Shelter hospital wounded vital sign cluster monitoring system based on internet of things

Abstract

This invention relates to the field of vital sign monitoring technology, specifically to an IoT-based cluster monitoring system for the vital signs of patients in makeshift hospitals. The system acquires vital sign information from patients, analyzes deviations in vital signs over time to identify abnormal fluctuations, and analyzes the distribution of these abnormal fluctuations by comparing the fluctuations of individual patients with those of similar patients, combined with the distribution of abnormal fluctuations to determine the degree of electromagnetic interference. By analyzing the frequency distribution of historical treatment periods and the degree of abnormal deviations, and adjusting electromagnetic interference indicators, the system prioritizes and categorizes output for the current patient. This invention combines vital sign information from patients with electromagnetic interference analysis of fluctuations from similar patients to determine the most accurate and reliable needs of patients for categorized output, thereby improving the efficiency of medical personnel in acquiring patient information within makeshift hospitals.

Description

Technical Field

[0001] This invention relates to the field of vital sign monitoring technology, specifically to an Internet of Things-based cluster monitoring system for vital signs of wounded patients in makeshift hospitals. Background Technology

[0002] Fangcang hospitals typically utilize Internet of Things (IoT) technology to collect real-time physiological parameters of large numbers of injured patients through wearable or lightweight sensing devices. This data is then fed into a central processing system for centralized display, storage, and early warning of abnormalities in the patients' vital signs. The central processing system usually employs methods such as CNN or random forest to analyze the monitoring data of each patient, thereby identifying and issuing warnings of abnormal vital signs, enabling medical staff to promptly detect changes in the patients' conditions.

[0003] However, there may be a situation where a large number of wounded are introduced into makeshift hospitals. These wounded may be located at different monitoring points, including fixed monitoring points inside the makeshift hospital and mobile monitoring points outside the hospital, such as mobile communication vehicles used for temporary monitoring. In addition, the location of makeshift hospitals is usually quite complex, and the monitored data is very susceptible to interference. For example, there may be many electromagnetic interference devices operating at the same time, including multiple vital sign monitoring terminals, battlefield communication equipment, etc. In this case, the fixed output mode of monitoring data for each wounded may drown out the risk of fluctuations in the real vital signs of wounded who have higher needs, and the risk of delay in processing wounded information is high. Summary of the Invention

[0004] To address the technical problems in the prior art, the present invention aims to provide an Internet of Things-based cluster monitoring system for vital signs of wounded patients in makeshift hospitals. The specific technical solution adopted is as follows: This invention provides an IoT-based cluster monitoring system for vital signs of wounded patients in makeshift hospitals, the system comprising: The data preparation module is used to obtain the data values ​​of each vital sign and the initial severity classification of each injured person in time sequence, as well as the historical treatment and location information; The abnormal moment analysis module is used to determine the degree of deviation at each moment for each vital sign of each injured person based on the changes and deviations of the data values ​​at each moment; by determining the degree of abnormal deviation at each moment and the initial severity level, the module also filters abnormal moments. The electromagnetic interference analysis module is used to analyze the deviation correlation of vital signs between each injured person and similar injured persons, and to determine the abnormal correlation of each injured person; based on the continuous distribution and abnormal correlation of each injured person at abnormal times, as well as the degree of synchronous distribution of abnormal times in the vicinity, the electromagnetic interference index of each injured person at the current time is determined. The priority analysis module is used to determine the urgency of each wounded person's attention based on the similarity of the distribution of each wounded person's historical treatment period; to determine the current priority index of each wounded person by the deviation changes and urgency of attention of each wounded person in continuous time, as well as the location distribution and electromagnetic interference index of the wounded persons; and to determine the current output priority based on the wounded person's priority index and initial severity level. The output module is used to classify and output data based on the priority of the wounded.

[0005] Furthermore, the method for obtaining the deviation includes: For any vital sign of each wounded soldier, the difference between the data value of that vital sign at each moment and the previous moment is normalized and used as the degree of change at each moment. The difference between the data value of this vital sign at each moment and the expected standard value is used as the numerical difference degree at each moment; The product of the degree of change and the degree of numerical difference at each time point is normalized to obtain the deviation of the vital sign at each time point.

