Acute event alerting method, device, and medium

Abstract

This application provides an acute event early warning method, device, and medium. The method includes: acquiring multi-source fusion data, wherein the multi-source fusion data is used to characterize multi-source data representing potential acute events of a user; performing multi-level feature extraction on the multi-source fusion data based on a preset physiological baseline model to obtain corresponding multi-level feature data, wherein the physiological baseline model is obtained in advance through unsupervised learning based on historical multi-source disease data and multi-level disease features; calculating the AERS value and probability of occurrence of the acute event based on the multi-level feature data to obtain the AERS value and probability of occurrence of the acute event; and providing a graded early warning based on the AERS value and probability of occurrence of the acute event. This addresses the technical problems of lag and low accuracy in existing acute event early warning technologies.

Description

Technical Field

[0001] This application relates to the field of medical technology, specifically to an acute event early warning method, device, and medium. Background Technology

[0002] In the current medical context, chronic diseases have become a major global health challenge. Existing chronic disease management primarily relies on patients seeking medical attention after experiencing discomfort or on device alarms based on fixed thresholds. However, these existing solutions suffer from significant delays and low accuracy, often only issuing warnings and taking action after an acute event has already occurred or symptoms are very pronounced, missing the optimal intervention window. Furthermore, fixed threshold alarms cannot adapt to individual physiological differences and dynamic changes; different users may have different sensitive alarm thresholds, resulting in a high false alarm rate and undoubtedly increasing the workload of relevant personnel.

[0003] Therefore, there is an urgent need to propose a better early warning scheme for acute events. Summary of the Invention

[0004] In view of this, the embodiments of this application aim to provide an acute event early warning method, device and medium, which can solve the technical problems of lagging and low accuracy in the early warning of acute events in the prior art.

[0005] Firstly, this application provides an acute event early warning method, including: Acquire multi-source fusion data, which is used to characterize multi-source data of potential acute events of users; Based on a pre-set physiological baseline model, multi-level feature extraction is performed on the multi-source fusion data to obtain corresponding multi-level feature data. The physiological baseline model is obtained in advance through unsupervised learning based on historical multi-source disease data and multi-level disease features. Based on the multi-level feature data, the AERS value and occurrence probability of the acute event are calculated to obtain the AERS value and occurrence probability of the acute event; A graded early warning system is implemented based on the AERS value and occurrence probability of the acute event.

[0006] In some embodiments, performing multi-level feature extraction on the multi-source fused data to obtain corresponding multi-level feature data includes: First-level feature extraction is performed on the multi-source fusion data to obtain corresponding first-level feature data, which is used to reflect the user's abnormal physiological data. Secondary feature extraction is performed on the multi-source fusion data to obtain corresponding secondary feature data, which is used to reflect the user's behavior and environmental risk data. The multi-source fusion data is subjected to three-level feature extraction to obtain corresponding three-level feature data, which is used to reflect the user's clinical background data.

[0007] In some embodiments, the multi-source fusion data includes at least heart rate variability (HRV) time-series data, activity level time-series data, and weight time-series data. The step of performing first-level feature extraction on the multi-source fusion data to obtain corresponding first-level feature data includes: Based on the physiological baseline model, the target data in the multi-source fusion data is reconstructed to obtain the corresponding target reconstructed data. Based on the target data in the multi-source fusion data and the target reconstructed data, the reconstruction error is calculated to obtain the abnormal error value corresponding to the target data; The abnormal error value corresponding to the target data is determined as the first-level feature data; The target data includes the heart rate variability (HRV) time-series data, the activity level time-series data, or the weight time-series data.

[0008] In some embodiments, the calculation of the AERS value and probability of occurrence of the acute event based on the multi-level feature data to obtain the AERS value and probability of occurrence of the acute event includes: The AERS value of the acute event is obtained by weighting the first-level feature data, second-level feature data and third-level feature data in the multi-level feature data based on the preset AERS formula. The probability of occurrence of the acute event is obtained by performing regression probability calculation on the first-level feature data, second-level feature data and third-level feature data in the multi-level feature data based on the preset probability formula. The AERS values ​​are positively correlated with the first-level feature data, the second-level feature data, and the third-level feature data, respectively, and the occurrence probabilities are exponentially negatively correlated with the first-level feature data, the second-level feature data, and the third-level feature data, respectively.

[0009] In some embodiments, the secondary characteristic data includes at least sleep efficiency, medication deviation rate, and environmental PM2.5 values, and the tertiary characteristic data includes at least comorbidity data and past acute medical history.

