Quantitative evaluation method and system for repropagation risk of HIV infected individual

Abstract

The invention discloses a quantitative evaluation method and system for repropagation risks of HIV infected individuals, and relates to the technical field of HIV prevention and control, and the method comprises the steps: carrying out the multi-dimensional cross validation of the behaviors of a patient through an intelligent verification engine based on the preprocessed multi-source data, screening out the credible data, and predicting the behavior risk index of the patient; constructing a dynamic risk coupling model, calculating the propagation risk value of the HIV infected individual in real time based on the behavior risk index of the patient, and generating a propagation risk trend chart through time sequence analysis; and grading propagation risks according to the propagation risk trend chart, marking a high-risk area, and updating the high-risk area by monitoring an actual propagation event of HIV (Human Immunodeficiency Virus). The method comprises the following steps: calculating a propagation risk value of an HIV infected individual in real time to generate a propagation risk trend chart; and in combination with a spatial hotspot density analysis method and an actual propagation event, labeling and dynamically updating a high-risk area, thereby realizing comprehensive, dynamic and accurate assessment of the HIV re-propagation risk.

Description

Technical Field

[0001] The present invention relates to the technical field of HIV prevention and control, and in particular to a method and system for quantitatively assessing the risk of retransmission of HIV-infected individuals. Background Art

[0002] In the field of HIV prevention and control, quantifying the risk of retransmission among HIV-infected individuals is crucial for developing effective interventions. In recent years, with the advancement of big data technology and artificial intelligence, multi-source data fusion and analysis has become a key approach for assessing HIV transmission risk. Existing technologies primarily assess risk based on a single data source (such as medication records or location tracking) or a simple combination of data (such as medication adherence and social activity). Examples include adherence scoring models based on medication records, spatial activity analysis models based on location tracking, and behavioral feature extraction models based on social networks. Furthermore, existing technologies lack the ability to pre-process, validate, and fuse multi-source data, resulting in inaccurate and unreliable assessment results.

[0003] The main drawback of existing technologies lies in their lack of deep integration and dynamic coupling capabilities for multi-source data. First, existing methods typically employ static models that fail to reflect in real time the impact of changes in patient behavior on transmission risk. Second, existing technologies lack the ability to dynamically couple transmission risk values ​​and conduct trend analysis, making it difficult to generate highly accurate transmission risk trend maps and heat maps of high-risk areas. These issues limit the practicality and effectiveness of HIV retransmission risk assessment. Summary of the Invention

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

[0005] Therefore, the present invention provides a quantitative assessment method for the risk of re-transmission of HIV-infected individuals to address the shortcomings of existing technologies in multi-source data integration, dynamic coupling and risk assessment accuracy, and realize a comprehensive, dynamic and accurate assessment of transmission risk.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: In the first aspect, the present invention provides a quantitative assessment method for the re-transmission risk of HIV-infected individuals, which includes collecting multi-source data of patients and preprocessing the multi-source data; based on the preprocessed multi-source data, performing multi-dimensional cross-validation on the patient's behavior through an intelligent verification engine, screening out reliable data, and predicting the patient's behavioral risk index; constructing a dynamic risk coupling model, based on the patient's behavioral risk index, calculating the transmission risk value of HIV-infected individuals in real time, and generating a transmission risk trend graph through time series analysis; classifying the transmission risk according to the transmission risk trend graph, marking high-risk areas, and updating the high-risk areas by monitoring actual HIV transmission events.

[0007] As a preferred solution of the quantitative assessment method for the risk of retransmission of HIV-infected individuals described in the present invention, the preprocessing includes anomaly cleaning, missing completion, standardized coding, data deduplication and format conversion.

[0008] As a preferred solution of the quantitative assessment method for the risk of retransmission of HIV-infected individuals described in the present invention, wherein: the patient behavior is cross-validated in multiple dimensions by the intelligent verification engine to screen out credible data. The specific steps are as follows: The spherical distance formula is used to calculate the deviation distance between the centroid coordinates and the reported address, and the spatial consistency coefficient is generated through the exponential decay function; By comparing the actual medication taking time with the planned time, the deviation proportion identification method was used to calculate the patient's medication compliance score; The patients' social frequency was counted using the sliding window statistical method.

