Accompanying emergency treatment vital sign real-time monitoring system based on AI early warning

Abstract

The invention discloses an accompanying emergency treatment vital sign real-time monitoring system based on AI early warning, and belongs to the technical field of vital sign real-time monitoring. The multi-parameter vital sign sensor is used for detecting vital sign parameters of an emergency patient in real time; collecting vital sign parameters of an emergency patient and performing anomaly analysis to obtain corresponding abnormal sign parameters; obtaining abnormal sign parameters of an emergency patient, associating the abnormal sign parameters with local time, and generating an abnormal sign trend curve of each dimension by establishing a multi-dimensional rectangular coordinate system; performing risk analysis on any single abnormal sign trend curve to obtain risk change levels of single abnormal signs, including low risk, medium risk or high risk; and receiving a single abnormal sign risk change level, carrying out comprehensive early warning analysis in combination with the superposition influence of the multi-dimensional abnormal signs, generating a graded early warning signal, and realizing multi-terminal real-time pushing.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of real-time monitoring of vital signs, and particularly relates to a real-time monitoring system for emergency vital signs based on AI early warning. BACKGROUND

[0002] The core of emergency medical treatment is the rapid and accurate assessment and intervention of patients with severe and rapidly changing conditions, and real-time monitoring of vital signs (heart rate, blood pressure, etc.) is a key support. Especially in the scenes of ambulatory emergency such as ambulance transport and outdoor first aid, the patient's condition fluctuates violently, and the treatment environment is complex, so the real-time, accuracy and early warning ability of monitoring are required higher.

[0003] The existing ambulatory emergency monitoring relies on traditional multi-parameter equipment, which can collect basic data, but has significant defects: abnormal identification depends on manual observation by medical staff, which is easy to miss due to limited energy, and the reaction is lagging, which is easy to miss the golden treatment time; lack of time dimension and trend analysis of abnormal signs, unable to predict the development of the disease; only rely on single parameter threshold alarm, without considering the synergistic effect of multiple dimensions, the early warning accuracy is low, and the early warning information transmission is not timely.

[0004] In summary, the existing technology cannot meet the needs of ambulatory emergency, and the development of a real-time monitoring system for emergency vital signs based on AI early warning has become a key breakthrough direction to improve the efficiency and quality of treatment. SUMMARY

[0005] The purpose of the present application is to overcome the shortcomings of the prior art and provide a real-time monitoring system for emergency vital signs based on AI early warning to solve the problems raised in the background.

[0006] The purpose of the present application can be achieved by the following technical solution: a real-time monitoring system for emergency vital signs based on AI early warning, comprising: A vital sign sensing module comprising a multi-parameter vital sign sensor; the multi-parameter vital sign sensor is used for real-time detection of vital sign parameters of emergency patients; A vital sign abnormality analysis module for collecting vital sign parameters of emergency patients and performing abnormality analysis to obtain corresponding abnormal sign parameters; A vital sign risk change evaluation module for obtaining abnormal sign parameters of emergency patients and associating with local time, generating abnormal sign trend curves of each dimension by establishing a multi-dimensional rectangular coordinate system; performing risk analysis on any single abnormal sign trend curve to obtain the risk change level of the single abnormal sign, including low risk, medium risk or high risk; A monitoring and early warning module for receiving the risk change level of the single abnormal sign, performing comprehensive early warning analysis combined with the superimposed effect of multi-dimensional abnormal signs, generating a graded early warning signal and realizing multi-end real-time pushing.

[0007] Preferably, the vital sign parameters include heart rate, blood oxygen saturation, blood pressure, body temperature and respiratory rate.

[0008] Preferably, the process of acquiring abnormal vital sign parameters comprises: acquiring any single vital sign parameter of the emergency patient and comparing it with the corresponding preset standard threshold range to obtain a corresponding judgment mark; if the corresponding single vital sign parameter is within the preset standard threshold range, the judgment mark of the single vital sign parameter is set to 0; otherwise, the judgment mark of the single vital sign parameter is set to 1.

[0009] Preferably, it further comprises: traversing and analyzing the judgment marks of the corresponding vital sign parameters of the emergency patient, if there is no element with a value of 1, it indicates that the current vital sign of the emergency patient is normal; if there is an element with a value of 1, it indicates that the current vital sign of the emergency patient is abnormal, and the single vital sign parameter with a value of 1 is acquired as the abnormal vital sign parameter.

