A hysteroscopic surgery early warning method, device and system

Abstract

The present application discloses a hysteroscopic surgery early warning method, device and system, which are applied to the field of surgical early warning technology to solve the problem of poor safety of hysteroscopic surgery early warning in the prior art. Specifically, it is as follows: real-time electrocoagulation and electroresection data, real-time negative underflow of uterine distention fluid and current operation type are obtained; real-time electrocoagulation and electroresection data and real-time negative underflow are input into the negative underflow prediction model to obtain the predicted negative underflow output by the negative underflow prediction model; based on the preset mapping relationship, the first type of early warning level and the first type of early warning threshold range corresponding to the current operation type are obtained; the first type of early warning level corresponding to the threshold range to which the predicted negative underflow belongs is used as the predicted early warning level, and the early warning operation corresponding to the level of the predicted early warning level is executed. In this way, the prediction of negative underflow is realized in combination with electrocoagulation and electroresection data, and the negative underflow warning for the current operation type is predicted, thereby improving the safety of hysteroscopic surgery early warning.

Description

Technical Field

[0001] The present application relates to the field of surgical warning technology, and in particular to a hysteroscopic surgery warning method, device and system. Background Art

[0002] Excessive absorption of distending fluid during hysteroscopic surgery can lead to pulmonary edema, neurological complications and even death, which is one of the serious complications of hysteroscopic surgery. How to quickly and accurately calculate the amount of distending fluid in and out has always been a problem that has troubled clinical medical staff.

[0003] At present, the existing hysteroscopic surgery warning is achieved by monitoring and displaying the negative undervalue value, uterine cavity pressure value, changes in inflow and outflow, and changes in the negative undervalue value, and issuing a sound alarm when the negative undervalue value or uterine cavity pressure value meets the requirements, so as to reduce the risk of excessive absorption of uterine distension fluid-fluid overload syndrome. However, this hysteroscopic surgery warning method is not related to the doctor's electrocoagulation and electroresection behavior during the operation, and its safety is poor. Summary of the invention

[0004] The embodiments of the present application provide a hysteroscopic surgery early warning method, device and system to solve the problem of poor safety of hysteroscopic surgery early warning in the prior art.

[0005] The technical solutions provided by the embodiments of this application are as follows:

[0006] On the one hand, the embodiment of the present application provides a hysteroscopic surgery early warning method, comprising:

[0007] Acquire real-time electrocoagulation and electroresection data, real-time negative and insufficient amount of uterine distention fluid, and current operation type; wherein, the real-time electrocoagulation and electroresection data are the real-time electrocoagulation pedal pressure of the hysteroscope electrocoagulation control pedal and the real-time electroresection pedal pressure of the hysteroscope electroresection control pedal; the real-time negative and insufficient amount of uterine distention fluid is determined by the real-time infusion weight and the real-time outflow weight of the uterine distention fluid;

[0008] Inputting the real-time electrocoagulation and electroresection data and the real-time negative underflow into the negative underflow prediction model to obtain the predicted negative underflow outputted by the negative underflow prediction model;

[0009] Based on the preset mapping relationship between the surgery type, the first warning level and the first warning threshold range, the first warning level corresponding to the current surgery type and the first warning threshold range corresponding to the first warning level are obtained;

[0010] The first type of warning level corresponding to the threshold range to which the predicted under-volume belongs is taken as the predicted warning level, and a warning operation corresponding to the level of the predicted warning level is executed.

[0011] In a possible implementation, after obtaining real-time electrocoagulation and electroresection data, real-time negative or negative volume of uterine distention fluid, and current operation type, the method further includes:

[0012] Obtaining the historical negative or negative amount of the uterine distension fluid; wherein the historical negative or negative amount of the uterine distension fluid is determined by the historical infusion weight and the historical outflow weight of the uterine distension fluid;

[0013] Based on the historical under-volume and the real-time under-volume, determine the real-time change value of the under-volume;

[0014] Determine whether the real-time change value is greater than a preset change threshold;

[0015] If so, an operation risk prompt will be issued if the real-time pedal pressure is not zero.

[0016] In a possible implementation, after obtaining real-time electrocoagulation and electroresection data, real-time negative or negative volume of uterine distention fluid, and current operation type, the method further includes:

[0017] Obtain the patient's medical records and uterine distention fluid type; the medical records include the patient's age, current condition, and underlying condition;

[0018] Inputting the patient's age, current condition of the patient and type of uterine distention fluid into the first threshold evaluation model to obtain the second warning level and the threshold range corresponding to the second warning level;

[0019] Determine a target threshold range corresponding to the second warning level based on the patient's underlying symptoms and the threshold range corresponding to the second warning level;

[0020] Based on the second warning level and the target threshold range corresponding to the second warning level, determine the second warning level corresponding to the real-time under-volume, and use the second warning level corresponding to the real-time under-volume as the second target warning level;

[0021] Based on the correspondence between the second type of warning level and the warning operation, the warning operation corresponding to the second type of target warning level is executed.

[0022] In a possible implementation, based on the patient's basic condition and the threshold range corresponding to the second warning level, determining the target threshold range corresponding to the second warning level includes:

[0023] Determine whether the patient's underlying condition belongs to the preset type of condition;

[0024] If yes, then the threshold range corresponding to each second-class warning level is adjusted downward, and the lowered threshold range is used as the target threshold range corresponding to each second-class warning level;

[0025] If not, the threshold ranges corresponding to the respective second warning levels output by the first threshold assessment model are used as the target threshold ranges corresponding to the respective second warning levels.

