Auxiliary system and method for intestinal preparation before colonoscopy

Abstract

The invention provides an auxiliary system and method for intestinal preparation before colonoscopy. According to the auxiliary system and method, body fluid loss records of a patient to be examined can be monitored; net liquid loss rates are determined according to the body fluid loss records, and a dynamic balance relation between body fluid and electrolyte of the examined patient is constructed through all the net liquid loss rates; determining efficacy contribution degrees of different metabolites to intestinal preparation, and predicting the intestinal cleanliness of the patient to be examined through a pre-trained cleanliness prediction model; and carrying out fusion evaluation on the dynamic equilibrium relationship between the body fluid and electrolyte of the patient to be examined and the prediction result of the intestinal tract cleanliness to obtain the in-vivo osmotic pressure imbalance risk of the patient to be examined when the intestinal tract is prepared. By adopting the scheme of the invention, non-standardized fluid infusion can be performed on the patient based on the dynamic association relationship between the body fluid loss rate of the patient and the electrolyte concentration change.

Description

Technical Field

[0001] This application relates to the technical field of intestinal preparation assistance, and more specifically, to an assistance system and method for intestinal preparation before colonoscopy. Background Art

[0002] Intestinal preparation assistance technology is mainly used for preoperative examinations (such as colonoscopy) or intestinal cleansing before surgery to improve the accuracy and safety of the examination or surgery; common methods include oral bowel cleansing solutions, dietary adjustments, the use of drugs to promote intestinal peristalsis, and new physical assistance means; in recent years, a variety of assistance technologies have been introduced, such as low-residue diet combined with personalized hydration plans, intelligent emptying monitoring systems, probiotics to regulate the intestinal flora to promote emptying, vibrating capsules to enhance intestinal peristalsis, and transcutaneous electrical stimulation to regulate gastrointestinal motility; by analyzing the patient's physical constitution, eating habits, and previous bowel cleansing reactions, the most suitable plan is recommended to improve the adequacy and comfort of bowel cleansing, thereby enhancing the efficiency of intestinal preparation, reducing the repetition of examinations caused by incomplete cleansing, and increasing the early diagnosis rate of digestive tract diseases.

[0003] Intestinal preparation before colonoscopy is crucial, directly affecting the accuracy of the examination and the comfort of the patient; traditional methods usually use bowel cleansing solutions such as polyethylene glycol or sodium phosphate for intestinal cleansing, but due to the large liquid intake and possible adverse reactions (such as nausea, vomiting, electrolyte disorders, etc.), the compliance of some patients is relatively low, affecting the bowel cleansing effect; to optimize the intestinal preparation process, a variety of assistance technologies have been introduced in recent years, including personalized diet adjustments, intelligent monitoring systems, biological regulation interventions, and physical assistance emptying means; personalized diet adjustments combined with low-residue diets and customized hydration strategies can reduce intestinal residues and maintain electrolyte balance. However, in the existing intestinal preparation assistance methods before colonoscopy, it is usually through collecting the total body fluid data of the patient and the results of stage cleanliness assessments, and intervening based on a standardized fluid replacement plan to meet the requirements of intestinal cleanliness; however, this method often fails to fully capture the dynamic relationship between the patient's body fluid loss rate and the change in electrolyte concentration (such as the non-linear fluctuation of sodium ion concentration presenting 0.5 - 2.1 mmol / L per hour in continuous monitoring), that is, it causes a single fluid replacement model to be difficult to adapt to diverse physiological characteristics, and further makes the fluid replacement plan for the patient deviate from the actual needs. Therefore, how to perform non-standardized fluid replacement for patients based on the dynamic relationship between the patient's body fluid loss rate and the change in electrolyte concentration has become a difficult problem faced by the industry. Summary of the Invention

[0004] This application provides an assistance system and method for intestinal preparation before colonoscopy, which can perform non-standardized fluid replacement for patients based on the dynamic relationship between the patient's body fluid loss rate and the change in electrolyte concentration.

[0005] In a first aspect, the present application provides a method for detecting the risk of intestinal osmotic pressure, comprising the following steps: Monitoring the fluid loss record of the patient to be examined; Determining the net fluid loss rate of the patient to be examined in different time periods according to the fluid loss record, and then constructing a dynamic balance relationship between the body fluid and electrolytes of the patient to be examined by combining all the net fluid loss rates with the concentration characteristics of electrolytes in the body fluid of the patient to be examined; Determining the contribution degree of different metabolites to the efficacy of intestinal preparation based on the intestinal metabolism data of the patient to be examined, and then inputting all the contribution degrees and the clinical characteristics of the patient to be examined into a pre-trained cleanliness prediction model to predict the intestinal cleanliness of the patient to be examined; Fusing and evaluating the dynamic balance relationship between the body fluid and electrolytes of the patient to be examined and the prediction result of the intestinal cleanliness to obtain the risk of osmotic pressure imbalance in the body of the patient to be examined during intestinal preparation.

[0006] In some embodiments, determining the net fluid loss rate of the patient to be examined in different time periods according to the fluid loss record specifically includes: Selecting the fluid loss amount corresponding to one sampling period in the fluid loss record as the selected fluid loss amount; Obtaining the fluid replenishment amount of the patient to be examined in this sampling period; Determining the net fluid loss rate of the patient to be examined in this sampling period through the fluid replenishment amount and the selected fluid loss amount; Continuing to determine the net fluid loss rate of the patient to be examined in the remaining sampling periods, that is, obtaining the net fluid loss rate of the patient to be examined in different time periods.

[0007] In some embodiments, constructing a dynamic balance relationship between the body fluid and electrolytes of the patient to be examined by combining all the net fluid loss rates with the concentration characteristics of electrolytes in the body fluid of the patient to be examined specifically includes: Obtaining the electrolyte concentration data of the patient to be examined in multiple sampling periods; Calculating the body fluid concentration change rate of the patient to be examined in each sampling period according to all the net fluid loss rates and the electrolyte concentration data; Determining the dynamic balance parameters by combining all the body fluid concentration change rates with the normal electrolyte concentration range; Constructing a dynamic balance relationship between the body fluid and electrolytes of the patient to be examined through the dynamic balance parameters.