[0006] Furthermore, the method for obtaining the abnormal deviation includes: For each injured person, the mean of the deviation of all vital signs at each time point is used as the abnormality significance at each time point; the variance of the deviation of all vital signs at each time point is negatively correlated to obtain the abnormality synchronization at each time point; the product of the abnormality significance and the abnormality synchronization at each time point is used as the abnormality assessment index at each time point. The product of the anomaly assessment index at each time step and the initial severity level is normalized to obtain the anomaly deviation at each time step.

[0007] Furthermore, the method for obtaining the abnormal moment includes: The moment when the abnormal deviation exceeds the preset abnormal threshold is defined as an abnormal moment.

[0008] Furthermore, the method for obtaining the abnormal correlation includes: For any wounded soldier, based on the initial severity level and case history, identify similar wounded soldiers; sequentially, use each vital sign as the analysis sign, and at the abnormal moments before the current moment, obtain the correlation between the data values ​​of the wounded soldier and each similar wounded soldier on the analysis sign, and use the average correlation with all similar wounded soldiers on the analysis sign as the abnormality similarity of the wounded soldier on the analysis sign. At non-abnormal moments before the current moment, after obtaining the correlation between the injured person and each similar injured person in terms of analyzed vital signs, the average correlation of the data values ​​of the injured person with all similar injured persons in terms of analyzed vital signs is used as the normal approximation of the injured person in terms of analyzed vital signs. The product of the normal approximation and abnormal approximation of the patient's physical signs in the analysis is taken as the abnormal correlation degree of the patient's physical signs in the analysis. The mean of the abnormal correlations of all vital signs for the injured person is taken as the abnormal correlation of the injured person.

[0009] Furthermore, the method for obtaining the electromagnetic interference index includes: For any wounded soldier, combine the consecutive abnormal moments of the wounded soldier before the current moment to obtain the abnormal time period; normalize the product of the average duration of all abnormal time periods after negative correlation mapping and the total number of abnormal time periods to obtain the abnormal random index of the wounded soldier. At each abnormal moment of the injured person, the number of other injured persons in the vicinity of the injured person's preset location is obtained as the abnormal range index of the injured person at each abnormal moment; the sum of the abnormal range indexes of the injured person at all abnormal moments is normalized to obtain the group abnormal characteristic index of the injured person at the current moment. The electromagnetic interference index of the injured person at the current moment is obtained by normalizing the product of the negative correlation mapping value of the abnormal correlation of the injured person, the group abnormal characteristic index, and the abnormal random index.

[0010] Furthermore, the method for obtaining the urgency of attention includes: For any wounded person, obtain the interval between adjacent historical treatment periods before the current moment, normalize the product of the mean of all intervals after negative correlation mapping and the total number of intervals, and obtain the urgency of attention for the wounded person. When the interval period is not available, the average of the abnormal deviations of all abnormal moments of the injured person before the current moment is taken as the urgency of the injured person's attention.

[0011] Furthermore, the method for obtaining the priority index includes: For any wounded person, calculate the difference between the data values ​​of each vital sign of the wounded person at the current time and the previous time, and then take the average of the differences of the data values ​​of all vital signs as the abnormal increase rate at the current time; take the difference between the abnormal increase rate at the current time and the previous time as the abnormal attention indicator at the current time. The distance between the injured person's current location and the center of the makeshift hospital was normalized and used as a distance monitoring indicator. The current priority index of the injured person is obtained by multiplying the electromagnetic interference index of the injured person after negative correlation mapping, the urgency of attention, the abnormal attention index and the distance attention index, and then normalizing the result.

[0012] Furthermore, the method for obtaining the output priority includes: The product of the priority index of each wounded soldier and the corresponding initial severity level is used as the level adjustment degree; the sum of the initial severity level and the level adjustment degree is normalized and used as the output priority of each wounded soldier.

[0013] Furthermore, the hierarchical output based on the output priority of the wounded includes: The information of the wounded is sorted and output in descending order of output priority. When the priority output degree is greater than or equal to the preset high priority threshold, all information of the corresponding wounded is output. When the priority output degree is greater than the preset low priority threshold and less than the preset high priority threshold, the key information of the corresponding wounded person will be output. When the priority output degree is less than or equal to the preset low priority threshold, the basic information of the corresponding wounded person will be output; the preset low priority threshold is less than the preset high priority threshold.

