Intensive care unit patient early warning method and system based on clinical data

Abstract

The invention discloses an intensive care unit patient early warning method and system based on clinical data, and belongs to the technical field of medical monitoring, and the method comprises the steps: medical staff carries out the setting of a two-dimensional grading system for an intensive care unit patient, and collects the input information data and monitoring data of the patient; constructing a risk factor joint model to evaluate the multi-dimensional potential crisis of the patient in the intensive care unit, giving out early warning according to the evaluation result of the risk factor joint model, and adjusting the severity level and the monitoring level of the patient; key physiological parameters of the patient are calculated in real time, the threshold value is corrected, the corrected threshold value serves as a new threshold value to be written into a database of the risk joint model, and the new threshold value is synchronized to a monitoring terminal through a timestamp. Potential medical risks are effectively reduced, the survival rate of the patient is improved, early warning is given out in time, the monitoring level is optimized, implementation of targeted medical services is ensured, the situation changes of the patient are rapidly recognized, the safety and efficiency of critical care are improved, and powerful technical support is provided for the patient.

Description

Technical Field

[0001] The present invention belongs to the technical field of medical monitoring, and in particular relates to an intensive care unit patient early warning method and system based on clinical data. Background Art

[0002] In the management of the intensive care unit (ICU), the monitoring of patients' vital signs and the assessment of their condition are crucial. With the continuous advancement of medical technology, clinical monitoring methods are gradually developing in the direction of real-time and refinement. The traditional intensive care model mainly relies on medical staff to regularly evaluate and observe patients' vital signs, implement independent monitoring points and fail to comprehensively consider multi-dimensional data. In recent years, the rise of data science and machine learning has made it possible to improve early warning capabilities by analyzing large-scale clinical data. Current technologies such as smart monitoring devices, electronic health records, remote monitoring systems, and algorithmic prediction models have enhanced the timeliness and accuracy of monitoring to a certain extent. However, these technologies still face many challenges, including the diversity and complexity of data, the impact of individual differences among patients, and the adaptability and reliability of decision-making models.

[0003] The deficiencies of existing technologies in early warning are mainly reflected in the following aspects: First, traditional vital signs monitoring usually lacks multi-dimensional analysis of patients' potential crises, and can often only rely on changes in a single vital sign to judge the progression of the disease. This single-dimensional assessment can easily lead to missed diagnoses or misjudgments, especially in complex conditions. Secondly, the existing monitoring system fails to fully combine the patient's genetic information and past medical history for a comprehensive assessment, ignoring the important impact of individual patient differences on the progression of the disease. In addition, the data obtained from real-time monitoring is often massive, and how to effectively extract key features and provide real-time feedback is still a problem that needs to be solved. Such deficiencies limit the efficiency and accuracy of nursing staff in patient risk assessment and intervention decisions. Summary of the invention

[0004] In view of the above existing problems, the technical problem solved by the present invention is: how to achieve real-time early warning and dynamic monitoring of patients in the intensive care unit based on clinical data to improve the accuracy and timeliness of patient management. Specifically, the present invention evaluates patients through a two-dimensional grading system, combines genetic information, chronic disease history and real-time monitoring data, and constructs a multi-dimensional risk assessment model, thereby achieving timely early warning of potential crises of patients and dynamic adjustment of monitoring levels.

[0005] In order to solve the above technical problems, an early warning method for ICU patients based on clinical data is proposed, including: Medical staff set up a two-dimensional grading system for patients in the ICU and collect the patients' input information data and monitoring data; combine the input information data and monitoring data, extract data features, and build a risk factor joint model to evaluate the multi-dimensional potential crises of patients in the ICU, issue warnings based on the evaluation results of the risk factor joint model, and adjust the patient's severity level and monitoring level; calculate the patient's key physiological parameters in real time, establish a dynamic coupling index within the time window by collecting key physiological parameters in clinical monitoring data, adjust the dynamic weight ratio between parameters, and correct the baseline threshold. The corrected baseline threshold will be written into the database of the risk factor joint model as a new threshold and synchronized to all monitoring terminals through timestamps.