[0010] Preferably, the method for acquiring the risk change level result of the single abnormal vital sign is as follows: record the abnormal vital sign parameters of the patient in real time with local time as the node; construct an abnormal vital sign trend curve, establish a multi-dimensional rectangular coordinate system with time as the X-axis and each abnormal vital sign parameter as the Y-axis, and record the collected abnormal vital sign parameters in the multi-dimensional rectangular coordinate system to obtain the abnormal vital sign trend curve of each dimension of the emergency patient; acquire any single abnormal vital sign trend curve in the abnormal vital sign trend curve, denoted as a target trend curve; linearly fit the target trend curve to obtain a target vital sign change function.

[0011] Preferably, it further comprises: acquire the coordinate value corresponding to each data point in the target trend curve, denoted as ( , ); wherein, represents the time of the i-th data point, represents the value of the single abnormal vital sign parameter corresponding to the time, i=1, 2, 3,..., n; n is the total number of data points; acquire adjacent two data points and denote them as a risk change interval; acquire the risk change slope of the curve corresponding to each risk change interval through the formula ; wherein, Km represents the risk change slope of the m-th risk change interval, 1≤m≤n-1, and m is a positive integer; A risk assessment model is established, using the obtained risk change slope as input data and the output data as the risk value of the corresponding single abnormal symptom.

[0012] Preferably, the expression of the risk assessment model is as follows: ; In the formula, FX(Km) is the risk value of a single abnormal sign corresponding to each risk change interval, B1 and B2 are the risk change slope thresholds of different single abnormal signs, and B1 < B2.

[0013] Preferably, determining the risk change level of a corresponding single abnormal physical sign includes: Based on the risk assessment model, the risk change level of a single abnormal sign is determined by comprehensively judging the risk value of a single abnormal sign corresponding to multiple risk change intervals; Obtain the corresponding risk change level for a single abnormal vital sign; If at least one risk change interval has an FX(Km) of 3, the risk change level of the single abnormal sign is determined to be high risk; if all risk change intervals have an FX(Km) of 1, the risk change level of the single abnormal sign is determined to be low risk. Conversely, the risk level of the single abnormal physical sign is determined to be medium risk.

[0014] Preferably, the specific implementation details of the AI ​​monitoring and early warning module include: Risk level for accepting a single abnormal physical sign; Based on abnormal vital signs parameters, calculate the comprehensive risk value of the current vital signs of emergency patients; The formula for calculating the overall risk value is as follows: ; In the formula, ZX is the comprehensive risk value, YCj is the score corresponding to different individual abnormal signs risk levels, j is different abnormal sign parameters, j=1,2,3,...,M, and M is the number of abnormal signs; low risk corresponds to a score of 1, medium risk corresponds to a score of 3, and high risk corresponds to a score of 5; 1+0.2×(M-1) is the quantity correction coefficient; wj is the corresponding weight coefficient.

[0015] Preferably, it further includes: Based on the comprehensive risk value, the warning level thresholds A1 and A2 are determined, and a three-level warning signal is generated. If the calculated comprehensive risk value ZX < A1, it is determined to be a Level 1 warning and a prompt warning signal is generated, including a mobile pop-up prompt and a low-volume voice broadcast. The prompt content includes the type of abnormal signs and the current risk level. If A1≤ZX<A2, it is determined to be a Level II warning and an alarm warning signal is generated, including high-volume voice broadcast, terminal light flashing, continuous pop-up prompts, and simultaneous push of key node data of abnormal vital signs trend curve; If ZX≥A2, it is determined to be a Level 3 warning, and an emergency warning signal is generated, including a high-volume looping voice broadcast and terminal light flashing, and is synchronized to the hospital emergency command center platform to ensure that medical staff can respond immediately.

[0016] Compared to existing solutions, the beneficial effects achieved by this invention are: This invention achieves synchronous real-time capture of core vital signs such as heart rate, blood oxygen, and blood pressure through multi-parameter sensors, solving the problems of data fragmentation and delayed updates in existing technologies, and providing a complete vital sign data stream for key scenarios such as pre-hospital transport of emergency patients. This invention transforms discrete abnormal parameters into visual trend curves through time correlation and multidimensional coordinate system modeling, enabling predictive analysis of the deterioration trend of vital signs. In particular, the classification of individual risk levels further quantifies the degree of risk, allowing medical staff to perceive the evolution trajectory of low, medium and high risks in advance, and avoid passive response when emergencies occur. This invention comprehensively assesses the synergistic effects of multiple abnormal signs, and the graded early warning signals are more closely aligned with the patient's actual condition. This reduces the waste of medical resources caused by excessive early warnings, avoids the omission of key risks, and the real-time push function breaks down information barriers between pre-hospital and in-hospital care, and between medical staff and the command system. It enables the synchronous flow of treatment instructions and patient vital sign data, helping medical teams to develop personalized treatment plans in advance and improving overall treatment efficiency and success rate. Attached Figure Description

[0017] The invention will now be further described with reference to the accompanying drawings.