[0026] In a possible implementation, the hysteroscopic surgery early warning method further includes:

[0027] Obtain the patient's current intrauterine pressure and mean arterial pressure;

[0028] The difference between the intrauterine pressure and the mean arterial pressure was determined as the pressure difference, and the ratio of the pressure difference to the mean arterial pressure was determined as the pressure increase ratio;

[0029] Based on the preset third warning level and the threshold range corresponding to the third warning level, determine the third warning level corresponding to the boost ratio, and use the third warning level corresponding to the boost ratio as the third target warning level;

[0030] Based on the correspondence between the third type of warning level and the warning operation, the warning operation corresponding to the third type of target warning level is executed.

[0031] In a possible implementation, the hysteroscopic surgery early warning method further includes:

[0032] After the operation is completed, all the electrocoagulation and electroresection data and negative and insufficient volume data during the operation are saved;

[0033] Based on all the electrocoagulation and electroresection data, the behavioral data during the operation are determined, wherein the behavioral data includes the single duration, total number and total duration of the electrocoagulation and electroresection behavior;

[0034] Establish the association between the current operation type, negative volume data and behavior data, and save the association as well as the current operation type, uterine distension fluid data and behavior data.

[0035] In a possible implementation, before obtaining real-time electrocoagulation and electroresection data, real-time negative or negative volume of uterine distention fluid, and current operation type, the method further includes:

[0036] Obtaining a training set; wherein the training set includes multiple groups of monitoring data, wherein each group of monitoring data includes electrocoagulation and electroresection data and negative or insufficient amount of uterine fluid at the same time;

[0037] Input each set of monitoring data in the training set into the negative quantity shortage prediction model to obtain the negative quantity shortage prediction result corresponding to each set of monitoring data; wherein the negative quantity shortage prediction result includes the predicted negative quantity shortage at the first time after the monitoring data is collected;

[0038] Based on the negative quantity shortage prediction results and negative quantity shortage marking results corresponding to each set of monitoring data, the loss function value is determined; wherein the negative quantity shortage marking result is the actual negative quantity shortage at the first time after the monitoring data is collected;

[0039] Based on the loss function value, the model parameters of the negative under-volume prediction model are updated.

[0040] On the other hand, an embodiment of the present application provides a hysteroscopic surgery early warning device, comprising:

[0041] A data acquisition unit is used to acquire real-time electrocoagulation and electroresection data, real-time negative and insufficient amount of uterine distention fluid, and the current operation type; wherein the real-time electrocoagulation and electroresection data are the real-time electrocoagulation pedal pressure of the hysteroscope electrocoagulation control pedal and the real-time electroresection pedal pressure of the hysteroscope electroresection control pedal; the real-time negative and insufficient amount of uterine distention fluid is determined by the real-time infusion weight and the real-time outflow weight of the uterine distention fluid;

[0042] A data prediction unit, used for inputting real-time electrocoagulation and electroresection data and real-time negative underflow into a negative underflow prediction model to obtain a predicted negative underflow outputted by the negative underflow prediction model;

[0043] A first threshold determination unit, configured to obtain a first warning level corresponding to a current surgery type and a first warning threshold range corresponding to the first warning level based on a preset mapping relationship between the surgery type, the first warning level, and the first warning threshold range;

[0044] The first risk warning unit is used to use the first type of warning level corresponding to the threshold range to which the predicted negative or insufficient amount belongs as the predicted warning level, and to issue a first type of operation risk warning when the predicted warning level is higher than a preset level.

[0045] On the other hand, an embodiment of the present application provides a hysteroscopic surgery early warning system, including: a first weight sensor, a second weight sensor, a first pressure sensor, a second pressure sensor, and a processor;

[0046] The first weight sensor is arranged at the bottom of the uterine distension fluid supply device, and the first weight sensor is used to collect the weight of the uterine distension fluid injected;

[0047] The second weight sensor is arranged at the bottom of the uterine distension fluid outflow storage device, and the second weight sensor is used to collect the outflow weight of the uterine distension fluid;

[0048] The first pressure sensor is arranged at the bottom of the hysteroscope electrocoagulation control pedal, and the first pressure sensor is used to collect the electrocoagulation pedal pressure;

[0049] The second pressure sensor is arranged at the bottom of the hysteroscope electroresection control pedal, and the second pressure sensor is used to collect the electroresection pedal pressure;

[0050] The processor is connected to the first weight sensor, the second weight sensor, the first pressure sensor and the second pressure sensor respectively; the processor is used to execute the computer program corresponding to the hysteroscopic surgery early warning method provided in the embodiment of the present application.

[0051] In a possible implementation, the hysteroscopic surgery early warning system further includes: a first flow sensor disposed on the inlet pipeline of the uterine distension fluid and a second flow sensor disposed on the outlet pipeline of the uterine distension fluid;

[0052] The first flow sensor is used to collect the inflow flow of the uterine distension fluid; the second flow sensor is used to collect the outflow flow of the uterine distension fluid.

[0053] The beneficial effects of the embodiments of the present application are as follows:

[0054] In an embodiment of the present application, real-time electrocoagulation and electroresection data and real-time negative underflow are input into a negative underflow prediction model to obtain a predicted negative underflow output by the negative underflow prediction model, thereby realizing the prediction of negative underflow through electrocoagulation and electroresection data; based on the warning level and threshold corresponding to the current surgical type, the predicted warning level is further determined, and the warning operation corresponding to the predicted warning level is executed to realize the negative underflow warning for the current surgical type, thereby improving the safety of hysteroscopic surgical warning.

