Artificial intelligence-based rapid warning system for sudden increase of drainage fluid

Abstract

The present application relates to the technical field of drainage liquid sudden increase early warning, in particular to a drainage liquid sudden increase rapid early warning system based on artificial intelligence. The system acquires drainage volume data and various physiological indexes in real time; according to the difference between the current patient and the preset similar historical patient in terms of drainage volume data change, and the current patient's drainage volume data change, the drainage abnormality degree is determined to determine the drainage abnormal period; according to the length of the current patient's current time in the drainage abnormal period, the change of the drainage abnormality degree in the drainage abnormal period, and the abnormal situation of the physiological indexes, as well as the occurrence of the current patient's drainage abnormal period up to the current time, the overall abnormal situation of the physiological indexes, and the change of the adjacent drainage abnormal period interval length, the warning degree is obtained to warn the current patient's current time of the drainage sudden increase abnormality. The present application accurately warns the current patient's drainage sudden increase abnormality, effectively reducing the harm of drainage abnormality.

Description

Technical Field

[0001] This invention relates to the field of early warning technology for sudden increases in drainage fluid, and more specifically to a rapid early warning system for sudden increases in drainage fluid based on artificial intelligence. Background Technology

[0002] In the medical field, patients following pneumothorax, cardiac surgery, or thoracic surgery often require thoracic drainage. The core purpose is to remove abnormally accumulated gas, blood, and exudate from the pleural cavity using drainage equipment, helping to restore a normal negative pressure environment and ensuring normal lung expansion and respiratory function. During drainage, it is crucial to monitor the drainage volume. A sudden increase in drainage volume is an important signal indicating potential active bleeding or other critical pathological conditions. Timely and accurate identification and early warning of this signal are of significant clinical importance in preventing delays in treatment and reducing the risk of postoperative complications.

[0003] Current clinical methods for warning of sudden increases in drainage fluid largely rely on fixed threshold logic. This involves real-time monitoring of drainage volume data using the drainage device, calculating the rate of increase per unit time, and setting a uniform alarm threshold for all patients or patients of similar types. When the monitored rate of increase in drainage volume exceeds this threshold, the drainage device automatically issues an alarm. However, in actual clinical applications, normal patient positioning changes alter the intrathoracic pressure distribution and the fluid flow state of the drainage tube, potentially leading to a rapid increase in drainage volume within a short period. This increase is not caused by pathological factors, and the drainage volume data quickly returns to normal after the position stabilizes. Existing methods for warning of sudden increases in drainage fluid cannot eliminate such physical interference, easily leading to frequent false alarms. This increases the risk of missing truly critical pathological conditions (such as active bleeding) and fails to meet the needs of refined monitoring and safety assurance for postoperative patients. Summary of the Invention

[0004] To address the technical problem that existing early warning methods for sudden increases in drainage fluid cannot accurately identify actual drainage abnormalities, the present invention aims to provide an artificial intelligence-based rapid early warning system for sudden increases in drainage fluid. The specific technical solution adopted is as follows:

[0005] This invention provides an artificial intelligence-based rapid early warning system for sudden increases in drainage fluid. The system includes:

[0006] The data acquisition module is used to acquire patients' drainage volume data and various physiological indicators in real time;

[0007] The abnormal drainage period acquisition module is used to obtain the degree of abnormal drainage at each moment of the current patient based on the difference in drainage volume data changes between the current patient and preset similar historical patients at each same moment during the drainage process, as well as the changes in drainage volume data of the current patient at each moment, and to determine the abnormal drainage period of the current patient.

[0008] The warning level acquisition module is used to obtain the warning level of the current patient at the current moment based on the duration of the abnormal drainage period, the changes in the degree of abnormal drainage during the abnormal drainage period, the abnormality of various physiological indicators, the occurrence of the abnormal drainage period, the overall abnormality of various physiological indicators, and the changes in the interval between adjacent abnormal drainage periods.

[0009] The data processing module is used to issue early warnings for sudden increases in drainage in the current patient at the current moment, based on the level of warning.

[0010] Furthermore, the method for obtaining the degree of abnormality in the drainage is as follows:

[0011] The drainage data of the current patient and each of its preset similar historical patients are arranged in chronological order to obtain the drainage sequence of the corresponding patient; wherein, the initial drainage data in the drainage sequence is not 0, and the drainage data at the same position in all drainage sequences correspond to the same moment in the drainage process;

[0012] For any moment and any drainage volume sequence of the current patient during the drainage process, the ratio of the drainage volume data corresponding to that moment in the drainage volume sequence to the initial drainage volume data in the drainage volume sequence is used as the drainage growth index of the patient at that moment for that drainage volume sequence.

[0013] The mean of the drainage growth index of all pre-set similar historical patients of the current patient at this moment is used as the reference value for drainage growth at this moment;

[0014] The difference between the current patient's drainage growth index at that moment and the drainage growth reference value at that moment is used as the first drainage growth analysis value for the current patient at that moment.

[0015] The current patient's drainage volume sequence is fitted into a curve, and the slope of the tangent line of the drainage volume data at that moment is obtained on the curve, which is used as the second drainage growth analysis value of the current patient at that moment.

[0016] The result of adding the first and second drainage growth analysis values ​​and normalizing them is taken as the degree of drainage abnormality of the patient at that time.

[0017] Furthermore, the method for obtaining the abnormal drainage period is as follows:

[0018] When the degree of drainage abnormality exceeds the preset threshold for drainage abnormality, the corresponding time will be taken as the current time of drainage abnormality for the patient.