[0008] In some embodiments, determining the contribution degree of different metabolites to the efficacy of intestinal preparation based on the intestinal metabolism data of the patient to be examined specifically includes: Obtaining the intestinal metabolism data of the patient to be examined; Determine the linear correlation degree between each metabolite and the bowel preparation of the patient to be examined based on the intestinal metabolism data; Determine the efficacy contribution degree of different metabolites to bowel preparation based on all the linear correlation degrees.

[0009] In some embodiments, inputting all the efficacy contribution degrees and the clinical characteristics of the patient to be examined into a pre-trained cleanliness prediction model to predict the bowel cleanliness of the patient to be examined specifically includes: Obtain the clinical characteristics of the patient to be examined; Take all the efficacy contribution degrees as the feature weights of the cleanliness prediction model and the clinical characteristics as the basic input variables of the cleanliness prediction model; Output the prediction result of the bowel cleanliness of the patient to be examined through the cleanliness prediction model.

[0010] In some embodiments, fusing and evaluating the dynamic balance relationship between the body fluid and electrolytes of the patient to be examined and the prediction result of the bowel cleanliness to obtain the risk of osmotic pressure imbalance in the body of the patient to be examined during bowel preparation specifically includes: Determine the real-time imbalance index between the body fluid and electrolytes of the patient to be examined through the dynamic balance relationship between the body fluid and electrolytes of the patient to be examined; Fuse the real-time imbalance index with the prediction result of the bowel cleanliness into the risk of osmotic pressure imbalance in the body of the patient to be examined during bowel preparation.

[0011] In some embodiments, it further includes: adjusting the bowel rehydration plan of the patient to be examined in real time according to the imbalance risk.

[0012] In a second aspect, the present application provides an auxiliary system for bowel preparation before colonoscopy. The auxiliary system for bowel preparation before colonoscopy includes a risk detection unit, and the risk detection unit includes: A monitoring module for monitoring the body fluid loss record of the patient to be examined; A processing module for determining the net fluid loss rate of the patient to be examined in different time periods according to the body fluid loss record, and then constructing the dynamic balance relationship between the body fluid and electrolytes of the patient to be examined by combining all the net fluid loss rates with the concentration characteristics of electrolytes in the body fluid of the patient to be examined; The processing module is further configured to determine the efficacy contribution degree of different metabolites to bowel preparation based on the intestinal metabolism data of the patient to be examined, and then input all the efficacy contribution degrees and the clinical characteristics of the patient to be examined into a pre-trained cleanliness prediction model to predict the bowel cleanliness of the patient to be examined; The execution module is further configured to perform a fusion evaluation on the dynamic balance relationship between the body fluid and electrolytes of the patient to be examined and the prediction result of the intestinal cleanliness, so as to obtain the imbalance risk of the body osmotic pressure in the patient to be examined during intestinal preparation.

[0013] In a third aspect, the present application provides a computer device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the steps of the above-mentioned intestinal osmotic pressure risk detection method are implemented.

[0014] In a fourth aspect, the present application provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned intestinal osmotic pressure risk detection method are implemented.

[0015] The technical solutions provided by the disclosed embodiments of the present application have the following beneficial effects: In the auxiliary system and method for intestinal preparation before colonoscopy provided by the present application, by monitoring the body fluid loss record of the patient to be examined; determining the net fluid loss rate of the patient to be examined in different time periods according to the body fluid loss record, and then constructing the dynamic balance relationship between the body fluid and electrolytes of the patient to be examined by combining all the net fluid loss rates with the concentration characteristics of electrolytes in the body fluid of the patient to be examined; determining the efficacy contribution degree of different metabolites to intestinal preparation based on the intestinal metabolism data of the patient to be examined, and then inputting all the efficacy contribution degrees and the clinical characteristics of the patient to be examined into a pre-trained cleanliness prediction model to predict the intestinal cleanliness of the patient to be examined; performing a fusion evaluation on the dynamic balance relationship between the body fluid and electrolytes of the patient to be examined and the prediction result of the intestinal cleanliness, so as to obtain the imbalance risk of the body osmotic pressure in the patient to be examined during intestinal preparation.

[0016] It can be seen that in this application, first, by monitoring the patient's body fluid loss in real time and combining it with the changes in the electrolyte concentration in the body fluid, a dynamic balance relationship between the patient's body fluid and electrolytes is established, which helps to comprehensively understand the patient's water-salt balance state. Specifically, by using intelligent devices to collect continuous data, the net fluid loss rate in different time periods can be accurately calculated, and then combined with the electrolyte concentration characteristics, the dynamic fluctuation of the patient's body fluid composition can be reflected, thereby providing a scientific basis for formulating personalized and non-standardized fluid replacement plans. Through quantitative analysis of the dynamic balance, it can be identified whether the patient is in different stages such as dehydration, overhydration, or electrolyte disorder, ensuring that the fluid replacement plan can meet clinical needs and avoid the risks of over-replacement or under-replacement. Then, on the basis of establishing the dynamic balance relationship, the plan further integrates the prediction results of intestinal cleanliness to comprehensively evaluate the risk of in vivo osmotic pressure imbalance and provides a risk grading reference for personalized fluid replacement. Specifically, through the joint analysis of the dynamic change data of the patient's body fluid and electrolytes and the contribution degree of metabolite efficacy, the risk of in vivo osmotic pressure imbalance during the intestinal preparation period can be predicted, and possible osmotic abnormalities can be detected in advance. The evaluation results can guide medical staff to adjust the fluid replacement plan in real time according to different risk levels, such as adjusting the type, concentration, and infusion rate of the fluid, so as to achieve accurate fluid replacement. This process not only helps to avoid individual differences caused by standardized plans, but also realizes the whole-process dynamic monitoring of patients through risk early warning, effectively improving the safety of patients and the effect of intestinal preparation before examination. In summary, this plan can determine the risk of osmotic pressure imbalance based on the dynamic correlation between the patient's body fluid loss rate and the change in electrolyte concentration, so as to perform non-standardized fluid replacement for the patient. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 is a schematic flowchart of a method for detecting intestinal osmotic pressure risk according to some embodiments of the present application; Figure 2 is a schematic flowchart of constructing a dynamic smoothing relationship according to some embodiments of the present application; Figure 3 is a schematic flowchart of risk early warning according to some embodiments of the present application; Figure 4 is a schematic structural diagram of an auxiliary system for intestinal preparation before colonoscopy according to some embodiments of the present application; Figure 5 is an internal structural diagram of a computer device for implementing the method for detecting intestinal osmotic pressure risk according to some embodiments of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0018] In order to better understand the technical solutions in this embodiment, the technical solutions in this embodiment will be described in detail below in combination with the accompanying drawings of the specification and specific implementation manners.