[0055] Other features and advantages of the present application will be described in the subsequent description, and in part, will become apparent from the description, or will be understood by practicing the present application. The purpose and other advantages of the present application can be realized and obtained by the structures specifically pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0057] Figure 1 This is a schematic diagram of the overview of the hysteroscopic surgery early warning method in the embodiment of the present application;

[0058] Figure 2 It is a schematic diagram of the overview of the real-time early warning method for the under-volume of uterine distention fluid during hysteroscopic surgery in the embodiment of the present application;

[0059] Figure 3 This is a schematic diagram of the overview of the real-time early warning method for intrauterine pressure during hysteroscopic surgery in an embodiment of the present application;

[0060] Figure 4 This is a functional structure diagram of the hysteroscopic surgery early warning device in the embodiment of the present application;

[0061] Figure 5 It is a schematic diagram of the framework of the hysteroscopic surgery early warning system in the embodiment of the present application. DETAILED DESCRIPTION

[0062] In order to make the purpose, technical solution and beneficial effects of this application clearer, the technical solution in the embodiment of this application will be clearly and completely described below in conjunction with the drawings in the embodiment of this application. Obviously, the described embodiment is only a part of the embodiment of this application, not all the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0063] The present application embodiment provides a hysteroscopic surgery early warning method, see Figure 1 As shown, the overview process of the hysteroscopic surgery early warning method provided in the embodiment of the present application is as follows:

[0064] Step 101: Acquire real-time electrocoagulation and electroresection data, real-time negative or insufficient amount of uterine distention fluid, and current operation type; wherein, the real-time electrocoagulation and electroresection data are the real-time electrocoagulation pedal pressure of the hysteroscopic electrocoagulation control pedal and the real-time electroresection pedal pressure of the hysteroscopic electroresection control pedal; the real-time negative or insufficient amount of uterine distention fluid is determined by the real-time infusion weight and the real-time outflow weight of the uterine distention fluid.

[0065] In actual applications, the types of surgeries include: hysteroscopic electroresection, intrauterine adhesion separation, myomectomy, hysteroscopic tubal insufflation, hysteroscopic endometriosis treatment, hysteroscopic embryo retrieval, and hysteroscopic foreign body removal. The current type of surgery is at least one of the types of surgeries. A first pressure sensor is provided at the bottom of the hysteroscopic electrocoagulation control pedal, and the pressure collected in real time by the first pressure sensor is used as the real-time electrocoagulation pedal pressure. A second pressure sensor is provided at the bottom of the hysteroscopic electroresection control pedal, and the pressure collected in real time by the second pressure sensor is used as the real-time electroresection pedal pressure. Since the hysteroscope can only work in electrocoagulation or electroresection mode, at the same time, at least one of the real-time electrocoagulation pedal pressure and the real-time electroresection pedal pressure is zero. A first weight sensor is provided on the distension fluid injection device, and a second weight sensor is provided on the distension fluid collection device. The weight collected in real time by the first weight sensor is the real-time injection weight of the distension fluid, and the weight collected in real time by the second weight sensor is the real-time outflow weight of the distension fluid. The real-time negative or negative weight of the distension fluid is determined by subtracting the real-time outflow weight from the real-time injection weight at the same time, and the real-time negative or negative amount of the distension fluid is determined according to the real-time negative or negative weight and density of the distension fluid.

[0066] Step 102: input the real-time electrocoagulation and electroresection data and the real-time negative underflow into the negative underflow prediction model to obtain the predicted negative underflow outputted by the negative underflow prediction model.

[0067] In practical applications, the negative underflow prediction model can be an observation model based on a machine learning method, and specifically, a neural network model can be used. The negative underflow prediction model can output the predicted negative underflow at the first time in the future based on the input real-time electrocoagulation and electroresection data and the real-time negative underflow of the uterine distention fluid. The first time is after the future time and separated from the future time by a preset time interval.

[0068] Step 103: Based on the preset mapping relationship between the surgery type, the first warning level and the first warning threshold range, obtain the first warning level corresponding to the current surgery type and the first warning threshold range corresponding to the first warning level.

[0069] Step 104: taking the first type of warning level corresponding to the threshold range to which the predicted under-volume belongs as the predicted warning level, and executing the warning operation corresponding to the level of the predicted warning level.

[0070] In actual applications, each type of surgery corresponds to a first-class warning level and a first-class warning threshold range; each first-class warning level is set with a corresponding first-class warning threshold range. The first-class warning level is the level of warning for predicted negative underflow, which can be divided into multiple levels. The first-class warning threshold range is the warning threshold range for predicted negative underflow, which can include multiple non-overlapping negative underflow ranges. Each level in the first-class warning level corresponds to a negative underflow range. As the level of the first-class warning level increases, the corresponding negative underflow range segment increases, and the predicted risk of excessive absorption of uterine distension fluid gradually increases; each level of the first-class warning level corresponds to different warning operations. Specifically, the first-class warning level can include the first-class level 1 warning, the first-class level 2 warning, and the first-class level 3 warning. The warning operation corresponding to the first-level warning of the first category is to display the predicted warning level and the predicted negative amount, light up the corresponding indicator light or make the indicator light display the corresponding color; the warning operation corresponding to the first-level warning of the first category is to display the predicted warning level and the predicted negative amount, light up the corresponding indicator light, make a sound alarm, and issue a voice prompt corresponding to the risk of excessive absorption of uterine distention fluid, so that the doctor can adjust the surgical operation in time; the warning operation corresponding to the first-level warning of the third category is to display the predicted warning level and the predicted negative amount, light up the corresponding indicator light, make frequent sound alarms, and issue a voice prompt corresponding to the high risk of excessive absorption of uterine distention fluid, so that the doctor can adjust the surgical operation in time. In the case of a large number of first-level warning levels, multiple level thresholds can also be set, and the first-level warning levels within each level threshold range match the same warning operation, and the first-level warning levels within different level threshold ranges match different warning operations.

[0071] In a possible implementation, after obtaining the electrocoagulation and electroresection data, the uterine distention fluid data, and the current operation type, the method further includes:

[0072] Firstly, based on the historical under-volume and the real-time under-volume, the real-time change value of the under-volume is determined;

[0073] Then, it is determined whether the real-time change value is greater than a preset change threshold; if so, an operation risk prompt is issued when the real-time electrocoagulation pedal pressure or the real-time electroresection pedal pressure is not zero.