[0019] The continuous time period consisting of at least two consecutive moments of abnormal drainage is taken as the current period of abnormal drainage for the patient.

[0020] Furthermore, the method for obtaining the warning level is as follows:

[0021] Based on the duration of the abnormal drainage period in which the patient is currently experiencing the current moment, as well as the changes in the degree of abnormal drainage and the abnormality of various physiological indicators during the abnormal drainage period, the first degree of abnormality analysis of the patient at the current moment is obtained.

[0022] Based on the occurrence of abnormal drainage periods for the current patient up to the current moment, the overall abnormality of various physiological indicators, and the changes in the interval between adjacent abnormal drainage periods, the degree of second abnormality analysis for the current patient at the current moment is obtained.

[0023] The sum of the first and second abnormality analysis levels, after normalization, is used as the warning level for the current patient at the current moment.

[0024] Furthermore, the method for obtaining the first anomaly analysis level is as follows:

[0025] The current period of abnormal drainage experienced by the patient at the current moment is taken as the target period; the end time of the target period is the current moment.

[0026] The slope of the straight line fitted to the degree of drainage abnormality in the target time period according to the time sequence is used as the value of the change in drainage abnormality of the current patient at the current moment.

[0027] Based on the magnitude of each physiological indicator of the current patient at each time point, obtain the degree of deviation of each physiological indicator of the current patient at each time point, and determine the reference abnormal time of each physiological indicator of the current patient;

[0028] For any physiological indicator, the duration between the initial reference abnormality time of the physiological indicator within the target time period and the initial time of the target time period is taken as the lag duration of the physiological indicator.

[0029] The total number of times from the initial reference abnormal time to the current time within the target time period is taken as the first quantity; the total number of reference abnormal times of the physiological indicator within the target time period is taken as the second quantity; and the ratio of the second quantity to the first quantity is taken as the abnormal persistence analysis value of the physiological indicator.

[0030] The result of normalizing the sum of the total duration of the target period, the abnormal change value of drainage, the mean of the lag duration of all physiological indicators, the mean of the abnormal persistence analysis value of all physiological indicators, and the number of types of physiological indicators corresponding to the reference abnormal time within the target period is used as the first degree of abnormality analysis for the current patient at the current time.

[0031] Furthermore, the method for obtaining the degree of deviation is as follows:

[0032] For any moment and any physiological indicator of the current patient during the drainage process, obtain the mean value of the physiological indicator of all preset similar historical patients at that moment, and use it as the target analysis value of the physiological indicator.

[0033] The result of normalizing the difference between the current patient's physiological indicator at that moment and the target analysis value is taken as the degree of deviation of the current patient's physiological indicator at that moment.

[0034] Furthermore, the method for obtaining the reference anomaly moment is as follows:

[0035] When the deviation exceeds the preset deviation threshold, the corresponding time will be used as the reference abnormal time for the current patient's physiological indicator.

[0036] Furthermore, the method for obtaining the second degree of anomaly analysis is as follows:

[0037] The interval between any two adjacent abnormal drainage periods is taken as the first duration.

[0038] The first duration is fitted into a curve according to the time sequence to serve as the interval duration curve; the slope of the tangent line for each first duration on the interval duration curve is obtained as the value of the change trend analysis for each first duration.

[0039] The ratio of the number of trend analysis values ​​less than 0 to the total number of trend analysis values ​​is taken as the first value;

[0040] The product of the first value and the negative of the mean of all trend analysis values ​​less than 0 is used as the abnormal shortening index for the current patient.

[0041] The result of normalizing the number of times the abnormal drainage period occurred up to the current time is used as the cumulative abnormal drainage analysis value for the current patient at the current time.

[0042] The ratio of the number of reference abnormal times for each physiological indicator of the current patient to the total number of times corresponding to the current patient up to the current time is used as the cumulative reference abnormality analysis value for each physiological indicator of the current patient at the current time.

[0043] The result of normalizing the sum of the mean of the cumulative reference abnormality analysis values, the abnormal shortening index, and the cumulative drainage abnormality analysis values ​​is used as the second degree of abnormality analysis for the current patient at the current moment.

[0044] Furthermore, the method for issuing early warnings for sudden increases in drainage in the current patient at the current moment based on the level of warning is as follows:

[0045] When the warning level exceeds the preset warning level threshold, an early warning is issued for the sudden increase in drainage abnormality of the current patient at the current moment.

[0046] Furthermore, the method for obtaining the preset patients with similar histories is as follows:

[0047] A preset number of historical patients who share the same disease type, gender, surgical and drainage treatment plan, and age difference within a first preset range as the current patient will be considered as the current patient's preset similar historical patients.