[0010] In some embodiments, the graded early warning based on the AERS value and probability of occurrence of the acute event includes any one of the following: When the AERS value is less than or equal to a preset first AERS threshold and the occurrence probability is less than or equal to a preset first probability threshold, a first-level risk warning is issued for the acute event. When the AERS value is greater than the preset first AERS threshold and less than the preset second AERS threshold, and the occurrence probability is greater than the preset first probability threshold and less than the preset second probability threshold, a second-level risk warning is issued for the acute event. When the AERS value is greater than or equal to the preset second AERS threshold and the occurrence probability is greater than or equal to the preset second probability threshold, a third-level risk warning is issued for the acute event; The first level is lower than the second level, which is lower than the third level.

[0011] In some embodiments, acquiring multi-source fusion data includes: Obtain the user's multi-source disease data; The multi-source disease data is preprocessed to obtain preprocessed multi-source disease data. The preprocessing includes at least timestamp alignment and data standardization. The preprocessed multi-source disease data is fused to obtain the multi-source fused data.

[0012] In some embodiments, the acute event includes at least one of the following: cardiovascular acute event, respiratory acute event, metabolic acute event, and other systemic acute events.

[0013] Secondly, this application provides an acute event early warning device, comprising: The acquisition module is used to acquire multi-source fusion data, which is used to characterize multi-source data of potential acute events of users; The processing module is used to perform multi-level feature extraction on the multi-source fusion data based on a preset physiological baseline model to obtain corresponding multi-level feature data. The physiological baseline model is obtained in advance through unsupervised learning based on historical multi-source disease data and multi-level disease features. The processing module is also used to calculate the AERS value and probability of occurrence of acute events based on the multi-level feature data, so as to obtain the AERS value and probability of occurrence of the acute events. The processing module is also used to perform graded early warning based on the AERS value and occurrence probability of the acute event.

[0014] For any content not introduced or described in the embodiments of this application, please refer to the relevant descriptions in the foregoing method embodiments; they will not be repeated here.

[0015] Thirdly, this application provides an electronic device, including: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to execute the executable instructions to implement the steps of the above-described acute event early warning method.

[0016] Fourthly, this application provides a computer-readable storage medium storing computer program instructions thereon, which, when executed by a processor, implement the steps of the above-described acute event early warning method.

[0017] The technical solution provided in this application can include the following beneficial effects: This application can acquire multi-source fusion data, which is used to characterize multi-source data of potential acute events in users; based on a preset physiological baseline model, multi-level feature extraction is performed on the multi-source fusion data to obtain corresponding multi-level feature data, wherein the physiological baseline model is obtained in advance through unsupervised learning based on historical multi-source disease data and multi-level disease features; based on the multi-level feature data, the AERS value and probability of occurrence of acute events are calculated to obtain the AERS value and probability of occurrence of the acute events; and a graded early warning is performed based on the AERS value and probability of occurrence of the acute events. In this way, multi-level feature extraction and tiered early warning of acute events can be performed on the user's multi-source fusion data based on the physiological baseline model, thereby improving the accuracy, efficiency, and reliability of the early warning. It also solves the technical problems of lag and low accuracy in early warning of acute events in the prior art.

[0018] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, specific embodiments of this application are given below. Attached Figure Description

[0019] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the scope of this application. Furthermore, the same reference numerals denote the same parts throughout the drawings.

[0020] Figure 1 This is a schematic diagram of the structure of an acute event early warning system provided in an embodiment of this application.

[0021] Figure 2 This is a flowchart illustrating an acute event early warning method provided in an embodiment of this application.

[0022] Figure 3 This is a schematic diagram of the structure of an acute event early warning device provided in an embodiment of this application.

[0023] Figure 4 This is a schematic diagram of another acute event early warning device provided in an embodiment of this application.

[0024] Figure 5This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0025] 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.

[0026] Unless otherwise defined, the technical or scientific terms used in the embodiments of this specification shall have the ordinary meaning understood by one of ordinary skill in the art to which this specification pertains. The terms "first," "second," and similar terms used in the embodiments of this specification do not indicate any order, quantity, or importance, but are merely used to avoid confusion of constituent elements.

[0027] Unless the context otherwise requires, throughout this specification, "a plurality of" means "at least two," and "including" is interpreted as open-ended or encompassing, that is, "including, but not limited to." In the description of this specification, terms such as "one embodiment," "some embodiments," "exemplary embodiment," "example," "specific example," or "some examples" are intended to indicate that a particular feature, structure, material, or characteristic associated with that embodiment or example is included in at least one embodiment or example of this specification. The illustrative representations of the above terms do not necessarily refer to the same embodiment or example.

[0028] Exemplary embodiments of the present application will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present application are shown in the drawings, it should be understood that the present application may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this application will be thorough and complete, and will fully convey the scope of the present application to those skilled in the art.