[0074] In actual applications, the real-time change value of the negative underflow is the real-time negative underflow minus the historical negative underflow, and the real-time change value of the negative underflow is greater than the preset change threshold, which corresponds to a rapid increase in the negative underflow. The real-time electrocoagulation foot pressure or the real-time electroresection foot pressure is not zero, which means that the electrocoagulation and electroresection operation is currently being performed under hysteroscopy. When it is determined that the real-time change value of the negative underflow is greater than the preset change threshold and the real-time electrocoagulation foot pressure or the real-time electroresection foot pressure is not zero, it is determined that the electrocoagulation and electroresection operation causes a rapid increase in the negative underflow, and an operation risk prompt is performed, wherein the operation risk prompt corresponds to the situation where the electrocoagulation and electroresection operation causes a rapid increase in the negative underflow, and the operation risk prompt is at least one of a voice prompt that indicates that there is a risk of a rapid increase in the negative underflow with the current operation, the corresponding indicator light is lit, and the corresponding icon or text is displayed on the display. When it is determined that the real-time change value of the negative underflow is greater than the preset change threshold and the real-time electrocoagulation foot pressure and the real-time electroresection foot pressure are both zero, it is determined that other operations cause a rapid increase in the negative underflow, and other risk prompts are performed. Among them, other risk warnings correspond to situations where other operations cause a rapid increase in negative balance. Other risk warnings are at least one of the following means: voice prompts related to other factors that cause a rapid increase in negative balance, lighting of corresponding indicator lights, and display of corresponding icons or texts on the display.

[0075] In one possible implementation, see Figure 2 As shown in the figure, after obtaining the electrocoagulation and electroresection data, uterine distention fluid data and the current operation type, it also includes:

[0076] Step 201: Obtain the patient's case data and uterine distention fluid type; wherein the case data includes the patient's age, the patient's current condition, and the patient's underlying condition.

[0077] In actual application, the types of uterine distension fluid include electrolyte solutions and non-electrolyte solutions. The patient's current condition is the condition corresponding to the type of surgery. The patient's current condition includes: endometrial polyps, submucosal myomas and endometrial hyperplasia corresponding to hysteroscopic transurethral resection, intrauterine adhesions corresponding to intrauterine adhesion separation, intrauterine myomas corresponding to myomectomy, fallopian tube obstruction corresponding to hysteroscopic tubal insufflation, endometriosis corresponding to hysteroscopic endometriosis treatment, early miscarriage, incomplete miscarriage and missed miscarriage corresponding to hysteroscopic embryo retrieval; intrauterine foreign bodies, IUD incarceration, IUD breakage and IUD displacement corresponding to hysteroscopic foreign body retrieval. The patient's underlying condition refers to the condition that the patient has suffered for a long time.

[0078] Step 202: Input the patient's age, the patient's current condition, and the type of uterine distention fluid into the first threshold evaluation model to obtain the second warning level and the threshold range corresponding to the second warning level.

[0079] In actual applications, each second-class warning level is set with a corresponding second-class warning threshold range. The second-class warning level is the warning level for real-time negative under-volume, which can be divided into multiple levels. The second-class warning threshold range is the warning threshold range for real-time negative under-volume, which can include multiple non-overlapping negative under-volume ranges. Each level in the second-class warning level corresponds to a negative under-volume range. As the level of the second-class warning level increases, the actual risk of excessive absorption of uterine distention fluid increases.

[0080] In specific implementation, the first threshold evaluation model can output the corresponding second-class warning level and the threshold range corresponding to the second-class warning level according to the input patient age, patient current condition and uterine distention fluid type. The first threshold evaluation model can be a neural network model or a linear regression model. The first threshold evaluation model is trained in the following way.

[0081] First, a training set is obtained; wherein the training set includes multiple data groups, each data group includes the patient's age and the patient's current condition, and the age and / or condition in each data group are different.

[0082] Then, each data group in the training set is input into the first threshold evaluation model respectively to obtain the prediction result corresponding to each data group; wherein the prediction result includes the second type of warning level and the threshold range corresponding to the second type of warning level.

[0083] Finally, based on the prediction results and target results corresponding to each data group, the model parameters of the first threshold evaluation model are updated; wherein the target result is the second warning level corresponding to the data group in the training set and the threshold range corresponding to the second warning level.

[0084] Step 203: Determine a target threshold range corresponding to the second warning level based on the patient's basic symptoms and the threshold range corresponding to the second warning level.

[0085] In actual applications, since patients have different tolerances when they suffer from different underlying diseases, it can be determined whether to adjust the threshold range corresponding to the second warning level, and the adjustment range of the threshold range corresponding to the second warning level can be determined according to whether the patient's underlying disease belongs to the preset type of disease. Among them, the preset type of disease includes comorbidities such as cardiovascular disease and renal failure, and different preset types of diseases can correspond to different preset adjustment ranges.

[0086] Specifically, based on the patient's basic symptoms and the threshold range corresponding to the second warning level, the target threshold range corresponding to the second warning level is determined, which may be in the following ways but not limited to:

[0087] First, determine whether the patient's underlying disease belongs to the preset type of disease;

[0088] Then, if the patient's underlying condition belongs to the preset type of condition, the threshold range corresponding to each second-class warning level will be lowered, and the lowered threshold range will be used as the target threshold range corresponding to each second-class warning level; if the patient's underlying condition does not belong to the preset type of condition, the threshold range corresponding to each second-class warning level output by the first threshold assessment model will be used as the target threshold range corresponding to each second-class warning level.

[0089] Step 204: Based on the second warning level and the target threshold range corresponding to the second warning level, determine the second warning level corresponding to the real-time under-volume, and use the second warning level corresponding to the real-time under-volume as the second target warning level.

[0090] Step 205: Based on the correspondence between the second type of warning level and the warning operation, execute the warning operation corresponding to the second type of target warning level.