[0048] The present invention has the following beneficial effects:

[0049] This invention first determines the degree of drainage abnormality at each moment by comparing the current patient's drainage volume data with that of similar historical patients, and by analyzing the current patient's drainage volume data at each moment. This accurately reflects the current patient's drainage abnormality at each moment, and then accurately determines the period of drainage abnormality based on the degree of abnormality, preparing for subsequent real-time analysis. Next, based on the duration of the current patient's drainage abnormality period, the changes in the degree of abnormality within that period, and abnormalities in various physiological indicators, a preliminary analysis of the current patient's actual drainage abnormality at that moment is conducted. This analysis is further combined with the occurrence of the current patient's drainage abnormality period up to the current moment. This analysis examines the patient's overall condition, the overall abnormality of various physiological indicators, and the changes in the intervals between adjacent periods of abnormal drainage. It identifies the accumulated actual drainage abnormalities up to the current moment and further analyzes the patient's actual drainage abnormality at that moment. This allows for accurate assessment of the patient's current level of warning and reflects the true extent of drainage abnormalities, effectively avoiding interference from normal physiological fluctuations such as postural adjustments. Furthermore, based on the warning level, it provides accurate early warnings for sudden increases in drainage abnormalities at the current moment, significantly improving the accuracy of identifying actual drainage abnormalities. This facilitates the timely detection of the patient's critical pathological condition, enabling prompt treatment of the actual drainage abnormalities and effectively reducing their harm to the patient. Attached Figure Description

[0050] 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.

[0051] Figure 1 This is a structural block diagram of an artificial intelligence-based rapid early warning system for sudden increases in drainage fluid, provided in one embodiment of the present invention.

[0052] Figure 2 A flowchart illustrating a method for obtaining early warning levels according to an embodiment of the present invention;

[0053] Figure 3 This is a schematic diagram of a computer device provided according to an embodiment of the present invention. Detailed Implementation

[0054] 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 the artificial intelligence-based rapid early warning system for sudden increases in drainage fluid proposed according to 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.

[0055] 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.

[0056] The specific solution of the artificial intelligence-based rapid early warning system for sudden increase in drainage fluid provided by the present invention will be described in detail below with reference to the accompanying drawings.

[0057] Example 1:

[0058] This invention proposes an artificial intelligence-based rapid early warning system for sudden increases in drainage fluid. Please refer to [link / reference]. Figure 1 The diagram shows a structural block diagram of an artificial intelligence-based rapid early warning system for sudden increases in drainage fluid provided in an embodiment of the present invention. The system includes: a data acquisition module 10, a drainage abnormality period acquisition module 20, an early warning level acquisition module 30, and a data processing module 40.

[0059] The data acquisition module 10 is used to acquire the patient's drainage volume data and various physiological indicators in real time.

[0060] Specifically, this embodiment uses a drainage device to acquire drainage volume data of the patient at each moment during the drainage process in real time. Simultaneously, a body monitor acquires various physiological indicators of the patient at each moment in real time, including blood pressure, heart rate, blood oxygen saturation, and intrathoracic negative pressure. This embodiment sets the acquisition of drainage volume data and various physiological indicators synchronously, with a time interval of 0.1 seconds between two adjacent data acquisition moments. The implementer can set the time interval between two adjacent data acquisition moments according to the actual situation; no limitation is imposed here.

[0061] The abnormal drainage period acquisition module 20 is used to obtain the degree of abnormal drainage at each moment of the current patient based on the difference in drainage volume data changes between the current patient and preset similar historical patients at each same moment during the drainage process, as well as the changes in drainage volume data of the current patient at each moment, and to determine the abnormal drainage period of the current patient.

[0062] Specifically, it is known that when a patient experiences a sudden increase in drainage volume, it indicates a higher likelihood of drainage abnormalities. To accurately analyze whether the current patient's sudden increase in drainage volume is abnormal and to adjust the drainage promptly to avoid irreversible harm, this embodiment first obtains a preset group of similar patients from the patient's history. This is because drainage volume naturally fluctuates over time, but the fluctuation patterns differ significantly among patients. This difference is mainly determined by physiological function and drainage purpose. For example, the drainage goal for pneumothorax patients is to empty the abnormally accumulated gas in the pleural cavity, resulting in a smaller drainage volume and a more gradual fluctuation. Conversely, the drainage goal for post-cardiac surgery patients is to drain blood from the pleural cavity, with a relatively larger amount of blood in the early postoperative period, leading to a larger overall drainage volume and potentially more pronounced fluctuations. Using a uniform standard to judge the drainage volume of all patients could easily lead to misjudgments due to individual differences. Therefore, it is necessary to first match the current patient with a similar group, i.e., a preset group of similar patients from the patient's history. Using the drainage fluctuations of this similar group as a benchmark allows for more accurate screening of abnormalities. It should be noted that the preset group of similar patients from the patient's history are all currently recovered patients.

[0063] Furthermore, the differences in drainage volume data changes between the current patient and pre-set similar historical patients at the same moment during the drainage process are analyzed. The greater the difference, the more different the drainage changes between the current patient and pre-set similar historical patients at that moment, indirectly indicating that the drainage of the current patient at that moment is more likely to be unreasonable. Further analysis of the changes in drainage volume data of the current patient at that moment shows that the greater the increase in drainage volume data of the current patient at that moment, the more likely the drainage is unreasonable. Therefore, this embodiment obtains the degree of drainage abnormality of the current patient at each moment based on the differences in drainage volume data changes between the current patient and pre-set similar historical patients at each moment during the drainage process, as well as the changes in drainage volume data of the current patient at each moment. The greater the degree of drainage abnormality, the more likely the corresponding moment is a sudden abnormal increase in drainage volume for the current patient; thus, the abnormal drainage period of the current patient is determined based on the degree of drainage abnormality, preparing for subsequent real-time and accurate analysis of the abnormal drainage situation of the current patient.

[0064] Preferably, in one implementable method of this embodiment, the method for obtaining preset similar historical patients is as follows: A preset number of historical patients who share the same disease type, gender, surgical and drainage treatment plan, and age difference within a first preset range as the current patient are all considered as preset similar historical patients. In this embodiment, the preset number is set to 50, and the first preset range is... The implementer can set the preset quantity and the first preset range according to the actual situation, which are not limited here.

