable device; the terminal 140 extracts features from the PPG signal to obtain multi-dimensional morphological features; the terminal 140 acquires the information of the wearing finger and the assessment model of the wearable device, and calibrates the multi-dimensional morphological features based on the information of the wearing finger to obtain calibrated features; the terminal 140 evaluates the calibrated features based on the assessment model to obtain an estimated vascular age value.

[0032] The vascular age assessment method provided in this application embodiment will be described below with reference to the accompanying drawings. The execution subject of the vascular age assessment method described below is a terminal device, specifically implemented by the terminal device running the various computer programs described above. Of course, based on the understanding of the following text, it is not difficult to see that the vascular age assessment method provided in this application embodiment can also be implemented collaboratively by the terminal device and the server. This application embodiment uses the vascular age assessment of a smart ring as an example.

[0033] Please see Figure 2 ,like Figure 2 The diagram shown is a flowchart of a vascular age assessment method provided in this embodiment. The method includes: Step 201: Obtain the photoplethysmography (PPG) signal of the wearer of the wearable device.

[0034] Wearable devices, such as smart rings, are designed for users who need vascular age detection and cardiovascular health assessment.

[0035] Photoplethysmography (PPG) signals can be obtained by capturing the fluctuating electrical signals formed by the periodic changes in subcutaneous blood vessel volume with the heartbeat using photoelectric detection. They can be obtained by real-time acquisition of the original physiological signals of subcutaneous blood flow fluctuations using wearable photoelectric sensors.

[0036] Step 202: Extract features from the photoplethysmography signal to obtain multi-dimensional morphological features.

[0037] Feature extraction can be a computational process that removes invalid and noisy data and mines the core correlation information of pulse waves.

[0038] Multidimensional morphological features can be pulse wave waveform parameters that directly reflect vascular elasticity, blood flow efficiency, and the degree of vessel wall aging. After acquiring the raw pulse wave signal, signal preprocessing removes invalid clutter caused by environmental interference and motion noise. The normalized effective waveform is then quantified and calculated, and multiple morphological parameters such as waveform peak value, fluctuation period, rising edge, and falling edge are decomposed and extracted. These parameters are then integrated to form a multidimensional morphological feature set, transforming the abstract waveform signal into quantified data that can be recognized and processed by the model.

[0039] In one implementation, the multidimensional morphological features include at least two of the following: time-domain features, amplitude features, and second-derivative features.

[0040] In this embodiment, the time-domain features can be parameters that describe the periodic changes and temporal distribution of the pulse wave on a time scale. They are used to reflect the temporal patterns of heart rhythm, pulse rise and fall duration, and overall fluctuation period, and to reflect the rhythmic characteristics of vasodilation and vasoconstriction.

[0041] Amplitude characteristics can be amplitude-type parameters that characterize the strength of pulse wave fluctuations and the difference between peak values. Here, they can reflect the intensity of subcutaneous blood flow perfusion and the amplitude of vascular pulsation, directly corresponding to vascular tension and local blood circulation status.

[0042] The second derivative feature can be the rate of change obtained by performing a second derivative operation on the original pulse wave waveform. It is used to capture subtle inflection points, local deformations and attenuation trends of the waveform, and reflect subtle pathological changes such as the hardness and elasticity of the blood vessel wall.

[0043] By combining waveform parameters from different dimensions, the system comprehensively covers the temporal changes of pulse waves, pulsation intensity, and microscopic deformation patterns, fully preserving key information strongly correlated with vascular physiological state and improving the comprehensiveness of feature representation.

[0044] Step 203: Obtain the information of the wearing finger of the wearable device and the evaluation model, and calibrate the multi-dimensional morphological features based on the information of the wearing finger to obtain the calibration features.

[0045] The information on the finger being worn can be an identifier marking the current wearing position. In this solution, it can be manually entered and generated by the user to distinguish between different fingers such as the ring finger, middle finger, and index finger, and to characterize the physiological differences in different detection sites.

[0046] The evaluation model can be a pre-trained intelligent computing model, which in this case is a dedicated regression algorithm model that takes pulse wave features as input and vascular age as output, and is used to establish a mapping relationship between pulse wave features and the degree of vascular aging.