[0091] In actual applications, the second warning level is the warning level of real-time negative underflow, and the second warning level can include the second level one warning, the second level two warning, and the second level three warning. Each warning level corresponds to a warning operation. The warning operation corresponding to the second level one warning is to display the warning level and the real-time negative underflow, light up the corresponding indicator light or make the indicator light display the corresponding color; the warning operation corresponding to the second level one warning is to display the warning level and the real-time negative underflow, light up the corresponding indicator light or make the indicator light display the corresponding color, and issue a voice prompt corresponding to the current abnormal absorption of uterine distension fluid; the warning operation corresponding to the second level three warning is to display the warning level and the real-time negative underflow, light up the corresponding indicator light or make the indicator light display the corresponding color, issue a voice prompt corresponding to the current excessive absorption of uterine distension fluid, and control the uterine distension fluid injection device to stop injecting uterine distension fluid. As the second warning level increases, the intensity and frequency of the alarm sound will increase.

[0092] In one possible embodiment, since systemic absorption of fluid increases significantly when intrauterine pressure exceeds mean arterial pressure, to reduce the risk of excessive absorption of distending fluid, see Figure 3 As shown in the figure, after obtaining the electrocoagulation and electroresection data, uterine distention fluid data and the current operation type, it also includes:

[0093] Step 301: Obtain the patient's current intrauterine pressure and mean arterial pressure.

[0094] Step 302: Determine the difference between the intrauterine pressure and the mean arterial pressure as the pressure difference, and determine the ratio of the pressure difference to the mean arterial pressure as the pressure increase ratio.

[0095] Step 303: Based on the preset third warning level and the threshold range corresponding to the third warning level, determine the third warning level corresponding to the boost ratio, and use the third warning level corresponding to the boost ratio as the third target warning level.

[0096] Step 304: Based on the correspondence between the third type of warning level and the warning operation, execute the warning operation corresponding to the third type of target warning level.

[0097] In actual applications, the current intrauterine pressure is detected and sent by the distending fluid supply device, and the average pulsatile pressure is collected and sent by the external blood pressure monitoring device. The third category warning level includes the third category level 1 warning, the third category level 2 warning, and the third category level 3 warning. Correspondingly, the threshold range of the third category level 1 warning is 0~20%, the threshold range of the third category level 2 warning is 20~30%, and the threshold range of the third category level 3 warning is greater than 30%. Each warning level corresponds to an indicator light of a certain color. As the third category warning level increases, the intensity and frequency of the alarm sound will increase.

[0098] In a possible implementation, the hysteroscopic surgery early warning method further includes:

[0099] First, after the operation, all the electrocoagulation and electroresection data and uterine distention fluid data during the operation should be saved;

[0100] Then, based on all the electrocoagulation and electroresection data and uterine distention fluid data, an electrocoagulation and electroresection data-uterine distention fluid data image is drawn and saved;

[0101] Next, based on all the electrocoagulation and electroresection data, the behavioral data during the operation are determined, wherein the behavioral data includes the single duration, total number and total duration of the electroresection and electrocoagulation behaviors;

[0102] Finally, an association relationship between the current operation type, uterine distension fluid data, and behavior data is established, and the association relationship and the current operation type, uterine distension fluid data, and behavior data are saved.

[0103] In practical applications, all the electrocoagulation and electroresection data and uterine distention fluid data during the operation can be used to train the negative underflow prediction model. Based on the electrocoagulation and electroresection data and the negative underflow of uterine distention fluid during the entire operation, the electrocoagulation and electroresection data at the same time are used as the horizontal coordinate, and the real-time negative underflow of uterine distention fluid is used as the vertical coordinate to draw the electrocoagulation and electroresection data-uterine distention fluid negative underflow image, wherein the image includes multiple segment data curves, and the data curve can be a curve between the electrocoagulation foot pressure and the negative underflow or a curve between the electroresection foot pressure and the negative underflow. During the patient's operation of this type, the changing relationship between the electrocoagulation and electroresection data-uterine distention fluid data image intuitively shows the impact of electrocoagulation and electroresection behavior on negative underflow. The storage medium stores multiple groups of associations and the current operation type, uterine distention fluid data, and behavior data. For the data of the same current operation type, the uterine distention fluid data that meets the preset requirements can be screened out, and the corresponding behavior data can be obtained, the rules of the behavior data can be summarized, and the electrocoagulation and electroresection recommendations for the current operation type can be given.

[0104] In a possible implementation, the hysteroscopic surgery early warning method further comprises:

[0105] When the operation duration exceeds the preset duration, the warning for the operation will be stopped.

[0106] In a possible implementation, before obtaining real-time electrocoagulation and electroresection data, real-time negative and insufficient volume of uterine distention fluid, and the current operation type, it is necessary to train a negative and insufficient volume prediction model. The specific training method may be, but is not limited to, the following methods:

[0107] First, a training set is obtained; wherein the training set includes multiple groups of monitoring data, wherein each group of monitoring data includes electrocoagulation and electroresection data and negative or insufficient amount of uterine fluid at the same time;

[0108] Then, each set of monitoring data in the training set is input into the negative quantity shortage prediction model to obtain the negative quantity shortage prediction result corresponding to each set of monitoring data; wherein the negative quantity shortage prediction result includes the predicted negative quantity shortage at the first time after the collection time of the monitoring data;

[0109] Next, based on the negative quantity shortage prediction results and negative quantity shortage labeling results corresponding to each set of monitoring data, the loss function value is determined; wherein the negative quantity shortage labeling result is the actual negative quantity shortage at the first time after the monitoring data is collected;

[0110] Finally, based on the loss function value, the model parameters of the negative under-quantity prediction model are updated.