[0065] Preferably, in one feasible method of this embodiment, the method for obtaining the degree of drainage abnormality is as follows: The drainage volume data of the current patient and each of its preset similar historical patients are arranged in chronological order to obtain the drainage volume sequence of the corresponding patient; wherein, the initial drainage volume data in the drainage volume sequence is not 0, and the drainage volume data at the same position in all drainage volume sequences correspond to the same moment in the drainage process. It should be noted that the drainage volume sequence of the current patient's preset similar historical patients all correspond to a complete drainage process. For any moment and any drainage volume sequence of the current patient in the drainage process, the ratio of the drainage volume data corresponding to that moment in the drainage volume sequence to the initial drainage volume data in the drainage volume sequence is used as the drainage growth index of the patient at that moment; the larger the drainage growth index, the greater the increase in drainage volume of the corresponding patient at that moment compared to the initial moment of the drainage process;

[0066] To accurately analyze the abnormal changes in drainage volume of the current patient at a given moment, the mean of the drainage growth index of all pre-defined similar historical patients at that moment is used as the reference value for drainage growth at that moment. Then, the absolute value of the difference between the current patient's drainage growth index at that moment and the reference value is used as the first drainage growth analysis value for the current patient at that moment. The larger the first drainage growth analysis value, the more abnormal the drainage volume data of the current patient at that moment, indirectly indicating that the drainage volume data of the current patient at that moment is more likely to have a sudden abnormal increase. Furthermore, the drainage volume sequence of the current patient is fitted into a curve, and the slope of the tangent line to the drainage volume data at that moment is obtained as the second drainage growth analysis value for the current patient at that moment. The larger the second drainage growth analysis value, the greater the increase in the drainage volume data of the current patient at that moment, and the more likely that the drainage volume data of the current patient at that moment is a sudden abnormal increase. Finally, the sum of the first and second drainage growth analysis values ​​is normalized to represent the degree of drainage abnormality of the current patient at that moment. In this embodiment, the sum of the first and second drainage growth analysis values ​​is normalized using the norm normalization function. The methods for curve fitting and obtaining the tangent slope are well-known techniques and will not be elaborated further.

[0067] Preferably, in one implementable method of this embodiment, the method for obtaining the abnormal drainage time period is as follows: when the degree of abnormal drainage is greater than a preset abnormal drainage degree threshold, the corresponding time is taken as the current patient's abnormal drainage time. In this embodiment, the preset abnormal drainage degree threshold is set to 0.5. The implementer can set the size of the preset abnormal drainage degree threshold according to the actual situation, which is not limited here. Considering that in actual situations, isolated abnormal drainage times, that is, abnormal drainage times where neither adjacent time is an abnormal drainage time, are mostly random data fluctuations and not real abnormalities, this embodiment does not consider isolated abnormal drainage times, and instead takes the continuous time period consisting of at least two consecutive abnormal drainage times as the current patient's abnormal drainage time period.

[0068] The warning level acquisition module 30 is used to acquire the warning level of the current patient at the current moment based on the duration of the abnormal drainage period in which the current patient is currently in the current moment, the changes in the degree of abnormal drainage during the abnormal drainage period, the abnormality of various physiological indicators, as well as the occurrence of the current patient's abnormal drainage period up to the current moment, the overall abnormality of various physiological indicators, and the changes in the interval between adjacent abnormal drainage periods.

[0069] In drainage monitoring, abnormal increases in drainage volume are a key warning signal. However, this signal can be caused by two completely different reasons: one is normal physiological fluctuations due to changes in patient position (requiring no emergency intervention), and the other is a sudden increase in actual drainage due to active bleeding (requiring immediate medical attention). Because the clinical needs for these two situations differ greatly, drainage volume data alone cannot accurately distinguish between them. Changes in position are known to be a transient physical disturbance, affecting drainage volume data only by altering external conditions such as intrathoracic pressure and drainage tube position, without causing pathological damage to the patient's physiological state. Sudden increases in actual drainage, on the other hand, are a pathological and persistent influence. For example, active bleeding can lead to changes in blood volume and circulatory system compensation, resulting in an overall physiological imbalance, representing a clinical risk requiring emergency intervention. Therefore, it is necessary to consider the feedback from the patient's current physiological indicators after the occurrence of drainage abnormalities to promptly identify the actual increase in drainage and address the abnormal drainage in a timely manner.

[0070] It is known that when abnormal growth in drainage volume data is caused by changes in patient posture, the feedback of physiological indicators is instantaneous and recoverable. That is, abnormal physiological indicators and abnormal growth in drainage volume data occur almost simultaneously, without significant lag. At the same time, the duration of abnormal physiological indicators is short and can be quickly recovered as the posture stabilizes, without a sustained abnormal trend. When abnormal increases in drainage volume are caused by pathological conditions such as active bleeding, the feedback from physiological indicators is delayed and persistent. That is, the abnormality of physiological indicators lags behind the abnormal increase in drainage volume. In the early stages of active bleeding, the drainage volume shows an abnormal increase first, but the patient's body has a compensatory mechanism, and physiological indicators will not show obvious abnormalities immediately. Usually, after bleeding continues for a period of time and the compensatory mechanism is insufficient to maintain physiological balance, abnormal physiological indicators such as decreased blood pressure, persistently increased heart rate, and decreased blood oxygen saturation will appear. The feedback from physiological indicators is significantly delayed. At the same time, the abnormal state of physiological indicators persists and is difficult to recover on its own. Because the pathological factor (bleeding) is not intervened, the patient's physiological imbalance will continue to worsen, and physiological indicators will remain abnormal. Even if the rate of increase in drainage volume temporarily slows down, physiological indicators will not return to normal on their own and can only be improved through medical intervention (such as hemostasis and fluid replacement).