[0014] The present invention has the following beneficial effects: This invention acquires vital sign information of wounded patients, analyzes the differences in changes of different vital sign information at different times, focuses on moments of abnormal fluctuation, and, based on the distribution of abnormal moments, combines the similarity of the fluctuations of a single wounded patient's vital sign with the fluctuations of similar wounded patients, as well as the distribution characteristics of abnormal moments in time sequence and the actual location of the wounded patients, to obtain the degree of electromagnetic interference that the wounded patients may be experiencing. It distinguishes between possible real anomalies and electromagnetic interference anomalies, improving the priority and accuracy of information for wounded patients with high levels of real anomalies. Finally, by analyzing the frequency distribution of historical treatment periods and the degree of abnormal deviations, combined with adjustments to electromagnetic interference indicators, it determines the current output priority of wounded patients, reflecting more accurate attention needs and providing tiered output. This invention, by combining wounded patients' vital sign information with electromagnetic interference analysis of fluctuations in similar wounded patients, determines more realistic and reliable attention needs for wounded patients and provides tiered output, improving the efficiency of medical personnel in acquiring wounded patients in makeshift hospitals. Attached Figure Description

[0015] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 This is a structural diagram of a mobile hospital patient vital signs cluster monitoring system based on the Internet of Things, provided as an embodiment of the present invention. Detailed Implementation

[0017] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of an Internet of Things-based cluster monitoring system for vital signs of wounded patients in a makeshift hospital, based on the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0018] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0019] The following description, in conjunction with the accompanying drawings, details the specific scheme of the IoT-based mobile hospital patient vital sign cluster monitoring system provided by this invention.

[0020] Please see Figure 1 The diagram shows a structural diagram of a mobile hospital patient vital signs cluster monitoring system based on the Internet of Things provided in an embodiment of the present invention. The system includes: a data preparation module 101, an abnormal moment analysis module 102, an electromagnetic interference analysis module 103, a priority analysis module 104, and an output module 105.

[0021] The data preparation module 101 is used to obtain the data values ​​of each vital sign and the initial severity classification of each injured person in the time sequence, as well as the historical treatment and location information.

[0022] In the context of makeshift hospitals, there are fixed monitoring points inside the hospital, such as bedside monitoring for fixed beds, as well as more random mobile monitoring points, such as portable monitoring devices used at temporary tents or communication vehicles outside the hospital to monitor the vital signs of the injured. In this embodiment of the invention, various devices are used for each injured person to collect time-series data values ​​of multidimensional vital signs, such as heart rate, blood oxygen saturation, systolic blood pressure, diastolic blood pressure, respiratory rate, body temperature, etc.

[0023] To maximize the use of limited medical resources, medical staff usually conduct an initial assessment and classification of injuries upon receiving each injured person. In this embodiment of the invention, the initial severity classification can be divided into four levels: Level 1, ordinary injuries are marked in green; Level 2, relatively serious injuries are marked in yellow; Level 3, serious injuries are marked in orange; and Level 4, critical injuries are marked in red. The higher the initial severity classification, the more attention the injury requires. The specific classification can be adjusted by the implementer according to the specific implementation scenario, and there are no restrictions here.

[0024] Considering the potential electromagnetic interference in the makeshift hospital environment, the location information of the injured was marked. To ensure more reliable analysis of subsequent needs, the treatment periods for each injured person were also marked, such as hemostasis and adrenaline injection after arrival. Each treatment was recorded, and the data was transmitted to the nearest edge processing device for storage and analysis. It should be noted that preprocessing was performed during data collection and preparation. Preprocessing may include data standardization and time-scale normalization to facilitate unified data analysis and remove the influence of dimensions. Data preprocessing is a well-known technique in the art and will not be elaborated or limited here.

[0025] The abnormal moment analysis module 102 is used to determine the deviation degree of each vital sign of each injured person based on the change and deviation of the data value at each moment; and to determine the abnormal deviation degree of each moment and filter abnormal moments by the magnitude of the deviation degree of each vital sign at each moment and the initial severity level.