[0029] Please see Figure 1 This is a schematic diagram of the structure of an acute event early warning system provided in an embodiment of this application. For example... Figure 1The system 10 shown may include a data acquisition and fusion module 101, a feature engineering module 102, a feature calculation module 103, and an early warning and intervention module 104. The data acquisition and fusion module 101, also known as a multi-source data acquisition and fusion module, is primarily responsible for acquiring and fusing multi-source data, such as acquiring and fusing multi-source symptom data of a user. In specific implementations, this application can acquire multi-source data of the corresponding user from other devices through methods such as application programming interfaces (APIs) and Bluetooth protocols. For example, it can acquire heart rate, heart rate variability (HRV), activity levels, sleep, or other time-series data from wearable devices such as smart bracelets; acquire weight and height data from smart scales; acquire PM2.5 data from environmental sensors; and acquire user medical history, medication lists, and medical appointment times from hospital information systems. This application does not impose further limitations on these acquisition methods. The aforementioned feature engineering module 102, also known as the temporal anomaly detection and feature engineering module, is mainly responsible for performing temporal anomaly detection and key feature extraction on the multi-source fusion data obtained by the aforementioned acquisition and fusion module 101. This includes, for example, multi-level key feature extraction, which will not be further limited or detailed in this application. The aforementioned feature calculation module 103, also known as the multi-level feature fusion and calculation module, is mainly responsible for performing corresponding calculations based on the multi-level feature data extracted by the aforementioned feature engineering module 102. This includes, for example, calculating Adverse Event Reporting System (AERS) values ​​and the probability of acute events. The aforementioned early warning and intervention module 104, also known as the intelligent early warning and intervention engine module 104, is mainly responsible for providing early warnings and interventions based on the data calculated by the aforementioned feature calculation module 103, to prevent users from experiencing acute events or dangers. The specific implementation details of each of the above modules will be detailed below in this application, and will not be further limited or described here.

[0030] Based on the above embodiments, please refer to Figure 2 This is a flowchart illustrating an acute event early warning method provided in an embodiment of this application. Figure 2 The method shown can be applied to Figure 1 In the system shown, the method may include the following implementation steps: S201. Obtain multi-source fusion data, which is used to characterize multi-source data of potential acute events of users.

[0031] The multi-source fusion data mentioned above in this application can refer to relevant data used to analyze the impact of users on acute events. This data may include, but is not limited to, the user's heart rate time series data, heart rate variability (HRB) time series data, activity level time series data, weight time series data, sleep time series data, heart rate and pulse time series data, respiration time series data, blood pressure time series data, user medical history data, medication record data, environmental data (e.g., PM2.5), or other data used to analyze the impact of users on acute events. This application does not impose further limitations or provide detailed descriptions in this regard.

[0032] This application does not limit the implementation method for acquiring the aforementioned multi-source fusion data. For example, this application can first acquire the user's multi-source symptom data. This application also does not limit the implementation method for acquiring the aforementioned multi-source symptom data. For example, relevant data for analyzing the impact of acute events on the user can be acquired from other devices (such as web servers, wearable devices, or other terminal devices) through application programming interfaces or related communication protocols. This data may include, but is not limited to, the user's historical medical records, historical medical records, weight time-series data, heart rate time-series data, heart rate variability (RHV) time-series data, sleep time-series data, activity time-series data, environmental monitoring data, etc. This application does not impose further limitations or details on this. Next, this application can preprocess the acquired multi-source symptom data, such as performing timestamp alignment, standard conversion processing to a unified format, or other custom data processing on each data point in the multi-source symptom data, thereby obtaining preprocessed multi-source symptom data. Optionally, this application can also perform time-series anomaly detection on each data point in the multi-source symptom data, discarding or supplementing data with time-series anomalies, etc. This application does not impose further limitations or details on this. Finally, this application can fuse the preprocessed multi-source disease data together to form a unified vector or matrix representation of the multi-source fused data, which facilitates subsequent processing.

[0033] The acute events mentioned above in this application can refer to clinical events requiring emergency medical intervention when a user suffers from a chronic disease but is induced by emotional instability or other factors. These acute events may include, but are not limited to, acute events of the cardiovascular system, respiratory system, metabolic system, or other systems. Specifically, acute events of the cardiovascular system may include, but are not limited to, acute decompensated events of heart failure, such as fluid retention, abnormal heart rate or rhythm, or other acute cardiovascular events; or risk events for acute coronary syndrome, such as a significant decrease in heart rate variability, the appearance of specific arrhythmia patterns, etc., which this application does not further limit or elaborate on. Acute events of the respiratory system may include, but are not limited to, acute exacerbations of chronic obstructive pulmonary disease, a trend of decreasing three-dimensional oxygen saturation, a sharp decrease in exercise tolerance steps, and increased heart rate with concurrent infection, etc. Acute events of the metabolic system may include, but are not limited to, severe or high-osmolarity risk events of diabetic ketoacidosis, such as continuous blood glucose monitoring showing extreme or persistent high or low values, etc., which this application does not further limit or elaborate on.

[0034] S202. Based on the preset physiological baseline model, multi-level feature extraction is performed on the multi-source fusion data to obtain corresponding multi-level feature data. The physiological baseline model is obtained in advance through unsupervised learning based on historical multi-source disease data and multi-level disease features.