[0071] Furthermore, considering that in cases of drainage abnormalities caused by actual pathological abnormalities, the degree of drainage abnormality may continue to increase due to the potential for worsening of the pathological process. Therefore, this embodiment first conducts a preliminary analysis of the actual drainage abnormality of the current patient at the current moment based on the duration of the drainage abnormality period, the changes in the degree of drainage abnormality during the period, and the abnormalities in various physiological indicators. It is known that for patients with good drainage outcomes, the fluctuations in their physiological indicators should gradually stabilize. However, when a patient's drainage outcome is poor, even if the drainage volume data at a certain moment does not show a sudden increase, the patient's physiological indicators are difficult to maintain stability, and the frequency of drainage abnormalities gradually increases. Therefore, to more accurately analyze the drainage abnormality of the current patient at the current moment, it is also necessary to combine the patient's long-term historical drainage outcomes and the cumulative trend of drainage abnormalities.

[0072] Among these, the historical drainage effect focuses on the long-term abnormal trends of physiological indicators during the drainage process, as the stability of physiological indicators directly reflects the patient's body's response to drainage treatment. The cumulative trend of drainage abnormalities focuses on analyzing the changes in the occurrence patterns of drainage abnormalities, paying particular attention to whether the number of drainage abnormalities up to the current moment and the interval between two adjacent drainage abnormalities are continuously shortening. A higher number of drainage abnormalities indicates a more unstable condition and a higher potential risk; a shorter interval between two adjacent drainage abnormalities indicates that the condition may be progressing (e.g., increased bleeding rate), requiring an urgent increase in the warning level. Therefore, further analysis of the current patient's actual drainage abnormality at the current moment is conducted based on the occurrence of drainage abnormality periods up to the current moment, the overall abnormality of various physiological indicators, and the changes in the interval between adjacent drainage abnormality periods. To accurately determine the true drainage abnormality of the current patient at the current moment, this embodiment obtains the warning level for the current patient based on the duration of the drainage abnormality period, the changes in the degree of drainage abnormality within the abnormality period, the abnormality of various physiological indicators, the occurrence of drainage abnormality periods up to the current moment, the overall abnormality of various physiological indicators, and the changes in the interval between adjacent drainage abnormality periods. A higher warning level indicates a greater likelihood of a true drainage abnormality at the current moment, and a greater need for warning.

[0073] Preferably, in one possible implementation of this embodiment, the method for obtaining the warning level is described in [reference needed]. Figure 2 The document presents a flowchart of a method for obtaining the level of early warning provided in this embodiment. The method includes the following steps:

[0074] Step S201: Based on the duration of the abnormal drainage period in which the patient is currently experiencing the current moment, as well as the changes in the degree of abnormal drainage and the abnormality of various physiological indicators during the abnormal drainage period, obtain the first degree of abnormality analysis for the current patient at the current moment.

[0075] The greater the degree of abnormality analysis, the more likely the drainage abnormality of the current patient at the current moment is caused by active bleeding and true drainage abnormality, and the more necessary it is to issue an early warning for the sudden increase in drainage abnormality of the current patient at the current moment.

[0076] In one possible implementation of this embodiment, the method for obtaining the degree of first abnormality analysis is as follows: The current period of drainage abnormality for the current patient at the current moment is taken as the target period; the end time of the target period is the current moment; the current moment is essentially the time of drainage abnormality. The slope of the straight line fitted to the degree of drainage abnormality within the target period according to the time sequence is taken as the change value of drainage abnormality for the current patient at the current moment; the larger the change value of drainage abnormality, the more likely the current patient is to have active bleeding and true drainage abnormality at the current moment; further, based on the magnitude of each physiological indicator of the current patient at each moment, the deviation degree of each physiological indicator of the current patient at each moment is obtained; the greater the deviation degree, the more abnormal the corresponding physiological indicator of the current patient is at the corresponding moment, and thus the reference abnormal moment of each physiological indicator of the current patient can be determined based on the deviation degree; then, for any physiological indicator, the time of the target period is taken as the slope of the straight line fitted to the target period. The duration between the initial reference abnormal time of the physiological indicator and the initial time of the target time period is taken as the lag duration of the physiological indicator; the total number of times from the initial reference abnormal time of the physiological indicator to the current time within the target time period is taken as the first quantity; the total number of reference abnormal times of the physiological indicator within the target time period is taken as the second quantity; the ratio of the second quantity to the first quantity is taken as the abnormality persistence analysis value of the physiological indicator; when both the lag duration and the abnormality persistence analysis value are larger, it indicates that the abnormality of the physiological indicator has lag and persistence, and it is more likely to reflect that the patient is currently experiencing active bleeding and true drainage abnormality at the current time.