[0006] As a preferred embodiment of the ICU patient early warning method based on clinical data described in the present invention, the two-dimensional grading system includes that the medical staff performs two-dimensional grading on the patient after the patient enters the ICU, establishes a severity classification based on the patient's initial vital signs and the degree of organ failure, and marks the patient as red when any of the symptoms of multiple organ failure, need for continuous organ support, and positive genetic risk markers are present; When there is any symptom of single organ failure, potential decompensation and need for intermittent organ support, it is marked as yellow level; When there is any symptom of unstable vital signs but not reaching the failure standard, high-risk genetics or chronic disease history, it is marked as green level; At the same time, it forms an orthogonal relationship with the severity level, and dynamically calibrates the monitoring level through real-time monitoring of data streams.

[0007] As a preferred solution of the intensive care unit patient early warning method based on clinical data described in the present invention, the information data and monitoring data include: The information data includes genetic information and chronic disease history entered by the patient before entering the intensive care unit; The monitoring data include clinical monitoring data and intensive care unit-specific monitoring data.

[0008] As a preferred embodiment of the intensive care unit patient early warning method based on clinical data described in the present invention, the risk factor joint model includes setting a comprehensive score of the patient's genetic information, a rating of the chronic disease history, and a comprehensive value of the bed monitoring data from the patient's genetic information, chronic disease history, and clinical monitoring data. The comprehensive score of the patient's genetic information and the rating of the chronic disease history are both scored by medical staff before the patient is admitted to the intensive care unit, and the comprehensive value is obtained by performing time series analysis on the clinical monitoring data.

[0009] As a preferred embodiment of the intensive care unit patient early warning method based on clinical data described in the present invention, the risk factor joint model also includes, based on the set comprehensive score of the patient's genetic information, the rating of chronic disease history and the comprehensive value of clinical monitoring data, a multi-dimensional evaluation is performed to construct a basic risk score, and the final risk score is calculated in combination with the clinical cycle.

[0010] As a preferred embodiment of the ICU patient early warning method based on clinical data described in the present invention, the early warning according to the evaluation result of the risk factor joint model includes setting a first baseline threshold, a second baseline threshold and a third baseline threshold, and issuing an early warning signal according to the final risk score. When the final risk score is less than the first baseline threshold, it is normal; When the first baseline threshold ≤ the final risk score < the second baseline threshold, it is a caution signal, and the medical staff is notified immediately to check and determine whether there is a worsening trend. If the medical staff determines that there is a worsening trend, it is changed to a critical signal and rescue measures are immediately taken. After the rescue is completed, the monitoring level is increased according to the patient's current condition. If the medical staff determines that there is no worsening trend, the signal is stopped, normal monitoring is resumed, and the current monitoring level is maintained; When the second baseline threshold ≤ the final risk score < the third baseline threshold, it is a warning signal, and the medical staff is notified immediately to evaluate the patient's chronic medical history and potential risks, re-evaluate the treatment plan based on the known patient's condition, consider adjusting the drug dosage or treatment method, and prepare rescue measures. When the patient is treated and the current condition is stable, the severity level and monitoring level are increased; When the final risk score is ≥ the third baseline threshold, it is a critical signal, and medical staff will be notified immediately to take rescue measures, while the severity level and monitoring level will be increased. When the patient's condition improves, medical staff will be allowed to downgrade through the visual interface.

[0011] As a preferred solution of the ICU patient early warning method based on clinical data described in the present invention, wherein: the correction threshold includes establishing a dynamic coupling index within a time window by collecting key physiological parameters in clinical monitoring data; The coupling index is input into the sliding window difference analyzer to adjust the dynamic weight ratio between the parameters. The dynamic weight ratio is input into the differential regulator to generate the baseline threshold adjustment amount. The baseline threshold adjustment amount is coupled with the three baseline thresholds output by the risk assessment model to correct the baseline threshold. The corrected threshold will be written into the database of the risk factor joint model as a new baseline and synchronized to all monitoring terminals through timestamps.