[0009] As a preferred embodiment of the quantitative assessment method for the risk of retransmission of HIV-infected individuals described in the present invention, the predicted patient behavioral risk index includes a spatial consistency coefficient, a patient medication compliance score, and a patient's social activity, using nonlinear exponential decay and logarithmically smoothing extreme values ​​for prediction.

[0010] As a preferred embodiment of the quantitative assessment method for the risk of retransmission of HIV-infected individuals according to the present invention, the dynamic risk coupling model includes: The input layer receives data from multiple sources and performs preliminary formatting and standardization; Feature extraction layer, extracting HIV risk transmission features from multi-source data; Dynamic coupling layer, the patient's behavioral risk index Dynamically coupled with HIV transmission characteristics, the transmission risk value of HIV-infected individuals is calculated in real time; Output layer, outputs the transmission risk value of HIV-infected individuals.

[0011] As a preferred embodiment of the quantitative assessment method for the retransmission risk of HIV-infected individuals of the present invention, the real-time calculation of the transmission risk value of HIV-infected individuals and the generation of a transmission risk trend graph through time series analysis are as follows: Combine multi-source data and patients' behavioral risk index , input the dynamic risk coupling model to calculate the transmission risk value of HIV-infected individuals; Organize the transmission risk value and timestamp information at each time point to generate a time series dataset; Based on the time series data set, a transmission risk trend graph was drawn using the time series smoothing analysis method, with time as the horizontal axis and the transmission risk value of HIV-infected individuals as the vertical axis.

[0012] As a preferred embodiment of the quantitative assessment method for the retransmission risk of HIV-infected individuals described in the present invention, the transmission risk is graded and high-risk areas are marked, and the high-risk areas are updated by monitoring actual HIV transmission events. The specific steps are as follows: According to the transmission risk trend chart, the transmission risk value of HIV-infected individuals is analyzed over time through time series decomposition; Combining the transmission risk level and the patient's location trajectory data, the spatial hotspot density analysis method is used to generate a heat map of high-risk areas and mark them on the map. At the same time, the high-risk areas are updated by monitoring actual HIV transmission events.

[0013] In a second aspect, the present invention provides a quantitative assessment system for the risk of re-transmission of HIV-infected individuals, including a data acquisition module, a risk index prediction module, a transmission trend prediction module and a region identification module; the data acquisition module is used to collect multi-source data of patients and pre-process the multi-source data; the risk index prediction module is used to perform multi-dimensional cross-validation of patient behavior through an intelligent verification engine based on the pre-processed multi-source data, screen out reliable data, and predict the patient's behavioral risk index; the transmission trend prediction module is used to construct a dynamic risk coupling model, calculate the transmission risk value of HIV-infected individuals in real time based on the patient's behavioral risk index, and generate a transmission risk trend map through time series analysis; the region identification module is used to classify the transmission risk according to the transmission risk trend map, mark high-risk areas, and update the high-risk areas by monitoring actual HIV transmission events.

[0014] In a third aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, it implements any step of the method for quantitatively assessing the risk of reinfection in HIV-infected individuals as described in the first aspect of the present invention.

[0015] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the method for quantitatively assessing the risk of reinfection in HIV-infected individuals as described in the first aspect of the present invention.

[0016] The beneficial effects of the present invention are: by collecting and preprocessing multi-source data of patients, using an intelligent verification engine to perform multi-dimensional cross-validation on patient behavior, combining spatial consistency coefficient, medication compliance score and social activity, predicting the patient's behavioral risk index; constructing a dynamic risk coupling model, calculating the transmission risk value of HIV-infected individuals in real time, and generating a transmission risk trend map; combining spatial hotspot density analysis and actual transmission events, marking and dynamically updating high-risk areas, and realizing a comprehensive, dynamic and accurate assessment of HIV re-transmission risk. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0018] Figure 1 This is a flow chart of the method for quantitatively assessing the risk of retransmission of HIV-infected individuals in Example 1.

[0019] Figure 2 Schematic diagram of the quantitative assessment system for the risk of retransmission of HIV-infected individuals in Example 1.

[0020] Figure 3 This is a flow chart of the process of generating the propagation risk trend graph in Example 1.