[0047] Feature calibration can be a correction method that adjusts data deviations based on differential conditions. In this case, it can be a unified correction and adaptation of morphological features by combining the differences in subcutaneous tissue and blood vessel distribution among different fingers. First, the user's pre-set information on the wearing finger is read. Combining the natural differences in skin thickness, blood vessel superficiality, and signal transmission loss among different fingers, targeted deviation compensation and standardization corrections are made for multi-dimensional morphological features to eliminate systematic data offsets caused by changing wearing positions. Finally, calibration features that are adapted to the current wearing position and conform to the model input standards are generated.

[0048] In one implementation, multi-dimensional morphological features are calibrated based on information about the worn finger to obtain calibrated features, including: Acquire baseline differences between different fingers and evaluate the training finger information corresponding to the model; Based on information from the worn finger, the trained finger, and baseline differences, multi-dimensional morphological features are calibrated to obtain calibrated features.

[0049] In this embodiment, the baseline difference can be the difference between various basic reference benchmarks when different fingers are used as detection sites. That is, after the same wearer collects photoplethysmography signals and extracts multidimensional morphological features from different fingers (index finger, middle finger, ring finger, etc.), the quantitative deviation between multidimensional morphological features caused by the inherent differences in subcutaneous tissue thickness, blood vessel distribution density, signal transmission loss, and blood perfusion intensity of each finger.

[0050] Training finger information can be the information corresponding to the fixed wearing finger (such as uniformly using the index finger as the training benchmark) used by the evaluation model during the training phase to collect sample data, train features and the mapping relationship between vascular age.

[0051] Calibration can combine the above three types of information to perform targeted deviation compensation, numerical adjustment and standardization on the extracted multi-dimensional morphological features, thereby eliminating feature shifts caused by different fingers being worn.

[0052] By standardizing and correcting the extracted multi-dimensional morphological features, signal offset caused by differences in finger parts is eliminated, ensuring that the corrected calibration features are consistent with the feature benchmark during the training of the evaluation model in terms of distribution and numerical range, thereby improving the output accuracy of the evaluation model.

[0053] In one embodiment, obtaining information about the finger wearing the wearable device includes: Receive wireless communication information from applications associated with wearable devices; The wearer's finger information is determined based on wireless communication information.

[0054] In this embodiment, the application software associated with the wearable device can be a mobile APP paired with the smart ring, that is, a mobile program that realizes data interaction and control.

[0055] Wireless communication information can be configuration data sent by the APP to the smart ring via wireless links such as Bluetooth. The received wireless communication information is parsed, identified, and extracted. From this data, the wear position identifiers manually set and entered by the user are filtered out. The parsed position identifiers are then fixed into locally recognizable wear finger information, thus completing the active determination and local storage of the wear position.

[0056] By wirelessly transmitting configuration information through application software to instruct the wearing finger information, the wearing finger information can be configured quickly.

[0057] Step 204: Evaluate the calibration features based on the evaluation model to obtain the estimated vascular age.

[0058] The calibration features, after site-specific calibration, are input into the preset evaluation model. The model performs intelligent calculations and deductions based on the correlation between the features established during the training phase and vascular aging. It combines the comprehensive performance of various morphological features to complete the quantitative judgment and finally outputs the estimated value of vascular age.

[0059] In one implementation, the calibration features are evaluated based on an evaluation model to obtain an estimated vascular age, including: Acquire multiple calibration features corresponding to the repeated acquisition process according to a preset cycle; Each calibration feature is evaluated based on the evaluation model to obtain the estimated vascular age value corresponding to each calibration feature; A vascular age time series is established based on the estimated vascular age values ​​corresponding to each calibration feature, and risk warning is performed based on the vascular age time series.

[0060] In this embodiment, the photoplethysmography (PPG) signal is continuously collected in a loop according to a fixed time period pre-configured by the device. The feature extraction and finger differentiation calibration process is repeated to generate multiple calibration features corresponding to different times in sequence, forming a time-series feature sample set.