[0018] Figure 1 This is a module structure diagram of an AI-based early warning system for real-time monitoring of vital signs in emergency patients, as proposed in this invention. Detailed Implementation

[0019] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments.

[0020] like Figure 1 As shown, this invention is an AI-based early warning system for real-time monitoring of vital signs in accompanying emergency patients, comprising: The vital signs sensing module includes a multi-parameter vital signs sensor; the multi-parameter vital signs sensor is used to detect the vital signs parameters of emergency patients in real time; wherein, the vital signs parameters include heart rate, blood oxygen saturation, blood pressure, body temperature and respiratory rate; The vital signs abnormality analysis module is used to collect vital sign parameters of emergency patients and perform abnormality analysis to obtain the corresponding abnormal sign parameters; It should be further explained that the process of obtaining abnormal vital sign parameters includes: Obtain any single vital sign parameter from the vital sign parameters of an emergency patient, compare it with the corresponding preset standard threshold range, and obtain the corresponding judgment label; If the corresponding single vital sign parameter is within the preset standard threshold range, the judgment flag of the single vital sign parameter is set to 0; otherwise, the judgment flag of the single vital sign parameter is set to 1. The preset standard threshold range is determined based on the statistical analysis of historical emergency clinical data of the corresponding vital sign type and is the normal physiological critical range of the vital sign. The judgment markers of the corresponding vital signs parameters of emergency patients are traversed and analyzed. If there is no element with a value of 1, it means that the current vital signs of the emergency patient are normal. If there is an element with a value of 1, it indicates that the patient's vital signs are abnormal. The single vital sign parameter with a value of 1 for the corresponding element is the abnormal vital sign parameter.

[0021] The vital signs risk change assessment module is used to acquire abnormal vital sign parameters of emergency patients and associate them with local time. By establishing a multidimensional rectangular coordinate system, it generates abnormal vital sign trend curves in various dimensions. Risk analysis is performed on any single abnormal vital sign trend curve to obtain the risk change level of the single abnormal vital sign, including low risk, medium risk, or high risk. It should be further explained that the method for obtaining the risk change level results of a single abnormal vital sign is as follows: Record the patient's abnormal vital signs parameters in real time, using local time as the node; Construct abnormal sign trend curves, establish a multidimensional rectangular coordinate system with time as the X-axis and each abnormal sign parameter as the Y-axis, and record the collected abnormal sign parameters into this multidimensional rectangular coordinate system to obtain the abnormal sign trend curves of emergency patients in each dimension; Obtain any single abnormal sign trend curve from the abnormal sign trend curves, and denote it as the target trend curve; perform linear fitting on the target trend curve to obtain the target sign change function F(x); Obtain the coordinate values ​​corresponding to each data point in the target trend curve, denoted as ( , );in, This represents the time of the i-th data point. Represents the value of a single abnormal vital sign parameter at the corresponding time, i=1,2,3,...,n; n is the total number of data points; Obtain two adjacent data points and record them as the risk change interval; Through formula Obtain the slope of the risk change curve corresponding to each risk change interval; where Km represents the slope of the risk change in the m-th risk change interval, 1≤m≤n-1, and m is a positive integer; Establish a risk assessment model, using the obtained risk change slope as input data and outputting the risk value of the corresponding single abnormal sign; The expression for the risk assessment model is as follows: ; In the formula, FX(Km) is the risk value of a single abnormal sign corresponding to each risk change interval, B1 and B2 are the risk change slope thresholds for different single abnormal signs, and B1 < B2. The specific values ​​are determined according to the sign type, clinical criteria and historical emergency data risk change rate data. Based on the risk assessment model, the risk change level of a single abnormal sign is determined by comprehensively judging the risk value of a single abnormal sign corresponding to multiple risk change intervals; Obtain the corresponding risk change level for a single abnormal vital sign; If at least one risk change interval has an FX(Km) of 3, the risk change level of the single abnormal sign is determined to be high risk; if all risk change intervals have an FX(Km) of 1, the risk change level of the single abnormal sign is determined to be low risk. Conversely, the risk level of the single abnormal physical sign is determined to be medium risk.