[0012] Another object of the present invention is to provide an intensive care unit patient early warning system based on clinical data. The present invention solves how to achieve real-time early warning and dynamic adjustment of patients by comprehensively analyzing the clinical data of intensive care unit patients to improve monitoring effects and response speed, aiming to provide accurate decision-making support for medical staff, thereby improving the clinical outcomes of critically ill patients.

[0013] As a preferred solution of the intensive care unit patient early warning system based on clinical data described in the present invention, it is characterized by comprising a rating module, a data acquisition module, an early warning module, and a correction module; The rating module allows medical staff to set up a two-dimensional grading system for ICU patients; The data acquisition module is responsible for collecting input information data and monitoring data, including genetic information and chronic disease history recorded before the patient enters the ICU, and physiological parameters monitored in real time in the ICU; The early warning module combines the patient's input information data and monitoring data, uses the risk factor joint model to conduct a multi-dimensional assessment of the patient, calculates the basic risk score by extracting features, and issues an early warning signal based on the assessment results; The correction module is responsible for real-time calculation and dynamic adjustment of the thresholds of the patient's key physiological parameters, by establishing a dynamic coupling index, adjusting the weight ratio between parameters, correcting the thresholds, and synchronizing the corrected baseline thresholds to all monitoring terminals.

[0014] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and is characterized in that when the processor executes the computer program, the steps of the intensive care unit patient early warning method based on clinical data are implemented.

[0015] 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 intensive care unit patient early warning method based on clinical data are implemented.

[0016] Beneficial effects of the present invention: By setting up a two-dimensional grading system, the present invention enables medical staff to comprehensively evaluate the vital signs and organ functions of patients in the intensive care unit, thereby effectively reducing potential medical risks and improving the survival rate of patients. The risk factor joint model constructed by combining genetic information, chronic disease history and monitoring data can issue early warnings in a timely manner, optimize the monitoring level, ensure the implementation of targeted medical services, and achieve rapid identification of changes in patient conditions. Further real-time calculation of the dynamic coupling index of key physiological parameters and adjustment of monitoring thresholds can make the monitoring plan more personalized and detect potential crises in a timely manner, ultimately significantly improving the safety and efficiency of critical care and providing strong technical support for patients. 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 those skilled in the art, other drawings can be obtained based on these drawings without creative work, among which: Figure 1 An overall flow chart of an intensive care unit patient early warning method based on clinical data provided by one embodiment of the present invention.

[0018] Figure 2 A system solution module diagram of an intensive care unit patient early warning system based on clinical data provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0019] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0020] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and 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.

[0021] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it an embodiment that is mutually exclusive with other embodiments, either individually or selectively.

[0022] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0023] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, which are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0024] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0025] Example 1, reference Figure 1 , which is the first embodiment of the present invention, provides an intensive care unit patient early warning method based on clinical data, comprising: S1: Medical staff set up a two-dimensional grading system for patients in the intensive care unit and collected patients' input information data and monitoring data.

[0026] It should be noted that medical staff perform a two-dimensional classification on patients after they enter the intensive care unit, establishing a severity classification based on the patient's initial vital signs and the degree of organ failure. If there is any symptom of multiple organ failure, the need for continuous organ support, or a positive genetic risk marker, the patient is marked as red. When there is any symptom of single organ failure, potential decompensation and need for intermittent organ support, it is marked as yellow level; When there is any symptom of unstable vital signs but not reaching the failure standard, high-risk genetics or chronic disease history, it is marked as green level; At the same time, it forms an orthogonal relationship with the severity level, and dynamically calibrates the monitoring level through real-time monitoring of data streams, including using level I monitoring when marked as red level, real-time continuous monitoring, and using multi-device collaborative monitoring to collect all data; When the yellow level is indicated, level II monitoring is adopted, and the collected data is integrated and analyzed every 3 minutes; When marked as green, level III monitoring is adopted, and the collected data is integrated and analyzed at a low frequency of 5 minutes.