[0021] Figure 4 This is a flow chart for calculating the transmission risk value of an HIV-infected individual in Example 1. DETAILED DESCRIPTION

[0022] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0023] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0024] Secondly, the term "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in various places throughout this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive of other embodiments.

[0025] Example 1, reference Figures 1 to 4 , which is the first embodiment of the present invention, provides a quantitative assessment method for the risk of retransmission of HIV-infected individuals, comprising the following steps: S1. Collect multi-source data of patients and pre-process the multi-source data; Multi-source data includes patients’ medication records, location trajectories, and social network data; Furthermore, multi-source data is automatically collected through interfaces: medication records come from smart medicine box devices, which upload minute-level medication time data in real time; positioning tracks are provided by operator base stations, recording the patient's GPS coordinates every hour, with an accuracy of less than 100 meters; social network data is obtained through a secure API interface, including behavioral characteristics such as the frequency of logins to dating apps used by patients and session duration.

[0026] All the above data are obtained with the user's consent and used for legal purposes.

[0027] Preprocessing includes anomaly cleaning, missing data completion, standardized encoding, data deduplication and format conversion.

[0028] Furthermore, anomaly cleaning: correct incorrect timestamps in medication records (such as future times or old data from ten years ago) to ensure that the time logic is correct.

[0029] It should be noted that for the timestamp data in the medication records, first identify and mark abnormal values, including future times (such as 2025), obviously wrong times (such as 1970), and time points that are seriously inconsistent with the patient's diagnosis date; then, based on the patient's historical medication patterns, use fitting and inference methods (such as interpolation methods) to calculate a reasonable time range, and correct the abnormal timestamps to logical medication times to ensure the accuracy of the time series.

[0030] Missing coordinates: The missing GPS coordinates in the positioning trajectory are calculated and completed based on the patient's historical activity pattern to ensure trajectory continuity.

[0031] It should be noted that for the missing GPS coordinates in the positioning trajectory, the patient's historical activity pattern is first analyzed, including the permanent area, movement patterns and activity time characteristics; then, based on the Markov chain model, combined with the known coordinates of the previous and next time points, the reasonable value of the missing position is calculated; finally, the completed GPS coordinates are seamlessly connected with the original data to form a complete positioning trajectory, where the original data refers to the GPS positioning coordinate data actually recorded by the patient, including the missing parts.

[0032] Standardized coding: Convert the app types (such as dating and social) in social network data into unified classification codes to facilitate subsequent analysis.

[0033] It should be noted that for the APP type information in social network data, we first establish a unified classification standard, and encode different types of APPs such as dating, social, and entertainment as A1, A2, A3, etc.; then traverse the original data and map each APP name to the corresponding classification code; finally, generate a new data set containing standardized codes.

[0034] Data deduplication: Deduplication is performed on multiple positioning coordinates at the same time point to avoid redundant trajectory data.

[0035] It should be noted that for multiple positioning coordinates at the same time point, duplicate records are first identified. For example, a patient may have multiple GPS coordinates at 12:00 on October 1, 2023. Then, based on the coordinate accuracy and activity scenarios, the most reasonable records are retained, such as the coordinates with the highest accuracy or the coordinates that best match the permanent area. Finally, a deduplicated positioning trajectory is generated.

[0036] Format conversion: Convert multi-source data (medication records, location trajectories, social behavior) into a standard time series format to ensure data compatibility.

[0037] It should be noted that for multi-source data (including medication records, location trajectories, and social behaviors), a unified time series format is first defined, including standard timestamps, data fields, and units; then each type of data is converted according to the unified time series format, for example, medication time is converted to a standard time format, and GPS coordinates are converted to a "longitude, latitude" format; finally, a standardized time series dataset is generated to ensure the compatibility and processing efficiency of multi-source data.

[0038] S2. Based on the pre-processed multi-source data, the intelligent verification engine performs multi-dimensional cross-validation on the patient's behavior, screens out credible data, and uses it to predict the patient's behavioral risk index; Credible data include spatial consistency coefficient, patient medication adherence score, and patient social activity.