[0019] Reference Figure 1 , the figure is a schematic flowchart of a method for detecting intestinal osmotic pressure risk shown according to some embodiments of the present application. The intestinal osmotic pressure risk detection method 100 mainly includes the following steps In step 101, monitor the body fluid loss record of the patient to be examined.

[0020] Specifically, an intelligent toilet can be used to measure the urine volume record of the patient to be examined through a set sampling period. Then, an intelligent bracelet is used to measure the sweat evaporation record of the patient to be examined through a set sampling period. After that, the urine volume and sweat evaporation amount in each sampling period in the urine volume record and the sweat evaporation record are added together as the body fluid loss amount of the patient to be examined. Furthermore, the time series obtained by sorting all body fluid loss amounts in the chronological order of the sampling period is used as the body fluid loss record in the present application.

[0021] It should be noted that in the present application, the intelligent toilet measures the urine volume of the patient to be examined in real time through a flow sensor (such as a Hall effect flowmeter), and the intelligent bracelet detects the local skin humidity change through a humidity sensor to calculate the sweat evaporation amount. In addition, the sampling period is set to 3 hours.

[0022] In step 102, determine the net fluid loss rate of the patient to be examined in different time periods according to the body fluid loss record. Then, through all the net fluid loss rates, combined with the concentration characteristics of electrolytes in the body fluid of the patient to be examined, a dynamic balance relationship between the body fluid and electrolytes of the patient to be examined is constructed.

[0023] It should be noted that each sampling period in the present application has a uniquely corresponding time period; therefore, in some embodiments, determining the net fluid loss rate of the patient to be examined in different time periods according to the body fluid loss record can be implemented by the following steps: Select the body fluid loss amount corresponding to a sampling period in the body fluid loss record as the selected body fluid loss amount; Obtain the fluid replenishment amount of the patient to be examined in this sampling period; Determine the net fluid loss rate of the patient to be examined in this sampling period through the fluid replenishment amount and the selected body fluid loss amount; Continue to determine the net fluid loss rate of the patient to be examined in the remaining sampling periods, that is, obtain the net fluid loss rate of the patient to be examined in different time periods.

[0024] It should be noted that the liquid replenishment amount described in this application refers to the total amount of liquid obtained by the patient to be examined through various channels (including intravenous infusion and oral intake) within a specific sampling period. Specifically, when implemented, after obtaining the liquid replenishment record from the electronic medical record of the patient to be examined, the liquid replenishment amount of the patient to be examined in this sampling period can be obtained from the liquid replenishment record. It should be noted that the liquid replenishment record includes the liquid replenishment amounts of the patient to be examined in different sampling periods, and the liquid replenishment amount includes the sum of the volumes of intravenous infusions (such as physiological saline, glucose solution) and oral liquids (such as water, juice, decoction) of the patient to be examined in the corresponding sampling period.

[0025] Specifically, when implemented, the net liquid loss rate of the patient to be examined in this sampling period can be determined by the following method through the liquid replenishment amount and the selected body fluid loss amount, that is: First, determine the difference between the liquid replenishment amount and the selected body fluid loss amount, and then, take the ratio of the difference to the sampling period as the net liquid loss rate of the patient to be examined in this sampling period.

[0026] It should be noted that the net liquid loss rate described in this application refers to the quantified value of the dynamic change trend of the body fluid balance state of the patient to be examined within a specific time. The actual net loss rate of the liquid in the patient to be examined can be measured by the net liquid loss rate. When the net liquid loss rate is positive, it indicates that the body fluid of the patient to be examined is generally in a net loss state during this time period, which may lead to the risk of dehydration; when the net liquid loss rate is negative, it means that the liquid intake of the patient to be examined exceeds the loss during this time period, and there may be a situation of fluid retention; when the net liquid loss rate is close to zero, it indicates that the body fluid of the patient to be examined is in a relatively balanced state during this time period.

[0027] In some embodiments, referring to Figure 2 As shown, this figure is a schematic flowchart of constructing a dynamic smoothing relationship shown in some embodiments of this application. The dynamic balance relationship between the body fluid and electrolytes of the patient to be examined can be constructed by combining all the net liquid loss rates with the concentration characteristics of electrolytes in the body fluid of the patient to be examined, which can be implemented by the following steps: First, in 1021, obtain the electrolyte concentration data of the patient to be examined in multiple sampling periods; Then, in 1022, calculate the change amount of the body fluid concentration of the patient to be examined in each sampling period based on all the net liquid loss rates and the electrolyte concentration data; Subsequently, in 1023, determine the dynamic balance parameter of each sampling period by combining all the change amounts of the body fluid concentration with the normal electrolyte concentration range; Finally, in 1024, construct the dynamic balance relationship between the body fluid and electrolytes of the patient to be examined through all the dynamic balance parameters.

[0028] In specific implementation, the electrolyte concentration in the subcutaneous tissue fluid of the patient to be examined can be collected by a patch-type biosensor (such as a wearable device) at a set sampling period, and then the electrolyte concentration data of the patient to be examined in multiple sampling periods can be obtained. It should be noted that the electrolyte concentration data described in this application refers to a data set composed of the concentration content values of electrolytes in the body fluid of the patient to be examined at each sampling period.

[0029] It should be noted that in this application, it is set that the total amount of electrolytes in the patient to be examined is approximately constant, that is, in a short period of time (adjacent sampling periods), the total amount of electrolytes in the patient to be examined is regarded as unchanged. Therefore, in specific implementation, the change amount of the body fluid concentration of the patient to be examined in each sampling period can be calculated based on all net fluid loss rates and the electrolyte concentration data in the following way: First, obtain the reference body fluid volume of the patient to be examined. Then, select a sampling period and determine the result of multiplying the electrolyte concentration value in this sampling period by the reference body fluid volume. Subsequently, determine the result of the difference between the reference body fluid volume and the net fluid loss rate in this sampling period. Finally, take the ratio of the result of the above multiplication to the result of the above difference as the change amount of the body fluid concentration in this sampling period. Repeat the above steps to determine the change amount of the body fluid concentration of the patient to be examined in the remaining sampling periods.