[0027] Furthermore, information data and monitoring data include, The information data includes genetic information and chronic disease history entered by the patient before entering the intensive care unit; Among them, genetic information includes genetic-related data such as whole genome sequencing data, drug metabolism-related gene loci, hereditary arrhythmia gene markers, and immune-related HLA typing data; chronic disease history includes past organ dysfunction index, long-term medication spectrum, metabolic syndrome-related factors, tumor history molecular typing data, and other past medication history and medical history; The monitoring data include clinical monitoring data and intensive care unit-specific monitoring data; The monitoring data include the six parameters of routine vital signs (heart rate, blood pressure, blood oxygen saturation, etc.) and core indicators of blood gas analysis as the benchmark items of Level III monitoring; the non-invasive cardiac output and dynamic lung compliance curve are added to Level II monitoring; the microcirculation perfusion parameters (sublingual microcirculation flow rate, vascular density, etc.) and dual-channel monitoring of cerebral oxygen saturation (rSO2) and ultrasound indicators of myocardial strain rate are added to Level I monitoring.

[0028] S2: Combine the input information data and monitoring data, extract data features, and build a joint risk factor model to evaluate the multi-dimensional potential crises of patients in the intensive care unit. According to the evaluation results of the joint risk factor model, issue an early warning and adjust the patient's severity level and monitoring level.

[0029] Furthermore, the patient's genetic information, chronic disease history, and clinical monitoring data are used to set A comprehensive score for the patient's genetic information. Rating of chronic disease history, is the comprehensive value of clinical monitoring data, and All patients were scored by medical staff before admission to the intensive care unit, and the comprehensive value was obtained by time series analysis of clinical monitoring data. : ; in, is the ith clinical monitoring data point, is the total number of clinical monitoring data points, i is the variable index, is the time value of the ith clinical monitoring data point, is the time derivative of the monitoring data.

[0030] Based on the comprehensive score of the patient's genetic information, the rating of chronic disease history and the comprehensive value of clinical monitoring data, a basic risk score is constructed through multi-dimensional evaluation: ; in, It indicates the basic risk value of the patient's potential crisis. , , Represents the weight of each factor, and the weight amplitude range is [1, 3], represents a complementary factor, such as other clinical interventions; is the time decay factor; Get the final risk score: ; in, For the final risk score, and is a constant that adjusts the amplitude of the nonlinear term and the periodic effect, For the clinical cycle.

[0031] It should be noted that the first baseline threshold is set , second baseline threshold and the third baseline threshold , issue a warning signal based on the final risk score. < When , it is normal; when ≤ < When the patient's condition worsens, the alarm is turned on, and the medical staff is notified to check and determine whether the condition is getting worse. If the medical staff determines that the condition is getting worse, the alarm is turned on, and emergency measures are taken immediately. After the emergency treatment is completed, the monitoring level is increased according to the patient's current condition. If the medical staff determines that the condition is not getting worse, the alarm stops sending signals, normal monitoring is resumed, and the current monitoring level is maintained. when ≤ < When the patient is diagnosed with a serious illness, it is a warning signal. Immediately notify medical staff to evaluate the patient's chronic medical history and potential risks, re-evaluate the treatment plan based on the known patient's condition, consider adjusting the drug dosage or treatment method, and prepare rescue measures. When the patient is treated and the current condition is stable, the severity level and monitoring level will be increased. , , They are 75 points, 90 points and 108 points respectively.

[0032] when ≥ When the patient's condition improves, the medical staff is allowed to downgrade the level through the visual interface. S3: Calculate the key physiological parameters of patients in real time. By collecting the key physiological parameters in the clinical monitoring data, establish the dynamic coupling index within the time window, adjust the dynamic weight ratio between the parameters, and correct the baseline threshold. The corrected baseline threshold will be written into the database of the risk factor joint model as a new threshold and synchronized to all monitoring terminals through timestamps.