[0035] The physiological baseline model described in this application is a pre-defined model set by the system according to actual conditions. It can be used to perform a series of analyses and processing on the multi-source fusion data of the user experiencing acute events. The model may include, but is not limited to, self-coded decoding models or other supervised learning models. Different physiological baseline models can be designed for different users. These models can be obtained by unsupervised learning and training based on the user's historical multi-source disease data and multi-layered disease characteristics. This application does not impose further limitations or details on this.

[0036] This application does not limit the specific implementation of the above-mentioned multi-level feature extraction. Taking three-level feature extraction as an example, the above-mentioned multi-level feature data may specifically include first-level feature data, second-level feature data, and third-level feature data. In specific implementation, this application can first perform first-level feature extraction on the above-mentioned multi-source fusion data to obtain the corresponding first-level feature data. The above-mentioned first-level feature data can be used to reflect the user's physiological abnormal data. In specific implementation, taking the above-mentioned multi-source fusion data including heart rate variability (HRV) time series data, activity time series data, and weight time series data as an example, this application can reconstruct the target data based on the above-mentioned physiological baseline model. For example, the target data can be encoded and then decoded using the physiological baseline model to obtain the corresponding target reconstructed data. Then, the reconstruction error is calculated on the target data and the target reconstructed data to obtain the corresponding abnormal error value, which can also be called the abnormal score. This application does not limit the specific implementation of the above-mentioned reconstruction error calculation. For example, the mean square error can be calculated on the target data and the target reconstructed data. For example, the mean square error between the target data and its corresponding reconstructed data at each time point can be calculated. This application does not limit or elaborate on this. The target data mentioned above can be the HRV time-series data, the activity level time-series data, or the weight time-series data. When the target data is the HRV time-series data, its corresponding anomaly error value can be specifically referred to as the HRB anomaly error value HRV_Anomaly_Score; when the target data is the activity level time-series data, its corresponding anomaly error value can be specifically referred to as the activity level anomaly error value Activity_Anomaly_Score; when the target data is the weight time-series data, its corresponding anomaly error value can be specifically referred to as the weight anomaly error value Weight_Anomaly_Score. This application does not impose further limitations on this. After obtaining the anomaly error values ​​corresponding to the three target data, this application can use these three anomaly error values, specifically HRV_Anomaly_Score, Activity_Anomaly_Score, and Weight_Anomaly_Score, as the aforementioned first-level feature data. This application does not impose further limitations or details on this.

[0037] Next, this application can perform secondary feature extraction on the aforementioned multi-source fusion data to obtain corresponding secondary feature data. This secondary feature data can specifically be used to reflect user behavior and environmental risk data, and may include, but is not limited to, user sleep efficiency, medication deviation rate, environmental PM2.5 values, or other feature data reflecting user behavior and environmental risk. This application can also perform tertiary feature extraction on the aforementioned multi-source fusion data to obtain corresponding tertiary feature data. This tertiary feature data can specifically be used to reflect the user's static clinical background data, and may include, but is not limited to, user complication data, past acute illness history or attack history, or other data describing the user's clinical condition background, etc., which this application does not limit or elaborate on further.

[0038] S203. Calculate the AERS value and probability of occurrence of the acute event based on the multi-level feature data to obtain the AERS value and probability of occurrence of the acute event.

[0039] This application does not limit the specific implementation method of the above-mentioned AERS value calculation. For example, this application can perform weighted calculation on the above-mentioned first-level feature data, the above-mentioned second-level feature data, and the above-mentioned third-level feature data based on a preset AERS formula to obtain the corresponding AERS value. The specific calculation of the above-mentioned AERS formula can be shown in the following formula (1): Formula (1) In this context, α, β, and γ are the corresponding weighting coefficients, which can be pre-defined by the system according to actual conditions. Typically, their sum is 1, and this application does not impose further limitations or details. T1, T2, and T3 represent the processing scores corresponding to the first-level, second-level, and third-level feature data, respectively. These processing scores are obtained by the system through customized processing based on actual needs; for example, their values ​​can range from 0 to 100, and this application does not impose further limitations or details. These processing scores, to a certain extent, reflect the contribution of the corresponding level of feature data to the prediction of acute events in users. In practical applications, the AERS values ​​can be positively correlated with the first-level, second-level, and third-level feature data, respectively, and this application does not impose further limitations or details.

[0040] This application does not limit the specific implementation method for calculating the probability of occurrence of the above-mentioned acute events. For example, this application can perform regression probability calculation on the above-mentioned first-level feature data, the above-mentioned second-level feature data, and the above-mentioned third-level feature data based on a preset probability formula, thereby obtaining the probability of occurrence of the above-mentioned acute events. Specifically, the specific calculation of the above-mentioned probability formula can be shown in the following formula (2): Formula (2) Where P represents the probability of the aforementioned acute event occurring, and z is the data obtained by weighted calculation based on the aforementioned primary feature data, secondary feature data, and tertiary feature data; this application does not impose further limitations on this. Sleep_sore represents sleep efficiency. w n This represents the weight coefficient of the nth item. These weight coefficients are obtained in advance by the system based on the actual situation, and this application will not impose further restrictions or details on them.