[0061] The locally deployed evaluation model is invoked, and each set of independent calibration features in the time series is input into the model for inference calculation. The estimated vascular age value at the corresponding time point is generated one by one, realizing quantitative measurement in multiple time periods and obtaining multiple sets of evaluation result data.

[0062] By integrating and arranging all estimated vascular ages obtained at different time points in chronological order to construct a continuous vascular age time series, the cardiovascular health status can be determined and risk warnings can be output based on changes such as abnormal increases or continuous deviations in the series.

[0063] By using an ordered time series to achieve long-term dynamic detection, the slow evolution trend and staged abnormal fluctuations of vascular aging can be effectively captured. It can distinguish between short-term random fluctuations and substantial degenerative changes in vascular status, reduce the probability of misjudgment, and comprehensively improve the timeliness and objectivity of cardiovascular health risk identification.

[0064] In one implementation, risk warning based on vascular age time series includes: The linear regression slope of the vascular age time series was calculated using a preset time window; When the slope exceeds the preset trend threshold, a trend deterioration warning is issued.

[0065] In this embodiment, the preset time window can be a data range of a continuous period in the vascular age time series, used to limit the sample interval for trend calculation.

[0066] The slope of linear regression can represent the overall rate of change of vascular age over time. A positive slope indicates that vascular age is gradually increasing, indicating that the aging process of blood vessels is accelerating. The larger the slope value, the more obvious the rate of deterioration.

[0067] The preset trend threshold can serve as a boundary value to distinguish between normal physiological fluctuations and pathological accelerated aging, and is used to standardize the determination of whether the upward trend of vascular age exceeds the reasonable fluctuation range. If the slope value exceeds the threshold range, it indicates that the vascular age shows an abnormal trend of continuous and rapid increase in the short term, which exceeds the scope of daily physiological fluctuations. At this time, the warning logic is triggered, and a trend deterioration reminder is sent to the wearer through the device or associated application software.

[0068] By relying on the slope exceeding the limit to trigger early warning, early trend changes in progressive vascular aging can be identified in a timely manner, and potential cardiovascular health risks can be detected early.

[0069] In one implementation, after evaluating the calibration features based on the evaluation model to obtain an estimated vascular age, the method further includes: The actual age of the wearer is obtained, and the risk assessment result is determined based on the age difference between the vascular age assessment value and the actual age. The risk assessment result includes: when the age difference is less than the first threshold, it is marked as a young vascular state; when the age difference is greater than the first threshold but less than the second threshold, it is marked as a normal state; when the age difference is greater than the second threshold but less than the third threshold, a yellow warning is issued; when the age difference exceeds the third threshold, a red warning is issued. The first threshold is a negative value, and the second and third thresholds are positive values.

[0070] In this embodiment, the actual age can be the real age parameter that the wearer enters into the associated application software and synchronizes to the wearable device.

[0071] The first threshold, second threshold, and third threshold can be used to progressively distinguish the boundaries between vascular conditions that are excellent, normal, mildly abnormal, and severely abnormal, thus achieving stratified judgment.

[0072] A youthful vascular state refers to a healthy state in which the degree of vascular aging is significantly lower than the actual physiological age, and the elasticity and blood flow of blood vessels are maintained at an excellent level.

[0073] A yellow warning indicates a mild risk, suggesting that the degree of vascular aging is relatively high and vascular function has undergone degenerative changes, which is a stage of abnormality.

[0074] A red alert indicates a severe risk, signifying that the degree of vascular aging is significantly excessive, with reduced vascular elasticity and a clear trend of hardening, corresponding to a high level of potential cardiovascular risks.

[0075] By specifically differentiating the severity of risks, it can accurately identify healthy vascular function and also provide tiered alerts for different degrees of vascular aging abnormalities. This allows wearers to intuitively understand their own basic cardiovascular health level and provides a tiered reference for daily health management and lifestyle adjustments.