[0033] Furthermore, by collecting key physiological parameters in clinical monitoring data, including patient heart rate, blood pressure, and blood oxygen saturation, a dynamic coupling index within a time window is established, the coupling index is input into a sliding window difference analyzer, the dynamic weight ratio between parameters is adjusted, and the dynamic weight ratio is input into a differential regulator to generate a baseline threshold adjustment amount. : ; in, is the dynamic weight ratio at the current moment, is the dynamic weight ratio of the previous moment, is the symbolic function, is the threshold value at the previous moment, The single adjustment shall not exceed 20%; Adjust the baseline threshold by The three baseline thresholds output by the risk assessment model are Perform coupling and baseline threshold correction: ; in, , is the updated threshold, include ,The revised threshold will be written into the database of the risk factor joint model as a new baseline and will be synchronized to all monitoring terminals through timestamps.

[0034] Embodiment 2, the second embodiment of the present invention, is different from the previous embodiment in that: If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0035] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0036] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0037] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0038] Example 3, reference Figure 2 , which is the third embodiment of the present invention, and which provides an intensive care unit patient warning system based on clinical data, including a rating module, a data acquisition module, a warning module, and a correction module; The rating module is responsible for setting up a two-dimensional grading system for ICU patients by medical staff; The data acquisition module is responsible for collecting and inputting the patient's clinical data, including genetic information and chronic disease history recorded before the patient enters the ICU, as well as physiological parameters monitored in real time in the ICU; The early warning module combines the patient's input information data and monitoring data, uses the risk factor joint model to conduct a multi-dimensional assessment of the patient, calculates the basic risk score by extracting features, and issues an early warning signal based on the assessment results; The correction module is responsible for real-time calculation and dynamic adjustment of the thresholds of the patient's key physiological parameters. It establishes a dynamic coupling index, adjusts the weight ratio between parameters, corrects the thresholds, and synchronizes the corrected baseline thresholds to all monitoring terminals. All modules are connected to a visual interface, making it easy for medical staff to view and correct them.

[0039] 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. An intensive care unit patient early warning method based on clinical data, characterized in that: include, Medical staff set up a two-dimensional grading system for patients in the ICU and collected patients’ input information and monitoring data; Combine input information data and monitoring data, extract data features, and build a joint risk factor model to evaluate the multi-dimensional potential crises of patients in the ICU. According to the evaluation results of the joint risk factor model, issue an early warning and adjust the severity and monitoring level of the patient. Calculate the patient's key physiological parameters in real time, collect key physiological parameters from clinical monitoring data, establish a dynamic coupling index within the time window, adjust the dynamic weight ratio between parameters, and correct the baseline threshold. The corrected baseline threshold will be written into the database of the risk factor joint model as a new threshold and synchronized to all monitoring terminals through timestamps.

2. The intensive care unit patient early warning method based on clinical data as claimed in claim 1, characterized in that: The two-dimensional grading system includes that medical staff conducts two-dimensional grading of patients after they enter the intensive care unit, establishes a severity classification based on the patient's initial vital signs and the degree of organ failure, and marks the patient as red when any of the following symptoms exist: multiple organ failure, need for continuous organ support, and positive genetic risk markers; When there is any symptom of single organ failure, potential decompensation and need for intermittent organ support, it is marked as yellow level; When there is any symptom of unstable vital signs but not reaching the failure standard, high-risk genetics or chronic disease history, it is marked as green level; At the same time, it forms an orthogonal relationship with the severity level, and dynamically calibrates the monitoring level through real-time monitoring of data streams.

3. The intensive care unit patient early warning method based on clinical data as claimed in claim 2, characterized in that: The information data and monitoring data include: The information data includes genetic information and chronic disease history entered by the patient before entering the intensive care unit; The monitoring data include clinical monitoring data and intensive care unit-specific monitoring data.