[0026] Fangcang hospitals may experience a large influx of injured people, some of whom may be monitored for vital signs in mobile facilities such as communication vehicles as they gradually approach the Fangcang hospital. This necessitates comprehensive monitoring of the injured people's vital signs over a wide area. Typically, lightweight monitoring devices are used to capture fluctuations in the injured people's vital signs. However, to ensure that the vital signs of critically injured people can be captured with limited medical resources, the initial monitoring indicators need to be analyzed at each edge computing node, and abnormal monitoring data should be transmitted first.

[0027] First, we identify possible abnormalities by analyzing the fluctuations in each vital sign for each injured person. Normally, the fluctuations in vital signs are relatively smooth. However, when injured persons are affected by factors such as injury or pain, the amplitude of these fluctuations may change. In emergency situations, the fluctuations are usually more dramatic and significant. Therefore, we use fluctuation deviations to conduct a preliminary screening for abnormalities in the vital signs of each injured person.

[0028] Preferably, in this embodiment of the invention, the method for obtaining the deviation of each vital sign at each moment includes: For any vital sign of each injured person, the difference between the data value of that vital sign at each moment and the previous moment is normalized and used as the degree of change at each moment. This quantifies the fluctuation range of the vital sign data value at each moment. When the degree of change is higher, it indicates that the abnormal state at that moment is more likely.

[0029] It should be noted that normalization is a technique well known to those skilled in the art. The choice of normalization can be linear normalization or standard normalization, etc., and the specific normalization method is not limited here.

[0030] Furthermore, the difference between the vital sign data value at each moment and the expected standard value is used as the numerical difference degree at each moment. The degree of difference between the data and the baseline standard value reflects the possible degree of abnormality. It should be noted that the implementer can adjust the expected standard values ​​for different vital sign data at their own discretion, and there are no restrictions here.

[0031] Finally, the product of the degree of change and the degree of numerical difference at each moment is normalized to obtain the deviation of the vital sign at each moment. The greater the deviation from the baseline at a moment and the higher the degree of fluctuation in the time series, the greater the abnormal deviation.

[0032] Secondly, based on the distribution of abnormal deviations of all vital signs at each time point and combined with the initial grading results, the abnormal status of the injured person at each time point is assessed. In this embodiment of the invention, the method for obtaining the degree of abnormal deviation includes: For each injured person, the mean of the deviation of all vital signs at each time point is used as the significance of the anomaly at that time point. When the overall vital sign data show a high degree of deviation, the anomaly is more likely. At the same time, the variance of the deviation of all vital signs at each time point is negatively correlated to obtain the anomaly synchronization at each time point. The more consistent the deviation of the overall vital signs, the higher the degree of synchronous change of multiple vital signs, and the greater the possibility of a real anomaly, such as the simultaneous decrease of blood pressure and blood oxygen.

[0033] It should be noted that negative correlation mapping is a technique well known to those skilled in the art, and can be in the form of inverse proportion or negative exponentiation with the natural constant as the base, etc., without any restrictions here.

[0034] Finally, the product of the anomaly significance and the anomaly synchronization at each time point is used as the anomaly assessment index for that time point, evaluating the degree of anomaly probability based on deviation. When the injured person is in a more serious condition, the anomaly deviation analysis should be more sensitive. Therefore, the product of the anomaly assessment index at each time point and the initial severity classification is normalized to obtain the anomaly deviation degree at each time point.

[0035] The higher the degree of abnormal deviation, the more significant the abnormality in the vital signs of the injured person at that time. Therefore, in this embodiment of the invention, the time when the degree of abnormal deviation is greater than the preset abnormal threshold is taken as the abnormal time. The preset abnormal threshold can be set to 0.5. The specific value can be adjusted by the implementer and will not be elaborated here.

[0036] The electromagnetic interference analysis module 103 is used to analyze the deviation correlation of vital signs between each injured person and similar injured persons, and to determine the abnormal correlation of each injured person; based on the continuous distribution and abnormal correlation of each injured person at abnormal times, as well as the degree of synchronous distribution of abnormal times in the vicinity, the electromagnetic interference index of each injured person at the current time is determined.

[0037] Electromagnetic interference can occur near makeshift hospitals due to the presence of specialized equipment or vehicles. When a large number of injured people arrive, the nearby medical equipment operating simultaneously may also cause electromagnetic interference, resulting in abnormal data capture and abnormal deviations in the patients' normal vital signs. Therefore, it is necessary to further assess the potential extent of electromagnetic interference by considering the correlation of similar injured people and the overall abnormal distribution in the surrounding area.