[0111] In the specific implementation, each group of monitoring data in the training set includes the electrocoagulation and electroresection data and the negative underflow of uterine fluid at the same time; the monitoring data in the training set can be obtained from all the electrocoagulation and electroresection data and uterine distention fluid data stored during the operation. The loss function can be one of the mean square error function, the root mean square error function, and the mean absolute error function. The loss function value output by the loss function can evaluate the difference between the negative underflow prediction result output by the negative underflow prediction model and the negative underflow description result. The smaller the loss function value, the higher the prediction accuracy of the negative underflow prediction model. Based on the loss function value, it is judged whether the loss function value is less than the preset threshold; wherein the preset threshold can be set according to actual needs. If the loss function value is not less than the preset threshold, the model parameters of the negative underflow prediction model are updated and retrained until the loss function value is less than the preset threshold to obtain the final negative underflow prediction model.

[0112] Based on the above embodiments, the present application provides a hysteroscopic surgery early warning device, see Figure 4 As shown, the hysteroscopic surgery early warning device 400 provided in the embodiment of the present application at least includes:

[0113] The data acquisition unit 401 is used to acquire real-time electrocoagulation and electroresection data, real-time negative or insufficient amount of uterine distention fluid, and the current operation type; wherein the real-time electrocoagulation and electroresection data are the real-time electrocoagulation pedal pressure of the hysteroscope electrocoagulation control pedal and the real-time electroresection pedal pressure of the hysteroscope electroresection control pedal; the real-time negative or insufficient amount of uterine distention fluid is determined by the real-time infusion weight and the real-time outflow weight of the uterine distention fluid;

[0114] The data prediction unit 402 is used to input the real-time electrocoagulation and electroresection data and the real-time negative underflow into the negative underflow prediction model to obtain the predicted negative underflow outputted by the negative underflow prediction model;

[0115] A first threshold determination unit 403 is used to obtain the first warning level corresponding to the current surgery type and the first warning threshold range corresponding to the first warning level based on a preset mapping relationship between the surgery type, the first warning level and the first warning threshold range;

[0116] The first risk warning unit 404 is used to use the first type of warning level corresponding to the threshold range to which the predicted under-volume belongs as the predicted warning level, and issue a first type of operation risk warning when the predicted warning level is higher than a preset level.

[0117] In a possible implementation, the hysteroscopic surgery early warning device further includes:

[0118] The second risk warning unit 405 is used to obtain the historical negative or insufficient amount of the uterine distension fluid; wherein the historical negative or insufficient amount of the uterine distension fluid is determined by the historical infusion weight and the historical outflow weight of the uterine distension fluid; based on the historical negative or insufficient amount and the real-time negative or insufficient amount, determine the real-time change value of the negative or insufficient amount; judge whether the real-time change value is greater than a preset change threshold; if so, issue an operation risk warning when the real-time pedal pressure is not zero.

[0119] In a possible implementation, the hysteroscopic surgery early warning device further includes:

[0120] The first warning unit 406 is used to obtain the patient's case data and uterine distension fluid type; wherein the case data includes the patient's age, the patient's current condition and the patient's basic condition; the patient's age, the patient's current condition and the uterine distension fluid type are input into the first threshold evaluation model to obtain the second type of warning level and the threshold range corresponding to the second type of warning level; based on the patient's basic condition and the threshold range corresponding to the second type of warning level, the target threshold range corresponding to the second type of warning level is determined; based on the second type of warning level and the target threshold range corresponding to the second type of warning level, the second type of warning level corresponding to the real-time negative under-volume is determined, and the second type of warning level corresponding to the real-time negative under-volume is used as the second type of target warning level; based on the correspondence between the second type of warning level and the warning operation, the warning operation corresponding to the second type of target warning level is executed.

[0121] In a possible implementation, the first early warning unit 406 is specifically configured to:

[0122] Determine whether the patient's underlying condition belongs to the preset type of condition;

[0123] If yes, then the threshold range corresponding to each second-class warning level is adjusted downward, and the lowered threshold range is used as the target threshold range corresponding to each second-class warning level;

[0124] If not, the threshold ranges corresponding to the respective second warning levels output by the first threshold assessment model are used as the target threshold ranges corresponding to the respective second warning levels.

[0125] In a possible implementation, the hysteroscopic surgery early warning device further includes:

[0126] The second warning unit 407 is used to obtain the patient's current intrauterine pressure and mean arterial pressure; determine the difference between the intrauterine pressure and the mean arterial pressure as the pressure difference, and determine the ratio of the pressure difference to the mean arterial pressure as the pressurization ratio; based on a preset third-category warning level and a threshold range corresponding to the third-category warning level, determine the third-category warning level corresponding to the pressurization ratio, and use the third-category warning level corresponding to the pressurization ratio as the third-category target warning level; based on the correspondence between the third-category warning level and the warning operation, execute the warning operation corresponding to the third-category target warning level.

[0127] In a possible implementation, the hysteroscopic surgery early warning device further comprises:

[0128] The data storage processing unit 408 is used to save all the electrocoagulation and electroresection data and negative underflow data during the operation after the operation is completed; determine the behavioral data during the operation based on all the electrocoagulation and electroresection data, wherein the behavioral data includes the single duration, total number and total duration of the electrocoagulation and electroresection behavior; establish an association between the current operation type, negative underflow data and behavioral data, and save the association as well as the current operation type, uterine distention fluid data and behavioral data.

[0129] In a possible implementation, the hysteroscopic surgery early warning device further comprises:

[0130] The model training unit 409 is used to obtain a training set; wherein the training set includes multiple groups of monitoring data, wherein each group of monitoring data includes electrocoagulation and electroresection data and negative underflow of uterine fluid at the same time; each group of monitoring data in the training set is input into the negative underflow prediction model respectively to obtain the negative underflow prediction result corresponding to each group of monitoring data; wherein the negative underflow prediction result includes the predicted negative underflow at the first time after the collection time of the monitoring data; based on the negative underflow prediction result and the negative underflow marking result corresponding to each group of monitoring data, the loss function value is determined; wherein the negative underflow marking result is the actual negative underflow at the first time after the collection time of the monitoring data; based on the loss function value, the model parameters of the negative underflow prediction model are updated.