[0076] In one example, the specific execution process of the vascular age assessment procedure is as follows: Figure 3 As shown: First, photoplethysmography (PPG) signals are acquired and preprocessed. Using the PPG sensor built into the smart ring, PPG signals from the finger area are acquired at a preset sampling rate (25Hz or 50Hz) using a 940nm infrared light source. The preprocessing steps include: using a 4th-order Butterworth bandpass filter (0.5-8Hz) to filter out baseline drift and high-frequency noise, purifying the original signal; further eliminating slow trend interference in the signal through cubic spline or higher-order polynomial detrending processing; dividing the continuous PPG signal into beat-to-beat independent pulse bands based on an adaptive peak detection algorithm (first derivative zero-crossing point + adaptive threshold); and introducing a signal quality assessment (SQI) mechanism, using the median waveform of the previous N pulse waves as a template to calculate the matching correlation coefficient between each pulse band and the template, eliminating unqualified pulse bands with an SQI < 0.8.

[0077] Next, calculate the first derivative PPG (VPG) and the second derivative PPG (APG / SDPPG). Where VPG = It is mainly used to reflect the velocity changes of the pulse wave and to locate key feature points of the pulse wave (including the onset, systolic peak, and dicrotic notch); APG= The SDPPG (Signaled Pulse Gaussian Gravitational) wave consists of five characteristic waves: a, b, c, d, and e. Each characteristic wave has a specific physiological meaning: wave a represents the peak of positive acceleration in early systole, corresponding to the initial acceleration after aortic valve opening; wave b represents the trough of negative acceleration in early systole, corresponding to the deceleration of the initial acceleration process; wave c represents the resurgence of positive acceleration in late systole, corresponding to the superposition effect of reflected waves; wave d represents negative acceleration in early diastole, corresponding to the deceleration process before aortic valve closure; and wave e represents the peak of positive acceleration in early diastole, corresponding to the dicrotic wave. A dedicated detection algorithm is used to sequentially search for five extreme points (positive-negative-positive-negative-positive) in the APG signal. Robustness and accuracy of characteristic wave detection are ensured through adaptive window and amplitude threshold settings.

[0078] Next, based on qualified beat-by-beat pulse bands, the system extracts multi-dimensional feature vectors to construct a complete feature input set, specifically including three types of features: First, time-domain features (5 dimensions), covering systole time T_systole (from wave start onset to systolic peak, in ms), diastole time T_diastole (from systolic peak to the next wave start onset, in ms), and systolic / diastolic time ratio T_ratio (…). The three dimensions of the Takazawa Age Index (SDPPG) are: 1) vascular compliance; 2) pulse wave rise time T_peak (from onset to systolic peak, in ms); 3) time interval T_notch (from systolic peak to dicrotic notch, in ms); 4) amplitude characteristics, including the reflection index RI (diastolic amplitude / systolic amplitude, reflecting peripheral vascular resistance); 5) sclerosis index SI (height (m) / time difference between systolic peak and reflection peak (s), in m / s, approximating pulse wave velocity PWV); 6) enhancement index AI (systolic wave enhancement / pulse pressure, reflecting the degree of reflection wave enhancement caused by arteriosclerosis); and 7) area ratio (area under the systolic curve AUC / diastolic curve AUC, reflecting the ratio of elastic energy storage to release in the vascular wall); and 8) SDPPG characteristics (7 dimensions, including the classic Takazawa Age Index Aging_index. (Correlation with actual age r>0.8) The ratio (approaching -0.3 with age from -0.8) Ratio (reflecting the intensity of reflected waves in the late stage of contraction) Ratio (reflecting early diastolic vascular elasticity) The ratio (reflects the amplitude of the dicrotic wave and is positively correlated with vascular elasticity) Ratio (comprehensively reflects changes in blood vessel wall elasticity) Ratio (an auxiliary feature used to distinguish different types of arteriosclerosis patterns).

[0079] Finally, vascular age is assessed based on the multi-dimensional feature vector using the evaluation model. To improve the stability of the assessment, the median value of the features of 10 qualified pulse segments can be selected as the feature vector of the week, and auxiliary features (gender, BMI segmentation) can be concatenated to construct an 18-dimensional complete input vector. This input vector is then fed into the XGBoost evaluation model, and the model outputs the final vascular age assessment value through calculation, completing the entire process of vascular age detection and assessment.