[0038] Under normal circumstances, injured individuals with similar severity and case characteristics exhibit certain similarities in the fluctuations of their physiological indicators. For example, after administering adrenaline to injured individuals with similar conditions, a short-term increase in heart rate may occur, although the amplitude of this change may vary among different individuals. Abnormal data generated by electromagnetic interference typically does not conform to normal human vital sign responses; this characteristic is used to assess the significance of electromagnetic interference anomalies.

[0039] First, based on similar circumstances among the injured, a correlation analysis of deviations in vital signs is performed. A higher correlation indicates that the anomaly is less consistent with electromagnetic interference characteristics. In this embodiment of the invention, the method for obtaining the anomaly correlation includes: For any wounded soldier, similar wounded soldiers are identified based on the initial severity level and medical records. In this embodiment of the invention, a regular expression method is used to match other similar wounded soldiers based on the information of the wounded soldier. It should be noted that regular expression matching is a well-known technical means familiar to those skilled in the art, and will not be described in detail here.

[0040] Each vital sign is sequentially used as an analysis sign. At the abnormal moments before the current moment, the correlation between the data values ​​of the injured person and each similar injured person in terms of the analysis sign is obtained. The average correlation with all similar injured persons in terms of the analysis sign is used as the abnormality approximation degree of the injured person in terms of the analysis sign. The higher the abnormality approximation degree, the smaller the possibility of random electromagnetic interference for the injured person. In this embodiment of the invention, the calculation of temporal data correlation can be obtained through a dynamic time warping algorithm. In other embodiments of the invention, Euclidean distance or Pearson correlation coefficient can also be used to obtain temporal data correlation, which will not be elaborated or limited here.

[0041] Furthermore, at non-abnormal times before the current moment, the correlation between the injured person and each similar injured person in terms of analyzed vital signs is obtained. The average correlation of the data values ​​of the injured person with all similar injured persons in terms of analyzed vital signs is used as the normal approximation of the injured person in terms of analyzed vital signs. At the same time, the approximation situation at all non-abnormal times, that is, normal times, is analyzed. The higher the normal approximation, the more reliable the similarity analysis is, and the similar injured persons have the characteristic of high fluctuation similarity.

[0042] Therefore, the product of the normal similarity and abnormal similarity of the patient's vital signs is taken as the abnormal correlation degree of the patient's vital signs. When the normal similarity is higher and the abnormal similarity is higher, it indicates that the patient has abnormal deviations from the normal in the corresponding vital signs and the possibility of random electromagnetic interference is lower.

[0043] Finally, combining the abnormal correlations of all vital signs, the mean of the abnormal correlations of the patient across all vital signs is taken as the patient's abnormal correlation degree. The smaller the abnormal correlation degree, the more likely there are unrelated abnormal deviations of the patient under each vital sign, and the higher the electromagnetic interference may be.

[0044] Considering the randomness and widespread impact of electromagnetic interference, and further combining the continuous distribution of abnormal moments and the synchronous distribution of abnormal moments in neighboring areas, the final electromagnetic interference index is determined. Preferably, in this embodiment of the invention, the method for obtaining the electromagnetic interference index includes: First, for any injured person, the consecutively adjacent abnormal moments before the current moment are combined to obtain the abnormal time period. The product of the mean duration of all abnormal time periods after negative correlation mapping and the total number of abnormal time periods is normalized to obtain the abnormal random index of the injured person. The shorter the duration and the greater the number of distributions, the more likely the current abnormal time period is to have a continuous short distribution characteristic, and the higher the electromagnetic interference may be.

[0045] Furthermore, at each abnormal moment for the injured person, the number of other injured persons within a preset location's vicinity that also constitute an abnormal moment is obtained. This number serves as an anomalous range index for the injured person at each abnormal moment, reflecting the degree of synchronous occurrence of abnormal moments. The sum of the anomalous range indices for the injured person at all abnormal moments is normalized to obtain the group anomalous characteristic index for the injured person at the current moment. The more significant the degree of synchronous occurrence of abnormal moments, the higher the likelihood of electromagnetic interference.