[0131] It should be noted that the principle of solving the technical problem by the hysteroscopic surgery warning device 400 provided in the embodiment of the present application is similar to the hysteroscopic surgery warning method provided in the embodiment of the present application. Therefore, the implementation of the hysteroscopic surgery warning device 400 provided in the embodiment of the present application can refer to the implementation of the hysteroscopic surgery warning method provided in the embodiment of the present application, and the repeated parts will not be repeated.

[0132] After introducing the hysteroscopic surgery early warning method and device provided in the embodiment of the present application, next, the hysteroscopic surgery early warning system provided in the embodiment of the present application is briefly introduced.

[0133] See also Figure 5 As shown, the hysteroscopic surgery early warning system 500 provided in the embodiment of the present application at least includes: a first weight sensor 501, a second weight sensor 502, a first pressure sensor 503, a second pressure sensor 504 and a processor 505;

[0134] The first weight sensor 501 is disposed at the bottom of the uterine distension fluid supply device, and the first weight sensor 501 is used to collect the weight of the uterine distension fluid injected;

[0135] The second weight sensor 502 is disposed at the bottom of the uterine distension fluid outflow storage device, and the second weight sensor 502 is used to collect the outflow weight of the uterine distension fluid;

[0136] The first pressure sensor 503 is arranged at the bottom of the hysteroscope electrocoagulation control pedal, and the first pressure sensor 503 is used to collect the electrocoagulation pedal pressure;

[0137] The second pressure sensor 504 is disposed at the bottom of the hysteroscope electrosurgical resection control pedal, and the second pressure sensor 504 is used to collect the electrosurgical resection pedal pressure;

[0138] The processor is connected to the first weight sensor 501, the second weight sensor 502, the first pressure sensor 503 and the second pressure sensor 504 respectively; the processor 505 is used to execute the computer program corresponding to the hysteroscopic surgery early warning method proposed in the above embodiment of the present application.

[0139] In a possible implementation, the hysteroscopic surgery warning system 500 further includes: a first flow sensor 506 disposed on the inlet pipeline of the uterine distension fluid and a second flow sensor 507 disposed on the outlet pipeline of the uterine distension fluid;

[0140] The first flow sensor 506 is used to collect the inflow flow of the uterine distension fluid; the second flow sensor 507 is used to collect the outflow flow of the uterine distension fluid.

[0141] It should be noted that, although several units or subunits of the device are mentioned in the above detailed description, this division is merely exemplary and not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more units described above can be embodied in one unit. Conversely, the features and functions of one unit described above can be further divided into multiple units to be embodied.

[0142] In addition, although the operations of the method of the present application are described in a specific order in the drawings, this does not require or imply that the operations must be performed in this specific order, or that all the operations shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps.

[0143] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0144] Obviously, those skilled in the art can make various changes and modifications to the embodiments of the present application without departing from the spirit and scope of the embodiments of the present application. Thus, if these modifications and variations of the embodiments of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A hysteroscopic surgery early warning device, characterized in that: include: A data acquisition unit, used to acquire real-time electrocoagulation and electroresection data, real-time negative and insufficient amount of uterine distention fluid, and current operation type; wherein the real-time electrocoagulation and electroresection data are real-time electrocoagulation pedal pressure of the hysteroscope electrocoagulation control pedal and real-time electroresection pedal pressure of the hysteroscope electroresection control pedal; the real-time negative and insufficient amount of uterine distention fluid is determined by the real-time infusion weight and real-time outflow weight of the uterine distention fluid; A data prediction unit, used for inputting the real-time electrocoagulation and electroresection data and the real-time negative underflow into a negative underflow prediction model to obtain a predicted negative underflow outputted by the negative underflow prediction model; A first threshold determination unit, configured to obtain a first warning level corresponding to a current surgery type and a first warning threshold range corresponding to the first warning level based on a preset mapping relationship between the surgery type, the first warning level, and the first warning threshold range; A first risk warning unit is used to take the first type of warning level corresponding to the threshold range to which the predicted under-volume belongs as the predicted warning level, and perform a warning operation corresponding to the level of the predicted warning level; The hysteroscopic surgery early warning device is used to perform a hysteroscopic surgery early warning method, and the hysteroscopic surgery early warning method includes: Acquire real-time electrocoagulation and electroresection data, real-time negative and insufficient amount of uterine distention fluid, and current operation type; wherein the real-time electrocoagulation and electroresection data are the real-time electrocoagulation pedal pressure of the hysteroscope electrocoagulation control pedal and the real-time electroresection pedal pressure of the hysteroscope electroresection control pedal; the real-time negative and insufficient amount of uterine distention fluid is determined by the real-time infusion weight and the real-time outflow weight of the uterine distention fluid; Inputting the real-time electrocoagulation and electroresection data and the real-time under-discharge into a under-discharge prediction model to obtain a predicted under-discharge output by the under-discharge prediction model; Based on the preset mapping relationship between the surgery type, the first warning level and the first warning threshold range, the first warning level corresponding to the current surgery type and the first warning threshold range corresponding to the first warning level are obtained; The first type of warning level corresponding to the threshold range to which the predicted under-volume belongs is used as the predicted warning level, and a warning operation corresponding to the level of the predicted warning level is performed.

2. The hysteroscopic surgery early warning device according to claim 1, characterized in that: During the process of the hysteroscopic surgery early warning device performing the hysteroscopic surgery early warning method, after obtaining the real-time electrocoagulation and electroresection data, the real-time negative and negative volume of the uterine distention fluid and the current surgery type, the device further comprises: Obtaining the historical negative or negative amount of the uterine distension fluid; wherein the historical negative or negative amount of the uterine distension fluid is determined by the historical infusion weight and the historical outflow weight of the uterine distension fluid; Based on the historical underpayment and the real-time underpayment, determining a real-time change value of the underpayment; Determine whether the real-time change value is greater than a preset change threshold; If so, an operation risk prompt will be issued if the real-time pedal pressure is not zero.