4. The intensive care unit patient early warning method based on clinical data as claimed in claim 3, characterized in that: The risk factor joint model includes setting a comprehensive score of the patient's genetic information, a rating of the chronic disease history, and a comprehensive value of the bed monitoring data from the patient's genetic information, chronic disease history, and clinical monitoring data. The comprehensive score of the patient's genetic information and the rating of the chronic disease history are both scored by medical staff before the patient is admitted to the intensive care unit, and the comprehensive value is obtained by performing time series analysis on the clinical monitoring data.

5. The intensive care unit patient early warning method based on clinical data as claimed in claim 4, characterized in that: The risk factor joint model also includes constructing a basic risk score through multi-dimensional evaluation based on the set comprehensive score of the patient's genetic information, the rating of chronic disease history and the comprehensive value of clinical monitoring data, and calculating the final risk score in combination with the clinical cycle.

6. The intensive care unit patient early warning method based on clinical data as claimed in claim 5, characterized in that: The issuing of an early warning according to the evaluation result of the risk factor joint model includes setting a first baseline threshold, a second baseline threshold and a third baseline threshold, issuing an early warning signal according to the final risk score, and when the final risk score is less than the first baseline threshold, it is normal; When the first baseline threshold ≤ the final risk score < the second baseline threshold, it is a caution signal, and the medical staff is notified immediately to check and determine whether there is a worsening trend. If the medical staff determines that there is a worsening trend, it is changed to a critical signal and rescue measures are immediately taken. After the rescue is completed, the monitoring level is increased according to the patient's current condition. If the medical staff determines that there is no worsening trend, the signal is stopped, normal monitoring is resumed, and the current monitoring level is maintained; When the second baseline threshold ≤ the final risk score < the third baseline threshold, it is a warning signal, and the medical staff is notified immediately to evaluate the patient's chronic medical history and potential risks, re-evaluate the treatment plan based on the known patient's condition, consider adjusting the drug dosage or treatment method, and prepare rescue measures. When the patient is treated and the current condition is stable, the severity level and monitoring level are increased; When the final risk score is ≥ the third baseline threshold, it is a critical signal, and medical staff will be notified immediately to take rescue measures, while the severity level and monitoring level will be increased. When the patient's condition improves, medical staff will be allowed to downgrade through the visual interface.

7. The intensive care unit patient early warning method based on clinical data as claimed in claim 6, characterized in that: The modified threshold includes establishing a dynamic coupling index within a time window by collecting key physiological parameters from clinical monitoring data; The coupling index is input into the sliding window difference analyzer to adjust the dynamic weight ratio between the parameters. The dynamic weight ratio is input into the differential regulator to generate the baseline threshold adjustment amount. The baseline threshold adjustment amount is coupled with the three baseline thresholds output by the risk assessment model to correct the baseline threshold. The corrected threshold will be written into the database of the risk factor joint model as a new baseline and synchronized to all monitoring terminals through timestamps.

8. A system using the intensive care unit patient early warning method based on clinical data as claimed in any one of claims 1 to 7, characterized in that: Including rating module, data collection module, early warning module and correction module; The rating module allows medical staff to set up a two-dimensional grading system for ICU patients; The data acquisition module is responsible for collecting input information data and monitoring data, including genetic information and chronic disease history recorded before the patient enters the ICU, and physiological parameters monitored in real time in the ICU; The early warning module combines the patient's input information data and monitoring data, uses the risk factor joint model to conduct a multi-dimensional assessment of the patient, calculates the basic risk score by extracting features, and issues an early warning signal based on the assessment results; The correction module is responsible for real-time calculation and dynamic adjustment of the thresholds of the patient's key physiological parameters, by establishing a dynamic coupling index, adjusting the weight ratio between parameters, correcting the thresholds, and synchronizing the corrected baseline thresholds to all monitoring terminals.

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 an intensive care unit patient early warning method based on clinical data as described in 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 an intensive care unit patient early warning method based on clinical data as claimed in any one of claims 1 to 7 are implemented.

Images