[0046] Finally, the product of the negative correlation mapping value of the patient's abnormal correlation, the group abnormal characteristic index, and the abnormal random index is normalized to obtain the patient's electromagnetic interference index at the current moment. The larger the electromagnetic interference index, the lower the probability that the abnormal deviation is a real abnormality.

[0047] The priority analysis module 104 is used to determine the urgency of each wounded person's attention based on the approximate distribution of each wounded person's historical treatment period; to determine the current priority index of each wounded person by the deviation changes and urgency of attention of each wounded person in continuous time, as well as the location distribution and electromagnetic interference index of the wounded persons; and to determine the current output priority based on the wounded person's priority index and initial severity level.

[0048] For each patient whose data is to be output, the more frequently there are historical treatment stages, the higher the treatment needs, and the more attention should be paid to their related data. In subsequent transmission, more comprehensive priority should be given to ensure timely and efficient monitoring and utilization of the data.

[0049] In this embodiment of the invention, the method for obtaining information focusing on urgency includes: For any injured person, obtain the interval between adjacent historical treatment periods before the current moment. Normalize the product of the mean of all intervals after negative correlation mapping and the total number of intervals to obtain the urgency of the injured person's attention. The shorter the interval between adjacent treatment periods in time and the more times the interval occurs, the higher the degree of attention and treatment the injured person needs and the higher the priority should be.

[0050] In particular, when there is no time interval, that is, when only a single treatment is performed, the average of the abnormal deviations of all abnormal moments of the injured person before the current moment can be used as the urgency of attention for the injured person. The need for attention can be directly quantified by monitoring the degree of deviation.

[0051] The final analysis examines the degree of anomaly reflected by the deviation change at the current moment. Considering that the farther the injured are from the makeshift hospital, the higher the timeliness requirement for their data, higher priority is given to injured individuals located further away to minimize potential delays. The priority index for the final draft is determined by adjusting the electromagnetic interference index.

[0052] Preferably, in this embodiment of the invention, the method for obtaining the priority index includes: For any injured person, after calculating the difference in the data value of each vital sign between the current moment and the previous moment, the average of the differences in all vital sign data values ​​is used as the abnormal increase rate at the current moment. The degree of abnormal change is reflected by the magnitude of the overall deviation increase of vital signs at the current moment. The difference in the abnormal increase rate between the current moment and the previous moment is used as the abnormal attention indicator at the current moment. The magnitude of the increase reflects the degree of abnormal upward trend. The larger the abnormal attention indicator, the more significant the abnormal trend, and the greater the need for early intervention.

[0053] The distance between the injured person's current location and the center of the makeshift hospital was then normalized and used as a distance attention indicator; the greater the distance, the higher the level of attention given.

[0054] Finally, the electromagnetic interference index of the injured person was negatively correlated, and the values ​​were multiplied by the urgency of attention, the abnormal attention index, and the distance attention index, and then normalized to obtain the current priority index of the injured person. The smaller the electromagnetic interference index, the lower the possibility of interference anomaly. At the same time, the larger the urgency of attention, the abnormal attention index, and the distance attention index, the higher the current attention demand for the injured person and the higher the priority output.

[0055] Based on the initial severity rating, the final output priority of each injured person is determined. In this embodiment of the invention, the product of the priority index of each injured person and the corresponding initial severity rating is used as the level adjustment degree. The sum of the initial severity rating and the level adjustment degree is normalized and used as the output priority of each injured person. The higher the output priority, the higher the need for attention for that patient.

[0056] Output module 105 is used to perform hierarchical output based on the output priority of the wounded.

[0057] In this embodiment of the invention, based on the output device, the information of the injured is sorted and output in descending order of output priority, with higher priority being output first.

[0058] When the priority output degree is greater than or equal to the preset high priority threshold, it indicates that the injured person's attention needs are extremely high. All information of the injured person will be output. In this embodiment of the invention, all information may include specific vital sign monitoring data, treatment records, abnormal deviation analysis, and the injured person's location, etc.

[0059] When the priority output degree is greater than the preset low priority threshold and less than the preset high priority threshold, it indicates that the injured person's attention needs are generally low. The key information of the injured person will be output. In this embodiment of the invention, the key information may only be treatment records, abnormal deviation results and injured person's location information, etc.