[0077] The greater the duration of the target time period, the greater the abnormal drainage value, the greater the lag duration and abnormal persistence analysis value of all physiological indicators within the target time period, and the greater the number of types of physiological indicators corresponding to the reference abnormal time within the target time period, the more likely the current patient is to have active bleeding and true abnormal drainage at the current moment. Therefore, in this embodiment, the total duration of the target time period, the abnormal drainage value, the mean of the lag duration of all physiological indicators, the mean of the deviation change of all physiological indicators, and the number of types of physiological indicators corresponding to the reference abnormal time within the target time period are added together and then normalized. This result is used as the first degree of abnormal analysis for the current patient at the current moment. In this embodiment, the sum of the total duration of the target time period, the abnormal drainage value, the mean of the lag duration of all physiological indicators, the mean of the deviation change of all physiological indicators, and the number of types of physiological indicators corresponding to the reference abnormal time within the target time period is normalized using the norm normalization function. The method of fitting a straight line is a well-known technique and will not be described in detail here. It should be noted that if the current time is not the time of drainage abnormality, the first abnormality analysis level of the current patient at the current time is assumed to be 0.

[0078] In one possible implementation of this embodiment, the deviation degree is obtained as follows: For any moment and any physiological indicator of the current patient during the drainage process, the mean value of the physiological indicator at that moment is obtained from all preset similar historical patients of the current patient, and this mean value is used as the target analysis value of the physiological indicator; then, the absolute value of the difference between the current patient's physiological indicator at that moment and the target analysis value is normalized, and this normalized result is used as the deviation degree of the current patient's physiological indicator at that moment. In this embodiment, the absolute value of the difference between the current patient's physiological indicator at that moment and the target analysis value is normalized using the norm normalization function.

[0079] In one possible implementation of this embodiment, the method for obtaining the reference abnormal time is as follows: when the deviation exceeds a preset deviation threshold, the corresponding time is used as the reference abnormal time for the current patient's physiological indicator. This embodiment sets the preset deviation threshold to 0.5. Implementers can set the size of the preset deviation threshold according to actual circumstances; this is not limited here.

[0080] Step S202: Based on the occurrence of abnormal drainage periods for the current patient up to the current moment, the overall abnormality of various physiological indicators, and the change in the interval between adjacent abnormal drainage periods, obtain the degree of second abnormality analysis for the current patient at the current moment.

[0081] The greater the degree of abnormality analysis, the more likely the patient is to have actual drainage abnormalities with active bleeding up to the current moment, and the more necessary it is to issue an early warning for sudden increases in drainage abnormalities in the current patient at the current moment.

[0082] In one possible implementation of this embodiment, the method for obtaining the degree of second abnormality analysis is as follows: The interval between any two adjacent abnormal drainage periods is obtained and taken as the first duration; the first duration is fitted into a curve according to the time sequence to form an interval duration curve; the slope of the tangent line for each first duration on the interval duration curve is obtained and taken as the trend analysis value for each first duration; the ratio of the number of trend analysis values ​​less than 0 to the total number of trend analysis values ​​is taken as the first value; the larger the first value, the more frequently the abnormal drainage periods of the current patient occur up to the current moment; the smaller all trend analysis values ​​less than 0 are, the more frequently the abnormal drainage periods of the current patient occur; furthermore, in this embodiment, the product of the first value and the negative of the mean of all trend analysis values ​​less than 0 is taken as the abnormal shortening index of the current patient; the larger the abnormal shortening index, the greater the degree of actual abnormal drainage in the current patient up to the current moment;

[0083] The result of normalizing the number of times the abnormal drainage period occurred up to the current time is used as the cumulative abnormal drainage analysis value for the current patient at the current time. The larger the cumulative abnormal drainage analysis value, the more frequently the abnormal drainage period occurred for the current patient, and the greater the degree of actual abnormal drainage for the current patient up to the current time.

[0084] The ratio of the number of reference abnormal times for each physiological indicator of the current patient to the total number of times corresponding to the current patient up to the current time is used as the cumulative reference abnormality analysis value for each physiological indicator of the current patient at the current time. The larger the cumulative reference abnormality analysis value, the more unstable and abnormal the corresponding physiological indicator of the current patient is up to the current time, which indirectly reflects the greater degree of actual drainage abnormality of the current patient up to the current time.

[0085] To comprehensively reflect the actual drainage abnormalities accumulated by the patient up to the current moment, this embodiment normalizes the sum of the mean of the cumulative reference abnormality analysis values, the abnormal shortening index, and the cumulative drainage abnormality analysis values, and uses this sum as the second degree of abnormality analysis for the current patient at the current moment. This embodiment normalizes the sum of the mean of the cumulative reference abnormality analysis values, the abnormal shortening index, and the cumulative drainage abnormality analysis values ​​using the norm normalization function.

[0086] Step S203: The sum of the first abnormality analysis degree and the second abnormality analysis degree is normalized and used as the warning degree for the current patient at the current moment.

[0087] It is known that the higher the degree of the first anomaly analysis and the higher the degree of the second anomaly analysis, the greater the need for early warning of the sudden increase in drainage abnormality in the current patient at the current moment. Therefore, in this embodiment, the sum of the first and second anomaly analysis degrees and the result normalized are used as the warning level for the current patient at the current moment. In this embodiment, the sum of the first and second anomaly analysis degrees is normalized using the norm normalization function.

[0088] The data processing module 40 is used to issue an early warning for the sudden increase in drainage abnormalities of the current patient at the current moment based on the level of warning.