[0030] In addition, it should be noted that the change amount of the body fluid concentration described in this application refers to the degree of change of the electrolyte concentration in the body fluid of the patient to be examined in a certain sampling period relative to the previous period, which is used to reflect the dynamic characteristics of body fluid dilution or concentration.

[0031] In specific implementation, the dynamic balance parameter can be determined by combining all the change amounts of the body fluid concentration and the normal electrolyte concentration range in the following way: First, obtain the normal electrolyte concentration range of the patient to be examined. Then, obtain the maximum electrolyte concentration and the minimum electrolyte concentration through the normal electrolyte concentration range. Furthermore, for each change amount of the body fluid concentration, using the maximum electrolyte concentration and the minimum electrolyte concentration as inputs, and adopting the normalization algorithm in the prior art, map each change amount of the body fluid concentration between (0, 1) to obtain the normalized value of each change amount of the body fluid concentration. Then, after obtaining the fitting parameters, taking all the fitting parameters as inputs, and using the non-linear mapping function in the prior art and combining the normalized values of each change amount of the body fluid concentration to determine the dynamic balance parameter of each sampling period. In other embodiments, other methods can also be used to determine it, which is not limited here.

[0032] It should be noted that the dynamic balance parameter described in this application refers to a value used to characterize the degree of deviation of the change in body fluid concentration from the normal electrolyte concentration range. This parameter is calculated by a non-linear mapping method so that it can not only reflect the fluctuations within the normal range but also amplify the abnormal changes beyond the normal range to improve the sensitivity to potential electrolyte imbalance. In addition, in order to make the dynamic balance parameter in this application reflect both the fluctuations of the concentration change amount within the normal range and amplify the abnormal changes beyond the range, the dynamic balance parameter is determined by combining the non-linear mapping function in the prior art with the average value. Among them, the non-linear mapping function includes multiple fitting parameters. Preferably, the fitting parameters can be determined by clinical trial fitting. In other embodiments, they can also be determined by other methods. For example, by combining historical data with the least squares method in the prior art, the partial derivatives of the fitting parameters are solved, and the error function is minimized to determine the numerical results of each fitting parameter. In other embodiments, other methods can also be used for determination, which is not limited here.

[0033] It should be noted that in this application, it is assumed that the total amount of electrolytes in the patient to be examined is approximately constant, and then a reference model of the patient to be examined is established based on this assumption. As a preferred embodiment, the equation that the electrolyte concentration in the patient to be examined is equal to the ratio of the total amount of electrolytes in the patient to be examined to the body fluid volume can be used as the reference model of the patient to be examined. Therefore, in specific implementation, the dynamic balance relationship between the body fluid and electrolytes of the patient to be examined can be constructed by all the dynamic balance parameters in the following way: that is, making the result of multiplying the ratio of the total amount of electrolytes to the body fluid volume in the above reference model by the dynamic balance parameter of the corresponding sampling period equal to the corrected electrolyte concentration in the body of the patient to be examined during the corresponding sampling period (that is, the electrolyte concentration adjusted by the dynamic balance parameter). Each obtained equation is used as the dynamic balance model between the body fluid and electrolytes of the patient to be examined during the corresponding sampling period. Then, all the dynamic balance models are used as the dynamic balance relationship between the body fluid and electrolytes of the patient to be examined in this application. In other embodiments, other methods can also be used for implementation, which is not limited here.

[0034] In addition, it should be noted that the dynamic balance relationship described in this application refers to a mathematical correlation model between body fluids and electrolytes in the patient to be examined during each sampling period; the dynamic balance relationship is constructed based on the reference body fluid volume, electrolyte concentration data, and dynamic balance parameters of the patient, and can quantify and predict the balance state and its change trend between body fluids and electrolytes. Among them, when the dynamic balance parameter in the dynamic balance relationship is greater than 1, it indicates that the change in the body fluid concentration exceeds the normal fluctuation range, and then the dynamic balance model will amplify the change in the predicted concentration, so as to more sensitively reflect the potential imbalance. On the contrary, when the dynamic balance parameter is close to 1, it indicates that the change in the body fluid concentration is within the normal range, and the output of the dynamic balance model is relatively stable.

[0035] In step 103, based on the intestinal metabolism data of the patient to be examined, the efficacy contribution degrees of different metabolites to intestinal preparation are determined, and then all the efficacy contribution degrees and the clinical characteristics of the patient to be examined are input into the pre-trained cleanliness prediction model to predict the intestinal cleanliness of the patient to be examined.

[0036] In some embodiments, the determination of the efficacy contribution degrees of different metabolites to intestinal preparation based on the intestinal metabolism data of the patient to be examined can be achieved by the following steps: Obtain the intestinal metabolism data of the patient to be examined; Determine the linear correlation degree between each metabolite and the intestinal preparation of the patient to be examined through the intestinal metabolism data; Determine the efficacy contribution degrees of different metabolites to intestinal preparation based on all the linear correlation degrees.

[0037] It should be noted that the intestinal metabolism data described in this application refers to the quantitative data of a series of metabolites produced by intestinal microorganisms, digestive enzymes, and host metabolism, which includes the detection values of each metabolite in the patient to be examined during different sampling periods. Among them, the metabolites include: salivary metabolites, urine metabolites, and intestinal flora activity indicators; preferably, short-chain fatty acids in the saliva of the patient to be examined can be quickly detected by microfluidic chip technology; the levels of hippuric acid and β-hydroxybutyric acid in urine can be analyzed by surface-enhanced Raman spectroscopy technology; the composition of intestinal flora can be evaluated by RNA sequencing technology, and then the set of detection results of each sampling period is used as the intestinal metabolism data of this application.

[0038] In specific implementation, the linear correlation degree between each metabolite and the bowel preparation of the patient to be examined can be determined based on the intestinal metabolism data in the following manner: First, obtain the bowel preparation record of the patient to be examined. Then, determine the mean value of the detection values of each metabolite in the intestinal metabolism data and the mean value of all bowel preparation evaluation values in the bowel preparation record. Subsequently, for each metabolite, use the detection values of the metabolite corresponding to all sampling periods and the bowel preparation record as the variable values of the Pearson correlation coefficient in the prior art, and use the mean value of the detection values of the corresponding metabolite and the mean value of the bowel preparation evaluation values as the variable means of the Pearson correlation coefficient in the prior art. Then, determine the Pearson correlation coefficient between each metabolite and the bowel preparation through the Pearson correlation coefficient, and use the corresponding Pearson correlation coefficient as the linear correlation degree between each metabolite and the bowel preparation of the patient to be examined. In other embodiments, it can also be implemented by other methods, which will not be elaborated here.