[0039] Based on pre-processed multi-source data, the intelligent verification engine verifies the patient's location trajectory, medication record, and social network behavior. Positioning trajectory verification is as follows: The spherical distance formula is used to calculate the deviation distance between the centroid coordinates and the reported address. The expression is: ; in, is the deviation distance between the centroid coordinates and the reported address, is the radius of the Earth, is the latitude of the reported address, is the longitude of the reported address, The patient The coordinate latitude of the activity, The patient The coordinate longitude of each activity, is the total number of patient activity coordinates; It should be noted that first, according to the patient's positioning trajectory data, the patient's first The coordinate latitude and longitude of each activity are calculated, and the average latitude and longitude of the activity coordinates of all patients are calculated; then the latitude and longitude of the reported address, the average latitude and the average longitude are substituted into the spherical distance formula, combined with the radius of the earth, and the deviation distance between the center of mass coordinates and the reported address is calculated through trigonometric function operations, and finally the deviation distance value reflecting the degree of deviation between the patient's activity range and the reported address is obtained.

[0040] The reported address refers to the permanent address registered and reported by the patient in the public health system or relevant institutions, which usually includes specific street, house number, city and postal code, etc., and is used as a reference benchmark for the patient's daily activities.

[0041] According to the deviation distance between the centroid coordinates and the reported address , the spatial consistency coefficient is generated by the exponential decay function; It should be noted that, first, the greater the deviation distance between the centroid coordinates and the reported address, the greater the degree of deviation between the patient's range of activity and the reported address. Then, an exponential decay function is used to map the deviation distance to the spatial consistency coefficient. The smaller the deviation distance, the closer the spatial consistency coefficient is to the maximum value, and the larger the deviation distance, the closer the spatial consistency coefficient is to the minimum value. For example, if the deviation distance is zero, the spatial consistency coefficient is maximum, indicating that the patient's range of activity is completely consistent with the reported address. If the deviation distance is large, the spatial consistency coefficient decreases significantly, indicating that the patient's range of activity deviates significantly from the reported address.

[0042] Medication record verification, as follows: By comparing the actual medication time with the planned time, the deviation ratio identification method is used to calculate the patient's medication compliance score, which is expressed as: ; in, is the patient's medication compliance score, is the average medication time deviation of patients, is the patient's maximum tolerated deviation; It should be noted that the actual medication time and planned time refer to the comparison between the time when the patient actually takes the medication during the medication process and the planned medication time specified by the doctor or treatment plan. The actual medication time is recorded by the smart medicine box device, and the patient's minute-level medication data is uploaded in real time; the planned time is determined according to the medication plan prescribed by the doctor, such as the time and frequency of daily medication. By comparing the actual medication time with the planned time, the patient's medication compliance can be evaluated. For example, if the planned time is 8 am every day, and the actual medication time is 10 am, there is a deviation between the actual medication time and the planned time, indicating that the patient did not take the medication completely according to the planned time.

[0043] Social network behavior verification refers to counting the patient's social frequency through sliding window statistics to reflect the patient's social activity; Based on the spatial consistency coefficient, the patient's medication compliance score and the patient's social activity, the patient's behavioral risk index is predicted by using nonlinear exponential decay and logarithmic smoothing of extreme values. The expression is: ; in, is the spatial consistency coefficient, is the patient's medication compliance score, The patient's social activity is the spatial consistency coefficient The weight coefficient of Patient medication compliance score The weight coefficient of Patient's social activity The weight coefficient of is the spatial consistency coefficient The attenuation factor, Patient medication compliance score The attenuation factor, Patient's social activity The attenuation factor, is the patient's behavioral risk index, is a very small positive number.

[0044] Furthermore, first, the spatial consistency coefficient is adjusted by an exponential decay function; the higher the spatial consistency coefficient, the greater the contribution to the behavioral risk index; second, the patient's medication compliance score is adjusted by an exponential decay function; the higher the patient's medication compliance score, the greater the contribution to the behavioral risk index; then, the patient's social activity is adjusted by an exponential growth function; the higher the patient's social activity, the greater the contribution to the behavioral risk index; finally, the contribution of the patient's social activity is smoothed by a logarithmic function to avoid the influence of extreme values ​​on the behavioral risk index, and a very small positive number is combined to ensure that the denominator is not zero, and finally the patient's behavioral risk index is calculated.