[0089] Specifically, the higher the known warning level, the more likely the sudden increase in drainage abnormality in the current patient at the current moment is a true drainage abnormality due to active bleeding, and the more necessary it is to issue a warning. Therefore, this embodiment issues a warning for the sudden increase in drainage abnormality in the current patient at the current moment based on the warning level.

[0090] Preferably, in one feasible embodiment of this method, the method for issuing an early warning for a sudden increase in drainage abnormality in the current patient at the current moment based on the warning level is as follows: when the warning level is greater than a preset warning level threshold, an early warning is issued for the sudden increase in drainage abnormality in the current patient at the current moment; that is, the drainage device emits an early warning sound to promptly remind staff to handle the drainage abnormality of the current patient, effectively reducing the adverse effects of the drainage abnormality on the current patient. In this embodiment, the preset warning level threshold is set to 0.5. The implementer can set the size of the preset warning level threshold according to the actual situation, which is not limited here.

[0091] In summary, this embodiment acquires drainage volume data and various physiological indicators in real time; based on the difference in drainage volume data changes between the current patient and preset similar historical patients, and the current patient's drainage volume data changes, it determines the degree of drainage abnormality and the period of drainage abnormality; based on the duration of the drainage abnormality period the current patient is currently in, the changes in the degree of drainage abnormality within the current drainage abnormality period, the abnormality of physiological indicators, and the occurrence of drainage abnormality periods, the overall abnormality of physiological indicators, and the changes in the interval between adjacent drainage abnormality periods up to the current moment, it obtains the warning level to provide an early warning for the current patient's sudden increase in drainage abnormality at the current moment. This invention effectively reduces the harm of drainage abnormalities by accurately providing early warning for the current patient's sudden increase in drainage abnormality.

[0092] Example 2:

[0093] This invention also proposes an artificial intelligence-based rapid early warning device for sudden increases in drainage fluid. This device includes a memory and a processor. The memory stores executable program code, and the processor is used to call and execute the executable program code to perform the artificial intelligence-based rapid early warning system for sudden increases in drainage fluid provided in the embodiments of this application. Specifically, the device may be a chip, component, or module. The chip may include a connected processor and memory; wherein the memory stores instructions, and when the processor calls and executes the instructions, it can cause the chip to perform the artificial intelligence-based rapid early warning system for sudden increases in drainage fluid provided in the above embodiments.

[0094] Furthermore, this application also protects a computer device; please refer to [link to relevant documentation]. Figure 3 The computer device includes a memory 401, a processor 402, and a computer program 403 stored in the memory 401 and running on the processor 402. When the processor 402 executes the computer program 403, the computer device can execute any of the aforementioned artificial intelligence-based rapid early warning systems for sudden increases in drainage fluid.

[0095] Example 3:

[0096] The present invention also provides a computer-readable storage medium storing computer program code, which, when executed on a computer, causes the computer to perform the aforementioned method steps to implement the artificial intelligence-based rapid early warning system for sudden increase in drainage fluid provided in the above embodiments.

[0097] Example 4:

[0098] The present invention also provides a computer program product that, when run on a computer, causes the computer to perform the aforementioned related steps to realize the artificial intelligence-based rapid early warning system for sudden increase in drainage fluid provided in the above embodiments.

[0099] In this embodiment, the device, computer-readable storage medium, computer program product, or chip are all used to execute the corresponding methods provided above. Therefore, the beneficial effects they can achieve can be referred to the beneficial effects in the corresponding methods provided above, and will not be repeated here.

[0100] 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.

[0101] 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. An artificial intelligence-based rapid early warning system for sudden increases in drainage fluid, characterized in that, The system includes: The data acquisition module is used to acquire patients' drainage volume data and various physiological indicators in real time; The abnormal drainage period acquisition module is used to obtain the degree of abnormal drainage at each moment of the current patient based on the difference in drainage volume data changes between the current patient and preset similar historical patients at each same moment during the drainage process, as well as the changes in drainage volume data of the current patient at each moment, and to determine the abnormal drainage period of the current patient. The warning level acquisition module is used to obtain the warning level of the current patient at the current moment based on the duration of the abnormal drainage period, the changes in the degree of abnormal drainage during the abnormal drainage period, the abnormality of various physiological indicators, the occurrence of the abnormal drainage period, the overall abnormality of various physiological indicators, and the changes in the interval between adjacent abnormal drainage periods. The data processing module is used to issue early warnings for sudden increases in drainage in the current patient at the current moment based on the level of warning. The method for obtaining the warning level is as follows: Based on the duration of the abnormal drainage period in which the patient is currently experiencing the current moment, as well as the changes in the degree of abnormal drainage and the abnormality of various physiological indicators during the abnormal drainage period, the first degree of abnormality analysis of the patient at the current moment is obtained. Based on the occurrence of abnormal drainage periods for the current patient up to the current moment, the overall abnormality of various physiological indicators, and the changes in the interval between adjacent abnormal drainage periods, the degree of second abnormality analysis for the current patient at the current moment is obtained. The sum of the first and second abnormality analysis levels, after normalization, is used as the warning level for the current patient at the current moment.