[0039] It should be noted that the bowel preparation record in this application refers to a set composed of evaluation values obtained by evaluating the effect of bowel preparation during the bowel preparation process of the patient to be examined. Preferably, after scoring the bowel preparation effects of different sampling periods during the bowel preparation process of the patient to be examined by using the Boston bowel preparation score method in the prior art, multiple bowel preparation evaluation values can be obtained, and the set composed of all bowel preparation evaluation values is used as the bowel preparation record. Among them, the Boston bowel preparation score is a standardized method for evaluating the degree of bowel cleansing. Its basic principle is to divide the colon into three regions (usually the right colon, the middle colon, and the left colon), and score each region separately; the score range for each region is from 0 to 3 points, where 0 points indicates that the region is completely uncleaned or the field of view is severely blocked, and 3 points indicates that the region is clean and intact without residues; the scores of the three regions are added together to obtain the total score, and the total score range is from 0 to 9 points. The higher the total score, the better the bowel preparation effect. In addition, it should be noted that the linear correlation degree in this application refers to the strength of the linear relationship between the corresponding metabolite and the bowel preparation of the patient to be examined, and is used to measure the influence of the corresponding metabolite during the bowel preparation process.

[0040] In specific implementation, the contribution degree of different metabolites to the bowel preparation can be determined based on all linear correlation degrees in the following manner: First, obtain the maximum value and the minimum value among all linear correlation degrees. Then, for each metabolite, use the value obtained by dividing the result of subtracting the minimum value from the linear correlation degree of the metabolite by the result of subtracting the minimum value from the maximum value as the contribution degree of the corresponding metabolite to the bowel preparation, and thus obtain the contribution degree of each metabolite to the bowel preparation.

[0041] It should be noted that the efficacy contribution degree described in this application is a value used to characterize the degree of influence of the corresponding metabolite on bowel preparation. It is calculated based on the linear correlation of all metabolites and normalized to the interval (0, 1) to ensure comparability between different individuals or datasets.

[0042] In some embodiments, predicting the bowel cleanliness of a patient to be examined by inputting all efficacy contribution degrees and the clinical characteristics of the patient to be examined into a pre-trained cleanliness prediction model can be achieved by the following steps: Obtain the clinical characteristics of the patient to be examined; Take all efficacy contribution degrees as the feature weights of the cleanliness prediction model and the clinical characteristics as the basic input variables of the cleanliness prediction model; Output the prediction result of the bowel cleanliness of the patient to be examined through the cleanliness prediction model.

[0043] It should be noted that in this application, the clinical characteristics of the patient to be examined are obtained through electronic medical records. The clinical characteristics refer to data related to the patient's health status, medical history, physiological state, and medical examination results. The clinical characteristics can be used to evaluate the physical condition of the patient to be examined and thus achieve the prediction of bowel cleanliness; among them, the clinical characteristics include basic demographic characteristics (such as age, gender, height, weight), medical history-related characteristics (such as previous bowel diseases, diabetes, hypertension, kidney diseases), and drug use conditions (such as antibiotics, probiotics, laxatives, glucocorticoids, chemotherapy drugs).

[0044] Preferably, the pre-trained cleanliness prediction model in this application can be obtained by acquiring a large amount of relevant data (intestinal metabolism data, clinical characteristics, etc.) of the bowel preparation process from the electronic health records of colonoscopy surgeries, screening features through feature engineering to construct a feature matrix, and then training the pre-trained cleanliness prediction model through the combination of the feature matrix and neural network algorithms. In other embodiments, other methods can also be used to achieve this, which is not limited here.

[0045] It should be noted that the feature weight in this application refers to the relative importance weight of each feature for the final prediction result in the pre-trained cleanliness prediction model; the feature weight is calculated based on the efficiency contribution degree, reflecting the influence degree of each metabolite on the intestinal cleanliness; in practical applications, the feature weight is used to adjust the attention degree of the model to different input variables to improve the prediction accuracy; in addition, the basic input variable refers to the core input data of the cleanliness prediction model, which includes the clinical feature vector of the patient and the metabolite contribution degree; after the basic input variable undergoes feature engineering (such as one-hot encoding, normalization), it constitutes the input matrix of the model, providing a calculation basis for neural networks or other machine learning algorithms; therefore, in specific implementation, taking all the efficiency contribution degrees as the feature weights of the cleanliness prediction model and the clinical features as the basic input variables of the cleanliness prediction model can be achieved in the following way, that is: First, convert the clinical features of the patient to be examined into a clinical feature vector through the one-hot encoding technology in the prior art. Subsequently, run the Python software, and after calling pandas to read all the efficiency contribution degrees and the clinical feature vector, construct a neural network through Sequential, and then automatically compile the model (that is: taking all the efficiency contribution degrees as the feature weights of the cleanliness prediction model and the clinical features as the basic input variables of the cleanliness prediction model); in addition, as a preferred embodiment, the prediction result of the intestinal cleanliness of the patient to be examined output by the cleanliness prediction model can be achieved in the following way, that is: First, store the cleanliness prediction model in the.hs format, then load the cleanliness prediction model by calling the joblib tool in the Python software, and then run the cleanliness prediction model through the TensorFlow tool to output the regression value of the neural network. Finally, take the regression value as the prediction result of the intestinal cleanliness of the patient to be examined. In other embodiments, other methods can also be used to achieve this, which is not limited here.

[0046] It should be noted that the prediction result of the intestinal cleanliness in this application refers to the numerical value or category label output by the cleanliness prediction model according to the input feature weights and basic input variables, representing the intestinal cleanliness status of the patient to be examined. Among them, the prediction result of the intestinal cleanliness (obtained through a pre-trained neural network, for example) is a normalized numerical value, and the value range is within (0, 1). The higher the numerical value of the prediction result of the intestinal cleanliness, the better the intestinal cleanliness; the lower the numerical value of the prediction result of the intestinal cleanliness, the worse the intestinal cleanliness.