[0080] It is understandable that the input data in the training process of the evaluation model can also refer to the aforementioned feature processing method, which will not be elaborated here.

[0081] In one example, risk warnings can be issued for wearers based on vascular age time series. For instance, assuming the wearer is 35 years old, the vascular age detected in week 1 is 33 years old, which is an age difference of -2 years, and the wearer's condition is normal. In week 12, the vascular age detected is 31 years old, which is an age difference of -4 years, and the wearer's condition is still normal. The trend slope is -0.17 years / month (this slope can be within any time interval; this is just an example), meaning that the vascular age is slowly improving and no warning is needed. If the slope is positive and greater than a preset threshold, it indicates that the vascular age is deteriorating, and a warning needs to be issued to remind the wearer to pay attention.

[0082] The criteria for evaluating the wearer's condition in daily life can be shown in Table 1, with different risk levels and action recommendations based on different age differences.

[0083] Table 1

[0084] The above describes the method for assessing vascular age; the following describes the device used to perform this method.

[0085] See Figure 4 ,like Figure 4 The diagram shown is a structural schematic of a wearable device provided in this application, including: Acquisition unit 401 is used to acquire the photoplethysmography (PPG) signal of the finger of the wearer of the wearable device; Extraction unit 402 is used to extract features from photoplethysmography pulse wave signals to obtain multi-dimensional morphological features; The calibration unit 403 is used to acquire information about the wearing finger of the wearable device and the evaluation model, and to calibrate the multi-dimensional morphological features based on the information about the wearing finger to obtain calibration features; Evaluation unit 404 is used to evaluate calibration features based on the evaluation model to obtain an estimated vascular age.

[0086] Optionally, in one embodiment, the calibration unit 403 is specifically used for: Acquire baseline differences between different fingers and evaluate the training finger information corresponding to the model; Based on information from the worn finger, the trained finger, and baseline differences, multi-dimensional morphological features are calibrated to obtain calibrated features.

[0087] Optionally, in one embodiment, the calibration unit 403 is specifically used for: Receive wireless communication information from applications associated with wearable devices; The wearer's finger information is determined based on wireless communication information.

[0088] Optionally, in one embodiment, the evaluation unit 404 is specifically used for: Acquire multiple calibration features corresponding to the repeated acquisition process according to a preset cycle; Each calibration feature is evaluated based on the evaluation model to obtain the estimated vascular age value corresponding to each calibration feature; A vascular age time series is established based on the estimated vascular age values ​​corresponding to each calibration feature, and risk warning is performed based on the vascular age time series.

[0089] Optionally, in one embodiment, the evaluation unit 404 is specifically used for: The linear regression slope of the vascular age time series was calculated using a preset time window; When the slope exceeds the preset trend threshold, a trend deterioration warning is issued.

[0090] Optionally, in one embodiment, the evaluation unit 404 is further configured to: The actual age of the wearer is obtained, and the risk assessment result is determined based on the age difference between the vascular age assessment value and the actual age. The risk assessment result includes: when the age difference is less than the negative first threshold, it is marked as a young vascular state; when the age difference is within the range of the positive and negative first thresholds, it is marked as a normal state; when the age difference exceeds the second threshold, a yellow warning is issued; and when the age difference exceeds the third threshold, a red warning is issued.

[0091] Optionally, in one embodiment, the multidimensional morphological features include at least two of the following: time-domain features, amplitude features, and second-derivative features.

[0092] This application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the above-described vascular age assessment method. This electronic device can be any smart terminal, including tablet computers, in-vehicle computers, etc.

[0093] Please see Figure 5 , Figure 5 The hardware structure of an electronic device according to another embodiment is illustrated. The electronic device includes: The processor 501 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application. The memory 502 can be implemented as a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 502 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 502 and is called and executed by the processor 501 using the vascular age assessment method of the embodiments of this application. The input / output interface 503 is used to implement information input and output; The communication interface 504 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.). Bus 505 transmits information between various components of the device (e.g., processor 501, memory 502, input / output interface 503, and communication interface 504); The processor 501, memory 502, input / output interface 503, and communication interface 504 are connected to each other within the device via bus 505.