2. The artificial intelligence-based rapid early warning system for sudden increases in drainage fluid as described in claim 1, characterized in that, The method for obtaining the degree of abnormality in the drainage is as follows: The drainage data of the current patient and each of its preset similar historical patients are arranged in chronological order to obtain the drainage sequence of the corresponding patient; wherein, the initial drainage data in the drainage sequence is not 0, and the drainage data at the same position in all drainage sequences correspond to the same moment in the drainage process; For any moment and any drainage volume sequence of the current patient during the drainage process, the ratio of the drainage volume data corresponding to that moment in the drainage volume sequence to the initial drainage volume data in the drainage volume sequence is used as the drainage growth index of the patient at that moment for that drainage volume sequence. The mean of the drainage growth index of all pre-set similar historical patients of the current patient at this moment is used as the reference value for drainage growth at this moment; The difference between the current patient's drainage growth index at that moment and the drainage growth reference value at that moment is used as the first drainage growth analysis value for the current patient at that moment. The current patient's drainage volume sequence is fitted into a curve, and the slope of the tangent line of the drainage volume data at that moment is obtained on the curve, which is used as the second drainage growth analysis value of the current patient at that moment. The result of adding the first and second drainage growth analysis values ​​and normalizing them is taken as the degree of drainage abnormality of the patient at that time.

3. The artificial intelligence-based rapid early warning system for sudden increases in drainage fluid as described in claim 1, characterized in that, The method for obtaining the abnormal drainage period is as follows: When the degree of drainage abnormality exceeds the preset threshold for drainage abnormality, the corresponding time will be taken as the current time of drainage abnormality for the patient. The continuous time period consisting of at least two consecutive moments of abnormal drainage is taken as the current period of abnormal drainage for the patient.

4. The artificial intelligence-based rapid early warning system for sudden increases in drainage fluid as described in claim 1, characterized in that, The method for obtaining the first level of anomaly analysis is as follows: The current period of abnormal drainage experienced by the patient at the current moment is taken as the target period; the end time of the target period is the current moment. The slope of the straight line fitted to the degree of drainage abnormality in the target time period according to the time sequence is used as the value of the change in drainage abnormality of the current patient at the current moment. Based on the magnitude of each physiological indicator of the current patient at each time point, obtain the degree of deviation of each physiological indicator of the current patient at each time point, and determine the reference abnormal time of each physiological indicator of the current patient; For any physiological indicator, the duration between the initial reference abnormality time of the physiological indicator within the target time period and the initial time of the target time period is taken as the lag duration of the physiological indicator. The total number of times from the initial reference abnormal time to the current time within the target time period is taken as the first quantity; the total number of reference abnormal times of the physiological indicator within the target time period is taken as the second quantity; and the ratio of the second quantity to the first quantity is taken as the abnormal persistence analysis value of the physiological indicator. The result of normalizing the sum of the total duration of the target period, the abnormal change value of drainage, the mean of the lag duration of all physiological indicators, the mean of the abnormal persistence analysis value of all physiological indicators, and the number of types of physiological indicators corresponding to the reference abnormal time within the target period is used as the first degree of abnormality analysis for the current patient at the current time.

5. The artificial intelligence-based rapid early warning system for sudden increases in drainage fluid as described in claim 4, characterized in that, The method for obtaining the degree of deviation is as follows: For any moment and any physiological indicator of the current patient during the drainage process, obtain the mean value of the physiological indicator of all preset similar historical patients at that moment, and use it as the target analysis value of the physiological indicator. The result of normalizing the difference between the current patient's physiological indicator at that moment and the target analysis value is taken as the degree of deviation of the current patient's physiological indicator at that moment.

6. The artificial intelligence-based rapid early warning system for sudden increases in drainage fluid as described in claim 5, characterized in that, The method for obtaining the reference anomaly time is as follows: When the deviation exceeds the preset deviation threshold, the corresponding time will be used as the reference abnormal time for the current patient's physiological indicator.

7. The artificial intelligence-based rapid early warning system for sudden increases in drainage fluid as described in claim 1, characterized in that, The method for obtaining the second level of anomaly analysis is as follows: The interval between any two adjacent abnormal drainage periods is taken as the first duration. The first duration is fitted into a curve according to the time sequence to serve as the interval duration curve; the slope of the tangent line for each first duration on the interval duration curve is obtained as the value of the change trend analysis for each first duration. The ratio of the number of trend analysis values ​​less than 0 to the total number of trend analysis values ​​is taken as the first value; The product of the first value and the negative of the mean of all trend analysis values ​​less than 0 is used as the abnormal shortening index for the current patient. The result of normalizing the number of times the abnormal drainage period occurred up to the current time is used as the cumulative abnormal drainage analysis value for the current patient at the current time. The ratio of the number of reference abnormal times for each physiological indicator of the current patient to the total number of times corresponding to the current patient up to the current time is used as the cumulative reference abnormality analysis value for each physiological indicator of the current patient at the current time. The result of normalizing the sum of the mean of the cumulative reference abnormality analysis values, the abnormal shortening index, and the cumulative drainage abnormality analysis values ​​is used as the second degree of abnormality analysis for the current patient at the current moment.

8. The artificial intelligence-based rapid early warning system for sudden increases in drainage fluid as described in claim 1, characterized in that, The method for issuing early warnings based on the level of warning for sudden increases in drainage abnormalities in the current patient at the current moment is as follows: When the warning level exceeds the preset warning level threshold, an early warning is issued for the sudden increase in drainage abnormality of the current patient at the current moment.

9. The artificial intelligence-based rapid early warning system for sudden increases in drainage fluid as described in claim 1, characterized in that, The method for obtaining the preset patients with similar historical data is as follows: A preset number of historical patients who share the same disease type, gender, surgical and drainage treatment plan, and age difference within a first preset range as the current patient will be considered as the current patient's preset similar historical patients.

Images