[0022] The monitoring and early warning module is used to receive the risk level of a single abnormal physical sign, combine the superimposed effects of multiple abnormal physical signs to conduct a comprehensive early warning analysis, generate graded early warning signals, and realize real-time push to multiple terminals.

[0023] It should be further explained that the specific implementation details of the AI ​​monitoring and early warning module include: Accept the risk change level of a single abnormal sign; calculate the comprehensive risk value of the current vital signs of emergency patients based on the abnormal sign parameters; The formula for calculating the overall risk value is as follows: ; In the formula, ZX is the comprehensive risk value, YCj is the score corresponding to different risk levels of individual abnormal signs, j is different abnormal sign parameters, j=1,2,3,...,M, and M is the number of abnormal signs; where low risk corresponds to a score of 1, medium risk corresponds to a score of 3, and high risk corresponds to a score of 5; 1+0.2×(M-1) is the quantity correction coefficient, used to represent the risk amplification effect of multiple abnormal signs superimposed; wj is the corresponding weight coefficient, the specific value of which is determined according to the clinical emergency priority of the corresponding signs, for example, the weight of heart rate and blood oxygen saturation is higher than that of body temperature and respiratory rate, and in combination with historical case data; Based on the comprehensive risk value, warning level thresholds A1 and A2 are defined to generate a three-level warning signal; where A1 < A2, the specific values ​​are set by experts in the field through big data experiments; If the calculated comprehensive risk value ZX < A1, it is determined to be a Level 1 warning and a prompt warning signal is generated, including a mobile pop-up prompt and a low-volume voice broadcast. The prompt content includes the type of abnormal signs and the current risk level. If A1≤ZX<A2, it is determined to be a Level II warning and an alert warning signal is generated, including high-volume voice broadcast, terminal light flashing (yellow), continuous pop-up prompts, and simultaneous push of key node data of abnormal vital signs trend curve; If ZX≥A2, it is determined to be a Level 3 warning, and an emergency warning signal is generated, including a high-volume looping voice broadcast and terminal light flashing, and is synchronized to the hospital emergency command center platform to ensure that medical staff can respond immediately.

[0024] In the several embodiments provided by this invention, it should be understood that the disclosed system can be implemented in other ways. For example, the embodiments of the invention described above are merely illustrative; for example, the division of modules is only a logical functional division, and there may be other division methods in actual implementation.

[0025] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0026] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0027] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0028] Finally, 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 it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A real-time monitoring system for vital signs in an emergency room based on AI-based early warning, characterized in that, include: The vital signs sensing module includes a multi-parameter vital signs sensor; the multi-parameter vital signs sensor is used to detect the vital signs parameters of emergency patients in real time. The vital signs abnormality analysis module is used to collect vital sign parameters of emergency patients and perform abnormality analysis to obtain the corresponding abnormal sign parameters; The vital signs risk change assessment module is used to acquire abnormal vital sign parameters of emergency patients and associate them with local time. By establishing a multidimensional rectangular coordinate system, it generates abnormal vital sign trend curves in various dimensions. Risk analysis is performed on any single abnormal vital sign trend curve to obtain the risk change level of the single abnormal vital sign, including low risk, medium risk, or high risk. The monitoring and early warning module is used to receive the risk level of a single abnormal physical sign, combine the superimposed effects of multiple abnormal physical signs to conduct a comprehensive early warning analysis, generate graded early warning signals, and realize real-time push to multiple terminals.

2. The AI-based early warning real-time monitoring system for vital signs in an emergency room according to claim 1, characterized in that, The vital signs parameters include heart rate, blood oxygen saturation, blood pressure, body temperature, and respiratory rate.

3. The AI-based early warning real-time monitoring system for vital signs in an emergency room according to claim 1, characterized in that, The process of obtaining abnormal vital sign parameters includes: Obtain any single vital sign parameter from the vital sign parameters of an emergency patient, compare it with the corresponding preset standard threshold range, and obtain the corresponding judgment label; If the corresponding vital sign parameter is within the preset standard threshold range, the judgment flag of the vital sign parameter is set to 0; otherwise, the judgment flag of the vital sign parameter is set to 1.