[0045] The derivation process of the behavioral risk index expression for predicting patients is as follows: The derivation of the behavioral risk index expression is based on the systematic quantitative modeling of the key behavioral pathways of HIV transmission, by coupling the spatial exposure risk (spatial consistency coefficient ), treatment failure risk (medication compliance score ) and social transmission risk (social activity ) Three core indicators, using exponential decay function and To characterize positive indicators ( 、 ) and the nonlinear relationship between risk (when or When the risk decreases slightly from 1, it increases exponentially, which is consistent with the "critical shift amplification effect"). At the same time, the logarithmic function is used Social activity The unbounded characteristics of the data are compressed and adjusted (retaining the risk enhancement effect of high-frequency social interaction while avoiding extreme values ​​dominating the calculation results), and finally the risk coupling of multi-source behavioral data is achieved through weighted combination, where the weight coefficient reflects the relative importance of different behavioral factors (such as the risk of treatment interruption given by Higher weight), the attenuation factor controls the sensitivity of each indicator (such as The risk contribution of social activity is more significant when it increases), the minimum constant Ensure numerical stability.

[0046] It should be noted that the expression for predicting the patient's behavioral risk index is normalized to the interval [0, 1] by Min-Max normalization before calculation.

[0047] S3. Build a dynamic risk coupling model to calculate the transmission risk value of HIV-infected individuals in real time based on the patient's behavioral risk index, and generate a transmission risk trend chart through time series analysis; The dynamic risk coupling model is constructed by the input layer, feature extraction layer, time series analysis layer, dynamic coupling layer and output layer; The input layer receives data from multiple sources and performs preliminary formatting and standardization; Furthermore, first, the multi-source data is uniformly converted into a standard time series format to ensure data compatibility; then, the data integrity is checked, and missing values ​​and outliers are processed, such as correcting incorrect timestamps in medication records, completing missing coordinates in positioning trajectories, and converting APP types in social network data into unified classification codes; finally, a standardized multi-source dataset is generated.

[0048] Feature extraction layer, extracting HIV risk transmission features from multi-source data; HIV risk transmission characteristics include HIV risk transmission characteristics including patients' medication compliance characteristics, spatial activity characteristics and social behavior characteristics, which respectively reflect the patients' medication compliance, activity range and regularity, social activity and risk behavior tendencies.

[0049] Furthermore, first, based on the patient's medication records, medication compliance features are extracted to reflect the patient's compliance with medication. Second, based on the patient's location trajectory, spatial activity features are extracted to reflect the patient's activity range and regularity. Then, based on the patient's social network data, social behavior features are extracted to reflect the patient's social activity and risk behavior tendencies. Finally, the extracted features are integrated to generate an HIV risk transmission feature dataset.

[0050] Dynamic coupling layer, the patient's behavioral risk index Dynamically coupled with HIV transmission characteristics, the transmission risk value of HIV-infected individuals is calculated in real time; Furthermore, first, the patient's behavioral risk index is combined with the HIV risk transmission characteristics to reflect the relationship between the patient's behavior and transmission risk; then, through a dynamic coupling model, the transmission risk value at each time point is calculated in real time to ensure that the calculation results can reflect the current risk status; finally, time series data of the transmission risk value is generated.

[0051] Output layer, outputs the transmission risk value of HIV-infected individuals.

[0052] Furthermore, the propagation risk values ​​calculated by the dynamic coupling layer are organized into a time series dataset; then, the propagation risk values ​​are combined with timestamp information to generate a standardized output result; finally, the output result is used to generate a re-propagation risk trend graph.

[0053] It should be clarified that infected individuals refer to every patient with HIV; Combine multi-source data and patients' behavioral risk index , input the dynamic risk coupling model to calculate the transmission risk value of HIV-infected individuals, the expression is: ; in, It's time The transmission risk value of HIV-infected individuals at is the intensity of the impact of HIV risk transmission characteristics on the transmission risk value, It's time HIV risk transmission characteristics at that time, is a factor used to adjust the impact of the square root term on the transmission risk value. It's time is the patient's behavioral risk index; Furthermore, first, according to time The behavioral risk index and HIV risk transmission characteristics of the patient at the time of , calculate the product of the first item of the patient's behavioral risk index and HIV risk transmission characteristics, and then adjust the contribution of HIV risk transmission characteristics in combination with the intensity of the influence of HIV risk transmission characteristics on the transmission risk value; then, calculate the square root of the second item of the patient's behavioral risk index and HIV risk transmission characteristics, and adjust the contribution of the square root term in combination with the factor that adjusts the intensity of the influence of the square root term on the transmission risk value; finally, add the two results to get time The transmission risk value of an HIV-infected individual at the time of infection.