3. The hysteroscopic surgery early warning device according to claim 1, characterized in that: During the process of the hysteroscopic surgery early warning device executing the hysteroscopic surgery early warning method, after obtaining the real-time electrocoagulation and electroresection data, the real-time negative and negative volume of uterine distention fluid and the current surgery type, the device further comprises: Obtaining the patient's medical records and the type of uterine distention fluid; wherein the medical records include the patient's age, the patient's current condition, and the patient's underlying condition; Inputting the patient's age, the patient's current condition and the type of uterine distention fluid into a first threshold evaluation model to obtain a second warning level and a threshold range corresponding to the second warning level; Determining a target threshold range corresponding to the second warning level based on the patient's underlying condition and the threshold range corresponding to the second warning level; Based on the second warning level and the target threshold range corresponding to the second warning level, determine the second warning level corresponding to the real-time under-volume, and use the second warning level corresponding to the real-time under-volume as the second target warning level; Based on the correspondence between the second type of warning level and the warning operation, the warning operation corresponding to the second type of target warning level is executed.

4. The hysteroscopic surgery early warning device according to claim 3, characterized in that: During the process of the hysteroscopic surgery early warning device executing the hysteroscopic surgery early warning method, determining the target threshold range corresponding to the second type of early warning level based on the patient's basic condition and the threshold range corresponding to the second type of early warning level includes: Determine whether the patient's underlying condition belongs to a preset type of condition; If yes, then the threshold range corresponding to each second-class warning level is adjusted downward, and the lowered threshold range is used as the target threshold range corresponding to each second-class warning level; If not, the threshold ranges corresponding to the respective second warning levels output by the first threshold assessment model are used as the target threshold ranges corresponding to the respective second warning levels.

5. The hysteroscopic surgery early warning device according to claim 1, characterized in that: The process in which the hysteroscopic surgery early warning device performs the hysteroscopic surgery early warning method also includes: Obtain the patient's current intrauterine pressure and mean arterial pressure; Determining the difference between the intrauterine pressure and the mean arterial pressure as a pressure difference, and determining the ratio of the pressure difference to the mean arterial pressure as a pressure increase ratio; Based on a preset third warning level and a threshold range corresponding to the third warning level, determining the third warning level corresponding to the boost ratio, and using the third warning level corresponding to the boost ratio as the third target warning level; Based on the correspondence between the third type of warning level and the warning operation, the warning operation corresponding to the third type of target warning level is performed.

6. The hysteroscopic surgery early warning device according to any one of claims 1 to 5, characterized in that: The process of the hysteroscopic surgery early warning device executing the hysteroscopic surgery early warning method further includes: After the operation is completed, all the electrocoagulation and electroresection data and negative and insufficient volume data during the operation are saved; Based on all the electrocoagulation and electroresection data, determining the behavior data during the operation, wherein the behavior data includes the single duration, total number and total duration of the electroresection and electrocoagulation behavior; Establish an association relationship between the current operation type, the negative and insufficient volume data, and the behavior data, and save the association relationship as well as the current operation type, the uterine distension fluid data, and the behavior data.

7. The hysteroscopic surgery early warning device according to claim 6, characterized in that: In the process of the hysteroscopic surgery early warning device performing the hysteroscopic surgery early warning method, before obtaining the real-time electrocoagulation and electroresection data, the real-time negative and negative volume of the uterine distention fluid and the current surgery type, the device also includes: Acquire a training set; wherein the training set includes multiple groups of monitoring data, wherein each group of monitoring data includes electrocoagulation and electroresection data and negative or insufficient volume of uterine fluid at the same time; Input each set of monitoring data in the training set into the negative quantity shortage prediction model to obtain the negative quantity shortage prediction result corresponding to each set of monitoring data; wherein the negative quantity shortage prediction result includes the predicted negative quantity shortage at the first time after the collection time of the monitoring data; Determine the loss function value based on the negative quantity shortage prediction result and the negative quantity shortage marking result corresponding to each set of monitoring data; wherein the negative quantity shortage marking result is the actual negative quantity shortage at the first time after the monitoring data is collected; Based on the loss function value, the model parameters of the negative shortage prediction model are updated.

8. A hysteroscopic surgery early warning system, characterized in that: include: a first weight sensor, a second weight sensor, a first pressure sensor, a second pressure sensor, and a processor; The first weight sensor is disposed at the bottom of the uterine distension fluid supply device, and the first weight sensor is used to collect the weight of the uterine distension fluid injected; The second weight sensor is disposed at the bottom of the uterine distension fluid outflow storage device, and the second weight sensor is used to collect the outflow weight of the uterine distension fluid; The first pressure sensor is arranged at the bottom of the hysteroscope electrocoagulation control pedal, and the first pressure sensor is used to collect the electrocoagulation pedal pressure; The second pressure sensor is arranged at the bottom of the hysteroscope electroresection control pedal, and the second pressure sensor is used to collect the electroresection pedal pressure; The processor is connected to the first weight sensor, the second weight sensor, the first pressure sensor and the second pressure sensor respectively; the processor is used to execute the computer program corresponding to the hysteroscopic surgery warning method in the hysteroscopic surgery warning device as described in any one of claims 1-7.

9. The hysteroscopic surgery early warning system according to claim 8, characterized in that: Also includes: A first flow sensor is arranged on the inlet pipeline of the uterine distension fluid, and a second flow sensor is arranged on the outlet pipeline of the uterine distension fluid; The first flow sensor is used to collect the infusion flow of the uterine distension fluid; the second flow sensor is used to collect the outflow flow of the uterine distension fluid.

Images