[0047] Among them, the clinical features of the patient to be examined are converted into a clinical feature vector through the one-hot encoding technology in the prior art, that is: First, determine the set of category features of the clinical features. For example: age group (infant, adolescent, adult, elderly), past medical history (no underlying disease, hypertension, diabetes, cardiovascular disease), medication status (not taking medicine, taking antihypertensive drugs, taking hypoglycemic drugs, taking anticoagulant drugs), living habits (smoking, drinking, regular work and rest, balanced diet). Subsequently, perform one-hot encoding on each category feature of the clinical features, that is: assign a unique index to each category. For example, for the age group: infant (index 0), adolescent (index 1), adult (index 2), elderly (index 3); for the past medical history: no underlying disease (index 0), hypertension (index 1), diabetes (index 2), cardiovascular disease (index 3); for the medication status: not taking medicine (index 0), taking antihypertensive drugs (index 1), taking hypoglycemic drugs (index 2), taking anticoagulant drugs (index 3); for the living habits: smoking (index 0), drinking (index 1), regular work and rest (index 2), balanced diet (index 3); Finally, splice the one-hot encoding results of all categories into a complete clinical feature vector. In other embodiments, other methods can also be used to achieve this, which is not limited here.

[0048] In step 104, the dynamic balance relationship between the body fluid and electrolyte of the patient to be examined and the prediction result of the intestinal cleanliness are fused and evaluated to obtain the risk of osmotic pressure imbalance in the body of the patient to be examined during intestinal preparation.

[0049] In some embodiments, the dynamic balance relationship between the body fluid and electrolyte of the patient to be examined and the prediction result of the intestinal cleanliness are fused and evaluated to obtain the risk of osmotic pressure imbalance in the body of the patient to be examined during intestinal preparation, which can be achieved by the following steps: Determine the real-time imbalance index between the body fluid and electrolyte of the patient to be examined through the dynamic balance relationship between the body fluid and electrolyte of the patient to be examined; Fuse the real-time imbalance index with the prediction result of the intestinal cleanliness to obtain the risk of osmotic pressure imbalance in the body of the patient to be examined during intestinal preparation.

[0050] In specific implementation, the real-time imbalance index between the body fluid and electrolyte of the patient to be examined can be determined through the dynamic balance relationship between the body fluid and electrolyte of the patient to be examined, which can be implemented in the following manner: First, obtain the dynamic balance model between the body fluid and electrolyte of the patient to be examined in the latest sampling period from the dynamic balance relationship; then, substitute the body fluid volume of the patient to be examined in the latest sampling period and the dynamic balance parameters of the latest sampling period into the dynamic balance model to obtain the corrected electrolyte concentration value of the patient to be examined in the latest sampling period. Subsequently, the result of dividing the absolute value of the difference between the corrected electrolyte concentration value and the electrolyte concentration value of the patient to be examined in the latest sampling period by the corrected electrolyte concentration value is used as the real-time imbalance index between the body fluid and electrolyte of the patient to be examined.

[0051] It should be noted that the real-time imbalance index in this application refers to a numerical index that reflects the degree of deviation of the balance state between the body fluid and electrolyte of the patient to be examined in the most recent sampling period. This application evaluates the balance of the patient's body fluid and electrolyte in real time through the real-time imbalance index and timely discovers potential abnormal fluctuations.

[0052] In specific implementation, the real-time imbalance index and the predicted result of the intestinal cleanliness can be fused into the imbalance risk of the body osmotic pressure in the patient to be examined during intestinal preparation, which can be implemented in the following manner: First, subtract the predicted result of the intestinal cleanliness from the natural constant 1. Then, the result of multiplying the above result by the real-time imbalance index is used as the imbalance risk of the body osmotic pressure in the patient to be examined during intestinal preparation. As a preferred embodiment, after setting a cleanliness risk weight for the result of subtracting the predicted result of the intestinal cleanliness from the natural constant 1 and setting an imbalance risk weight for the real-time imbalance index, determine the result of multiplying the result of subtracting the predicted result of the intestinal cleanliness from the natural constant 1 by the cleanliness risk weight, and determine the result of multiplying the real-time imbalance index by the imbalance risk weight. Finally, the sum value of the above two results is used as the imbalance risk of the body osmotic pressure in the patient to be examined during intestinal preparation. In other embodiments, other methods can also be used, which are not limited here.

[0053] It should be noted that the imbalance risk in this application refers to the possibility of body osmotic pressure imbalance in the patient to be examined during intestinal preparation. By combining the predicted result of intestinal cleanliness and the electrolyte imbalance situation, this application can identify the imbalance risk of osmotic pressure in advance and avoid risks such as severe dehydration, hypotension, or water intoxication caused by excessive water loss or electrolyte disorder. Furthermore, according to the imbalance risk of different patients, dynamically adjust the bowel cleansing plan (such as selecting different types of laxatives, fluid replacement plans, etc.) to improve the effectiveness and safety of intestinal cleansing.

[0054] In addition, it should be noted that the cleanliness risk weight is a coefficient used to measure the degree of influence of intestinal cleanliness on the risk of osmotic imbalance in the body of the patient to be examined during the intestinal preparation process, indicating the relative importance of intestinal cleanliness in the overall risk of osmotic imbalance; in addition, the imbalance risk weight is a coefficient used to measure the degree of influence of the imbalance of the dynamic balance between body fluids and electrolytes on the risk of osmotic imbalance in the body of the patient to be examined; as a preferred embodiment, a large amount of clinical data can be trained using machine learning algorithms (such as regression analysis, support vector machines, decision trees, etc.) to automatically learn the key features affecting the risk of osmotic imbalance in the body and extract reasonable weights therefrom; for example, through the model coefficients obtained by training, appropriate weight values can be set for the prediction result of the intestinal cleanliness and the real-time imbalance index respectively. In other embodiments, other methods can also be used to set the cleanliness risk weight and the imbalance risk weight, which are not limited here.

[0055] In addition, the present application may further include step 105 of adjusting the intestinal fluid replacement plan of the patient to be examined in real time according to the imbalance risk.

[0056] In some embodiments, adjusting the intestinal fluid replacement plan of the patient to be examined in real time according to the imbalance risk can be implemented by the following steps: Set the risk threshold for the patient to be examined during intestinal preparation; Perform risk warning on the intestinal preparation process of the patient to be examined through the risk threshold and the imbalance risk; Adjust the intestinal fluid replacement plan of the patient to be examined in real time based on the risk warning result.