[0054] time HIV risk transmission characteristics at the time of Before participating in the calculation, sliding window mean smoothing and Z-score normalization are performed to eliminate short-term fluctuations and unify the dimensions.

[0055] Organize the transmission risk value and timestamp information at each time point to generate a time series dataset; It should be noted that, first, the time series dataset consists of two core fields, namely timestamp and transmission risk value. The timestamp records the specific date and time of each time point, and the transmission risk value records the transmission risk value of the HIV-infected individual at the corresponding time point; then, the transmission risk values ​​and timestamp information corresponding to all time points are arranged one by one in chronological order, for example, the transmission risk value with a timestamp of 12:00 on October 1, 2023 is 0.5, and the transmission risk value with a timestamp of 13:00 on October 1, 2023 is 0.6; then, check the integrity and consistency of the data, and handle missing values ​​or outliers, such as filling in missing transmission risk values ​​through interpolation to ensure the continuity of the time series; finally, generate a time series dataset containing timestamps and transmission risk values, providing a basis for subsequent analysis and visualization. For example, a time series dataset may contain the following records: the transmission risk value at 12:00 on October 1, 2023 is 0.5, the transmission risk value at 13:00 on October 1, 2023 is 0.6, the transmission risk value at 14:00 on October 1, 2023 is 0.7, and so on, forming a complete time series dataset.

[0056] Based on the time series data set, a transmission risk trend graph was drawn using the time series smoothing analysis method, with time as the horizontal axis and the transmission risk value of HIV-infected individuals as the vertical axis.

[0057] It should be explained that, first, timestamps and transmission risk values ​​are extracted from the time series dataset and arranged in chronological order; then, the transmission risk values ​​are smoothed using a time series smoothing analysis method (such as the moving average method), and the moving average value for each time point is calculated. For example, the transmission risk values ​​of the current time point and several previous time points are averaged as the smoothed value for the current time point; then, the timestamp of each time point is marked with time as the horizontal axis to ensure that the time scale is evenly distributed; the range of the transmission risk value is marked with the vertical axis to ensure that the vertical axis scale can cover all transmission risk values; then, the original data points are plotted in the transmission risk trend chart, and the transmission risk values ​​corresponding to each time point are marked in the form of scatter points in the transmission risk trend chart; at the same time, a smoothed transmission risk trend line is drawn, and the moving average value corresponding to each time point is marked in the form of a continuous curve in the transmission risk trend chart; finally, a legend, title, and annotation are added to explain the meaning and drawing method of the transmission risk trend chart to ensure that the chart is clear and easy to read.

[0058] S4. Classify the transmission risk according to the transmission risk trend chart and mark the high-risk areas. At the same time, update the high-risk areas by monitoring the actual transmission events of HIV.

[0059] According to the transmission risk trend chart, through time series decomposition, the transmission risk value of HIV-infected individuals is analyzed over time; When the transmission risk value of an HIV-infected individual shows an increasing trend over time, the current transmission risk is high; It should be noted that, first, the changes in the transmission risk value are observed through the transmission risk trend chart. If the transmission risk value gradually increases over time, for example, from 0.5 at 12:00 on October 1, 2023 to 0.8 at 14:00 on October 1, 2023, then the transmission risk is judged to be on an upward trend; then, the current transmission risk level is evaluated based on the increasing amplitude and speed of the transmission risk value. If the increasing amplitude is large and the speed is fast, then the current transmission risk is judged to be in a high-risk state.

[0060] When the transmission risk value of an HIV-infected individual shows a downward trend over time, the current transmission risk is low; It should be noted that, first, the changes in the transmission risk value are observed through the transmission risk trend chart. If the transmission risk value gradually decreases over time, for example, from 0.8 at 12:00 on October 1, 2023 to 0.5 at 14:00 on October 1, 2023, then the transmission risk is judged to be on a downward trend; then, the current transmission risk level is evaluated based on the decrease in the transmission risk value and the speed. If the decrease is large and the speed is fast, then the current transmission risk is judged to be in a low-risk state.