[0041] S204. Based on the AERS value and occurrence probability of the acute event, a graded early warning is issued.

[0042] This application does not limit the specific implementation of the above-mentioned tiered early warning system. For example, this application may have a pre-set rule base, and this application may automatically trigger the corresponding tiered early warning system based on the above-mentioned AERS value and the probability of occurrence of acute events by querying the rule base. Several possible implementation methods are described below as examples, but they do not constitute a limitation.

[0043] In one implementation, when the AERS value is less than or equal to a preset first AERS threshold and the occurrence probability is less than or equal to a preset first probability threshold, this application can determine that the acute event is at a first risk level, such as a low risk level. Furthermore, this application can provide a first-level risk warning for the acute event. Specifically, for example, this application can push corresponding risk warning information to the user via a user's mobile application or SMS, such as prompting that today's activity level is low and suggesting appropriate walking, sending timely medication notifications, or mild warnings such as monitoring a recent weight gain trend and paying attention to dietary intake. The preset first AERS threshold and the preset first probability threshold are corresponding thresholds pre-defined by the system based on actual conditions. They can be empirical values ​​customized based on user experience, or statistical values ​​calculated based on a series of experimental data, for example, the preset first AERS threshold is 30, and the preset first probability threshold is 0.3, etc.

[0044] In another embodiment, when the AERS value is greater than the preset first AERS threshold and less than the preset second AERS threshold, and the probability of occurrence is greater than the preset first probability threshold and less than the preset second probability threshold, this application can determine that the acute event is at a second risk level, such as a medium risk level. Furthermore, this application can provide a second-level risk warning for the acute event, where the second level is higher than the first level. Specifically, this application can notify community doctors and family members to strengthen care, supervise medication administration, and conduct daily monitoring through a nursing management platform, telephone, or SMS. The preset second AERS threshold and the preset second probability threshold are corresponding thresholds pre-defined by the system based on actual conditions. They can be empirical values ​​customized based on user experience or statistical values ​​calculated from a series of experimental data. Typically, the preset second AERS threshold is greater than the preset first AERS threshold, and the preset second probability threshold is greater than the preset first probability threshold; for example, the preset second AERS threshold is 60, and the preset second probability threshold is 0.7, etc. This application does not impose further limitations on this.

[0045] In another embodiment, when the AERS value is greater than or equal to the preset second AERS threshold and the occurrence probability is greater than or equal to the preset second probability threshold, this application can determine that the acute event is at a third risk level, such as a high-risk level. Furthermore, a third-level risk warning can be issued for the acute event; specifically, for example, this application can directly contact doctors for emergency intervention and treatment through hospital internal alarm systems, instant messaging tools, or telephones. Simultaneously, some abnormal indicators, risk probabilities, and automatically generated electronic medical records of the user can be pushed to doctors to assist them in making rapid diagnostic decisions, etc., which this application will not limit or elaborate on further.

[0046] As can be seen, this application can analyze potential acute events of users by analyzing continuous and subtle time-series data trends, thus solving the problem of lag. By replacing fixed threshold judgments with a physiological baseline model, the judgment criteria vary from person to person and from time to time, significantly improving prediction accuracy. Through the extraction and fusion of multi-level features, various factors of user health status are comprehensively considered, providing a more comprehensive assessment basis for acute event early warning, thereby providing more targeted early warning assistance.

[0047] In specific implementation, this application can acquire multi-source fusion data, which is used to characterize multi-source data representing potential acute events of users; based on a preset physiological baseline model, multi-level feature extraction is performed on the multi-source fusion data to obtain corresponding multi-level feature data. The physiological baseline model is obtained in advance through unsupervised learning based on historical multi-source disease data and multi-level disease features; based on the multi-level feature data, the AERS value and probability of occurrence of acute events are calculated to obtain the AERS value and probability of occurrence of the acute events; and a graded early warning is performed based on the AERS value and probability of occurrence of the acute events. In this way, multi-level feature extraction and tiered early warning of acute events can be performed on the user's multi-source fusion data based on the physiological baseline model, thereby improving the accuracy, efficiency, and reliability of the early warning. It also solves the technical problems of lag and low accuracy in early warning of acute events in the prior art.