[0057] Preferably, the risk threshold for the patient to be examined during intestinal preparation can be set according to the clinical characteristics of the patient to be examined. For example, for patients to be examined with clinical characteristics of high-risk groups (such as the elderly, those with multiple chronic diseases, and those with low immunity), a lower risk threshold is set to achieve early detection and intervention. For patients to be examined with clinical characteristics of low-risk groups (such as the young, those without chronic diseases, and those with high immunity), a higher risk threshold is set to avoid over-intervention. In other embodiments, other methods can also be used to set it, which are not limited here.

[0058] During specific implementation, refer to Figure 3As shown, the figure is a schematic flowchart of risk warning shown in some embodiments of the present application. The risk warning for the bowel preparation process of the patient to be examined by the risk threshold and the imbalance risk can be achieved in the following manner, that is: when the imbalance risk is greater than or equal to the risk threshold, an alarm signal is sent to the electronic medical record of the bowel preparation of the patient to be examined as the risk warning result; when the imbalance risk is less than the risk threshold, a normal signal is sent to the electronic medical record of the bowel preparation of the patient to be examined as the risk warning result; as a preferred embodiment, the bowel fluid replacement plan of the patient to be examined can be adjusted in real time based on the risk warning result in the following manner, that is: when the risk warning result of the patient to be examined received is an alarm signal, the fluid replacement volume for the patient to be examined is increased. For example, the intravenous infusion flow rate or total volume can be increased by 10% - 20% to dilute the electrolyte concentration in the body, slow down the concentration effect, and appropriately adjust the electrolyte ratio in the replacement fluid (such as adding an appropriate amount of low-concentration sodium salt solution or other regulators) to correct the abnormal electrolyte concentration; when the risk warning result of the patient to be examined received is a normal signal, the current fluid replacement flow rate and fluid composition are maintained, and at the same time, real-time monitoring continues according to the established sampling period to ensure that the dynamic balance is continuously maintained.

[0059] In addition, on the other hand of the present application, in some embodiments, the present application provides an auxiliary system for bowel preparation before colonoscopy. The system includes a risk detection unit, and the risk detection unit can detect the intestinal osmotic pressure risk according to the above method, which will not be repeated here. Refer to Figure 4 , this figure is a schematic structural diagram of the risk detection unit shown in some embodiments of the present application. The risk detection unit 200 includes: a monitoring module 201, a processing module 202, and an execution module 203, which are described as follows: Monitoring module 201, in the present application, the monitoring module 201 is mainly used to monitor the body fluid loss record of the patient to be examined; Processing module 202, in the present application, the processing module 202 is mainly used to determine the net fluid loss rate of the patient to be examined in different time periods according to the body fluid loss record, and then construct the dynamic balance relationship between the body fluid and electrolytes of the patient to be examined by combining all the net fluid loss rates with the concentration characteristics of electrolytes in the body fluid of the patient to be examined; In addition, in the present application, the processing module 202 is also used to determine the contribution degree of different metabolites to the efficacy of bowel preparation based on the intestinal metabolism data of the patient to be examined, and then input all the contribution degrees and the clinical characteristics of the patient to be examined into a pre-trained cleanliness prediction model to predict the intestinal cleanliness of the patient to be examined; The execution module 202. The execution module 203 in this application is mainly used to fuse and evaluate the dynamic balance relationship between the body fluids and electrolytes of the patient to be examined and the prediction result of the intestinal cleanliness, so as to obtain the imbalance risk of the osmotic pressure in the body of the patient to be examined during intestinal preparation.

[0060] In addition, this application also provides a computer device, which includes a memory and a processor. The memory stores code, and the processor is configured to obtain the code and execute the above-mentioned intestinal osmotic pressure risk detection method.

[0061] In some embodiments, refer to Figure 5 , this figure is the internal structure diagram of a computer device for implementing the intestinal osmotic pressure risk detection method according to some embodiments of this application. The intestinal osmotic pressure risk detection method in the above embodiments can be implemented by Figure 5 the computer device shown. This computer device 300 includes at least one processor 301, a communication bus 302, a memory 303, and at least one communication interface 304.

[0062] The processor 301 can be a general-purpose central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more for controlling the execution of the intestinal osmotic pressure risk detection method in this application.

[0063] The communication bus 302 is used to transmit information between the above components.

[0064] The memory 303 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM), or other types of dynamic storage devices that can store information and instructions. It may also be an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM), or other optical disc storage, optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), a magnetic disk, or other magnetic storage devices, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 303 may exist independently and be connected to the processor 301 through the communication bus 302. The memory 303 may also be integrated with the processor 301.

[0065] Among them, the memory 303 is used to store the program code for executing the solution of this application and is controlled by the processor 301 to execute. The processor 301 is used to execute the program code stored in the memory 303. The program code may include one or more software modules. The intestinal osmotic pressure risk detection method in the above embodiments may be implemented by one or more software modules in the program code in the processor 301 and the memory 303.

[0066] The communication interface 304 uses any device such as a transceiver to communicate with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.

[0067] In a specific implementation, as an embodiment, the computer device may include multiple processors, and each of these processors may be a single-core (single-CPU) processor or a multi-core (multi-CPU) processor. The processor here may refer to one or more devices, circuits, and / or processing cores for processing data (such as computer program instructions).

[0068] The above computer device can be a general-purpose computer device or a special-purpose computer device. In specific implementations, the computer device can be a desktop computer, a laptop computer, a network server, a personal digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device, or an embedded device. The embodiments of the present application do not limit the type of the computer device.

[0069] In addition, the present application also provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the above-mentioned intestinal osmotic pressure risk detection method is implemented.