[0061] Combining the transmission risk level and the patient's location trajectory data, the spatial hotspot density analysis method is used to generate a heat map of high-risk areas and mark them on the map. At the same time, the high-risk areas are updated by monitoring actual HIV transmission events.

[0062] It should be noted that, first, high-risk time periods are screened according to the transmission risk level, and the patient's location trajectory data during the high-risk time period is extracted, including GPS coordinates and timestamps; then, spatial hotspot density analysis (such as kernel density estimation) is used to perform spatial density analysis on the GPS coordinates. The spatial hotspot density analysis method generates a kernel function around each GPS coordinate point and superimposes all kernel functions to generate a spatial density distribution map. The higher the density, the more concentrated the risk; then, the spatial density distribution map is converted into a heat map. The darker the color in the heat map, the higher the risk, and the lighter the color, the lower the risk; the heat map is superimposed on the map, and high-risk areas are marked, for example, high-risk areas are marked in red and medium-risk areas are marked in yellow on a city map; finally, the accuracy of the high-risk areas is verified by monitoring actual HIV transmission events, such as the time and location of new cases. If the new case is found to be located in the marked high-risk area, the risk level of the area is further confirmed; if the new case is located in an unmarked area, the area is included in the high-risk area and the heat map is updated.

[0063] This embodiment also provides a quantitative assessment system for the risk of re-transmission of HIV-infected individuals, including: a data acquisition module, a risk index prediction module, a transmission trend prediction module and a region identification module; the data acquisition module is used to collect multi-source data of patients and pre-process the multi-source data; the risk index prediction module is used to perform multi-dimensional cross-validation of patient behavior through an intelligent verification engine based on the pre-processed multi-source data, screen out reliable data, and predict the patient's behavioral risk index; the transmission trend prediction module is used to construct a dynamic risk coupling model, calculate the transmission risk value of HIV-infected individuals in real time based on the patient's behavioral risk index, and generate a transmission risk trend map through time series analysis; the region identification module is used to classify the transmission risk according to the transmission risk trend map, mark high-risk areas, and update the high-risk areas by monitoring actual HIV transmission events.

[0064] This embodiment also provides a computer device suitable for a quantitative assessment method for the risk of retransmission of HIV-infected individuals, comprising: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute computer-executable instructions to implement the quantitative assessment method for the risk of retransmission of HIV-infected individuals proposed in the above embodiment.

[0065] The computer device may be a terminal, comprising a processor, memory, a communication interface, a display, and an input device connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores an operating system and computer programs. The internal memory provides an environment for the operating system and computer programs stored in the non-volatile storage media. The communication interface of the computer device is used to communicate with external terminals via wired or wireless communication. Wireless communication may be achieved via Wi-Fi, a carrier network, NFC (near-field communication), or other technologies. The display of the computer device may be a liquid crystal display or an electronic ink display. The input device may be a touchscreen overlay on the display, buttons, a trackball, or a touchpad on the computer device housing, or an external keyboard, touchpad, or mouse.

[0066] This embodiment also provides a storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for quantitatively assessing the risk of retransmission of HIV-infected individuals as proposed in the above embodiment; the storage medium 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.

[0067] In summary, the present invention achieves this by: collecting and preprocessing multi-source data of patients, performing multi-dimensional cross-validation on patient behavior using an intelligent verification engine, and predicting the patient's behavioral risk index by combining spatial consistency coefficients, medication compliance scores, and social activity; constructing a dynamic risk coupling model to calculate the transmission risk value of HIV-infected individuals in real time and generate a transmission risk trend map; combining the kernel density estimation method with actual transmission events to mark and dynamically update high-risk areas, thereby achieving a comprehensive, dynamic, and accurate assessment of the risk of HIV re-transmission.

[0068] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for quantitatively assessing the risk of retransmission in HIV-infected individuals, characterized by: include, Collecting and preprocessing multi-source data of patients, including medication records, location trajectories, and social network data; Based on pre-processed multi-source data, the intelligent verification engine performs multi-dimensional cross-validation on patient behavior, screens out reliable data, and predicts the patient's behavioral risk index. The reliable data includes spatial consistency coefficient, patient medication compliance score, and patient social activity. Build a dynamic risk coupling model to calculate the transmission risk value of HIV-infected individuals in real time based on the patient's behavioral risk index, and generate a transmission risk trend chart through time series analysis; The transmission risk is graded according to the transmission risk trend chart, and high-risk areas are marked. At the same time, high-risk areas are updated by monitoring actual HIV transmission events.