[0048] Based on the foregoing embodiments, please refer to Figure 3 This is a schematic diagram of the structure of an acute event early warning device provided in an embodiment of this application. For example... Figure 3 The device 300 shown may include an acquisition module 301 and a processing module 302, wherein: The acquisition module 301 is used to acquire multi-source fusion data, which is used to characterize multi-source data of potential acute events of users. The processing module 302 is used to perform multi-level feature extraction on the multi-source fusion data based on a preset physiological baseline model to obtain corresponding multi-level feature data. The physiological baseline model is obtained in advance through unsupervised learning based on historical multi-source disease data and multi-level disease features. The processing module 302 is also used to calculate the AERS value and probability of occurrence of acute events based on the multi-level feature data, so as to obtain the AERS value and probability of occurrence of the acute events. The processing module 302 is also used to perform graded early warning based on the AERS value and occurrence probability of the acute event.

[0049] In some embodiments, the processing module 302 is specifically used for: First-level feature extraction is performed on the multi-source fusion data to obtain corresponding first-level feature data, which is used to reflect the user's abnormal physiological data. Secondary feature extraction is performed on the multi-source fusion data to obtain corresponding secondary feature data, which is used to reflect the user's behavior and environmental risk data. The multi-source fusion data is subjected to three-level feature extraction to obtain corresponding three-level feature data, which is used to reflect the user's clinical background data.

[0050] In some embodiments, the multi-source fusion data includes at least heart rate variability (HRV) time-series data, activity level time-series data, and weight time-series data, and the processing module 302 is specifically used for: Based on the physiological baseline model, the target data in the multi-source fusion data is reconstructed to obtain the corresponding target reconstructed data. Based on the target data in the multi-source fusion data and the target reconstructed data, the reconstruction error is calculated to obtain the abnormal error value corresponding to the target data; The abnormal error value corresponding to the target data is determined as the first-level feature data; The target data includes the heart rate variability (HRV) time-series data, the activity level time-series data, or the weight time-series data.

[0051] In some embodiments, the processing module 302 is specifically used for: The AERS value of the acute event is obtained by weighting the first-level feature data, second-level feature data and third-level feature data in the multi-level feature data based on the preset AERS formula. The probability of occurrence of the acute event is obtained by performing regression probability calculation on the first-level feature data, second-level feature data and third-level feature data in the multi-level feature data based on the preset probability formula. The AERS values ​​are positively correlated with the first-level feature data, the second-level feature data, and the third-level feature data, respectively, and the occurrence probabilities are exponentially negatively correlated with the first-level feature data, the second-level feature data, and the third-level feature data, respectively.

[0052] In some embodiments, the secondary characteristic data includes at least sleep efficiency, medication deviation rate, and environmental PM2.5 values, and the tertiary characteristic data includes at least comorbidity data and past acute medical history.

[0053] In some embodiments, the processing module 302 is specifically configured to perform any of the following: When the AERS value is less than or equal to a preset first AERS threshold and the occurrence probability is less than or equal to a preset first probability threshold, a first-level risk warning is issued for the acute event. When the AERS value is greater than the preset first AERS threshold and less than the preset second AERS threshold, and the occurrence probability is greater than the preset first probability threshold and less than the preset second probability threshold, a second-level risk warning is issued for the acute event. When the AERS value is greater than or equal to the preset second AERS threshold and the occurrence probability is greater than or equal to the preset second probability threshold, a third-level risk warning is issued for the acute event; The first level is lower than the second level, which is lower than the third level.

[0054] In some embodiments, the acquisition module 301 is specifically used for: Obtain the user's multi-source disease data; The multi-source disease data is preprocessed to obtain preprocessed multi-source disease data. The preprocessing includes at least timestamp alignment and data standardization. The preprocessed multi-source disease data is fused to obtain the multi-source fused data.

[0055] In some embodiments, the acute event includes at least one of the following: cardiovascular acute event, respiratory acute event, metabolic acute event, and other systemic acute events.

[0056] Please see Figure 4 This is a schematic diagram of another acute event early warning device provided in an embodiment of this application. For example... Figure 4 The device shown may be a mobile phone, computer, digital broadcasting terminal, messaging device, game console, tablet device, medical device, fitness equipment, personal digital assistant or other electronic device, etc.

[0057] Reference Figure 4 The device 400 may include one or more of the following components: processing component 402, memory 404, power supply component 406, multimedia component 408, audio component 410, input / output interface 412, sensor component 414, and communication component 416.

[0058] Processing component 402 typically controls the overall operation of device 400, such as operations associated with display, telephone calls, data communication, camera operation, and recording. Processing component 402 may include one or more processors 420 to execute instructions to complete all or part of the steps of the aforementioned acute event warning method. Furthermore, processing component 402 may include one or more modules to facilitate interaction between processing component 402 and other components. For example, processing component 402 may include a multimedia module to facilitate interaction between multimedia component 408 and processing component 402.

[0059] Memory 404 is configured to store various types of data to support the operation of device 400. Examples of such data include instructions for any application or method operating on device 400, contact data, phonebook data, messages, pictures, videos, etc. Memory 404 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0060] Power supply component 406 provides power to various components of device 400. Power supply component 406 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to device 400.