[0060] When the priority output degree is less than or equal to the preset low priority threshold, the attention demand for the injured person is low, and the basic information of the injured person is output. In the embodiments of the present invention, the basic information may only be case data and output priority, etc. The implementer may adjust the content of the specific information according to the specific implementation scenario, and there is no limitation here.

[0061] In this embodiment of the invention, the preset low priority threshold must be less than the preset high priority threshold. The preset high priority threshold can be set to 0.7, and the preset low priority threshold can be set to 0.3. The implementer can adjust these settings as needed.

[0062] In summary, this invention acquires vital sign information of wounded patients, analyzes the differences in changes of different vital sign information at different times, focuses on moments of abnormal fluctuation, and, based on the distribution of abnormal moments, combines the similarity of the fluctuations of a single wounded patient's vital sign with those of similar wounded patients, and the distribution characteristics of abnormal moments in time sequence and the actual location of the wounded patient, to obtain the degree of electromagnetic interference that the wounded patient may be experiencing. It distinguishes between possible real anomalies and electromagnetic interference anomalies, improving the priority and accuracy of information for wounded patients with high levels of real anomalies. Finally, by analyzing the frequency distribution of historical treatment periods and the degree of abnormal deviations, combined with adjustments to electromagnetic interference indicators, the current output priority for wounded patients is determined, reflecting more accurate attention needs and enabling tiered output. This invention, by combining wounded patient vital sign information with electromagnetic interference analysis of fluctuations in similar wounded patients, determines more realistic and reliable attention needs for wounded patients and provides tiered output, improving the efficiency of medical personnel in acquiring information about wounded patients in makeshift hospitals.

[0063] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0064] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

Claims

1. A cluster monitoring system for vital signs of wounded patients in a makeshift hospital based on the Internet of Things, characterized in that, The system includes: The data preparation module is used to obtain the data values ​​of each vital sign and the initial severity classification of each injured person in time sequence, as well as the historical treatment and location information; The abnormal moment analysis module is used to determine the degree of deviation at each moment for each vital sign of each injured person based on the changes and deviations of the data values ​​at each moment; by determining the degree of abnormal deviation at each moment and the initial severity level, the module also filters abnormal moments. The electromagnetic interference analysis module is used to analyze the deviation correlation of vital signs between each injured person and similar injured persons, and to determine the abnormal correlation of each injured person; based on the continuous distribution and abnormal correlation of each injured person at abnormal times, as well as the degree of synchronous distribution of abnormal times in the vicinity, the electromagnetic interference index of each injured person at the current time is determined. The priority analysis module is used to determine the urgency of each wounded person's attention based on the similarity of the distribution of each wounded person's historical treatment period; to determine the current priority index of each wounded person by the deviation changes and urgency of attention of each wounded person in continuous time, as well as the location distribution and electromagnetic interference index of the wounded persons; and to determine the current output priority based on the wounded person's priority index and initial severity level. The output module is used to classify and output data based on the priority of the wounded.

2. The IoT-based cluster monitoring system for vital signs of wounded patients in a makeshift hospital according to claim 1, characterized in that, The method for obtaining the deviation includes: For any vital sign of each wounded soldier, the difference between the data value of that vital sign at each moment and the previous moment is normalized and used as the degree of change at each moment. The difference between the data value of this vital sign at each moment and the expected standard value is used as the numerical difference degree at each moment; The product of the degree of change and the degree of numerical difference at each time point is normalized to obtain the deviation of the vital sign at each time point.

3. The IoT-based cluster monitoring system for vital signs of wounded patients in a makeshift hospital as described in claim 1, characterized in that, The method for obtaining the abnormal deviation includes: For each injured person, the mean of the deviation of all vital signs at each time point is used as the abnormality significance at each time point; the variance of the deviation of all vital signs at each time point is negatively correlated to obtain the abnormality synchronization at each time point; the product of the abnormality significance and the abnormality synchronization at each time point is used as the abnormality assessment index at each time point. The product of the anomaly assessment index at each time step and the initial severity level is normalized to obtain the anomaly deviation at each time step.

4. The IoT-based cluster monitoring system for vital signs of wounded patients in a makeshift hospital as described in claim 1, characterized in that, The method for obtaining the abnormal moment includes: The moment when the abnormal deviation exceeds the preset abnormal threshold is defined as an abnormal moment.