2. The method for quantitatively assessing the risk of retransmission of HIV-infected individuals according to claim 1, wherein: The preprocessing includes anomaly cleaning, missing completion, standardized encoding, data deduplication and format conversion.

3. The method for quantitatively assessing the risk of retransmission of HIV-infected individuals according to claim 1, wherein: The intelligent verification engine is used to perform multi-dimensional cross-validation on patient behavior to screen out credible data. The specific steps are as follows: The spherical distance formula is used to calculate the deviation distance between the centroid coordinates and the reported address, and the spatial consistency coefficient is generated through the exponential decay function; By comparing the actual medication taking time with the planned time, the deviation proportion identification method was used to calculate the patient's medication compliance score; The patients' social frequency was counted using the sliding window statistical method.

4. The method for quantitatively assessing the risk of retransmission of HIV-infected individuals according to claim 3, wherein: The method for predicting the patient's behavioral risk index includes predicting based on a spatial consistency coefficient, a patient's medication compliance score, and a patient's social activity, using nonlinear exponential decay, and performing logarithmic smoothing of extreme values.

5. The method for quantitatively assessing the risk of retransmission of HIV-infected individuals according to claim 1, wherein: The dynamic risk coupling model includes: The input layer receives data from multiple sources and performs preliminary formatting and standardization; Feature extraction layer, extracting HIV risk transmission features from multi-source data; Dynamic coupling layer, the patient's behavioral risk index Dynamically coupled with HIV transmission characteristics, the transmission risk value of HIV-infected individuals is calculated in real time; Output layer, outputs the transmission risk value of HIV-infected individuals.

6. The method for quantitatively assessing the risk of retransmission of HIV-infected individuals according to claim 5, wherein: The real-time calculation of the transmission risk value of HIV-infected individuals and the generation of a transmission risk trend graph through time series analysis are as follows: Combine multi-source data and patients' behavioral risk index , input the dynamic risk coupling model to calculate the transmission risk value of HIV-infected individuals; Organize the transmission risk value and timestamp information at each time point to generate a time series dataset; Based on the time series data set, a transmission risk trend graph was drawn using the time series smoothing analysis method, with time as the horizontal axis and the transmission risk value of HIV-infected individuals as the vertical axis.

7. The method for quantitatively assessing the risk of retransmission of HIV-infected individuals according to claim 6, wherein: The transmission risk is graded and high-risk areas are marked. At the same time, high-risk areas are updated by monitoring actual HIV transmission events. The specific steps are as follows: According to the transmission risk trend chart, through time series decomposition, the transmission risk value of HIV-infected individuals is analyzed over time; Combining the transmission risk level and the patient's location trajectory data, the spatial hotspot density analysis method is used to generate a heat map of high-risk areas and mark them on the map. At the same time, the high-risk areas are updated by monitoring actual HIV transmission events.

8. A quantitative assessment system for the risk of retransmission of HIV-infected individuals, based on the quantitative assessment method for the risk of retransmission of HIV-infected individuals according to any one of claims 1 to 7, characterized in that: Including data collection module, danger index prediction module, spread trend prediction module and area identification module; Data acquisition module, used to collect multi-source data of patients and pre-process the multi-source data; The risk index prediction module is used to perform multi-dimensional cross-validation of patient behavior based on pre-processed multi-source data through an intelligent verification engine, screen out reliable data, and predict the patient's behavioral risk index; The transmission trend prediction module is used to build a dynamic risk coupling model, calculate the transmission risk value of HIV-infected individuals in real time based on the patient's behavioral risk index, and generate a transmission risk trend chart through time series analysis; The regional identification module is used to classify the transmission risk according to the transmission risk trend map and mark the high-risk areas. At the same time, it updates the high-risk areas by monitoring the actual transmission events of HIV.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method for quantitatively assessing the risk of retransmission of HIV-infected individuals according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for quantitatively assessing the risk of retransmission of HIV-infected individuals according to any one of claims 1 to 7 are implemented.

Images