4. The AI-based early warning real-time monitoring system for accompanying emergency vital signs according to claim 3, characterized in that, Also includes: The judgment markers of the corresponding vital signs parameters of emergency patients are traversed and analyzed. If there is no element with a value of 1, it means that the current vital signs of the emergency patient are normal. If there is an element with a value of 1, it indicates that the patient's vital signs are abnormal. The single vital sign parameter with a value of 1 for the corresponding element is the abnormal vital sign parameter.

5. The AI-based early warning real-time monitoring system for accompanying emergency vital signs according to claim 4, characterized in that, The method for obtaining the risk change level results of a single abnormal vital sign is as follows: Record the patient's abnormal vital signs parameters in real time, using local time as the node; Construct abnormal sign trend curves, establish a multidimensional rectangular coordinate system with time as the X-axis and each abnormal sign parameter as the Y-axis, and record the collected abnormal sign parameters into this multidimensional rectangular coordinate system to obtain the abnormal sign trend curves of emergency patients in each dimension; Obtain any single abnormal sign trend curve from the abnormal sign trend curves, and denote it as the target trend curve; Linear fitting is performed on the target trend curve to obtain the target vital sign change function.

6. The AI-based early warning real-time monitoring system for accompanying emergency vital signs according to claim 5, characterized in that, Also includes: Obtain the coordinate values ​​corresponding to each data point in the target trend curve, denoted as ( , );in, This represents the time of the i-th data point. Represents the value of a single abnormal vital sign parameter at the corresponding time, i=1,2,3,...,n; n is the total number of data points; Obtain two adjacent data points and record them as the risk change interval; Through formula Obtain the slope of the risk change curve corresponding to each risk change interval; where Km represents the slope of the risk change in the m-th risk change interval, 1≤m≤n-1, and m is a positive integer; A risk assessment model is established, using the obtained risk change slope as input data and the output data as the risk value of the corresponding single abnormal symptom.

7. The AI-based early warning real-time monitoring system for accompanying emergency vital signs according to claim 6, characterized in that, The expression for the risk assessment model is as follows: ； In the formula, FX(Km) is the risk value of a single abnormal sign corresponding to each risk change interval, B1 and B2 are the risk change slope thresholds of different single abnormal signs, and B1 < B2.

8. The AI-based early warning real-time monitoring system for accompanying emergency vital signs according to claim 7, characterized in that, Determine the risk level of a single abnormal physical sign, including: Based on the risk assessment model, the risk change level of a single abnormal sign is determined by comprehensively judging the risk value of a single abnormal sign corresponding to multiple risk change intervals; Obtain the corresponding risk change level for a single abnormal vital sign; If at least one risk change interval has an FX(Km) of 3, the risk change level of the single abnormal sign is determined to be high risk; if all risk change intervals have an FX(Km) of 1, the risk change level of the single abnormal sign is determined to be low risk. Conversely, the risk level of the single abnormal physical sign is determined to be medium risk.

9. The AI-based early warning real-time monitoring system for accompanying emergency vital signs according to claim 1, characterized in that, The specific implementation details of the AI ​​monitoring and early warning module include: Risk level for accepting a single abnormal physical sign; Based on abnormal vital signs parameters, calculate the comprehensive risk value of the current vital signs of emergency patients; The formula for calculating the overall risk value is as follows: ； In the formula, ZX is the comprehensive risk value, YCj is the score corresponding to different individual abnormal signs risk levels, j is different abnormal sign parameters, j=1,2,3,...,M, and M is the number of abnormal signs; low risk corresponds to a score of 1, medium risk corresponds to a score of 3, and high risk corresponds to a score of 5; 1+0.2×(M-1) is the quantity correction coefficient; wj is the corresponding weight coefficient.

10. A real-time monitoring system for accompanying emergency vital signs based on AI early warning, as described in claim 9, is characterized in that, Also includes: Based on the comprehensive risk value, the warning level thresholds A1 and A2 are determined, and a three-level warning signal is generated. If the calculated comprehensive risk value ZX < A1, it is determined to be a Level 1 warning and a prompt warning signal is generated, including a mobile pop-up prompt and a low-volume voice broadcast. The prompt content includes the type of abnormal signs and the current risk level. If A1≤ZX<A2, it is determined to be a Level II warning and an alarm warning signal is generated, including high-volume voice broadcast, terminal light flashing, continuous pop-up prompts, and simultaneous push of key node data of abnormal vital signs trend curve; If ZX≥A2, it is determined to be a Level 3 warning, and an emergency warning signal is generated, including a high-volume looping voice broadcast and terminal light flashing, and is synchronized to the hospital emergency command center platform to ensure that medical staff can respond immediately.

Images