[0070] In summary, in the auxiliary system and method for intestinal preparation before colonoscopy disclosed in the embodiments of the present application, by monitoring the body fluid loss record of the patient to be examined; determining the net fluid loss rate of the patient to be examined in different time periods according to the body fluid loss record, and then constructing a dynamic balance relationship between the body fluid and electrolytes of the patient to be examined by combining all the net fluid loss rates with the concentration characteristics of electrolytes in the body fluid of the patient to be examined; determining the efficacy contribution degree of different metabolites to intestinal preparation based on the intestinal metabolism data of the patient to be examined, and then inputting all the efficacy contribution degrees and the clinical characteristics of the patient to be examined into a pre-trained cleanliness prediction model to predict the intestinal cleanliness of the patient to be examined; fusing and evaluating the dynamic balance relationship between the body fluid and electrolytes of the patient to be examined and the prediction result of the intestinal cleanliness to obtain the imbalance risk of the osmotic pressure in the body of the patient to be examined during intestinal preparation; that is, determining the imbalance risk of the osmotic pressure based on the dynamic correlation relationship between the body fluid loss rate of the patient and the change in the electrolyte concentration, so as to perform non-standardized fluid replacement for the patient.

[0071] Although the preferred embodiments of the present application have been described, those skilled in the art can make additional changes and modifications once they learn the basic creative concepts. Therefore, the appended claims are intended to be construed to include the preferred embodiments as well as all changes and modifications falling within the scope of the present application.

[0072] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalent technologies, the present application also intends to include these changes and modifications.

Claims

1. A method for detecting the risk of intestinal osmotic pressure, characterized in that, The method includes the following steps: Monitoring the fluid loss record of the patient to be examined; Determining the net fluid loss rate of the patient to be examined in different time periods according to the fluid loss record, and then constructing the dynamic balance relationship between the body fluid and electrolytes of the patient to be examined by combining all the net fluid loss rates with the concentration characteristics of electrolytes in the body fluid of the patient to be examined; Determining the efficacy contribution degree of different metabolites to bowel preparation based on the intestinal metabolism data of the patient to be examined, and then inputting all the efficacy contribution degrees and the clinical characteristics of the patient to be examined into a pre-trained cleanliness prediction model to predict the intestinal cleanliness of the patient to be examined; Performing a fusion evaluation on the dynamic balance relationship between the body fluid and electrolytes of the patient to be examined and the prediction result of the intestinal cleanliness to obtain the imbalance risk of the osmotic pressure in the body of the patient to be examined during bowel preparation.

2. The method according to claim 1, wherein Determining the net fluid loss rate of the patient to be examined in different time periods according to the fluid loss record specifically includes: Selecting the fluid loss amount corresponding to a sampling period in the fluid loss record as the selected fluid loss amount; Obtaining the fluid supplement amount of the patient to be examined in this sampling period; Determining the net fluid loss rate of the patient to be examined in this sampling period through the fluid supplement amount and the selected fluid loss amount; Continuing to determine the net fluid loss rate of the patient to be examined in the remaining sampling periods, that is, obtaining the net fluid loss rate of the patient to be examined in different time periods.

3. The method according to claim 1, characterized in that, Constructing the dynamic balance relationship between the body fluid and electrolytes of the patient to be examined by combining all the net fluid loss rates with the concentration characteristics of electrolytes in the body fluid of the patient to be examined specifically includes: Obtaining the electrolyte concentration data of the patient to be examined in multiple sampling periods; Calculating the body fluid concentration change rate of the patient to be examined in each sampling period according to all the net fluid loss rates and the electrolyte concentration data; Combining all the body fluid concentration change rates with the normal electrolyte concentration range to determine the dynamic balance parameters; Constructing the dynamic balance relationship between the body fluid and electrolytes of the patient to be examined through the dynamic balance parameters.

4. The method according to claim 1, wherein Determining the efficacy contribution degree of different metabolites to bowel preparation based on the intestinal metabolism data of the patient to be examined specifically includes: Obtaining the intestinal metabolism data of the patient to be examined; Determining the linear correlation degree between each metabolite and the bowel preparation of the patient to be examined through the intestinal metabolism data; Determining the efficacy contribution degree of different metabolites to bowel preparation based on all the linear correlation degrees.

5. The method according to claim 1, wherein Inputting all the efficacy contribution degrees and the clinical characteristics of the patient to be examined into a pre-trained cleanliness prediction model to predict the intestinal cleanliness of the patient to be examined specifically includes: Obtaining the clinical characteristics of the patient to be examined; Taking all the efficacy contribution degrees as the feature weights of the cleanliness prediction model and the clinical characteristics as the basic input variables of the cleanliness prediction model; Outputting the prediction result of the intestinal cleanliness of the patient to be examined through the cleanliness prediction model.

6. The method according to claim 1, characterized in that, Performing a fusion evaluation on the dynamic balance relationship between the body fluid and electrolytes of the patient to be examined and the prediction result of the intestinal cleanliness to obtain the imbalance risk of the osmotic pressure in the body of the patient to be examined during bowel preparation specifically includes: Determine the real-time imbalance index between the body fluid and electrolyte of the patient to be examined through the dynamic balance relationship between the body fluid and electrolyte of the patient to be examined; Fuse the real-time imbalance index with the predicted result of the intestinal cleanliness to obtain the imbalance risk of the body osmotic pressure in the patient to be examined during intestinal preparation.

7. The method according to claim 1, wherein It further includes: According to the imbalance risk, adjust the intestinal fluid replenishment plan of the patient to be examined in real time.

8. An auxiliary system for bowel preparation before colonoscopy, the auxiliary system for bowel preparation before colonoscopy includes a risk detection unit, characterized in that, The risk detection unit includes: A monitoring module for monitoring the body fluid loss record of the patient to be examined; A processing module for determining the net fluid loss rate of the patient to be examined in different time periods according to the body fluid loss record, and then constructing the dynamic balance relationship between the body fluid and electrolyte of the patient to be examined by combining all the net fluid loss rates with the concentration characteristics of electrolytes in the body fluid of the patient to be examined; The processing module is further used to determine the contribution degree of different metabolites to the efficacy of intestinal preparation based on the intestinal metabolism data of the patient to be examined, and then input all the contribution degrees and the clinical characteristics of the patient to be examined into a pre-trained cleanliness prediction model to predict the intestinal cleanliness of the patient to be examined; An execution module is further used to perform a fusion evaluation on the dynamic balance relationship between the body fluid and electrolyte of the patient to be examined and the predicted result of the intestinal cleanliness to obtain the imbalance risk of the body osmotic pressure in the patient to be examined during intestinal preparation.

9. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the steps of the intestinal osmotic pressure risk detection method described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, the steps of the intestinal osmotic pressure risk detection method described in any one of claims 1 to 7 are implemented.

Images