[0061] Multimedia component 408 includes a screen that provides an output interface between the device 400 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touchscreen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensors may sense not only the boundaries of the touch or swipe action but also the duration and pressure associated with the touch or swipe operation. In some embodiments, multimedia component 408 includes a front-facing camera and / or a rear-facing camera. When the device 400 is in an operating mode, such as a shooting mode or a video mode, the front-facing camera and / or the rear-facing camera may receive external multimedia data. Each front-facing camera and rear-facing camera may be a fixed optical lens system or have focal length and optical zoom capabilities.

[0062] Audio component 410 is configured to output and / or input audio signals. For example, audio component 410 includes a microphone (MIC) configured to receive external audio signals when device 400 is in an operating mode, such as call mode, recording mode, and voice recognition mode. The received audio signals may be further stored in memory 404 or transmitted via communication component 416. In some embodiments, audio component 410 also includes a speaker for outputting audio signals.

[0063] Input / output interface 412 provides an interface between processing component 402 and peripheral interface modules, which may be keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to, home buttons, volume buttons, start buttons, and lock buttons.

[0064] Sensor assembly 414 includes one or more sensors for providing status assessments of various aspects of device 400. For example, sensor assembly 414 may detect the on / off state of device 400, the relative positioning of components such as the display and keypad of device 400, changes in the position of device 400 or a component of device 400, the presence or absence of user contact with device 400, the orientation or acceleration / deceleration of device 400, and temperature changes of device 400. Sensor assembly 414 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. Sensor assembly 414 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, sensor assembly 414 may also include an accelerometer, a gyroscope, a magnetometer, a pressure sensor, or a temperature sensor.

[0065] Communication component 416 is configured to facilitate wired or wireless communication between device 400 and other devices. Device 400 can access wireless networks based on communication standards, such as WiFi, 2G, or 3G, or combinations thereof. In one exemplary embodiment, communication component 416 receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, communication component 416 also includes a near-field communication (NFC) module to facilitate short-range communication. For example, the NFC module may be implemented based on radio frequency identification (RFID) technology, Infrared Data Association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

[0066] In an exemplary embodiment, the device 400 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above-described acute event warning method.

[0067] Understandably, the processor 420 in this application embodiment can be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method embodiment can be completed by integrated logic circuits in the processor's hardware or by instructions in software form. The processor described above can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0068] Understandably, the memory 404 in the embodiments of this application can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (SLDRAM), and direct rambus RAM (DR RAM). It should be noted that the memory used in the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0069] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 404 including instructions, which can be executed by a processor 420 of the device 400 to complete the aforementioned upper-level acute event early warning method. For example, the non-transitory computer-readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0070] The aforementioned device can be a standalone electronic device or a part of a standalone electronic device. For example, in one embodiment, the device can be an integrated circuit (IC) or a chip, wherein the integrated circuit can be a single IC or a collection of multiple ICs. The chip can include, but is not limited to, the following types: GPU (Graphics Processing Unit), CPU (Central Processing Unit), FPGA (Field Programmable Gate Array), DSP (Digital Signal Processor), ASIC (Application Specific Integrated Circuit), and SoC (System on Chip). The aforementioned integrated circuit or chip can be used to execute executable instructions (or code) to implement the aforementioned acute event early warning method. The executable instructions can be stored in the integrated circuit or chip or obtained from other devices or equipment. For example, the integrated circuit or chip includes a processor, memory, and an interface for communicating with other devices. The executable instruction can be stored in the memory, and when the executable instruction is executed by the processor, it implements the above-mentioned acute event warning method; or, the integrated circuit or chip can receive the executable instruction through the interface and transmit it to the processor for execution to implement the above-mentioned acute event warning method.

[0071] Please see Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. For example, as shown... Figure 5 As shown, the electronic device 500 includes a memory 501 and a processor 502. The memory 501 stores executable program code 5011, and the processor 502 is used to call and execute the executable program code 5011 to perform an acute event warning method.

[0072] This application embodiment can divide the electronic device into functional modules according to the above method embodiment. For example, each function can be assigned to a separate module, or two or more functions can be integrated into a processing module. The integrated module can be implemented in hardware. It should be noted that the module division in this embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods. When dividing each functional module according to its corresponding function, the electronic device may include: a processing module and a communication module, etc.

[0073] It should be noted that all relevant content of each step involved in the above method embodiments can be referenced from the functional description of the corresponding functional module, and will not be repeated here. The electronic device provided in this embodiment is used to execute the above-described acute event early warning method, and therefore can achieve the same effect as the above-described implementation method.

[0074] In another exemplary embodiment, a computer program product is also provided, comprising a computer program executable by a programmable device, the computer program having a code portion for performing the above-described acute event warning method when executed by the programmable device.