[0094] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described vascular age assessment method.

[0095] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0096] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0097] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0098] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0099] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0100] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. 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 comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0101] It should be understood that in this application, "at least one (item)" means one or more, and "more than one" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0102] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above 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 apparatuses or units may be electrical, mechanical, or other forms.

[0103] The units described above 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.

[0104] Furthermore, the functional units in the various embodiments of this 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 functional unit.

[0105] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. 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 storage medium and includes multiple 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 of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0106] The preferred embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and substance of the embodiments of the present application shall be within the scope of the claims of the present application.

Claims

1. A method for assessing vascular age, characterized in that, include: Acquire the photoplethysmography (PPG) signal of the finger of the wearer of the wearable device; Feature extraction is performed on the photoplethysmography signal to obtain multi-dimensional morphological features; The wearer obtains the information of the wearing finger and the evaluation model of the wearable device, and calibrates the multi-dimensional morphological features based on the information of the wearing finger to obtain the calibration features; The calibration features are evaluated based on the evaluation model to obtain an estimated vascular age.

2. The method according to claim 1, characterized in that, The calibration of the multi-dimensional morphological features based on the information of the worn finger to obtain calibration features includes: Obtain baseline differences between different fingers and training finger information corresponding to the evaluation model; Based on the information of the worn finger, the information of the trained finger, and the baseline difference, the multi-dimensional morphological features are calibrated to obtain calibrated features.

3. The method according to claim 1, characterized in that, The step of obtaining the information of the finger worn by the wearable device includes: Receive wireless communication information from the application software associated with the wearable device; The wearer's finger information is determined based on the wireless communication information.

4. The method according to claim 1, characterized in that, The process of evaluating the calibration features based on the evaluation model to obtain an estimated vascular age includes: Acquire multiple calibration features corresponding to the repeated acquisition process according to a preset period; Each calibration feature is evaluated based on the evaluation model to obtain an estimated vascular age value corresponding to each calibration feature; A vascular age time series is established based on the estimated vascular age values ​​corresponding to each of the calibration features, and risk warning is performed based on the vascular age time series.

5. The method according to claim 4, characterized in that, The risk warning based on the vascular age time series includes: The linear regression slope of the vascular age time series was calculated using a preset time window; When the slope exceeds a preset trend threshold, a trend deterioration warning is issued.

6. The method according to claim 1, characterized in that, After evaluating the calibration features based on the evaluation model to obtain the estimated vascular age, the process further includes: The actual age of the wearer is obtained, and a risk assessment result is determined based on the age difference between the vascular age assessment value and the actual age. The risk assessment result includes: when the age difference is less than a first threshold, it is marked as a young vascular state; when the age difference is greater than the first threshold but less than a second threshold, it is marked as a normal state; when the age difference is greater than the second threshold but less than a third threshold, a yellow warning is issued; when the age difference exceeds the third threshold, a red warning is issued. The first threshold is a negative value, and the second and third thresholds are positive values.

7. The method according to claim 1, characterized in that, The multidimensional morphological features include at least two of the following: time-domain features, amplitude features, and second-derivative features.

8. A vascular age assessment device, characterized in that, include: The acquisition unit is used to acquire the photoplethysmography (PPG) signal of the finger of the wearer of the wearable device; The extraction unit is used to extract features from the photoplethysmography signal to obtain multi-dimensional morphological features; The calibration unit is used to acquire the wearing finger information and evaluation model of the wearable device, and calibrate the multi-dimensional morphological features based on the wearing finger information to obtain calibration features; An evaluation unit is used to evaluate the calibration features based on the evaluation model to obtain an estimated vascular age.

9. An electronic device, characterized in that, include: Memory, transceiver, processor, and bus system; The memory is used to store programs; The processor is configured to execute a program in the memory, including performing the method as described in any one of claims 1 to 7; The bus system is used to connect the memory and the processor to enable communication between the memory and the processor.

10. A computer-readable storage medium, characterized in that, Includes instructions that, when run on a computer, cause the computer to perform the method as described in any one of claims 1 to 7.

Images