5. The IoT-based cluster monitoring system for vital signs of wounded patients in a makeshift hospital according to claim 1, characterized in that, The method for obtaining the anomaly correlation includes: For any wounded soldier, based on the initial severity level and case history, identify similar wounded soldiers; sequentially, use each vital sign as the analysis sign, and at the abnormal moments before the current moment, obtain the correlation between the data values ​​of the wounded soldier and each similar wounded soldier on the analysis sign, and use the average correlation with all similar wounded soldiers on the analysis sign as the abnormality similarity of the wounded soldier on the analysis sign. At non-abnormal moments before the current moment, after obtaining the correlation between the injured person and each similar injured person in terms of analyzed vital signs, the average correlation of the data values ​​of the injured person with all similar injured persons in terms of analyzed vital signs is used as the normal approximation of the injured person in terms of analyzed vital signs. The product of the normal approximation and abnormal approximation of the patient's physical signs in the analysis is taken as the abnormal correlation degree of the patient's physical signs in the analysis. The mean of the abnormal correlations of all vital signs for the injured person is taken as the abnormal correlation of the injured person.

6. The IoT-based cluster monitoring system for vital signs of wounded patients in a makeshift hospital according to claim 1, characterized in that, The method for obtaining the electromagnetic interference index includes: For any wounded soldier, combine the consecutive abnormal moments of the wounded soldier before the current moment to obtain the abnormal time period; normalize the product of the average duration of all abnormal time periods after negative correlation mapping and the total number of abnormal time periods to obtain the abnormal random index of the wounded soldier. At each abnormal moment of the injured person, the number of other injured persons in the vicinity of the injured person's preset location is obtained as the abnormal range index of the injured person at each abnormal moment; the sum of the abnormal range indexes of the injured person at all abnormal moments is normalized to obtain the group abnormal characteristic index of the injured person at the current moment. The electromagnetic interference index of the injured person at the current moment is obtained by normalizing the product of the negative correlation mapping value of the abnormal correlation of the injured person, the group abnormal characteristic index, and the abnormal random index.

7. The IoT-based cluster monitoring system for vital signs of wounded patients in a makeshift hospital according to claim 1, characterized in that, The methods for obtaining the focus on urgency include: For any wounded person, obtain the interval between adjacent historical treatment periods before the current moment, normalize the product of the mean of all intervals after negative correlation mapping and the total number of intervals, and obtain the urgency of attention for the wounded person. When the interval period is not available, the average of the abnormal deviations of all abnormal moments of the injured person before the current moment is taken as the urgency of the injured person's attention.

8. The IoT-based cluster monitoring system for vital signs of wounded patients in a makeshift hospital according to claim 1, characterized in that, The method for obtaining the priority index includes: For any wounded person, calculate the difference between the data values ​​of each vital sign of the wounded person at the current time and the previous time, and then take the average of the differences of the data values ​​of all vital signs as the abnormal increase rate at the current time; take the difference between the abnormal increase rate at the current time and the previous time as the abnormal attention indicator at the current time. The distance between the injured person's current location and the center of the makeshift hospital was normalized and used as a distance monitoring indicator. The current priority index of the injured person is obtained by multiplying the electromagnetic interference index of the injured person after negative correlation mapping, the urgency of attention, the abnormal attention index and the distance attention index, and then normalizing the result.

9. The IoT-based cluster monitoring system for vital signs of wounded patients in a makeshift hospital according to claim 1, characterized in that, The method for obtaining the output priority includes: The product of the priority index of each wounded soldier and the corresponding initial severity level is used as the level adjustment degree; the sum of the initial severity level and the level adjustment degree is normalized and used as the output priority of each wounded soldier.

10. The IoT-based cluster monitoring system for vital signs of wounded patients in a makeshift hospital according to claim 1, characterized in that, The hierarchical output based on the output priority of the wounded includes: The information of the wounded is sorted and output in descending order of output priority. When the priority output degree is greater than or equal to the preset high priority threshold, all information of the corresponding wounded is output. When the priority output degree is greater than the preset low priority threshold and less than the preset high priority threshold, the key information of the corresponding wounded person will be output. When the priority output degree is less than or equal to the preset low priority threshold, the basic information of the corresponding wounded person will be output; the preset low priority threshold is less than the preset high priority threshold.

Images