[0075] It should be noted that the descriptions of the above embodiments of storage media, devices, and equipment are similar to the descriptions of the above method embodiments, and have similar beneficial effects. For technical details not disclosed in the embodiments of storage media, devices, and equipment of this application, please refer to the descriptions of the method embodiments of this application for understanding.

[0076] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of this application. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed in this application. The specification and embodiments are to be considered exemplary only, and the true scope and spirit of this application are indicated by the following claims.

[0077] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Any modifications or equivalent substitutions made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. An acute event early warning method, characterized in that, include: Acquire multi-source fusion data, which is used to characterize multi-source data of potential acute events of users; Based on a pre-set physiological baseline model, multi-level feature extraction is performed on the multi-source fusion data to obtain corresponding multi-level feature data. The physiological baseline model is obtained in advance through unsupervised learning based on historical multi-source disease data and multi-level disease features. Based on the multi-level feature data, the AERS value and occurrence probability of the acute event are calculated to obtain the AERS value and occurrence probability of the acute event; A graded early warning system is implemented based on the AERS value and occurrence probability of the acute event.

2. The method according to claim 1, characterized in that, The step of performing multi-level feature extraction on the multi-source fused data to obtain corresponding multi-level feature data includes: The multi-source fusion data is subjected to first-level feature extraction to obtain corresponding first-level feature data, which is used to reflect the user's physiological abnormal data. Secondary feature extraction is performed on the multi-source fusion data to obtain corresponding secondary feature data, which is used to reflect the user's behavior and environmental risk data. The multi-source fusion data is subjected to three-level feature extraction to obtain corresponding three-level feature data, which is used to reflect the user's clinical background data.

3. The method according to claim 2, characterized in that, The multi-source fusion data includes at least heart rate variability (HRV) time-series data, activity level time-series data, and weight time-series data. The step of performing first-level feature extraction on the multi-source fusion data to obtain corresponding first-level feature data includes: Based on the physiological baseline model, the target data in the multi-source fusion data is reconstructed to obtain the corresponding target reconstructed data. Based on the target data in the multi-source fusion data and the target reconstructed data, the reconstruction error is calculated to obtain the abnormal error value corresponding to the target data; The abnormal error value corresponding to the target data is determined as the first-level feature data; The target data includes the heart rate variability (HRV) time-series data, the activity level time-series data, or the weight time-series data.

4. The method according to claim 2, characterized in that, The calculation of the AERS value and probability of occurrence of acute events based on the multi-level feature data, to obtain the AERS value and probability of occurrence of the acute events, includes: The AERS value of the acute event is obtained by weighting the first-level feature data, second-level feature data and third-level feature data in the multi-level feature data based on the preset AERS formula. The probability of occurrence of the acute event is obtained by performing regression probability calculation on the first-level feature data, second-level feature data and third-level feature data in the multi-level feature data based on the preset probability formula. The AERS values ​​are positively correlated with the first-level feature data, the second-level feature data, and the third-level feature data, respectively, and the occurrence probabilities are exponentially negatively correlated with the first-level feature data, the second-level feature data, and the third-level feature data, respectively.

5. The method according to claim 2, characterized in that, The secondary characteristic data includes at least sleep efficiency, medication deviation rate, and environmental PM2.5 value, while the tertiary characteristic data includes at least comorbidity data and past acute medical history.

6. The method according to claim 1, characterized in that, The graded early warning based on the AERS value and occurrence probability of the acute event includes any one of the following: When the AERS value is less than or equal to a preset first AERS threshold and the occurrence probability is less than or equal to a preset first probability threshold, a first-level risk warning is issued for the acute event. When the AERS value is greater than the preset first AERS threshold and less than the preset second AERS threshold, and the occurrence probability is greater than the preset first probability threshold and less than the preset second probability threshold, a second-level risk warning is issued for the acute event. When the AERS value is greater than or equal to the preset second AERS threshold and the occurrence probability is greater than or equal to the preset second probability threshold, a third-level risk warning is issued for the acute event; The first level is lower than the second level, which is lower than the third level.

7. The method according to claim 1, characterized in that, The acquisition of multi-source fusion data includes: Obtain the user's multi-source disease data; The multi-source disease data is preprocessed to obtain preprocessed multi-source disease data. The preprocessing includes at least timestamp alignment and data standardization. The preprocessed multi-source disease data is fused to obtain the multi-source fused data.

8. The method according to any one of claims 1-7, characterized in that, The acute event includes at least one of the following: acute cardiovascular event, acute respiratory event, acute metabolic event, and acute event of other systems.

9. An electronic device, characterized in that, include: processor; A memory for storing processor-executable instructions; wherein the processor is configured to execute the executable instructions to implement the steps of the method according to any one of claims 1 to 8.

10. A computer-readable storage medium having computer program instructions stored thereon, characterized in that, When the computer program instructions are executed by the processor, they implement the steps of the method according to any one of claims 1 to 8.

Images